| Summary: | Current development in the field of wireless mobile communication is extremely limited by the capacity constraints of the available frequency spectrum. Hence proper utilisation of channel allocation techniques which are capable of ensuring efficient channel assignment is essential in order to solve the non-deterministic polynomial-time hard (NP-hard) channel assignment problem. The process of channel assignment must satisfy hard-constraints such as electromagnetic compatibility (EMC) and the demand of channels in a cell. Initial channel assignment parameters are obtained using self-learning scheme and evolutionary algorithms is used to fine-tune the estimated parameters from reinforcement learning algorithm to optimise the channel assignment problem in wireless mobile networks. Particle reselection and dynamic inertia approach in particle-swarm-optimisation (PSO) is shown to have 8 % improvement over the standard PSO algorithm. Subsequently, the introduction of PSO showed 70 -75 % power saving advantage over suboptimal resource allocation techniques.
|
|---|