Application a Novel Evolutionary Computation Algorithm for Load Forecasting of Air Conditioning

The accuracy in load forecasting of Air Conditioning is not only of magnificent meaning to high efficacy air-conditioning operation, but also of key advantage to the presently developing Smart Microgrid (SMG) power generating system control. In the present study, Wavelet Neural Network (WNN) was adopted as a principle part for load forecasting of Air Conditioning, and with Improvement Differential Evolution Algorithm (IDEA) as an optimizing method in adjusting WNN parameters, replacing formal method of feedback from solving network parameters. IDEA is a rising optimizing tech-nique in the solving process, with simple in realizing, less in adjustable parameters, thus the real optimum solution of the entire system can be acquired more accurately and rapidly. After each optimum parameters solved for WNN, further apply WNN to accomplish real load forecasting of air-conditioning, The study also made practical comparisons among generally applied methods for optimizing air-conditioning forecasting, such as Artificial Neural Network (ANN), Evolutionary Programming-Artificial Neural Net-work (EP-ANN), Genetic Algorithm- Artificial Neural Network (GA-ANN), Ant Colony Optimization- Artificial Neural Network (ACO-ANN) and Particle Swarm Optimization- Artificial Neural Network (PSO-ANN), to prove the advantageous and applicability of the study.