基于GAELM神经网络的日前电价预测

针对日前电价预测问题,利用极限学习机建立预测模型.鉴于极限学习机在训练前随机产生输入权重和隐藏节点偏置,可能导致预测结果不稳定以及预测精度太低的问题,提出了一种基于遗传算法(GA)和极限学习机(ELM)的预测方法.首先利用遗传算法对极限学习机随机生成的参数进行寻优,然后根据优化后的参数建立基于GA-ELM的电价预测模型.最后以此模型对PJM电力市场的日前电价进行预测.结果表明,相比ELM和BP神经网络,GA-ELM具有更高的预测精度.

Day-ahead Electricity Price Forecasting Based on Genetic Algorithm and Extreme Learning Machine

Regarding day-ahead forecast of electricity price,the extreme learning machine is used to set up a model,which randomly chooses input weights and hidden layer biases,and may lead to unstable performance and low prediction accuracy.This paper proposes a new forecasting method based on genetic algorithm (GA) and extreme learning machine(ELM).First,the genetic algorithm is used to determine the optimal parameters of the extreme learning machine.Secondly,the model of electricity price forecasting with optimized parameters is constructed based on GA-ELM.Finally,the proposed model is applied to day-ahead electricity price forecast of Pennsylvania-New Jersey-Maryland (PJM),and forecast results show that the proposed model has a higher accuracy than ELM and BP neural networks.