On Optimizing WiFi RSSI and Channel Assignment using Genetic Algorithm for WiFi Tuning

Abstract

In this work, we proposed a genetic algorithm-based Wi-Fi-tuning platform that could facilitate the network administrators to cope with co-channel interference triggered by other wireless sources. Generally, with a well-designed WLAN, signal interference from adjacent areas is usually minimized. Unfortunately, when other wireless sources are introduced into the WLAN system, co-channel interference is inevitable. Interference usually causes degradation and/or disruption of network services. Resolving this issue becomes even more complicated when the interfering signals come from access points owned by other ISPs and are not accessible by the network administrators. This paper proposed a Wi-Fi tuning platform that allowed automatic reconfiguration of WLAN settings by finding the best settings for channel assignment and transmission power level. When signal interference is detected, the platform attempts to find heuristic solutions for wireless settings based on a genetic algorithm. From our experiments, we could see that our proposed algorithm could regenerate WLAN settings that provided stronger signal levels, higher coverage ranges while reducing interference levels in the deployment area. With the proposed platform, troubleshooting became less complicated, requiring less cost and time. With the help of the Wi-Fi tuning platform, the network administrators could promptly react to the incidence leading to the enhancement of availability, reliability, and consistency of the WLAN system.

Indoor Genetic Algorithm-Based 5G Network Planning Using a Machine Learning Model for Path Loss Estimation

“…Rational planning (i.e., minimizing the number of APs) and effective planning of the wireless network (i.e., maximizing the throughput) for indoor/outdoor operation usually requires the consecutive evaluation of many candidate solutions using optimization algorithms. Among the optimization algorithms commonly used in network planning, we can mention: e.g., heuristics [12,[22][23][24], GA [25][26][27][28], or Particle Swarm Optimization (PSO) [29][30][31].…”