Abstract
The scope of this research is to propose an adaptive machine learning approach which can help the WSN’s nodes to manage their transmission power and to improve the internode wireless communications. The optimized transmission power has benefits in terms of WSN energy consumption and RF interlink interference. The paper proposes an adaptive method of a wireless sensor node based on Multi-Layer Perceptron (MLP) network representation and machine learning. The presented in the paper approach uses the SARSA (State-Action-Reward-State-Action) algorithm which is a form of reinforcement machine learning. The aim of the new method is to improve the sensor nodes Transmission Power Management (TPM) process. This inspires many practical solutions that max-imize resource utilization and prolong the shelf life of the battery-powered wireless sensor networks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gummeson, J., Ganesan, D., Corner, M.D., Shenoy, P.: An adaptive link layer for heterogeneous multi-radio mobile sensor networks. IEEE J. Sel. Areas Commun. 28, 1094–1104 (2010)
Lange, S., Gabel, T., Riedmiller, M.: Batch reinforcement learning. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning. Adaptation, Learning, and Optimization, vol. 12, pp. 45–73. Springer, Heidelberg (2012)
Rummery, G., Niranjan, M.: On-line Q-learning using Connectionist systems, Technical report no.166, University of Cambridge, Engineering Department (1994)
Watkins, J.C.H.: Learning from Delayed Rewards, Ph.D. thesis, University of Cambridge, England (1989)
Torrey, L., Shavlik, J.: Transfer learning. In: Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, pp. 242–264. IGI Global, Hershey, PA, USA (2009)
Sung, Y., Ahn, E., Cho, K.: Q-learning reward propagation method for reducing the transmission power of sensor nodes in wireless sensor networks. Wirel. Pers. Commun. 73, 257–273 (2013)
Udenze, A., McDonald-Maier, K.: Direct reinforcement learning for autonomous power configuration and control in wireless networks. In: Proceedings of the NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009, pp. 289–296, San Francisco, CA, USA, 29 July-1 August 2009
Forster, A.: Machine learning techniques applied to wireless ad-hoc networks: Guide and survey. In: 3rd International Conference on Intelligent Sensors, Sensor Networks and In-formation, pp. 365–370. IEEE (2007)
Alexandrov, A., Monov, V.: Q-learning based model of node transmission power management in WSN. In: Proceedings of International Conference on Big Data, Knowledge and Control Systems Engineering BdKCSE 2018, pp. 15–112, 21–22 November 2018
Kaelbling, L.P., Littman, M.L., Moore, A.P.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237–285 (1996)
Hocenski, Z., Antunovic, M., Filko, D.: Accelerated gradient learning algorithm for neural network weights update. In: Lovrek, I., Howlett, R.J., Jain, L.C. (eds.) KES 2008, Part I. LNCS (LNAI), vol. 5177, pp. 49–56. Springer, Heidelberg (2008)
Kadam, K., Srivastava, N.: Application of machine learning (reinforcement learning) for routing in Wireless Sensor Networks (WSNs). In: 1st International Symposium on Physics and Technology of Sensors (ISPTS-1), Vol. 2012, pp. 349–352, Pune (2012). https://doi.org/10.1109/ISPTS.2012.6260967
Cirstea, C., Davidescu, R., Gontean, A.: A reinforcement learning strategy for task scheduling of WSNs with mobile nodes. In: 2013 36th International Conference on Telecommunications and Signal Processing (TSP), pp. 348–353, Rome (2013). https://doi.org/10.1109/TSP.2013.6613950
Zhang, B., Wu, W., Bi, X., Wang, Y.: A task scheduling algorithm based on Q-learning for WSNs. In: Liu, X., Cheng, D., Jinfeng, L. (eds.) ChinaCom 2018. LNICST, vol. 262, pp. 521–530. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-06161-6_51
Wei, Z., Zhang, Y., Xiangwei, X., Shi, L., Feng, L.: A task scheduling algorithm based on Q-learning and shared value function for WSNs. Comput. Netw. 126, 141–149 (2017)
Van Seijen, H., Van Hasselt, H., Whiteson, S., Wiering, M.: A theoretical and empirical analysis of expected Sarsa. In: 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Nashville, 30 March-2 April 2009, pp. 177–184 (2009). https://doi.org/10.1109/ADPRL.2009.4927542
Yu, S., Zhou, J., Li, B., Mabu, S., Hirasawa, K.: Q value-based Dynamic Programming with SARSA Learning for real time route guidance in large scale road networks. In: Proceedings of the International Joint Conference on Neural Networks, pp. 1–7 (2012)
Wen, F., Wang, X.: Sarsa learning based route guidance system with global and local parameter strategy. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. E98A(12), 2686–2693 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Alexandrov, A., Monov, V. (2020). SARSA Based Method for WSN Transmission Power Management. In: Vishnevskiy, V.M., Samouylov, K.E., Kozyrev, D.V. (eds) Distributed Computer and Communication Networks: Control, Computation, Communications. DCCN 2020. Communications in Computer and Information Science, vol 1337. Springer, Cham. https://doi.org/10.1007/978-3-030-66242-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-66242-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66241-7
Online ISBN: 978-3-030-66242-4
eBook Packages: Computer ScienceComputer Science (R0)