The channel allocation problem (CAP) that involves the allocation a disjoint set of channels to meet the call demands for a cellular network is an NP-complete combinatorial optimisation problem [1]. The CAP can be viewed as: static (during the initial design/planning of the cellular network) and dynamic (when the network is operational). This paper presents a new algorithm designed to solve the online call control problem. This algorithm is a modified version of the maximum channel packing channel allocation (MCPCA) scheme, proposed by [19]. The original MCPCA scheme aims at maximising the reuse of channels (i.e. dense packing) and simulation results showed that it is more efficient than fixed channel assignment (FCA) or borrowing channel assignment (BCA) schemes for solving the class of minimum blocking frequency assignment problem (MB-FAP) [2]. The new algorithm, entitled maximum channel packing channel assignment with re-assignment (MCPCA-RA), takes the dense packing mechanism further by allowing a neighbouring cell to re-assigns a channel to an existing call and releases the channel previously used to the new request. Simulation results that the number of blocked calls is reduced by an average of 6% compared to the original MCPCA scheme, but at the cost of extra computations due to the reassignment mechanism. Since the reassignment computations only involve cells in the local neighbourhood and can be compute in a parallel manner, MCPCA-RA algorithm is practical and efficient in real-time.
Repacking on demand for speed-sensitive channel assignment