Analysis of Energy Consumption Prediction Model Based on Genetic Algorithm and Wavelet Neural Network

This paper analyzed the enterprise process energy consumption systematically with a lot of statistic data starting from energy efficiency, and established the energy consumption prediction model based on genetic algorithm of wavelet neural network (GA-WNN). This paper made previous optimization training with genetic algorithm, which have feature of natural evolution regularity, to the weights and dilation-shift scale of wavelet neural network. Partly replaced gradient descent method of wavelet frame neural network where parameters optimization only with a single gradient direction, overcame the shortcoming that easily into the local minimum and cause oscillation effect of the single gradient descent method. Simulation results showed the effectiveness of the forecasting model, and it is feasible for solving the process energy consumption multi-factor quantitative analysis problem which general mathematical model is difficult to describe.

[1]  Yao Zhang,et al.  Software Aging Forecasting Model of Service-Oriented Application Server Based on Wavelet Network with Adaptive Genetic Algorithm , 2007, Third International Conference on Natural Computation (ICNC 2007).

[2]  Yukio Yanagisawa,et al.  Estimation of energy consumption for each process in the Japanese steel industry: a process analysis , 1999 .

[3]  Shu-Ching Chen,et al.  Function approximation using robust wavelet neural networks , 2002, 14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings..

[4]  Arjen van Ooyen,et al.  Improving the convergence of the back-propagation algorithm , 1992, Neural Networks.

[5]  Abdallah Al-Shehri,et al.  Artificial neural network for forecasting residential electrical energy , 1999 .

[6]  Peter Tino,et al.  IEEE Transactions on Neural Networks , 2009 .

[7]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[8]  Vladik Kreinovich,et al.  Wavelet neural networks are asymptotically optimal approximators for functions of one variable , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[9]  F.H.F. Leung,et al.  Genetic algorithm-based variable translation wavelet neural network and its application , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[10]  Lei Jia,et al.  Wavelet network with genetic algorithm and its applications for traffic flow forecasting , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[11]  Xie Yongle,et al.  Wavelet neural network based fault diagnosis in nonlinear analog circuits , 2006 .