NeTS-NBD: WLAN Resource Management Using Multi-Agent Systems

研究无线局域网/无线个人区域网络干扰环境下多个无线局域网之间的协同资源管理问题。无线局域网部署的激增导致多个网络之间频繁的地理覆盖重叠。当这种情况发生时，由于无线局域网间干扰，缺乏协作资源管理导致性能显著下降。此外，多个网络之间的负载不平衡可能会在一些WLAN中导致拥塞，而在其他WLAN中则有未使用的资源。本研究的目标是在多个无线局域网之间公平地管理共享的系统资源，以优化整体性能。这项研究强调网络条件的潜在可预测性，并促进针对不同干扰环境量身定做的管理解决方案。为了实现多个无线局域网之间的分布式信息共享和决策分发，提出了一种基于多代理系统的方法。研究了无线局域网中的分布式约束优化问题，并研究了分布式约束优化算法通过分布式代理之间的通信来寻找最优资源分配的有效性。该项目的预期结果将对基于代理交互和协调的算法来促进资源管理、用于参数估计的预测模型和动态负载均衡算法的下一代WLAN网络管理产生重大影响。研究结果可用于支持FCC提高频谱利用率的倡议以及支持事件管理。研究成果将被广泛传播，并通过建立和维护一个网站，将作为这项研究的一部分开发的所有报告、软件和研究论文存档，向公众提供。

This research investigates cooperative resource management among multiple WLANs (wireless local area networks) in WLAN/WPAN (wireless personal area networks) interference environments. The proliferation of WLAN deployments causes frequent geographical coverage overlap among multiple networks. When this occurs, the lack of cooperative resource management results in significant performance degradation due to inter-WLAN interference. Moreover, unbalanced loads among multiple networks can incur congestion in a few WLANs while there are unused resources in others. The objective of this research is to manage shared system resources fairly among multiple WLANs to optimize the overall performance. This research emphasizes the underlying predictability of network conditions and promotes management solutions tailored to different interference environments. A multi-agent system-based approach is proposed to achieve information sharing and decision distribution among multiple WLANs in a distributed manner. This research addresses the distributed constraint optimization problem (DCOP) in WLANs and studies the effectiveness of DCOP algorithms to find the optimal resource assignment through communications between distributed agents. Expected results from the project will have a significant impact on next generation WLAN network management based on employing algorithms of agent interaction and coordination to facilitate resource management, predictive models for parameter estimation, and dynamic load balancing algorithms. Research results could be used to support the FCC initiative to improve spectrum utilization as well as to support incident management. Research results will be broadly disseminated and made available to the public by constructing and maintaining a web-site to archive all reports, software, and research papers developed as part of this research.