Channel estimation using heuristic algorithm methods

With the increasing demands of modern wireless communication systems for high data rates, low latency, and reliable transmission, innovative solutions have become essential. In this context, Orthogonal Frequency Division Multiplexing (OFDM) has emerged as a dominant technique due to its high spectral efficiency, robustness against multipath fading, and simplified modulation/demodulation processes. However, the performance of OFDM systems is significantly affected by the time-varying and frequency-selective nature of wireless channels, making channel estimation a critical issue. This thesis addresses the problem of channel estimation in OFDM systems using heuristic optimization algorithms. Traditional estimation methods such as Least Squares (LS) and Minimum Mean Square Error (MMSE) rely heavily on statistical assumptions and prior knowledge of the channel, which may not be feasible under dynamic real-time conditions. To overcome these limitations, bio-inspired heuristic algorithms, known for their ability to solve complex optimization problems, have been investigated. The study focuses on the implementation of Invasive Weed Optimization (IWO), Shuffled Frog Leaping Algorithm (SFLA), Teaching Learning Based Optimization (TLBO), and Walrus Optimization Algorithm (WOA) for improving channel estimation in OFDM-based systems. Each algorithm is mathematically modeled and integrated into the channel estimation process based on its natural behavior and optimization structure. Simulation studies are carried out in MATLAB to evaluate and compare the performance of these algorithms in terms of Bit Error Rate (BER), Mean Square Error (MSE), and convergence characteristics. The simulation results are also benchmarked against conventional LS and MMSE methods. Findings reveal that the proposed heuristic methods outperform traditional approaches in scenarios with complex and noisy channel conditions, offering enhanced estimation accuracy and system reliability. This thesis contributes to the literature by presenting AI-supported novel solutions for channel estimation and demonstrates that OFDM systems can significantly benefit from heuristic optimization techniques in terms of performance and robustness.