Genetic Algorithm And Its Applications To Communication

Genetic algorithms are probabilistic search techniques based on the principles of biological evolution. Recently, genetic algorithms are deeply studied and widely used in combinatorial optimization problems and a lot of successful application instances and good results are reported.Blind equalization is an adaptive equalization technique, which can equalize the properties of the channel just using the statistic properties of the received signal and overcome the disadvantages of conventional adaptive equalization techniques which require a training sequence and reduce effective information rate in system transmission. This paper gives a review of blind equalization, and builds a simple single-input-multiple-output model. We propose a blind equalization algorithm based on genetic algorithm. The simulations show that we can have better performances.In order to fully exploit the advantages of OFDM in cellular systems, resource allocation techniques need to be devised, which efficiently use the resources such as bandwidth, power, and modulation to increase the spectral efficiency of the system. There are two kinds of resource allocation schemes existing in current OFDM system: static and dynamic resource allocation schemes. This paper formulates an optimization problem and use GA to maximize the sum capacity of OFDM system with the total power constraints.Traditional OSI architecture is not suitable to wireless network with the development of wireless applications. Cross-layer design is proposed, its main content is that the protocol stack can realize self-adaptive optimization of resources according to the changes of wireless environment through transmitting specific information between the layers of protocol stack, in order to utilize wireless network resources effectively and improve the performance of the system. The optimal cross-layer scheduling algorithm for OFDMA/MISO is formulated, and the optimal solution is obtained. Because of the high computational complexity involved, we use genetic algorithms to obtain the multi-user performance. The results show that we can have better performance by multi-user selection based on genetic algorithm than traditional method.