基于改进天牛须搜索算法优化LSSVM短期电力负荷预测方法研究

Research of LSSVM short-term load forecasting method based on the improved beetle antennae search algorithm

为提高短期电力负荷预测精度,提出了一种天牛须搜索算法优化的LSSVM短期电力负荷预测模型。引入模拟退火算法的蒙特卡洛法则对优化算法进行改进,提高了该算法的稳定性。将改进BAS算法优化后的LSSVM模型用于短期电力负荷预测问题。使用小波阈值去噪处理电力负荷数据,减少一些不确定性因素对负荷预测的影响,提高了预测精度。选择四川某地区电网实际历史负荷数据进行分析和预测,并与PSO-LSSVM、LSSVM预测模型进行对比分析。算例结果表明,所提出的IBAS-LSSVM预测模型与LSSVM相比预测精度提升了1.5%左右,与PSO-LSSVM相比算法运行时间缩短了70%,且算法稳定性更高,证明了该方法的实用性与有效性。

In order to improve the short-term power load forecasting accuracy,a LSSVM short-term power load forecasting model based on beetle antennae search algorithm optimization is proposed in this paper.The Monte Carlo rule of simulated annealing algorithm is introduced to improve the optimized algorithm,which improves the stability of the algorithm.The prediction precision is improved with the use of wavelet threshold de-noising of power load data,which reduces the influence of uncertain factors on load forecasting.The actual historical load data of a regional power grid in Sichuan are selected for analysis and prediction,and compared with PSO-LSSVM and LSSVM prediction models.Numerical example shows that compared with LSSVM,the BAS-LSSVM prediction model proposed in this paper has improved the prediction accuracy by 1.55%.The running time of the algorithm is reduced by 70%compared with PSO-LSSVM,and the algorithm is more stable,which proves the practicability and effectiveness of the proposed method.