An effective spectrum handoff based on reinforcement learning for target channel selection in the industrial Internet of Things

Oyewobi, SSHancke, GPAbu-Mahfouz, Adnan MIOnumanyi, Adeiza J2019-11-082019-11-082019-03Oyewobi, S.S. et al. 2019. An effective spectrum handoff based on reinforcement learning for target channel selection in the industrial Internet of Things. Sensors, vol. 19, no. 6, pp. 1-21978-1-7281-3666-0978-1-7281-3667-71424-8220https://www.mdpi.com/1424-8220/19/6/1395DOI: 10.3390/s19061395http://hdl.handle.net/10204/11208Copyright 2019 The Authors. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.The overcrowding of the wireless space has triggered a strict competition for scare network resources. Therefore, there is a need for a dynamic spectrum access (DSA) technique that will ensure fair allocation of the available network resources for diverse network elements competing for the network resources. Spectrum handoff (SH) is a DSA technique through which cognitive radio (CR) promises to provide effective channel utilization, fair resource allocation, as well as reliable and uninterrupted real-time connection. However, SH may consume extra network resources, increase latency, and degrade network performance if the spectrum sensing technique used is ineffective and the channel selection strategy (CSS) is poorly implemented. Therefore, it is necessary to develop an SH policy that holistically considers the implementation of effective CSS, and spectrum sensing technique, as well as minimizes communication delays. In this work, two reinforcement learning (RL) algorithms are integrated into the CSS to perform channel selection. The first algorithm is used to evaluate the channel future occupancy, whereas the second algorithm is used to determine the channel quality in order to sort and rank the channels in candidate channel list (CCL). A method of masking linearly dependent and useless state elements is implemented to improve the convergence of the learning. Our approach showed a significant reduction in terms of latency and a remarkable improvement in throughput performance in comparison to conventional approaches.enChannel selection strategyCognitive radioDynamic spectrum accessIndustrial-internet of ThingsReinforcement learningSpectrum handoffAn effective spectrum handoff based on reinforcement learning for target channel selection in the industrial Internet of ThingsArticleOyewobi, S., Hancke, G., Abu-Mahfouz, A. M., & Onumanyi, A. (2019). An effective spectrum handoff based on reinforcement learning for target channel selection in the industrial Internet of Things. http://hdl.handle.net/10204/11208Oyewobi, SS, GP Hancke, Adnan MI Abu-Mahfouz, and AJ Onumanyi "An effective spectrum handoff based on reinforcement learning for target channel selection in the industrial Internet of Things." (2019) http://hdl.handle.net/10204/11208Oyewobi S, Hancke G, Abu-Mahfouz AM, Onumanyi A. An effective spectrum handoff based on reinforcement learning for target channel selection in the industrial Internet of Things. 2019; http://hdl.handle.net/10204/11208.TY - Article AU - Oyewobi, SS AU - Hancke, GP AU - Abu-Mahfouz, Adnan MI AU - Onumanyi, AJ AB - The overcrowding of the wireless space has triggered a strict competition for scare network resources. Therefore, there is a need for a dynamic spectrum access (DSA) technique that will ensure fair allocation of the available network resources for diverse network elements competing for the network resources. Spectrum handoff (SH) is a DSA technique through which cognitive radio (CR) promises to provide effective channel utilization, fair resource allocation, as well as reliable and uninterrupted real-time connection. However, SH may consume extra network resources, increase latency, and degrade network performance if the spectrum sensing technique used is ineffective and the channel selection strategy (CSS) is poorly implemented. Therefore, it is necessary to develop an SH policy that holistically considers the implementation of effective CSS, and spectrum sensing technique, as well as minimizes communication delays. In this work, two reinforcement learning (RL) algorithms are integrated into the CSS to perform channel selection. The first algorithm is used to evaluate the channel future occupancy, whereas the second algorithm is used to determine the channel quality in order to sort and rank the channels in candidate channel list (CCL). A method of masking linearly dependent and useless state elements is implemented to improve the convergence of the learning. Our approach showed a significant reduction in terms of latency and a remarkable improvement in throughput performance in comparison to conventional approaches. DA - 2019-03 DB - ResearchSpace DP - CSIR KW - Channel selection strategy KW - Cognitive radio KW - Dynamic spectrum access KW - Industrial-internet of Things KW - Reinforcement learning KW - Spectrum handoff LK - https://researchspace.csir.co.za PY - 2019 SM - 978-1-7281-3666-0 SM - 978-1-7281-3667-7 SM - 1424-8220 T1 - An effective spectrum handoff based on reinforcement learning for target channel selection in the industrial Internet of Things TI - An effective spectrum handoff based on reinforcement learning for target channel selection in the industrial Internet of Things UR - http://hdl.handle.net/10204/11208 ER -