An Efficient Load Forecasting in Predictive Control Strategy Using Hybrid Neural Network

Abstract

Load forecasting is a difficult task, because the load series is complex and exhibits several levels of seasonality. The load at a given hour is dependent not only on the load at the previous day, but also on the load at the same hour on the previous day and previous week, and because there are many important exogenous variables that must be considered. Most of the researches were simultaneously concentrated on the number of input variables to be considered for the load forecasting problem. In this paper, we concentrate on optimizing the load demand using forecasting of the weather conditions, water consumption, and electrical load. Here, the neural network (NN) power load forecasting model clubbed with Levy-flight from cuckoo search algorithm is proposed, i.e., called hybrid neural network (HNN), and named as LF-HNN, where the Levy-flight is used to automatically select the appropriate spread parameter value for the NN power load forecasting model. The results from the simulation work have demonstrated the value of the LF-HNN approach successfully selected the appropriate operating mode to achieve optimization of the overall energy efficiency of the system using all available energy resources.