Nowadays, Wireless sensor network is highly potential area in various sectors like industry, research, medical, education and IOT. Sensor nodes are generally equipped with tiny battery to perform various operations. The key area is to save energy consumption of WSN node. In this research study, we have proposed a novel algorithm to better improve the energy optimization using reinforcement learning. The reinforcement learning technique is based upon state, action, policy and certain learning and discount factors. We have simulated the proposed algorithm in mat lab and compared the findings with state of the art algorithm like RL-CRC [26] to better improve energy consumption and other performance parameters.

Wireless Sensor Network, Reinforcement Learning, State, Action, Policy, Learning and Discount factor

[1] Christopher J.C.H. Watkins, Technical Note Q-Learning, Kluwer Academic Publishers, Boston Machine Learning, 8, 279-292 (1992).
[2] Leslie Pack Kaelbling, Michael L. Littman, Andrew W. Moore, Reinforcement Learning: A Survey, Journal Of Artificial Intelligence Research 4, 237-285, (1996).
[3] Yu-Han Chang, Tracey Ho, Leslie Pack Kaelbling Mobilized Ad-Hoc Networks: A Reinforcement Learning Approach, Massachusetts Institute Of Technology — Computer Science And Artificial Intelligence Laboratory, (2003).
[4] Jamal N. Al-Karaki, The Hashemite University Ahmed E. Kamal, Iowa State University, Routing Techniques In Wireless Sensor Networks: A Survey, Ieee Wireless Communications December (2004).
[5] Aram Galstyan, Bhaskar Krishnamachari, Kristina Lerman, Resource Allocation And Emergent Coordination In Wireless Sensor Networks,Copyright © 2004, American Association For Artificial Intelligence (Www.Aaai.Org). All Rights Reserved (2004).
[6] J. N. Al-Karaki And A. E. Kamal, "Routing Techniques In Wireless Sensor Networks: A Survey," In IEEE Wireless Communications, Vol. 11, No. 6, Pp. 6-28, Doi: 10.1109/MWC.2004.1368893 , (2004).
[7] Z Liu , I Elhanany, RL-MAC: A Qos Aware Reinforcement Learning Based Mac Protocol For WSN, 1-4244-0065-1/06/$20.00 © IEEE (2006).
[8] N I K L A S W I R S T R Ö M, Optimization Of Wireless Sensor Networks Using Machine Learning, MS Thesis KTH CS And Foundation (2006).
[9] Ping Wang,Ting Wang, Adaptive Routing For Sensor Networks Using Reinforcement Learning, Proceedings Of The Sixth IEEE International Conference On Computer And Information Technology (CIT`06),0-7695-2687-X/06 $20.00 © IEEE (2006).
[10] Vladimir Dyo, Cecilia Mascolo, Efficient Node Discovery In Mobile Wireless Sensor Networks, (2007).
[11] Anna Egorova-F¨Orster Amy L. Murphy, Exploiting Reinforcement Learning For Multiple Sink Routing In Wsns, 1-4244-1455-5/07/$25.00, © IEEE (2007).
[12] Anna F¨Orster,University Of Lugano, Switzerland, Machine Learning Techniques Applied To Wireless Ad-Hoc Networks: Guide And Survey ,1-4244-1502-0/07/$25.00 © IEEE (2007).
[13] Anna F¨Orstery And Amy L. Murphy, FROMS: Feedback Routing For Optimizing Multiple Sinks In WSN With Reinforcement Learning, 1-4244-1502-0/07/$25.00 © IEEE (2007).
[14] E. Fasolo, M. Rossi, J. Widmer And M. Zorzi, "In-Network Aggregation Techniques For Wireless Sensor Networks: A Survey," In IEEE Wireless Communications, Vol. 14, No. 2, Pp. 70-87, Doi: 10.1109/MWC.2007.358967 (2007).
[15] Kunal Shah* And Mohan Kumar,*Sensorlogic Inc., Addison TX 75001, Distributed Independent Reinforcement Learning (DIRL) Approach To Resource Management In Wireless Sensor Networks, 1-4244-1455-5/07/$25.00 © IEEE (2007).
[16] Anna F¨Orster,Amy L. Murphy, Balancing Energy Expenditure In Wsns Through ,Reinforcement Learning: A Study, Workshop On Energy In Wireless Sensor Networks (WEWSN2008), Santorini Island, (2008).
[17] Mihail Mihaylov, Karl Tuyls,Ann Nowé, Decentralized Learning In Wireless Sensor Networks, Proc. Of The Adaptive And Learning Agents Workshop (ALA 2009), Taylor And Tuyls (Eds.), Budapest, Hungary (2009).
[18] Anna F¨Orster, Amy L. Murphy, CLIQUE: Role-Free Clustering With Reinforcement LearningFor Wireless Sensor Networks, 1063-6927/09 $25.00 © IEEE, DOI 10.1109/ICDCS.2009.43 (2009).
[19] Y. Zhang, N. Meratnia And P. Havinga, "Outlier Detection Techniques For Wireless Sensor Networks: A Survey," In IEEE Communications Surveys & Tutorials, Vol. 12, No. 2, Pp. 159-170, Second Quarter , Doi: 10.1109/SURV.2010.021510.00088 (2010).
[20] Somayeh Kianpisheh And Nasrolah Moghadam Charkari, A New Approach For Power Management In Sensor Node Based On Reinforcement Learning, © IEEE (2011).
[21] Nauman Ahad, Junaid Qadir, Nasir Ahsan, Neural Networks In Wireless Networks: Techniques, Applications And Guidelines, Journal Of Network And Computer Applications, Volume 68, Pages 1-27, ISSN 1084-8045, Http://Doi.Org/10.1016/J.Jnca.2016.04.006,(2016).
[22] Q. Zhou, D. Li, S. Kar, L. M. Huie, H. V. Poor And S. Cui, "Learning-Based Distributed Detection-Estimation In Sensor Networks With Unknown Sensor Defects," In IEEE Transactions On Signal Processing, Vol. 65, No. 1, Pp. 130-145, Doi: 10.1109/TSP.2016.2613062,(2017).
[23] Ibrahim Mustapha, Borhanuddin M. Ali, A. Sali, M.F.A. Rasid, H. Mohamad, An Energy Efficient Reinforcement Learning Based Cooperative Channel Sensing For Cognitive Radio Sensor Networks, Pervasive And Mobile Computing, Volume 35, Pages 165-184, ISSN 1574-1192,(2017). Http://Doi.Org/10.1016/J.Pmcj.2016.07.007.
[24] Russell, S, Norvig, P.: Artificial Intelligent: A Mordern Approach, Third Edition. Prentice Hall
[25] https://in.mathworks.com/products/matlab.html
[26] Thien T. T. Le And Sangman Moh† , Reinforcement-Learning-Based Topology Control For Wireless Sensor Networks, Advanced Science And Technology Letters Vol.142 , Pp.22-27 Http : // Dx . Doi . Org /10.14257/Astl.2016.142.04,(2016).