基于变分模态分解和改进粒子群算法优化最小二乘支持向量机的短期电价预测

Short term electricity price forecasting based on variational mode decomposition and improved particle swarm optimization-least square support vector machine

针对电价序列具有非线性强、波动性大的特点,提出一种基于变分模态分解(VMD)和改进粒子群算法(PSO)优化最小二乘支持向量机(LSSVM)的短期电价预测模型。首先利用VMD将原始电价数据分解为多个子序列,然后采取LSSVM模型分别对子序列进行预测。对于LSSVM预测模型的最优参数选择问题,利用改进的PSO优化LSSVM模型的参数,能够很好地提高模型预测精度。最后集成各子序列预测结果,获得最终电价预测值。为了验证所提模型的有效性,以美国PJM市场电价数据为例进行分析,并与其他预测模型进行对比,结果表明,所提模型能够很好地对短期电价进行预测。

According to the characteristics of strong non-linearity and high volatility of electricity price series,a short-term electricity price prediction model based on variational mode decomposition(VMD)and least square support vector machine(LSSVM)optimized by improved particle swarm optimization(PSO)is proposed.First of all,VMD is used to decompose the original electricity price sequence into multiple component sequences,and LSSVM modeling and prediction is performed on each component sequence.And then,in order to improve the prediction accuracy,aiming at the problem of selecting the optimal parameters of the LSSVM prediction model,an improved particle swarm algorithm is proposed to optimize the parameters of the LSSVM model.Finally,the prediction results of each component are integrated to obtain the final electricity price prediction value.In order to verify the effectiveness of the proposed model,the US PJM market electricity price data is used as an example to analyze and compare with other forecasting models.It shows that the proposed model can predict short-term electricity prices well.