Probability value for each level is determined based on Table 2. The higher the probability value is, the higher is the chance of being cluster head. After that the candidate cluster heads are chosen based on Fuzzy rules, other nodes should become a member of these cluster heads. Therefore, the members should be assigned to the cluster heads such that energy consumption gets balanced at each cluster. In this study, genetic algorithm is used for assigning members to cluster heads which will be described in the following section.
For the initial population of genetic algorithm, an integer coding scheme is used. Each gene has a random value between 1 and m (m is the number of cluster heads). The length of each individual or chromosome in this population equals the number of all nodes that exist in the network. Equation 1 is used to evaluate the fitness of each chromosome. …show more content…
E represents the required energy for sending data from nodes to cluster heads and from cluster heads to the main station. Sd represents the distance of all nodes to the base station and hsd represents the sum of the distances of all nodes to the cluster heads and the distances from cluster heads to the base station. α is a constant by which the importance of energy parameter is determined. To select chromosomes tournament strategy is used. In this strategy the chromosome population is compared pair wise and the chromosome with higher propriety is