In an electricity market,power producers’profits are determined by the market price instead of the regulated price.Therefore,the producers should be cautious in strategic bidding,for which prediction-based approaches...In an electricity market,power producers’profits are determined by the market price instead of the regulated price.Therefore,the producers should be cautious in strategic bidding,for which prediction-based approaches are widely used and have been proved effective for many areas.However,in a uniform pricing market,the market environment is so complicated,which is primarily due to the complexity of the participants’interaction,that even the strategies based on machine learning algorithms,which are generally considered as outstanding nonlinear prediction methods,may sometimes lead to unsatisfactory results.Therefore,a selective learning scheme for strategic bidding is proposed to ensure greater effectiveness.The proposed scheme is based on an ensemble technique,where several machine learning algorithms serve as the underlying algorithms to predict the price and generate a bidding recommendation.As the clearing iteration progresses,the most fitting ones will be chosen to dominate the bidding strategy.Considering the characteristics of the electricity market,the prediction method used in the selective learning scheme is modified to achieve higher accuracy.Simulation studies are presented to demonstrate the effectiveness of the proposed scheme,which leads to more reasonable bidding behaviors and higher profits.展开更多
Hydrogen as an energy carrier represents one of the most promising carbon-free energy solutions.The ongoing development of power-to-gas(Pt G)technologies that supports large-scale utilization of hydrogen is therefore ...Hydrogen as an energy carrier represents one of the most promising carbon-free energy solutions.The ongoing development of power-to-gas(Pt G)technologies that supports large-scale utilization of hydrogen is therefore expected to support hydrogen economy with a final breakthrough.In this paper,the economic performance of a MW-sized hydrogen system,i.e.a composition of water electrolysis,hydrogen storage,and fuel cell combined heat and power plant(FCCHP),is assessed as an example of hydrogen-based bidirectional electrical energy storage(EES).The analysis is conducted in view of the Danish electricity spot market that has high price volatility due to its high share of wind power.An economic dispatch model is developed as a mixed-integer programming(MIP)problem to support the estimation of variable cost of such a system taking into account a good granularity of the technical details.Based on a projected technology improvement by 2020,sensitivity analysis is conducted to illustrate how much the hydrogen-based EES is sensitive to variations of the hydrogen price and the capacity of hydrogen storage.展开更多
Estimating the price of a financial asset or any tradable product is a complex task that depends on the availability of a reasonable amount of data samples. In the Brazilian electricity market environment, where spot ...Estimating the price of a financial asset or any tradable product is a complex task that depends on the availability of a reasonable amount of data samples. In the Brazilian electricity market environment, where spot prices are centrally calculated by computational models, the projection of hourly energy prices at the spot market is essential for decision-making, and with the particularities of this sector, this task becomes even more complex due to the stochastic behavior of some variables, such as the inflow to hydroelectric power plants and the correlation between variables that affect electricity generation, traditional statistical techniques of time series forecasting present an additional complexity when one tries to project scenarios of spot prices on different time horizons. To address these complexities of traditional forecasting methods, this study presents a new approach based on Machine Learning methodology applied to the electricity spot prices forecasting process. The model’s Learning Base is obtained from public information provided by the Brazilian official computational models: NEWAVE, DECOMP, and DESSEM. The application of the methodology to real cases, using back-testing with actual information from the Brazilian electricity sector demonstrates that the research is promising, as the adherence of the projections with the realized values is significant.展开更多
基金partially supported by Natural Science Foundation of Guangdong Province(No.2018A030313822)。
文摘In an electricity market,power producers’profits are determined by the market price instead of the regulated price.Therefore,the producers should be cautious in strategic bidding,for which prediction-based approaches are widely used and have been proved effective for many areas.However,in a uniform pricing market,the market environment is so complicated,which is primarily due to the complexity of the participants’interaction,that even the strategies based on machine learning algorithms,which are generally considered as outstanding nonlinear prediction methods,may sometimes lead to unsatisfactory results.Therefore,a selective learning scheme for strategic bidding is proposed to ensure greater effectiveness.The proposed scheme is based on an ensemble technique,where several machine learning algorithms serve as the underlying algorithms to predict the price and generate a bidding recommendation.As the clearing iteration progresses,the most fitting ones will be chosen to dominate the bidding strategy.Considering the characteristics of the electricity market,the prediction method used in the selective learning scheme is modified to achieve higher accuracy.Simulation studies are presented to demonstrate the effectiveness of the proposed scheme,which leads to more reasonable bidding behaviors and higher profits.
基金the financial support of Innovation Fund Denmark through Project 3045-00012B
文摘Hydrogen as an energy carrier represents one of the most promising carbon-free energy solutions.The ongoing development of power-to-gas(Pt G)technologies that supports large-scale utilization of hydrogen is therefore expected to support hydrogen economy with a final breakthrough.In this paper,the economic performance of a MW-sized hydrogen system,i.e.a composition of water electrolysis,hydrogen storage,and fuel cell combined heat and power plant(FCCHP),is assessed as an example of hydrogen-based bidirectional electrical energy storage(EES).The analysis is conducted in view of the Danish electricity spot market that has high price volatility due to its high share of wind power.An economic dispatch model is developed as a mixed-integer programming(MIP)problem to support the estimation of variable cost of such a system taking into account a good granularity of the technical details.Based on a projected technology improvement by 2020,sensitivity analysis is conducted to illustrate how much the hydrogen-based EES is sensitive to variations of the hydrogen price and the capacity of hydrogen storage.
文摘Estimating the price of a financial asset or any tradable product is a complex task that depends on the availability of a reasonable amount of data samples. In the Brazilian electricity market environment, where spot prices are centrally calculated by computational models, the projection of hourly energy prices at the spot market is essential for decision-making, and with the particularities of this sector, this task becomes even more complex due to the stochastic behavior of some variables, such as the inflow to hydroelectric power plants and the correlation between variables that affect electricity generation, traditional statistical techniques of time series forecasting present an additional complexity when one tries to project scenarios of spot prices on different time horizons. To address these complexities of traditional forecasting methods, this study presents a new approach based on Machine Learning methodology applied to the electricity spot prices forecasting process. The model’s Learning Base is obtained from public information provided by the Brazilian official computational models: NEWAVE, DECOMP, and DESSEM. The application of the methodology to real cases, using back-testing with actual information from the Brazilian electricity sector demonstrates that the research is promising, as the adherence of the projections with the realized values is significant.
