Abstract
In wide-area networks (WANs), efficiently allocating distributed resources presents a significant challenge due to increasing node numbers and complex network conditions. Traditional algorithms, which heavily depend on global information, encounter scalability limitations. This study proposes an adaptive distributed optimal resource allocation consistency algorithm designed for WANs. The approach dynamically adjusts resource allocation based on real-time network conditions and user requirements, reducing dependence on global data. A time window distribution model and an information coding model are employed to optimize the resource allocation process. By integrating a Q-learning algorithm and extending the Paxos algorithm to WANs, global consistency among network nodes is ensured. The experimental results demonstrate the algorithm's superior performance, particularly in low-bandwidth WAN scenarios (below 2 Mb/s), where it significantly enhances throughput. An average resource utilization rate exceeding 97% is achieved, along with rapid convergence and high parallelism. This research underscores the algorithm's effectiveness and scalability, providing a robust solution to distributed resource allocation challenges in complex WAN environments.