【作者】 张博海； 何星； 章渊；

【Author】 ZHANG Bo-hai;HE Xing;ZHANG Yuan;Department of Automation,Shanghai Jiao Tong University,and Key Laboratory of System Control and Information Processing,Ministry of Education of China;Dispatching Control Center of Shanghai Electric Power Company;

【机构】 上海交通大学自动化系系统控制与信息处理教育部重点实验室； 上海市电力公司电力调度控制中心；

【摘要】 科学的发电与调度计划是智能电网的重要特征之一,短期电网负荷预测是根据历史电网负荷、气象等数据对未来若干天内的负荷预测,是指导电网科学发电与调度、保证电网稳定运行的的重要因素。为了提高在智能电网环境下短期电力负荷预测的精度,本文基于华东某地区历史负荷与气象数据,结合循环神经网络,对电网短期负荷预测进行了研究。最后通过实例结果证明循环神经网络在短期电网负荷预测中有较好的精确度与适用性。更多还原

【Abstract】 Scientific power generation and dispatch planning is one of the important characteristics of smart grid. Short-term load forecasting is load forecasting for the next few days, which based on historical load, weather and some other data. Short-term load forecasting is the guidance of scientific power generation and grid dispatching. It’s also the important factor to ensure the stable operation of the power grid. In order to improve the accuracy of short-term power load forecasting in smart grid, this paper studies the short-term load forecasting of power grid based on historical load and meteorological data of a certain area in East China, combined with the recurrent neural network. By analyzing the case results, The network has better accuracy and applicability in the short-term power load forecasting.更多还原