华东交通大学学报Issue(1)：93-98,104,7.
基于果蝇优化灰色神经网络的年电力负荷预测
Annual Electric Load Forecasting Based on Gray Neural Network with Fruit Fly Optimization Algorithm
傅军栋 1刘晶 1喻勇1
作者信息
- 1. 华东交通大学电气与电子工程学院，江西 南昌 330013
- 折叠
摘要
Abstract
The accuracy of annual electric load forecasting plays an important role in economic and social benefits of electric power systems. The Gray Neural Network is an innovative computing approach, which has found wide application in reality. As a novel meta-heuristic and evolutionary algorithm, the fruit fly optimization algorithm has the advantages of being easy to understand and fast convergence to the global optimal solution. Therefore, to improve the forecasting performance, this paper proposes a GNN-based annual electric load forecasting model that uses FOA to automatically determine the appropriate values of the parameters for the GNN model to improve the forecasting accuracy and stability of the model. By taking the annual electricity consumption of China as an in⁃stance, the computational result shows that the GNN combined with FOA outperforms other alternative methods, namely the single GNN, the generalized regression neural network, the least squares support vector machine (LSSUM) and the regression model.关键词
年度电力负荷预测/灰色神经网络/果蝇优化算法/优化问题Key words
annual electric load forecasting/gray neural network/fruit fly optimization algorithm/optimization problem分类
信息技术与安全科学引用本文复制引用
傅军栋,刘晶,喻勇..基于果蝇优化灰色神经网络的年电力负荷预测[J].华东交通大学学报,2015,(1):93-98,104,7.
