Forecasting uncertainties among meteorological fields have long been recognized as the main limitation on the accuracy and predictability of air quality forecasts.However,the particular impact of meteorological foreca...Forecasting uncertainties among meteorological fields have long been recognized as the main limitation on the accuracy and predictability of air quality forecasts.However,the particular impact of meteorological forecasting uncertainties on air quality forecasts specific to different seasons is still not well known.In this study,a series of forecasts with different forecast lead times for January,April,July,and October of 2018 are conducted over the Beijing-Tianjin-Hebei(BTH)region and the impacts of meteorological forecasting uncertainties on surface PM_(2.5)concentration forecasts with each lead time are investigated.With increased lead time,the forecasted PM_(2.5)concentrations significantly change and demonstrate obvious seasonal variations.In general,the forecasting uncertainties in monthly mean surface PM_(2.5)concentrations in the BTH region due to lead time are the largest(80%)in spring,followed by autumn(~50%),summer(~40%),and winter(20%).In winter,the forecasting uncertainties in total surface PM_(2.5)mass due to lead time are mainly due to the uncertainties in PBL heights and hence the PBL mixing of anthropogenic primary particles.In spring,the forecasting uncertainties are mainly from the impacts of lead time on lower-tropospheric northwesterly winds,thereby further enhancing the condensation production of anthropogenic secondary particles by the long-range transport of natural dust.In summer,the forecasting uncertainties result mainly from the decrease in dry and wet deposition rates,which are associated with the reduction of near-surface wind speed and precipitation rate.In autumn,the forecasting uncertainties arise mainly from the change in the transport of remote natural dust and anthropogenic particles,which is associated with changes in the large-scale circulation.展开更多
Since the Beijing 2022 Winter Olympics was the first Winter Olympics in history held in continental winter monsoon climate conditions across complex terrain areas,there is a deficiency of relevant research,operational...Since the Beijing 2022 Winter Olympics was the first Winter Olympics in history held in continental winter monsoon climate conditions across complex terrain areas,there is a deficiency of relevant research,operational techniques,and experience.This made providing meteorological services for this event particularly challenging.The China Meteorological Administration(CMA)Earth System Modeling and Prediction Centre,achieved breakthroughs in research on short-and medium-term deterministic and ensemble numerical predictions.Several key technologies crucial for precise winter weather services during the Winter Olympics were developed.A comprehensive framework,known as the Operational System for High-Precision Weather Forecasting for the Winter Olympics,was established.Some of these advancements represent the highest level of capabilities currently available in China.The meteorological service provided to the Beijing 2022 Games also exceeded previous Winter Olympic Games in both variety and quality.This included achievements such as the“100-meter level,minute level”downscaled spatiotemporal resolution and forecasts spanning 1 to 15 days.Around 30 new technologies and over 60 kinds of products that align with the requirements of the Winter Olympics Organizing Committee were developed,and many of these techniques have since been integrated into the CMA’s operational national forecasting systems.These accomplishments were facilitated by a dedicated weather forecasting and research initiative,in conjunction with the preexisting real-time operational forecasting systems of the CMA.This program represents one of the five subprograms of the WMO’s high-impact weather forecasting demonstration project(SMART2022),and continues to play an important role in their Regional Association(RA)II Research Development Project(Hangzhou RDP).Therefore,the research accomplishments and meteorological service experiences from this program will be carried forward into forthcoming highimpact weather forecasting activities.This article provides an overview and assessment of this program and the operational national forecasting systems.展开更多
To assess whether a development strategy will be profitable enough,production forecasting is a crucial and difficult step in the process.The development history of other reservoirs in the same class tends to be studie...To assess whether a development strategy will be profitable enough,production forecasting is a crucial and difficult step in the process.The development history of other reservoirs in the same class tends to be studied to make predictions accurate.However,the permeability field,well patterns,and development regime must all be similar for two reservoirs to be considered in the same class.This results in very few available experiences from other reservoirs even though there is a lot of historical information on numerous reservoirs because it is difficult to find such similar reservoirs.This paper proposes a learn-to-learn method,which can better utilize a vast amount of historical data from various reservoirs.Intuitively,the proposed method first learns how to learn samples before directly learning rules in samples.Technically,by utilizing gradients from networks with independent parameters and copied structure in each class of reservoirs,the proposed network obtains the optimal shared initial parameters which are regarded as transferable information across different classes.Based on that,the network is able to predict future production indices for the target reservoir by only training with very limited samples collected from reservoirs in the same class.Two cases further demonstrate its superiority in accuracy to other widely-used network methods.展开更多
Tunnel boring machines(TBMs)have been widely utilised in tunnel construction due to their high efficiency and reliability.Accurately predicting TBM performance can improve project time management,cost control,and risk...Tunnel boring machines(TBMs)have been widely utilised in tunnel construction due to their high efficiency and reliability.Accurately predicting TBM performance can improve project time management,cost control,and risk management.This study aims to use deep learning to develop real-time models for predicting the penetration rate(PR).The models are built using data from the Changsha metro project,and their performances are evaluated using unseen data from the Zhengzhou Metro project.In one-step forecast,the predicted penetration rate follows the trend of the measured penetration rate in both training and testing.The autoregressive integrated moving average(ARIMA)model is compared with the recurrent neural network(RNN)model.The results show that univariate models,which only consider historical penetration rate itself,perform better than multivariate models that take into account multiple geological and operational parameters(GEO and OP).Next,an RNN variant combining time series of penetration rate with the last-step geological and operational parameters is developed,and it performs better than other models.A sensitivity analysis shows that the penetration rate is the most important parameter,while other parameters have a smaller impact on time series forecasting.It is also found that smoothed data are easier to predict with high accuracy.Nevertheless,over-simplified data can lose real characteristics in time series.In conclusion,the RNN variant can accurately predict the next-step penetration rate,and data smoothing is crucial in time series forecasting.This study provides practical guidance for TBM performance forecasting in practical engineering.展开更多
Time series data plays a crucial role in intelligent transportation systems.Traffic flow forecasting represents a precise estimation of future traffic flow within a specific region and time interval.Existing approache...Time series data plays a crucial role in intelligent transportation systems.Traffic flow forecasting represents a precise estimation of future traffic flow within a specific region and time interval.Existing approaches,including sequence periodic,regression,and deep learning models,have shown promising results in short-term series forecasting.However,forecasting scenarios specifically focused on holiday traffic flow present unique challenges,such as distinct traffic patterns during vacations and the increased demand for long-term forecastings.Consequently,the effectiveness of existing methods diminishes in such scenarios.Therefore,we propose a novel longterm forecasting model based on scene matching and embedding fusion representation to forecast long-term holiday traffic flow.Our model comprises three components:the similar scene matching module,responsible for extracting Similar Scene Features;the long-short term representation fusion module,which integrates scenario embeddings;and a simple fully connected layer at the head for making the final forecasting.Experimental results on real datasets demonstrate that our model outperforms other methods,particularly in medium and long-term forecasting scenarios.展开更多
With a further increase in energy flexibility for customers,short-term load forecasting is essential to provide benchmarks for economic dispatch and real-time alerts in power grids.The electrical load series exhibit p...With a further increase in energy flexibility for customers,short-term load forecasting is essential to provide benchmarks for economic dispatch and real-time alerts in power grids.The electrical load series exhibit periodic patterns and share high associations with metrological data.However,current studies have merely focused on point-wise models and failed to sufficiently investigate the periodic patterns of load series,which hinders the further improvement of short-term load forecasting accuracy.Therefore,this paper improved Autoformer to extract the periodic patterns of load series and learn a representative feature from deep decomposition and reconstruction.In addition,a novel multi-factor attention mechanism was proposed to handle multi-source metrological and numerical weather prediction data and thus correct the forecasted electrical load.The paper also compared the proposed model with various competitive models.As the experimental results reveal,the proposed model outperforms the benchmark models and maintains stability on various types of load consumers.展开更多
For more than a century, forecasting models have been crucial in a variety of fields. Models can offer the most accurate forecasting outcomes if error terms are normally distributed. Finding a good statistical model f...For more than a century, forecasting models have been crucial in a variety of fields. Models can offer the most accurate forecasting outcomes if error terms are normally distributed. Finding a good statistical model for time series predicting imports in Malaysia is the main target of this study. The decision made during this study mostly addresses the unrestricted error correction model (UECM), and composite model (Combined regression—ARIMA). The imports of Malaysia from the first quarter of 1991 to the third quarter of 2022 are employed in this study’s quarterly time series data. The forecasting outcomes of the current study demonstrated that the composite model offered more probabilistic data, which improved forecasting the volume of Malaysia’s imports. The composite model, and the UECM model in this study are linear models based on responses to Malaysia’s imports. Future studies might compare the performance of linear and nonlinear models in forecasting.展开更多
Coffee is a significant industry, accounting for 3% of Vietnam’s GDP, with annual export turnover consistently exceeding USD 3 billion. Despite global economic challenges affecting purchasing power at various times, ...Coffee is a significant industry, accounting for 3% of Vietnam’s GDP, with annual export turnover consistently exceeding USD 3 billion. Despite global economic challenges affecting purchasing power at various times, Vietnam’s coffee exports in December 2023 continued to surge, reaching the highest level in the past 9 months at 190,000 tons, a 59.3% increase compared to November 2023, but still a slight 3.5% decrease from the same period last year. The export turnover reached USD 538 million, a 51% increase from November 2023 and a 26.4% increase from the same period last year. Therefore, forecasting the coffee export volume holds significant importance for coffee producers nationwide. This research employs the Box-Jenkins method to construct an ARIMA model for forecasting Vietnam’s coffee export volume based on annual data published by the General Statistics Office. Results indicate that among the models considered, the ARIMA(1, 1, 2) model is the most suitable. The study also provides short-term forecasts for Vietnam’s coffee export volume. However, the current model is limited to forecasting and is not yet optimized, as the assumed linearity in the model is a simplification.展开更多
Due to the high inherent uncertainty of renewable energy,probabilistic day-ahead wind power forecasting is crucial for modeling and controlling the uncertainty of renewable energy smart grids in smart cities.However,t...Due to the high inherent uncertainty of renewable energy,probabilistic day-ahead wind power forecasting is crucial for modeling and controlling the uncertainty of renewable energy smart grids in smart cities.However,the accuracy and reliability of high-resolution day-ahead wind power forecasting are constrained by unreliable local weather prediction and incomplete power generation data.This article proposes a physics-informed artificial intelligence(AI)surrogates method to augment the incomplete dataset and quantify its uncertainty to improve wind power forecasting performance.The incomplete dataset,built with numerical weather prediction data,historical wind power generation,and weather factors data,is augmented based on generative adversarial networks.After augmentation,the enriched data is then fed into a multiple AI surrogates model constructed by two extreme learning machine networks to train the forecasting model for wind power.Therefore,the forecasting models’accuracy and generalization ability are improved by mining the implicit physics information from the incomplete dataset.An incomplete dataset gathered from a wind farm in North China,containing only 15 days of weather and wind power generation data withmissing points caused by occasional shutdowns,is utilized to verify the proposed method’s performance.Compared with other probabilistic forecastingmethods,the proposed method shows better accuracy and probabilistic performance on the same incomplete dataset,which highlights its potential for more flexible and sensitive maintenance of smart grids in smart cities.展开更多
Solar stills are considered an effective method to solve the scarcity of drinkable water.However,it is still missing a way to forecast its production.Herein,it is proposed that a convenient forecasting model which jus...Solar stills are considered an effective method to solve the scarcity of drinkable water.However,it is still missing a way to forecast its production.Herein,it is proposed that a convenient forecasting model which just needs to input the conventional weather forecasting data.The model is established by using machine learning methods of random forest and optimized by Bayesian algorithm.The required data to train the model are obtained from daily measurements lasting9 months.To validate the accuracy model,the determination coefficients of two types of solar stills are calculated as 0.935and 0.929,respectively,which are much higher than the value of both multiple linear regression(0.767)and the traditional models(0.829 and 0.847).Moreover,by applying the model,we predicted the freshwater production of four cities in China.The predicted production is approved to be reliable by a high value of correlation(0.868)between the predicted production and the solar insolation.With the help of the forecasting model,it would greatly promote the global application of solar stills.展开更多
Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by 2050.However,they are exceedingly unpredictable since they rely h...Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by 2050.However,they are exceedingly unpredictable since they rely highly on weather and atmospheric conditions.In microgrids,smart energy management systems,such as integrated demand response programs,are permanently established on a step-ahead basis,which means that accu-rate forecasting of wind speed and solar irradiance intervals is becoming increasingly crucial to the optimal operation and planning of microgrids.With this in mind,a novel“bidirectional long short-term memory network”(Bi-LSTM)-based,deep stacked,sequence-to-sequence autoencoder(S2SAE)forecasting model for predicting short-term solar irradiation and wind speed was developed and evaluated in MATLAB.To create a deep stacked S2SAE prediction model,a deep Bi-LSTM-based encoder and decoder are stacked on top of one another to reduce the dimension of the input sequence,extract its features,and then reconstruct it to produce the forecasts.Hyperparameters of the proposed deep stacked S2SAE forecasting model were optimized using the Bayesian optimization algorithm.Moreover,the forecasting performance of the proposed Bi-LSTM-based deep stacked S2SAE model was compared to three other deep,and shallow stacked S2SAEs,i.e.,the LSTM-based deep stacked S2SAE model,gated recurrent unit-based deep stacked S2SAE model,and Bi-LSTM-based shallow stacked S2SAE model.All these models were also optimized and modeled in MATLAB.The results simulated based on actual data confirmed that the proposed model outperformed the alternatives by achieving an accuracy of up to 99.7%,which evidenced the high reliability of the proposed forecasting.展开更多
Photovoltaic(PV)systems are environmentally friendly,generate green energy,and receive support from policies and organizations.However,weather fluctuations make large-scale PV power integration and management challeng...Photovoltaic(PV)systems are environmentally friendly,generate green energy,and receive support from policies and organizations.However,weather fluctuations make large-scale PV power integration and management challenging despite the economic benefits.Existing PV forecasting techniques(sequential and convolutional neural networks(CNN))are sensitive to environmental conditions,reducing energy distribution system performance.To handle these issues,this article proposes an efficient,weather-resilient convolutional-transformer-based network(CT-NET)for accurate and efficient PV power forecasting.The network consists of three main modules.First,the acquired PV generation data are forwarded to the pre-processing module for data refinement.Next,to carry out data encoding,a CNNbased multi-head attention(MHA)module is developed in which a single MHA is used to decode the encoded data.The encoder module is mainly composed of 1D convolutional and MHA layers,which extract local as well as contextual features,while the decoder part includes MHA and feedforward layers to generate the final prediction.Finally,the performance of the proposed network is evaluated using standard error metrics,including the mean squared error(MSE),root mean squared error(RMSE),and mean absolute percentage error(MAPE).An ablation study and comparative analysis with several competitive state-of-the-art approaches revealed a lower error rate in terms of MSE(0.0471),RMSE(0.2167),and MAPE(0.6135)over publicly available benchmark data.In addition,it is demonstrated that our proposed model is less complex,with the lowest number of parameters(0.0135 M),size(0.106 MB),and inference time(2 ms/step),suggesting that it is easy to integrate into the smart grid.展开更多
The underground hydropower projects in Southwest China is characterized by large excavation sizes,high geostresses,complicated geological conditions and multiple construction processes.Various disasters such as collap...The underground hydropower projects in Southwest China is characterized by large excavation sizes,high geostresses,complicated geological conditions and multiple construction processes.Various disasters such as collapses,large deformations,rockbursts are frequently encountered,resulting in serious casualties and huge economic losses.This review mainly presents some representative results on microseismic(MS)monitoring and forecasting for disasters in hydropower underground engineering.First,a set of new denoising,spectral analysis,and location methods were developed for better identification and location of MS signals.Then,the tempo-spatial characteristics of MS events were analyzed to understand the relationship between field construction and damages of surrounding rocks.Combined with field construction,geological data,numerical simulation and parametric analysis of MS sources,the focal mechanism of MS events was revealed.A damage constitutive model considering MS fracturing size was put forward and feedback analysis considering the MS damage of underground surrounding rocks was conducted.Next,an MS multi-parameter based risk assessment and early warning method for dynamic disasters were proposed.The technology for control of the damage and deformation of underground surrounding rocks was proposed for underground caverns.Finally,two typical underground powerhouses were selected as case studies.These achievements can provide significant references for prevention and control of dynamic disasters for underground engineering with similar complicated geological conditions.展开更多
Short-term load forecasting (STLF) is part and parcel of theefficient working of power grid stations. Accurate forecasts help to detect thefault and enhance grid reliability for organizing sufficient energy transactio...Short-term load forecasting (STLF) is part and parcel of theefficient working of power grid stations. Accurate forecasts help to detect thefault and enhance grid reliability for organizing sufficient energy transactions.STLF ranges from an hour ahead prediction to a day ahead prediction. Variouselectric load forecasting methods have been used in literature for electricitygeneration planning to meet future load demand. A perfect balance regardinggeneration and utilization is still lacking to avoid extra generation and misusageof electric load. Therefore, this paper utilizes Levenberg–Marquardt(LM) based Artificial Neural Network (ANN) technique to forecast theshort-term electricity load for smart grids in a much better, more precise,and more accurate manner. For proper load forecasting, we take the mostcritical weather parameters along with historical load data in the form of timeseries grouped into seasons, i.e., winter and summer. Further, the presentedmodel deals with each season’s load data by splitting it into weekdays andweekends. The historical load data of three years have been used to forecastweek-ahead and day-ahead load demand after every thirty minutes makingload forecast for a very short period. The proposed model is optimized usingthe Levenberg-Marquardt backpropagation algorithm to achieve results withcomparable statistics. Mean Absolute Percent Error (MAPE), Root MeanSquared Error (RMSE), R2, and R are used to evaluate the model. Comparedwith other recent machine learning-based mechanisms, our model presentsthe best experimental results with MAPE and R2 scores of 1.3 and 0.99,respectively. The results prove that the proposed LM-based ANN modelperforms much better in accuracy and has the lowest error rates as comparedto existing work.展开更多
Wind speed forecasting is important for wind energy forecasting.In the modern era,the increase in energy demand can be managed effectively by fore-casting the wind speed accurately.The main objective of this research ...Wind speed forecasting is important for wind energy forecasting.In the modern era,the increase in energy demand can be managed effectively by fore-casting the wind speed accurately.The main objective of this research is to improve the performance of wind speed forecasting by handling uncertainty,the curse of dimensionality,overfitting and non-linearity issues.The curse of dimensionality and overfitting issues are handled by using Boruta feature selec-tion.The uncertainty and the non-linearity issues are addressed by using the deep learning based Bi-directional Long Short Term Memory(Bi-LSTM).In this paper,Bi-LSTM with Boruta feature selection named BFS-Bi-LSTM is proposed to improve the performance of wind speed forecasting.The model identifies relevant features for wind speed forecasting from the meteorological features using Boruta wrapper feature selection(BFS).Followed by Bi-LSTM predicts the wind speed by considering the wind speed from the past and future time steps.The proposed BFS-Bi-LSTM model is compared against Multilayer perceptron(MLP),MLP with Boruta(BFS-MLP),Long Short Term Memory(LSTM),LSTM with Boruta(BFS-LSTM)and Bi-LSTM in terms of Root Mean Square Error(RMSE),Mean Absolute Error(MAE),Mean Square Error(MSE)and R2.The BFS-Bi-LSTM surpassed other models by producing RMSE of 0.784,MAE of 0.530,MSE of 0.615 and R2 of 0.8766.The experimental result shows that the BFS-Bi-LSTM produced better forecasting results compared to others.展开更多
Urgent care clinics and emergency departments around the world periodically suffer from extended wait times beyond patient expectations due to surges in patient flows.The delays arising from inadequate staffing levels...Urgent care clinics and emergency departments around the world periodically suffer from extended wait times beyond patient expectations due to surges in patient flows.The delays arising from inadequate staffing levels during these periods have been linked with adverse clinical outcomes.Previous research into forecasting patient flows has mostly used statistical techniques.These studies have also predominately focussed on short‐term forecasts,which have limited practicality for the resourcing of medical personnel.This study joins an emerging body of work which seeks to explore the potential of machine learning algorithms to generate accurate forecasts of patient presentations.Our research uses datasets covering 10 years from two large urgent care clinics to develop long‐term patient flow forecasts up to one quarter ahead using a range of state‐of‐the‐art algo-rithms.A distinctive feature of this study is the use of eXplainable Artificial Intelligence(XAI)tools like Shapely and LIME that enable an in‐depth analysis of the behaviour of the models,which would otherwise be uninterpretable.These analysis tools enabled us to explore the ability of the models to adapt to the volatility in patient demand during the COVID‐19 pandemic lockdowns and to identify the most impactful variables,resulting in valuable insights into their performance.The results showed that a novel combination of advanced univariate models like Prophet as well as gradient boosting,into an ensemble,delivered the most accurate and consistent solutions on average.This approach generated improvements in the range of 16%-30%over the existing in‐house methods for esti-mating the daily patient flows 90 days ahead.展开更多
With the rapid development of artificial intelligence and computer technology,grid corporations have also begun to move towards comprehensive intelligence and informatization.However,data-based informatization can bri...With the rapid development of artificial intelligence and computer technology,grid corporations have also begun to move towards comprehensive intelligence and informatization.However,data-based informatization can bring about the risk of privacy exposure of fine-grained information such as electricity consumption data.The modeling of electricity consumption data can help grid corporations to have a more thorough understanding of users’needs and their habits,providing better services for users.Nevertheless,users’electricity consumption data is sensitive and private.In order to achieve highly efficient analysis of massive private electricity consumption data without direct access,a blockchain-based federated learning method is proposed for users’electricity consumption forecasting in this paper.Specifically,a blockchain systemis established based on a proof of quality(PoQ)consensus mechanism,and a multilayer hybrid directional long short-term memory(MHD-LSTM)network model is trained for users’electricity consumption forecasting via the federal learning method.In this way,the model of the MHD-LSTM network is able to avoid suffering from severe security problems and can only share the network parameters without exchanging raw electricity consumption data,which is decentralized,secure and reliable.The experimental result shows that the proposed method has both effectiveness and high-accuracy under the premise of electricity consumption data’s privacy preservation,and can achieve better performance when compared to traditional long short-term memory(LSTM)and bidirectional LSTM(BLSTM).展开更多
With the rapid development of the 5G communications,the edge intelligence enables Internet of Vehicles(IoV)to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simu...With the rapid development of the 5G communications,the edge intelligence enables Internet of Vehicles(IoV)to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simultaneously.To enhance the forecasting performance,a novel edge-enabled probabilistic graph structure learning model(PGSLM)is proposed,which learns the graph structure and parameters by the edge sensing information and discrete probability distribution on the edges of the traffic road network.To obtain the spatio-temporal dependencies of traffic data,the learned dynamic graphs are combined with a predefined static graph to generate the graph convolution part of the recurrent graph convolution module.During the training process,a new graph training loss is introduced,which is composed of the K nearest neighbor(KNN)graph constructed by the traffic feature tensors and the graph structure.Detailed experimental results show that,compared with existing models,the proposed PGSLM improves the traffic prediction performance in terms of average absolute error and root mean square error in IoV.展开更多
Random and fluctuating wind speeds make it difficult to stabilize the wind-power output,which complicates the execution of wind-farm control systems and increases the response frequency.In this study,a novel predictio...Random and fluctuating wind speeds make it difficult to stabilize the wind-power output,which complicates the execution of wind-farm control systems and increases the response frequency.In this study,a novel prediction model for ultrashort-term wind-speed prediction in wind farms is developed by combining a deep belief network,the Elman neural network,and the Hilbert-Huang transform modified using an improved particle swarm optimization algorithm.The experimental results show that the prediction results of the proposed deep neural network is better than that of shallow neural networks.Although the complexity of the model is high,the accuracy of wind-speed prediction and stability are also high.The proposed model effectively improves the accuracy of ultrashort-term wind-speed forecasting in wind farms.展开更多
Most studies have conducted experiments on predicting energy consumption by integrating data formodel training.However, the process of centralizing data can cause problems of data leakage.Meanwhile,many laws and regul...Most studies have conducted experiments on predicting energy consumption by integrating data formodel training.However, the process of centralizing data can cause problems of data leakage.Meanwhile,many laws and regulationson data security and privacy have been enacted, making it difficult to centralize data, which can lead to a datasilo problem. Thus, to train the model while maintaining user privacy, we adopt a federated learning framework.However, in all classical federated learning frameworks secure aggregation, the Federated Averaging (FedAvg)method is used to directly weight the model parameters on average, which may have an adverse effect on te model.Therefore, we propose the Federated Reinforcement Learning (FedRL) model, which consists of multiple userscollaboratively training the model. Each household trains a local model on local data. These local data neverleave the local area, and only the encrypted parameters are uploaded to the central server to participate in thesecure aggregation of the global model. We improve FedAvg by incorporating a Q-learning algorithm to assignweights to each locally uploaded local model. And the model has improved predictive performance. We validatethe performance of the FedRL model by testing it on a real-world dataset and compare the experimental results withother models. The performance of our proposed method in most of the evaluation metrics is improved comparedto both the centralized and distributed models.展开更多
基金supported by the National Key Research and Development Program of China(No.2022YFC3700701)National Natural Science Foundation of China(Grant Nos.41775146,42061134009)+1 种基金USTC Research Funds of the Double First-Class Initiative(YD2080002007)Strategic Priority Research Program of Chinese Academy of Sciences(XDB41000000).
文摘Forecasting uncertainties among meteorological fields have long been recognized as the main limitation on the accuracy and predictability of air quality forecasts.However,the particular impact of meteorological forecasting uncertainties on air quality forecasts specific to different seasons is still not well known.In this study,a series of forecasts with different forecast lead times for January,April,July,and October of 2018 are conducted over the Beijing-Tianjin-Hebei(BTH)region and the impacts of meteorological forecasting uncertainties on surface PM_(2.5)concentration forecasts with each lead time are investigated.With increased lead time,the forecasted PM_(2.5)concentrations significantly change and demonstrate obvious seasonal variations.In general,the forecasting uncertainties in monthly mean surface PM_(2.5)concentrations in the BTH region due to lead time are the largest(80%)in spring,followed by autumn(~50%),summer(~40%),and winter(20%).In winter,the forecasting uncertainties in total surface PM_(2.5)mass due to lead time are mainly due to the uncertainties in PBL heights and hence the PBL mixing of anthropogenic primary particles.In spring,the forecasting uncertainties are mainly from the impacts of lead time on lower-tropospheric northwesterly winds,thereby further enhancing the condensation production of anthropogenic secondary particles by the long-range transport of natural dust.In summer,the forecasting uncertainties result mainly from the decrease in dry and wet deposition rates,which are associated with the reduction of near-surface wind speed and precipitation rate.In autumn,the forecasting uncertainties arise mainly from the change in the transport of remote natural dust and anthropogenic particles,which is associated with changes in the large-scale circulation.
基金This work was jointly supported by the National Natural Science Foundation of China(Grant Nos.41975137,42175012,and 41475097)the National Key Research and Development Program(Grant No.2018YFF0300103).
文摘Since the Beijing 2022 Winter Olympics was the first Winter Olympics in history held in continental winter monsoon climate conditions across complex terrain areas,there is a deficiency of relevant research,operational techniques,and experience.This made providing meteorological services for this event particularly challenging.The China Meteorological Administration(CMA)Earth System Modeling and Prediction Centre,achieved breakthroughs in research on short-and medium-term deterministic and ensemble numerical predictions.Several key technologies crucial for precise winter weather services during the Winter Olympics were developed.A comprehensive framework,known as the Operational System for High-Precision Weather Forecasting for the Winter Olympics,was established.Some of these advancements represent the highest level of capabilities currently available in China.The meteorological service provided to the Beijing 2022 Games also exceeded previous Winter Olympic Games in both variety and quality.This included achievements such as the“100-meter level,minute level”downscaled spatiotemporal resolution and forecasts spanning 1 to 15 days.Around 30 new technologies and over 60 kinds of products that align with the requirements of the Winter Olympics Organizing Committee were developed,and many of these techniques have since been integrated into the CMA’s operational national forecasting systems.These accomplishments were facilitated by a dedicated weather forecasting and research initiative,in conjunction with the preexisting real-time operational forecasting systems of the CMA.This program represents one of the five subprograms of the WMO’s high-impact weather forecasting demonstration project(SMART2022),and continues to play an important role in their Regional Association(RA)II Research Development Project(Hangzhou RDP).Therefore,the research accomplishments and meteorological service experiences from this program will be carried forward into forthcoming highimpact weather forecasting activities.This article provides an overview and assessment of this program and the operational national forecasting systems.
基金This work is supported by the National Natural Science Foundation of China under Grant 52274057,52074340 and 51874335the Major Scientific and Technological Projects of CNPC under Grant ZD2019-183-008+2 种基金the Major Scientific and Technological Projects of CNOOC under Grant CCL2022RCPS0397RSNthe Science and Technology Support Plan for Youth Innovation of University in Shandong Province under Grant 2019KJH002111 Project under Grant B08028.
文摘To assess whether a development strategy will be profitable enough,production forecasting is a crucial and difficult step in the process.The development history of other reservoirs in the same class tends to be studied to make predictions accurate.However,the permeability field,well patterns,and development regime must all be similar for two reservoirs to be considered in the same class.This results in very few available experiences from other reservoirs even though there is a lot of historical information on numerous reservoirs because it is difficult to find such similar reservoirs.This paper proposes a learn-to-learn method,which can better utilize a vast amount of historical data from various reservoirs.Intuitively,the proposed method first learns how to learn samples before directly learning rules in samples.Technically,by utilizing gradients from networks with independent parameters and copied structure in each class of reservoirs,the proposed network obtains the optimal shared initial parameters which are regarded as transferable information across different classes.Based on that,the network is able to predict future production indices for the target reservoir by only training with very limited samples collected from reservoirs in the same class.Two cases further demonstrate its superiority in accuracy to other widely-used network methods.
文摘Tunnel boring machines(TBMs)have been widely utilised in tunnel construction due to their high efficiency and reliability.Accurately predicting TBM performance can improve project time management,cost control,and risk management.This study aims to use deep learning to develop real-time models for predicting the penetration rate(PR).The models are built using data from the Changsha metro project,and their performances are evaluated using unseen data from the Zhengzhou Metro project.In one-step forecast,the predicted penetration rate follows the trend of the measured penetration rate in both training and testing.The autoregressive integrated moving average(ARIMA)model is compared with the recurrent neural network(RNN)model.The results show that univariate models,which only consider historical penetration rate itself,perform better than multivariate models that take into account multiple geological and operational parameters(GEO and OP).Next,an RNN variant combining time series of penetration rate with the last-step geological and operational parameters is developed,and it performs better than other models.A sensitivity analysis shows that the penetration rate is the most important parameter,while other parameters have a smaller impact on time series forecasting.It is also found that smoothed data are easier to predict with high accuracy.Nevertheless,over-simplified data can lose real characteristics in time series.In conclusion,the RNN variant can accurately predict the next-step penetration rate,and data smoothing is crucial in time series forecasting.This study provides practical guidance for TBM performance forecasting in practical engineering.
基金funded by the Natural Science Foundation of Zhejiang Province of China under Grant (No.LY21F020003)Zhejiang Science and Technology Plan Project (No.2021C02060)the Scientific Research Foundation of Hangzhou City University (No.X-202206).
文摘Time series data plays a crucial role in intelligent transportation systems.Traffic flow forecasting represents a precise estimation of future traffic flow within a specific region and time interval.Existing approaches,including sequence periodic,regression,and deep learning models,have shown promising results in short-term series forecasting.However,forecasting scenarios specifically focused on holiday traffic flow present unique challenges,such as distinct traffic patterns during vacations and the increased demand for long-term forecastings.Consequently,the effectiveness of existing methods diminishes in such scenarios.Therefore,we propose a novel longterm forecasting model based on scene matching and embedding fusion representation to forecast long-term holiday traffic flow.Our model comprises three components:the similar scene matching module,responsible for extracting Similar Scene Features;the long-short term representation fusion module,which integrates scenario embeddings;and a simple fully connected layer at the head for making the final forecasting.Experimental results on real datasets demonstrate that our model outperforms other methods,particularly in medium and long-term forecasting scenarios.
基金supported by Science and Technology Project of State Grid Zhejiang Corporation of China“Research on State Estimation and Risk Assessment Technology for New Power Distribution Networks for Widely Connected Distributed Energy”(5211JX22002D).
文摘With a further increase in energy flexibility for customers,short-term load forecasting is essential to provide benchmarks for economic dispatch and real-time alerts in power grids.The electrical load series exhibit periodic patterns and share high associations with metrological data.However,current studies have merely focused on point-wise models and failed to sufficiently investigate the periodic patterns of load series,which hinders the further improvement of short-term load forecasting accuracy.Therefore,this paper improved Autoformer to extract the periodic patterns of load series and learn a representative feature from deep decomposition and reconstruction.In addition,a novel multi-factor attention mechanism was proposed to handle multi-source metrological and numerical weather prediction data and thus correct the forecasted electrical load.The paper also compared the proposed model with various competitive models.As the experimental results reveal,the proposed model outperforms the benchmark models and maintains stability on various types of load consumers.
文摘For more than a century, forecasting models have been crucial in a variety of fields. Models can offer the most accurate forecasting outcomes if error terms are normally distributed. Finding a good statistical model for time series predicting imports in Malaysia is the main target of this study. The decision made during this study mostly addresses the unrestricted error correction model (UECM), and composite model (Combined regression—ARIMA). The imports of Malaysia from the first quarter of 1991 to the third quarter of 2022 are employed in this study’s quarterly time series data. The forecasting outcomes of the current study demonstrated that the composite model offered more probabilistic data, which improved forecasting the volume of Malaysia’s imports. The composite model, and the UECM model in this study are linear models based on responses to Malaysia’s imports. Future studies might compare the performance of linear and nonlinear models in forecasting.
文摘Coffee is a significant industry, accounting for 3% of Vietnam’s GDP, with annual export turnover consistently exceeding USD 3 billion. Despite global economic challenges affecting purchasing power at various times, Vietnam’s coffee exports in December 2023 continued to surge, reaching the highest level in the past 9 months at 190,000 tons, a 59.3% increase compared to November 2023, but still a slight 3.5% decrease from the same period last year. The export turnover reached USD 538 million, a 51% increase from November 2023 and a 26.4% increase from the same period last year. Therefore, forecasting the coffee export volume holds significant importance for coffee producers nationwide. This research employs the Box-Jenkins method to construct an ARIMA model for forecasting Vietnam’s coffee export volume based on annual data published by the General Statistics Office. Results indicate that among the models considered, the ARIMA(1, 1, 2) model is the most suitable. The study also provides short-term forecasts for Vietnam’s coffee export volume. However, the current model is limited to forecasting and is not yet optimized, as the assumed linearity in the model is a simplification.
基金funded by the National Natural Science Foundation of China under Grant 62273022.
文摘Due to the high inherent uncertainty of renewable energy,probabilistic day-ahead wind power forecasting is crucial for modeling and controlling the uncertainty of renewable energy smart grids in smart cities.However,the accuracy and reliability of high-resolution day-ahead wind power forecasting are constrained by unreliable local weather prediction and incomplete power generation data.This article proposes a physics-informed artificial intelligence(AI)surrogates method to augment the incomplete dataset and quantify its uncertainty to improve wind power forecasting performance.The incomplete dataset,built with numerical weather prediction data,historical wind power generation,and weather factors data,is augmented based on generative adversarial networks.After augmentation,the enriched data is then fed into a multiple AI surrogates model constructed by two extreme learning machine networks to train the forecasting model for wind power.Therefore,the forecasting models’accuracy and generalization ability are improved by mining the implicit physics information from the incomplete dataset.An incomplete dataset gathered from a wind farm in North China,containing only 15 days of weather and wind power generation data withmissing points caused by occasional shutdowns,is utilized to verify the proposed method’s performance.Compared with other probabilistic forecastingmethods,the proposed method shows better accuracy and probabilistic performance on the same incomplete dataset,which highlights its potential for more flexible and sensitive maintenance of smart grids in smart cities.
基金Project supported by the National Key Research and Development Program of China(Grant No.2018YFE0127800)the Science,Technology&Innovation Funding Authority(STIFA),Egypt grant(Grant No.40517)+1 种基金China Postdoctoral Science Foundation(Grant No.2020M682411)the Fundamental Research Funds for the Central Universities(Grant No.2019kfy RCPY045)。
文摘Solar stills are considered an effective method to solve the scarcity of drinkable water.However,it is still missing a way to forecast its production.Herein,it is proposed that a convenient forecasting model which just needs to input the conventional weather forecasting data.The model is established by using machine learning methods of random forest and optimized by Bayesian algorithm.The required data to train the model are obtained from daily measurements lasting9 months.To validate the accuracy model,the determination coefficients of two types of solar stills are calculated as 0.935and 0.929,respectively,which are much higher than the value of both multiple linear regression(0.767)and the traditional models(0.829 and 0.847).Moreover,by applying the model,we predicted the freshwater production of four cities in China.The predicted production is approved to be reliable by a high value of correlation(0.868)between the predicted production and the solar insolation.With the help of the forecasting model,it would greatly promote the global application of solar stills.
文摘Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by 2050.However,they are exceedingly unpredictable since they rely highly on weather and atmospheric conditions.In microgrids,smart energy management systems,such as integrated demand response programs,are permanently established on a step-ahead basis,which means that accu-rate forecasting of wind speed and solar irradiance intervals is becoming increasingly crucial to the optimal operation and planning of microgrids.With this in mind,a novel“bidirectional long short-term memory network”(Bi-LSTM)-based,deep stacked,sequence-to-sequence autoencoder(S2SAE)forecasting model for predicting short-term solar irradiation and wind speed was developed and evaluated in MATLAB.To create a deep stacked S2SAE prediction model,a deep Bi-LSTM-based encoder and decoder are stacked on top of one another to reduce the dimension of the input sequence,extract its features,and then reconstruct it to produce the forecasts.Hyperparameters of the proposed deep stacked S2SAE forecasting model were optimized using the Bayesian optimization algorithm.Moreover,the forecasting performance of the proposed Bi-LSTM-based deep stacked S2SAE model was compared to three other deep,and shallow stacked S2SAEs,i.e.,the LSTM-based deep stacked S2SAE model,gated recurrent unit-based deep stacked S2SAE model,and Bi-LSTM-based shallow stacked S2SAE model.All these models were also optimized and modeled in MATLAB.The results simulated based on actual data confirmed that the proposed model outperformed the alternatives by achieving an accuracy of up to 99.7%,which evidenced the high reliability of the proposed forecasting.
基金supported by the National Research Foundation of Korea (NRF)grant funded by the Korean government (MSIT) (No.2019M3F2A1073179).
文摘Photovoltaic(PV)systems are environmentally friendly,generate green energy,and receive support from policies and organizations.However,weather fluctuations make large-scale PV power integration and management challenging despite the economic benefits.Existing PV forecasting techniques(sequential and convolutional neural networks(CNN))are sensitive to environmental conditions,reducing energy distribution system performance.To handle these issues,this article proposes an efficient,weather-resilient convolutional-transformer-based network(CT-NET)for accurate and efficient PV power forecasting.The network consists of three main modules.First,the acquired PV generation data are forwarded to the pre-processing module for data refinement.Next,to carry out data encoding,a CNNbased multi-head attention(MHA)module is developed in which a single MHA is used to decode the encoded data.The encoder module is mainly composed of 1D convolutional and MHA layers,which extract local as well as contextual features,while the decoder part includes MHA and feedforward layers to generate the final prediction.Finally,the performance of the proposed network is evaluated using standard error metrics,including the mean squared error(MSE),root mean squared error(RMSE),and mean absolute percentage error(MAPE).An ablation study and comparative analysis with several competitive state-of-the-art approaches revealed a lower error rate in terms of MSE(0.0471),RMSE(0.2167),and MAPE(0.6135)over publicly available benchmark data.In addition,it is demonstrated that our proposed model is less complex,with the lowest number of parameters(0.0135 M),size(0.106 MB),and inference time(2 ms/step),suggesting that it is easy to integrate into the smart grid.
基金The authors are grateful for the financial support from the National Natural Science Foundation of China(Grant Nos.42177143,42277461)the Science Foundation for Distinguished Young Scholars of Sichuan Province(Grant No.2020JDJQ0011).Thanks to the Chn Energy Dadu River Hydropower Development Co.,Ltd,China Three Gorges Construction Engineering Corporation,Yalong River Hydropower Development Company,Ltd,Power China Chengdu Engineering Co.,Ltd,Power China Northwest Engineering Co.,Ltd,Power China Sinohydro Bureau 7 Co.,Ltd,China Gezhouba Group No.1 Engineering Co.,Ltd.,and the 5th Engineering Co.,Ltd.of China Railway Construction Bridge Engineering Bureau Group for the support and assistance.
文摘The underground hydropower projects in Southwest China is characterized by large excavation sizes,high geostresses,complicated geological conditions and multiple construction processes.Various disasters such as collapses,large deformations,rockbursts are frequently encountered,resulting in serious casualties and huge economic losses.This review mainly presents some representative results on microseismic(MS)monitoring and forecasting for disasters in hydropower underground engineering.First,a set of new denoising,spectral analysis,and location methods were developed for better identification and location of MS signals.Then,the tempo-spatial characteristics of MS events were analyzed to understand the relationship between field construction and damages of surrounding rocks.Combined with field construction,geological data,numerical simulation and parametric analysis of MS sources,the focal mechanism of MS events was revealed.A damage constitutive model considering MS fracturing size was put forward and feedback analysis considering the MS damage of underground surrounding rocks was conducted.Next,an MS multi-parameter based risk assessment and early warning method for dynamic disasters were proposed.The technology for control of the damage and deformation of underground surrounding rocks was proposed for underground caverns.Finally,two typical underground powerhouses were selected as case studies.These achievements can provide significant references for prevention and control of dynamic disasters for underground engineering with similar complicated geological conditions.
基金support provided in part by the National Key Research and Development Program of China (No.2020YFB1005804)in part by the National Natural Science Foundation of China under Grant 61632009+1 种基金in part by the High-Level Talents Program of Higher Education in Guangdong Province under Grant 2016ZJ01in part by the NCRA-017,NUST,Islamabad.
文摘Short-term load forecasting (STLF) is part and parcel of theefficient working of power grid stations. Accurate forecasts help to detect thefault and enhance grid reliability for organizing sufficient energy transactions.STLF ranges from an hour ahead prediction to a day ahead prediction. Variouselectric load forecasting methods have been used in literature for electricitygeneration planning to meet future load demand. A perfect balance regardinggeneration and utilization is still lacking to avoid extra generation and misusageof electric load. Therefore, this paper utilizes Levenberg–Marquardt(LM) based Artificial Neural Network (ANN) technique to forecast theshort-term electricity load for smart grids in a much better, more precise,and more accurate manner. For proper load forecasting, we take the mostcritical weather parameters along with historical load data in the form of timeseries grouped into seasons, i.e., winter and summer. Further, the presentedmodel deals with each season’s load data by splitting it into weekdays andweekends. The historical load data of three years have been used to forecastweek-ahead and day-ahead load demand after every thirty minutes makingload forecast for a very short period. The proposed model is optimized usingthe Levenberg-Marquardt backpropagation algorithm to achieve results withcomparable statistics. Mean Absolute Percent Error (MAPE), Root MeanSquared Error (RMSE), R2, and R are used to evaluate the model. Comparedwith other recent machine learning-based mechanisms, our model presentsthe best experimental results with MAPE and R2 scores of 1.3 and 0.99,respectively. The results prove that the proposed LM-based ANN modelperforms much better in accuracy and has the lowest error rates as comparedto existing work.
文摘Wind speed forecasting is important for wind energy forecasting.In the modern era,the increase in energy demand can be managed effectively by fore-casting the wind speed accurately.The main objective of this research is to improve the performance of wind speed forecasting by handling uncertainty,the curse of dimensionality,overfitting and non-linearity issues.The curse of dimensionality and overfitting issues are handled by using Boruta feature selec-tion.The uncertainty and the non-linearity issues are addressed by using the deep learning based Bi-directional Long Short Term Memory(Bi-LSTM).In this paper,Bi-LSTM with Boruta feature selection named BFS-Bi-LSTM is proposed to improve the performance of wind speed forecasting.The model identifies relevant features for wind speed forecasting from the meteorological features using Boruta wrapper feature selection(BFS).Followed by Bi-LSTM predicts the wind speed by considering the wind speed from the past and future time steps.The proposed BFS-Bi-LSTM model is compared against Multilayer perceptron(MLP),MLP with Boruta(BFS-MLP),Long Short Term Memory(LSTM),LSTM with Boruta(BFS-LSTM)and Bi-LSTM in terms of Root Mean Square Error(RMSE),Mean Absolute Error(MAE),Mean Square Error(MSE)and R2.The BFS-Bi-LSTM surpassed other models by producing RMSE of 0.784,MAE of 0.530,MSE of 0.615 and R2 of 0.8766.The experimental result shows that the BFS-Bi-LSTM produced better forecasting results compared to others.
文摘Urgent care clinics and emergency departments around the world periodically suffer from extended wait times beyond patient expectations due to surges in patient flows.The delays arising from inadequate staffing levels during these periods have been linked with adverse clinical outcomes.Previous research into forecasting patient flows has mostly used statistical techniques.These studies have also predominately focussed on short‐term forecasts,which have limited practicality for the resourcing of medical personnel.This study joins an emerging body of work which seeks to explore the potential of machine learning algorithms to generate accurate forecasts of patient presentations.Our research uses datasets covering 10 years from two large urgent care clinics to develop long‐term patient flow forecasts up to one quarter ahead using a range of state‐of‐the‐art algo-rithms.A distinctive feature of this study is the use of eXplainable Artificial Intelligence(XAI)tools like Shapely and LIME that enable an in‐depth analysis of the behaviour of the models,which would otherwise be uninterpretable.These analysis tools enabled us to explore the ability of the models to adapt to the volatility in patient demand during the COVID‐19 pandemic lockdowns and to identify the most impactful variables,resulting in valuable insights into their performance.The results showed that a novel combination of advanced univariate models like Prophet as well as gradient boosting,into an ensemble,delivered the most accurate and consistent solutions on average.This approach generated improvements in the range of 16%-30%over the existing in‐house methods for esti-mating the daily patient flows 90 days ahead.
基金supported by the Technology Project of State Grid Tianjin Electric Power Company(KJ22-1-47).
文摘With the rapid development of artificial intelligence and computer technology,grid corporations have also begun to move towards comprehensive intelligence and informatization.However,data-based informatization can bring about the risk of privacy exposure of fine-grained information such as electricity consumption data.The modeling of electricity consumption data can help grid corporations to have a more thorough understanding of users’needs and their habits,providing better services for users.Nevertheless,users’electricity consumption data is sensitive and private.In order to achieve highly efficient analysis of massive private electricity consumption data without direct access,a blockchain-based federated learning method is proposed for users’electricity consumption forecasting in this paper.Specifically,a blockchain systemis established based on a proof of quality(PoQ)consensus mechanism,and a multilayer hybrid directional long short-term memory(MHD-LSTM)network model is trained for users’electricity consumption forecasting via the federal learning method.In this way,the model of the MHD-LSTM network is able to avoid suffering from severe security problems and can only share the network parameters without exchanging raw electricity consumption data,which is decentralized,secure and reliable.The experimental result shows that the proposed method has both effectiveness and high-accuracy under the premise of electricity consumption data’s privacy preservation,and can achieve better performance when compared to traditional long short-term memory(LSTM)and bidirectional LSTM(BLSTM).
基金supported by the project of the National Natural Science Foundation of China(No.61772562)the Knowledge Innovation Program of Wuhan-Basic Research(No.2022010801010225)the Fundamental Research Funds for the Central Universities(No.2662022YJ012)。
文摘With the rapid development of the 5G communications,the edge intelligence enables Internet of Vehicles(IoV)to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simultaneously.To enhance the forecasting performance,a novel edge-enabled probabilistic graph structure learning model(PGSLM)is proposed,which learns the graph structure and parameters by the edge sensing information and discrete probability distribution on the edges of the traffic road network.To obtain the spatio-temporal dependencies of traffic data,the learned dynamic graphs are combined with a predefined static graph to generate the graph convolution part of the recurrent graph convolution module.During the training process,a new graph training loss is introduced,which is composed of the K nearest neighbor(KNN)graph constructed by the traffic feature tensors and the graph structure.Detailed experimental results show that,compared with existing models,the proposed PGSLM improves the traffic prediction performance in terms of average absolute error and root mean square error in IoV.
基金This study was supported by the Research and Application of Key Technologies in the Design of Large Onshore Smart Wind Power Base(Grant No.XBY-ZDKJ-2020-05)the Scientific Research Project of the China Electric Power Construction Corporation:Research and Application of Key Technologies in the Design of an Onshore Smart Wind Power Base(Grant No.DJ-ZDXM-2020-52)+2 种基金the Danish Energy Agency(Grant No.64013-0405)the Fundamental Research Funds for the Central Universities(Grant No.B210201018)the Jiangsu Province Policy Guidance Program(Grant No.BZ2021019).
文摘Random and fluctuating wind speeds make it difficult to stabilize the wind-power output,which complicates the execution of wind-farm control systems and increases the response frequency.In this study,a novel prediction model for ultrashort-term wind-speed prediction in wind farms is developed by combining a deep belief network,the Elman neural network,and the Hilbert-Huang transform modified using an improved particle swarm optimization algorithm.The experimental results show that the prediction results of the proposed deep neural network is better than that of shallow neural networks.Although the complexity of the model is high,the accuracy of wind-speed prediction and stability are also high.The proposed model effectively improves the accuracy of ultrashort-term wind-speed forecasting in wind farms.
基金supported by National Key R&D Program of China(No.2020YFC2006602)National Natural Science Foundation of China(Nos.62172324,62072324,61876217,6187612)+2 种基金University Natural Science Foundation of Jiangsu Province(No.21KJA520005)Primary Research and Development Plan of Jiangsu Province(No.BE2020026)Natural Science Foundation of Jiangsu Province(No.BK20190942).
文摘Most studies have conducted experiments on predicting energy consumption by integrating data formodel training.However, the process of centralizing data can cause problems of data leakage.Meanwhile,many laws and regulationson data security and privacy have been enacted, making it difficult to centralize data, which can lead to a datasilo problem. Thus, to train the model while maintaining user privacy, we adopt a federated learning framework.However, in all classical federated learning frameworks secure aggregation, the Federated Averaging (FedAvg)method is used to directly weight the model parameters on average, which may have an adverse effect on te model.Therefore, we propose the Federated Reinforcement Learning (FedRL) model, which consists of multiple userscollaboratively training the model. Each household trains a local model on local data. These local data neverleave the local area, and only the encrypted parameters are uploaded to the central server to participate in thesecure aggregation of the global model. We improve FedAvg by incorporating a Q-learning algorithm to assignweights to each locally uploaded local model. And the model has improved predictive performance. We validatethe performance of the FedRL model by testing it on a real-world dataset and compare the experimental results withother models. The performance of our proposed method in most of the evaluation metrics is improved comparedto both the centralized and distributed models.