Energy Optimization of Solar Micro-Grid Using Multi Agent Reinforcement Learning

Abstract:

In this paper, two solar Photovoltaic (PV) systems are considered; one in the department with capacity of 100 kW and the other in the hostel with capacity of 200 kW. Each one has battery and load. The capital cost and energy savings by conventional methods are compared and it is proved that the energy dependency from grid is reduced in solar micro-grid element, operating in distributed environment. In the smart grid frame work, the grid energy consumption is further reduced by optimal scheduling of the battery, using Reinforcement Learning. Individual unit optimization is done by a model free reinforcement learning method, called Q-Learning and it is compared with distributed operations of solar micro-grid using a Multi Agent Reinforcement Learning method, called Joint Q-Learning. The energy planning is designed according to the prediction of solar PV energy production and observed load pattern of department and the hostel. A simulation model was developed using Python programming.

• Periodical: Applied Mechanics and Materials (Volume 787)
• Pages: 843-847
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.787.843
• Online since: August 2015
• Authors: Leo Raju*, R.S. Milton, S. Sakthiyanandan
• Keywords: Distributed Optimization, Multi Agent Reinforcement Learning, Smart Grid, Solar Micro-Grid

References

[1] Tine L. Vandoorn, Lieven Vandevelde, Contribution of micro-grids to development of SmartGrid, Smart grids : clouds, communications, open source, and automation. In Devices, Circuits and Systems pp.191-211, CRC Press, Washington, (2014).

DOI: 10.1201/b16908-9

[2] Ross Guttromson, Steve Glover, The advanced micro-grid integration and interoperability. Sandia National Laboratories, Sandia report, March (2014).

[3] ND Hatziargyriou, European transactions on electrical energy, Special issue: Micro-grid and energy management (2010), pp.1139-141.

[4] M. Abdirahman, M. W. Abdilahi, G. Mustafa, J Aliyu, Usman, Autonomous Integrated Micro-grid (AIMG) System, International Journal of Education and Research, 2 (1) (2014), pp.77-82.

[5] Z. Jun, L. Junfeng, W Jie, H Ng, A multi-agent solution to energy management in hybrid renewable energy generation system, Renewable Energy, 36 (5) (2011), pp.1352-63.

DOI: 10.1016/j.renene.2010.11.032

[6] M. Aymen Chaouachi, M. Rashad,. Kamel, Ridha Andoulsi, Ken Nagasaka, Multi objective Intelligent Energy Management for a Micro-grid. IEEE Transactions, Industrial Electronics, 60(4), (2013), pp.1688-99.

DOI: 10.1109/tie.2012.2188873

[7] E. Kuznetsova, Y. F. Li, C. Ruiz, E Zio, G. Ault, L. K Bel, Reinforcement learning for micro-grid energy management, Energy Journal, (59) (2013), pp.133-46.

DOI: 10.1016/j.energy.2013.05.060

[8] R. S. Sutton, A. G Barto, Reinforcement Learning: An introduction. London, England: The MIT Press, (1998).

[9] Marco Wiering, Martijn van Otterlo Ma, Reinforcement Learning: State- of-the- Art. New York: Springer; (2012).

[10] Gerhard Weiss, Multi Agent Systems. London, England: The MIT Press, (2013).

[11] Information on http: /www. nrel. gov.