A Hybrid Heuristic Algorithm for Optimizing the Optimal Landing Time Window Problem in Intelligent Air Transportation Systems

The Aircraft Landing Problem (ALP) involves optimizing the scheduling of flight arrivals and departures while simultaneously managing airport resources to maximize flight utilization, minimize delays, reduce costs, and enhance overall operational efficiency. However, existing algorithms for solving ALP often face challenges in converging optimally and effectively handling penalty values associated with timing violations. To address these issues, this paper proposes a novel hybrid heuristic algorithm, AGWOA, designed to enhance convergence rates and effectively manage penalties in ALP. AGWOA integrates Artificial Bee Colony (ABC) and Genetic Algorithm (GA) techniques into the Whale Optimization Algorithm (WOA), leveraging their complementary strengths to strengthen global search efficiency and refine local constraint handling. This integration accelerates convergence and significantly mitigates penalty costs. Moreover, AGWOA incorporates an adaptive coefficient to facilitate improved convergence, along with a Fast Convergence Update Mechanism (FCUM) to guide the algorithm toward optimal solutions more efficiently. Experimental results conducted on public datasets demonstrate that AGWOA outperforms existing advanced algorithms in both convergence speed and penalty minimization. Specifically, AGWOA achieves a 4.05% decrease in penalty costs compared to baseline algorithms. These results underscore AGWOA’s effectiveness in overcoming the challenge of slow convergence and its competitive advantage over other methods in optimizing ALP. The proposed algorithm offers a promising solution for real-world ALP applications, significantly enhancing airline operational efficiency and optimizing resource management.