基于改进深度稀疏自编码器及FOA-ELM的电力负荷预测

Power load forecasting based on improved deep sparse auto-encoder and FOA-ELM

智能电网的发展使得电网获取的数据逐渐增多,为了从多维大数据中获取有用信息并对短期内电力负荷进行准确的预测,提出了一种基于改进的深度稀疏自编码器(IDSAE)降维及果蝇优化算法(FOA)优化极限学习机(ELM)的短期电力负荷预测方法。将L1正则化加入到深度稀疏自编码器(DSAE)中能够诱导出更好的稀疏性,用IDSAE对影响电力负荷预测精度的高维数据进行特征降维,消除了指标间的多重共线性,实现高维数据向低维空间的压缩编码。采用FOA优化算法优化ELM的权值和阈值,得到最优值,能够克服因极限学习机随机选择权值和阈值导致预测精度低的缺点。首先将气象因素通过IDSAE降维,得到稀疏后的综合气象因素特征指标,协同电力负荷数据作为FOA优化的ELM预测模型的输入向量进行电力负荷预测。通过与DSAE-FOAELM、DSAE-ELM和IDSAE-ELM等模型的对比实验,证明了提出的预测模型能有效提高预测精度,经计算得出预测精度提升大约8%。

The development of smart grid makes the data obtained from the grid gradually increasing. In order to obtain useful information from multi-dimensional big data and accurately predict the short-term power load, this paper proposes a short-term power load forecasting method based on dimension reduction with improved deep sparse auto-encoder(IDSAE) and extreme learning machine(ELM) optimized with fruit fly optimization algorithm(FOA). Adding L1 regularization to the deep sparse auto-encoder(DSAE) can induce better sparsity, and the improved deep sparse auto-encoder is used to reduce the dimensionality of high-dimensional data that affects the accuracy of power load prediction, which eliminates the multi-collinearity among the indexes and realizes compression coding from high-dimensional data to low-dimensional space. The fruit fly optimization algorithm(FOA) is used to optimize the weights and thresholds of the extreme learning machine(ELM), and the optimal weights and thresholds are obtained, which can overcome the shortcomings of low prediction accuracy caused by the extreme learning machine randomly selecting the weights and thresholds. In this paper, the meteorological factors are first dimension reduced by the IDSAE to obtain the sparse comprehensive meteorological factor characteristic indexes, and the coordinated power load data are used as the input vector of the FOA optimized ELM prediction model to perform power load prediction. The comparison experiments with DSAE-FOAELM, DSAE-ELM, IDSAE-ELM and other models prove that the proposed prediction model can effectively improve the prediction accuracy, and the improved accuracy is about 8% after calculation.