科研之友
微信
新浪微博
Facebook
分享链接
摘要
Annual power load forecasting is essential for the planning, operation and maintenance of electric power system, which can also mirror the economic development of a country or region to some extent. Accurate annual power load forecasting can provide valuable reference for electric power system operators and economic managers. With the development of smart grid and renewable energy power, power load forecasting has become a more difficult and challenging task. In this paper, a hybrid optimized grey model (namely Grey Modelling (1, 1) optimized by Ant Lion Optimizer with Rolling mechanism, abbreviated as Rolling-ALO-GM (1, 1)) was proposed. The parameters of Grey Modelling (1, 1) were optimally determined by employing Ant Lion Optimizer, which is a new nature-inspired metaheuristic algorithm. Meanwhile, the rolling mechanism was incorporated to improve the forecasting accuracy. Two cases of annual electricity consumption in China and Shanghai city were selected to verify the effectiveness and feasibility of the proposed Rolling-ALO-GM (1, 1) for annual power load forecasting. The empirical results indicate the proposed Rolling-ALO-GM (1, 1) model shows much better forecasting performance than Grey Modelling (1,1), Grey Modelling (1,1) optimized by Particle Swarm Optimization, Grey Modelling (1, 1) optimized by Ant Lion Optimizer, Generalized Regression Neural Network, Grey Modelling (1, 1) with Rolling mechanism, and Grey Modelling (1, 1) optimized by Particle Swarm Optimization with Rolling mechanism. Ant Lion Optimizer, as a new intelligence optimization algorithm, is attractive and promising. The Grey Modelling (1, 1) optimized by Ant Lion Optimizer with Rolling mechanism can significantly improve annual power load forecasting accuracy.
- 出版日期2016-7-15
- 单位华北电力大学; 华北电力大学（保定）
