Hierarchical Simulated Annealing-Reinforcement Learning Energy Management for Smart Grids

Abstract:

For energy management problems in smart grid, a hybrid intelligent hierarchical controller based on simulated annealing (SA) and reinforcement learning (RL) is proposed. The SA is used to adjust the parameters of the controller. The RL algorithm shows the particular superiority, which is independent of the mathematic model and just needs simple fuzzy information obtained through trial-and-error and interaction with the environment. By means of learning procedures, the proposed controller can learn to take the best actions to regulate the energy usage for equipments with the features of high comfortable for energy usage and low electric charge meanwhile. Simulation results show that the proposed load controller can promote the performance energy usage in smart grids.

• Periodical: Advanced Materials Research (Volumes 805-806)
• Pages: 1206-1209
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.805-806.1206
• Online since: September 2013
• Authors: Xin Li, Chuan Zhi Zang, Xiao Ning Qin, Yang Zhang, Dan Yu
• Keywords: Energy Management, Hierarchical, Reinforcement Learning

References

[1] D. O'Neil, M. Levorato, A. Goldsmith, U. Mitra, Residential Demand Response Using Reinforcement Learning, IEEE International Conference on Samrt Grid Communications, (2010), pp.409-414.

DOI: 10.1109/smartgrid.2010.5622078

[2] J. Wang, S. Kennedy, and J. Kirtley, A New Whole Bidding Mechanism for Enhanced Demand Response in Smart Grids, Innovative Smart Grid Technologies, (2010).

DOI: 10.1109/isgt.2010.5434766

[3] S. D. Maqbool, M. Baba, E. A. Al-Amma. Effects of Demand Elasticity and Price Variation on Load Profile, IEEE PES Conference on Innovative Smart Grid Technologies - Middle East, (2011), pp.1-5.

DOI: 10.1109/isgt-mideast.2011.6220793

[4] M. LeMay, R. Nelli, G. Gross, A. Gunter, An Integrated Architecture for Demand Response Communications and Control, International Conference on System Sciences, (2008), p.174.

DOI: 10.1109/hicss.2008.60

[5] C. L. Su, and D. Kirschen, Direct Participation of Demand-Side in a Pool-based electricity market, Power System Technology, Vol. 31, No. 20 (2007), pp.7-14.

[6] Q. Dam, S. Mohagheghi, J. Stoupis, Intelligent Demand Response Scheme for Customer Side Load Management, IEEE Energy 2030 Conference, (2008), pp.1-7.

DOI: 10.1109/energy.2008.4781013

[7] A. F. Atiya, A. G. Parlos and L. Ingber, A reinforcement learning method based on adaptive simulated annealing, in Proc. of the 46th International Midwest Symposium on Circuits and Systems, (2003), pp.121-124.

DOI: 10.1109/mwscas.2003.1562233

[8] M. Rajesh, Kandadai and J. M. Tien, A knowledge-based generating hierarchical fuzzy-neural controller, IEEE Transactions on Neural Networks, Vol. 8, No. 6 (1997), pp.1531-1540.

DOI: 10.1109/72.641474

[9] M. G. Ji, Z. H. Jin and H. W. Tang, An improved simulated annealing for solving the linear constrained optimization problems, Applied Mathematics and Computation, Vol. 183, No. 1 (2006), pp.251-259.

DOI: 10.1016/j.amc.2006.05.070