摘要
空调负荷已经成为电网负荷中非常重要的组成部分,特别是在非工楼宇空调,对非工楼宇空调负荷进行准确负荷预测,可以进行更加合理的需求响应,提高区域用电质量。MM-LSTM (多路多层LSTM网络)预测方法对非工楼宇中央空调的用电负荷进行预测精度较高。通过数据实验表明,该负荷预测方法在适当的数据特征工程后,预测普遍优于一般LSTM网络的空调负荷预测方法,具有良好的预测精度。该方法可有效满足非工楼宇空调需求响应的需要,具有良好的实用价值。
Air-conditioning load has become a very important part of the grid load, especially in non-industrial buildings. Accurate load forecasting of non-industrial building air-conditioning loads can perform more reasonable demand response and improve regional power quality. MM-LSTM (multi-channel &multi-layer LSTM network) prediction method is used to predict the load of non-industrial building air conditioners in a short time, and the high-precision building air conditioning load prediction results are obtained. The experimental data shows that the proposed method is superior to the general LSTM network method under the premise of suitable feature engineering, and has good prediction accuracy. The method can effectively meet the needs of non-industrial building air conditioning demand response and has good practical value.
