Deep Learning in Economic Load Dispatch with Short-Term Wind Power

In economic load dispatch (ELD) complemented by wind power, it is highly desirable to develop a quick scheme to adjust the real power generated by thermal units. In this paper, we apply the deep learning (DL) methodology to solve such a problem. A system of multiple generators and 100 wind turbines is chosen as a case study. The DL scheme is implemented with the feed-forward neural network (FNN). All stages of DL, namely training, validation, and testing, are covered in the simulation. It is shown that the training and validation achieved the expected performance criteria. By using the trained FNN, the time of solving ELD is significantly reduced.

[1]  Allen J. Wood,et al.  Power Generation, Operation, and Control , 1984 .

[2]  Joseph Lipka,et al.  A Table of Integrals , 2010 .

[3]  A. Fabbri,et al.  Assessment of the cost associated with wind generation prediction errors in a liberalized electricity market , 2005, IEEE Transactions on Power Systems.

[4]  Zwe-Lee Gaing,et al.  Particle swarm optimization to solving the economic dispatch considering the generator constraints , 2003 .

[5]  Roger Fletcher,et al.  Practical methods of optimization; (2nd ed.) , 1987 .

[6]  Xian Liu,et al.  Economic Load Dispatch Constrained by Wind Power Availability: A Wait-and-See Approach , 2010, IEEE Transactions on Smart Grid.

[7]  Wilsun Xu,et al.  Economic Load Dispatch Constrained by Wind Power Availability: A Here-and-Now Approach , 2010, IEEE Transactions on Sustainable Energy.

[8]  Dick Duffey,et al.  Power Generation , 1932, Transactions of the American Institute of Electrical Engineers.

[9]  Philip G. Hill,et al.  Power generation , 1927, Journal of the A.I.E.E..

[10]  Willem K. Klein Haneveld,et al.  Stochastic Linear Programming Models , 1986 .

[11]  Nikos D. Sidiropoulos,et al.  Learning to optimize: Training deep neural networks for wireless resource management , 2017, 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[12]  John R. Birge,et al.  Introduction to Stochastic programming (2nd edition), Springer verlag, New York , 2011 .

[13]  Aarnout Brombacher,et al.  Probability... , 2009, Qual. Reliab. Eng. Int..

[14]  A. Llombart,et al.  Statistical Analysis of Wind Power Forecast Error , 2008, IEEE Transactions on Power Systems.

[15]  Xian Liu,et al.  QoS-Aware Power Management with Deep Learning , 2019, 2019 IFIP/IEEE Symposium on Integrated Network and Service Management (IM).