Load-aware multicast routing in multi-radio wireless mesh networks using FCA-CMAC neural network

Multicasting is a useful network service in wireless mesh networks (WMNs) for delivering same data from a source to multiple destinations. An effective multicast routing protocol in multi-channel multi-radio WMNs (MCMR-WMNs) is required to satisfy the following criteria together: high network throughput, low end-to-end delay, low tree cost, low computational time, and load-aware routing. Furthermore, how to fully exploit channel diversity in MCMR-WMNs to accomplish low channel interference criteria is a critical issue in designing multicast routing protocol. In spite of its significance, multicast routing which satisfies all of the mentioned criteria, has not drawn much attention so far. Besides, major multicast routing protocols proposed in MCMR-WMNs are centralized or solve two problems of multicast tree construction and channel assignment sequentially. These protocols are time-consuming in addition to suffering from a single-point-of-failure. In this paper, we propose a distributed cross-layer algorithm for joint multicast routing and channel assignment in MCMR-WMNs. For the first time, we apply fuzzy credit assigned cerebellum model articulation controller (FCA-CMAC) neural network model to construct multicast routing tree considering load on the mesh nodes and the delay between neighboring mesh nodes. Moreover, we present a heuristic channel assignment algorithm aiming to reduce interference among the links of the multicast tree. FCA-CMAC converges quickly and creates minimal delay and load-aware multicast tree. Therefore, proposed method can optimize the network throughput, end-to-end delay, tree cost, and computational time. Additionally, channel assignment algorithm is subject to produce the minimal interference multicast tree. Simulation results show that in terms of aforementioned criteria, the proposed FCA-CMAC based multicast algorithm achieves better performance than those comparative references.