摘要
通过频谱分析研究了需求响应负荷的基本特性,并以此为依据建立了计及需求响应的Elman神经网络(Elman-NN)预测模型。Elman-NN具有处理动态信息能力强、训练时间短、全局寻优性强的优点。通过实际算例,对比在Elman-NN模型中计及需求响应因素前后的预测性能,结果显示计及需求响应因素可显著提高Elman-NN模型预测精度。本文证实了在模型中计及需求响应因素的重要作用,为需求响应负荷的预测研究奠定了必要的理论基础。
This paper studies the basic characteristics of the load which takes demand response into consideration through frequency spectrum analysis and constructs a load forecasting model based on Elman-Neural Networks （E1- man-NN）, which also takes demand response into account. Elman-NN is characterized by a short training period and its ability to deal with dynamic information and achieve the whole optimum. An actual case is used to compare the forecasting performance of the models based on Elman-NN with and without taking demand response into ac- count. Results exhibit that considering demand response can markedly improve the forecasting accuracy of models based on Elman-NN. The paper confirms the significance of considering demand response in forecasting models and lays necessary theoretical foundation for the study of predicting load which takes demand response into account.
出处
《电工电能新技术》
CSCD
北大核心
2017年第4期59-65,共7页
Advanced Technology of Electrical Engineering and Energy
基金
国家自然科学基金项目(51477078)
关键词
需求响应
负荷特性
ELMAN神经网络
短期负荷预测
demand response
load characteristic
Elman-Neural Networks
short-term load forecasting
