Energy Management for Microgrids Using a Hierarchical Game-Machine Learning Algorithm

This paper presents an energy management strategy for microgrids using a multiagent game-learning algorithm. This microgrid is powered by photovoltaic (PV) systems equipped with batteries and is intended to be operating in islanded mode. The proposed energy management strategy is applied to wireless communication networks by addressing the tradeoff between the communication signal's quality of service (QoS) and energy availability. A two-layer algorithm combining multiagent-game and reinforcement learning (RL) is designed for base stations (BSs) in order to accomplish the goal mentioned above. The proposed method shows improvement in the microgrid's performance and has a higher converging speed compared to a direct RL approach. The designed energy management algorithm was tested in multiple case studies.

[1]  Nirwan Ansari,et al.  Green-energy Aware and Latency Aware user associations in heterogeneous cellular networks , 2013, 2013 IEEE Globecom Workshops (GC Wkshps).

[2]  Luis Alonso,et al.  A base station switching on-off algorithm using traditional MIMO and spatial modulation , 2013, 2013 IEEE 18th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD).

[3]  Rui Hu,et al.  Mixed strategy load management strategy for wireless communication network micro grid , 2016, 2016 IEEE International Telecommunications Energy Conference (INTELEC).

[4]  Tiankui Zhang,et al.  Distributed delay-energy aware user association in 3-tier HetNets with hybrid energy sources , 2014, 2014 IEEE Globecom Workshops (GC Wkshps).

[5]  Bart De Schutter,et al.  Multi-agent Reinforcement Learning: An Overview , 2010 .

[6]  Christos H. Papadimitriou,et al.  Three-Player Games Are Hard , 2005, Electron. Colloquium Comput. Complex..

[7]  Xiaohua Jia,et al.  Minimizing Energy Cost by Dynamic Switching ON/OFF Base Stations in Cellular Networks , 2016, IEEE Transactions on Wireless Communications.

[8]  Steven Homer,et al.  Computability and Complexity Theory , 2001, Texts in Computer Science.

[9]  Nikos D. Hatziargyriou,et al.  Microgrids : architectures and control , 2014 .

[10]  Alexis Kwasinski,et al.  Integrating cross-layer LTE resources and energy management for increased powering of base stations from renewable energy , 2015, 2015 13th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt).

[11]  V. V. Phansalkar,et al.  Decentralized Learning of Nash Equilibria in Multi-Person Stochastic Games With Incomplete Information , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[12]  Bhaskar Krishnamachari,et al.  Dynamic Base Station Switching-On/Off Strategies for Green Cellular Networks , 2013, IEEE Transactions on Wireless Communications.

[13]  Bhaskar Krishnamachari,et al.  Green Energy and Delay Aware Downlink Power Control and User Association for Off-Grid Solar-Powered Base Stations , 2018, IEEE Systems Journal.

[14]  Mary Hanna.  When disasters strike distributed systems , 1995 .

[15]  Tom Holvoet,et al.  Reinforcement Learning of Heuristic EV Fleet Charging in a Day-Ahead Electricity Market , 2015, IEEE Transactions on Smart Grid.

[16]  Alexis Kwasinski,et al.  The role of multimedia source codecs in green cellular networks , 2016, 2016 IEEE Wireless Communications and Networking Conference.

[17]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.