基于自学习优化模型的定制化居民需求响应预测研究

Forcasting research of tailored residential demand response based on self⁃learning optimization model

基于家庭智能电能表采集数据,构建居民需求响应样本库。基于该样本库,开展特征工程,充分挖掘响应用户的家庭属性、响应行为、用电行为等特征。在此基础上,构建居民电力需求响应神经网络自学习优化模型,根据不同家庭标签与历史响应结果数据,预测居民需求响应参与情况,随着典型场景下需求响应的不断开展,对模型进行循环迭代与优化。最终,依据调节目标,智能化制定需求响应调控策略。算例结果表明,所提的需求响应策略能够准确识别居民需求响应参与度,降低需求响应激励成本。

Based on the monitoring data of household smart meters,a sample database of residents’demand response is con⁃structed.Based on the sample database,feature engineering is car⁃ried out to fully mine the characteristics of responsive users,such as family attributes,response behavior and power consumption be⁃havior.On this basis,the self⁃learning optimization model of resi⁃dent power demand response neural network is constructed.Ac⁃cording to the data of different family labels and historical re⁃sponse results,the participation of resident demand response is predicted.With the continuous development of demand response in typical scenarios,the model is iterated and optimized.Finally,according to the regulation objectives,the demand response regula⁃tion strategy is intelligently formulated.Results show that the pro⁃posed demand response strategy can accurately identify the resi⁃dential demand response participation and reduce the demand re⁃sponse incentive cost.