基于多头自注意力机制和长短期记忆网络方法的区域售电量预测

Regional electricity sales forecasting based on multi-head attention mechanism and long short-term memory network

中文关键词: 售电量预测  气象因素  长短时记忆网络  多头注意力机制

英文关键词: electricity sales forecasting  meteorological factors  long short-term memory networks  multi-head attention mechanism

中文摘要:

      区域售电量的精确预测对于电力部门实施有效的能源管理和规划方面发挥着关键作用。现有的预测模型主要依赖于历史售电量数据,部分模型考虑到温度的影响,但对多种气象因素的综合考量不足。因此,考量多气象因子,提出一种多头注意力机制和长短期记忆网络结合的区域售电量预测方法（multi-head self-attention mechanism long short-term memory,MHAM-LSTM）。首先通过相关性分析筛选出关键变量,去除冗余变量。然后利用多头注意力机制重点关注对售电量有重要影响的关键指标,并生成新的指标变量。最后采用LSTM网络深入挖掘时间序列数据的潜在规律,实现区域售电量预测。实验表明,MHAM-LSTM模型在售电量预测精度方面优于随机森林、深度神经网络、长短时记忆网络、时间卷积神经网络和Transformer等对比模型,展现出较大的性能优势。此外,气象因素重要性分析结果显示,综合考虑多种气象变量,特别是温度、风速和湿度,能够提高预测的准确性。

英文摘要:

      Accurate prediction of regional electricity sales is crucial for the power sector’s effective energy management and planning. Existing forecasting models largely rely on historical electricity sales data and partially incorporate temperature effects, yet they inadequately consider a broad range of meteorological factors. In response, it introduces a novel forecasting method combining multi- head attention mechanisms with long short-term memory networks（MHAM-LSTM）for regional electricity sales. Initially, key variables are identified and redundant variables are eliminated through correlation analysis. Subsequently, the multi-head attention mechanism is used to focus on the key indicators that have an important impact on electricity sales. Finally, the LSTM network delves into the latent patterns of time-series data to forecast regional electricity sales. Experimental results show that the MHAM-LSTM model surpasses comparative models, including random forest, deep neural networks, long short-term memory networks, temporal convolutional networks, and transformer, in electricity sales forecasting accuracy, demonstrating significant performance advantages. Additionally, the analysis of meteorological factor importance reveals that incorporating multiple meteorological variables, particularly temperature, wind speed, and humidity, plays a crucial role in improving prediction accuracy.