Static and dynamic channel assignment using neural networks
IEEE Journal on Selected Areas in Communications
| Hi-index | 0.00 |
The Channel Assignment Problem (CAP) is an NP-complete problem. Different algorithms have been proposed based on techniques of combinatorial optimization. In this paper, the problem is formulated as a minimizing problem of a quadratic function with quadratic restrictions and binary variables. To solve this problem a binary recurrent neural network (RNN) is proposed with a quadratic energy function. Constrains are incorporated to the computational dynamics so that RNN always satisfy the problem constraints in each updating. A variety of test problems are used to compare the performances of CAP against traditional heuristic approaches.