Optimizing Access Point Placement in Industrial IoT: A Deep Reinforcement Learning Approach With Q-Learning Verification and Signal Heatmap Visualization

Optimal access point (AP) placement inside an industrial layout is important to ensure excellent connectivity. However, wireless fidelity (Wi-Fi) AP placement is complicated because industries exhibit distinct radio propagation characteristics and channel models compared to typical indoor offices and hotspots. In this work, we employ deep reinforcement learning (DRL) and Q-learning to optimize AP placement, with circle packing as the baseline. The performance metrics used are average received signal strength (RSS), average interference, and signal coverage across the industrial floor. These performance metrics are used to tailor the reward function used in DRL and Q-learning. The results obtained are reasonable, with an increase in average RSS by 3.55% and a decrease in average interference by 5.73% in one instance, and a 4.59% increase in signal coverage in another instance, compared to the results obtained using circle packing. DRL performed the best, followed by Q-learning and circle packing. Q-learning, though, matched the performance of DRL when the number of APs was low. An exploration prioritized epsilon decay function provided better results than an exploitation prioritized epsilon decay function, while the latter took less time to complete. The optimized AP locations and the corresponding RSS are further visualized using Wi-Fi heat maps. The proposed technique is effective for both small and large scaled industrial areas. However, the learning process takes significantly longer to complete in larger industrial areas. The technique presented in this work can be used during the initial network setup or to improve an existing network.