A routing algorithm based on the greedy neural network for non-sequential activation scheduling problems

This paper presents the routing algorithm based on the greedy neural network for non-sequential activation scheduling (NAS) problems in multihop radio networks. A multihop radio network with a set of station nodes and a set of communication links can be represented with a connected graph. In order to minimize the number of transmission time slots for given source-destination (SD)-pairs, the NAS problem must be solved to assign a transmission route for each SD-pair, and to find a link activation schedule for each assigned route. The simulation results show that our greedy neural network algorithms can find better solutions in the shorter time than the existing algorithms