摘要
针对用电力负荷典型的时间序列问题,本文提出了基于长短时间记忆网络(LSTM)的电力负荷预测模型。首先,训练区域电力负荷数据,将参数调整到最优后预测中短期的电力负荷数据;然后,针对普通工业、非普通工业、大工业、商业4种情况,考虑气象因素对电力负荷的影响,进一步构建改进LSTM模型,预测中长期的电力负荷数据。结果表明,该方法可以准确预测电力负荷的变化趋势,可广泛应用于不同行业。
Aiming at the typical time series problem of electricity load,this paper proposes an electricity load forecasting model based on long and short time memory network(LSTM).First of all,the regional electricity load data are trained and the parameters are adjusted to the optimum to predict the short-and medium-term electricity load data;then,in view of ordinary industry,non-ordinary industry,large industry and business,and considering the influence of meteorological factors on the power load,further build an improved LSTM model to forecast the power load data in the medium and long term.The results show that this method can accurately predict the variation trend of electric load and can be widely used in different industries.
作者
吴岳鹏
WU Yuepeng(Scholl of Electronic and Optical Engineering,Nanjing University of Science and Technology,Nanjing,Jiangsu 210094,China)
出处
《自动化应用》
2023年第10期76-78,共3页
Automation Application
