基于指数加权算子与自适应粒子群优化灰色模型的负荷预测

针对传统灰色预测模型GM(1,1)在预测增长较快的电力负荷时预测效果变差及数据离散度越大导致预测精度越差这一局限性,对传统灰色预测模型做进行改进。一方面,采用指数加权算子对原始数据序列进行处理,有效地减弱异常值的影响,强化了原始数据序列的大致趋势;另一方面,利用自适应粒子群优化算法与GM(1,1)模型相结合,优化GM(1,1)模型中的背景值,使其更合理,使原始信息得到更好的利用。

Power Load Forecasting Based on Grey Model Optimized by Index Weighted Operator and Adaptive Particle Swarm Optimization

When the power load forecasting grows quick and dispersion of data is great,the traditional gray prediction model GM(1,1) becomes worse.This paper proposes an improved grey forecasting model.On the one hand,the original data sequences are processed by index weighted operator,which can effectively weaken the impact of outliers,and strengthen the general trend of the original data series;on the other hand,combine adaptive particle swarm optimization algorithm with the GM(1,1) model for optimizing the background data in GM(1,1) model to make it more reasonable and make better use of the original message.