Energy-Efficient AP Selection Using Intelligent Access Point System to Increase the Lifespan of IoT Devices

• DOI: 10.3390/s23115197
• Publication Date: 2023-05-31T06:57:10Z
• Authors: Seungjin Lee; Jaeeun Park; Hyungwoo Choi; Hyeontaek Oh
• Keywords: reinforcement learning; Chemical technology; Longevity; Health Behavior; Intelligence; TP1-1185; 7. Clean energy; internet of things; Article; AP selection; Physical Phenomena; Computer Simulation; energy efficiency; latency; AP selection; energy efficiency; latency; internet of things; reinforcement learning

With the emergence of various Internet Things (IoT) technologies, energy-saving schemes for IoT devices have been rapidly developed. To enhance energy efficiency in crowded environments with multiple overlapping cells, selection access points (APs) should consider conservation by reducing unnecessary packet transmission activities caused collisions. Therefore, this paper, we present a novel energy-efficient AP scheme using reinforcement learning to address problem unbalanced load that arises from biased connections. Our proposed method utilizes Energy and Latency Reinforcement Learning (EL-RL) model takes into account average consumption latency devices. In EL-RL model, analyze collision probability Wi-Fi networks reduce number retransmissions induces more higher latency. According simulation, achieves maximum improvement 53% efficiency, 50% uplink latency, 2.1-times longer expected lifespan compared conventional scheme.