基于CEEMD-ISSA-LSSVM的日前电力市场价格预测

Day Ahead Electricity Market Price Forecasting Based on CEEMD-ISSA-LSSVM

日前电价预测的准确性对电力市场参与者的现货市场参与程度、交易策略选择、经济收益情况均有较大影响。针对电力现货市场日前电价序列具有较强的波动性,提出了一种基于互补集成经验模态分解-改进麻雀搜索算法-最小二乘法支持向量机的日前电力市场价格预测模型。首先,采用灰色关联分析法筛选得到预测日的相似日集合,然后利用互补集成经验模态分解法将相似日的历史电价序列分解;其次,以改进的麻雀搜索算法优化最小二乘法支持向量机得到改进麻雀搜索算法-最小二乘法支持向量机预测模型,并分别对分解结果进行预测,将预测结果叠加,最终得到日前电价预测值。经过算例仿真,其结果表明:与其他预测模型对电价的预测相比,所提方法具有更高的预测精度。

The accuracy of the day-ahead electricity price forecast has a great impact on the participation of electricity market participants in the spot market,the choice of trading strategies,and the economic benefits.Aiming at the strong volatility of the day-ahead electricity price sequence in the electricity spot market,a dayahead electricity market price prediction model based on CEEMD-ISSA-LSSVM is proposed.The grey relational analysis method was utilized to screen out the similar days set of forecast days,and the complementary ensemble empirical mode decomposition(CEEMD)method was used to decompose the historical electricity price series of similar days.Then the improved sparrow search algorithm(ISSA)is used to optimize the least square support vector machine(LSSVM)to obtain the ISSA-LSSVM prediction model,respectively predict the decomposition results,and carry out the prediction results.Superimpose to obtain the forecast value of the electricity price for the day before.After the simulation of the example,the electricity price forecast is compared with other forecasting models,and the results show that the proposed method has higher forecasting accuracy.