Reinforcement Learning Based Adaptive Duty Cycling in LR-WPANs

• Main Authors: Shahzad Sarwar, Rabia Sirhindi, Laeeq Aslam, Ghulam Mustafa, Muhammad Murtaza Yousaf, Syed Waqar Ul Qounain Jaffry
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Duty cycling; IEEE 802154; reinforcement learning; super frame parameters
• Online Access: https://ieeexplore.ieee.org/document/9183929/

For conserving energy, duty cycle is defined by setting up the active and sleep periods of network nodes. In beacon enabled networks, to provide support for duty cycle, the IEEE 802.15.4 standard uses optional super-frame structure. This duty cycle is usually fixed and does not consider the topology changes that often occur in dynamic sensor networks. In this paper, existing energy conserving duty cycling approaches for 802.15.4 networks especially the adaptive duty cycling techniques for wireless sensor networks are summed up. Also, this paper highlights the shortcomings of the proposals in the literature, such as induced additional latency, so that they may not support the practical scenarios of Internet of Things (IoT). Further, this study highlights a gross shortcoming that relative performance comparison of RL-based proposals cannot be performed without using a benchmarking framework and real test-bed environment. In this paper, we have presented the future research directions that would lay the foundation for successful development of energy efficient RL-based duty-cycling techniques.