Recently, many Computational-Intelligence algorithms have been proposed for solving continuous problem. The Differential Search Algorithm (DSA), a computational-intelligence based algorithm inspired by the migration movements of superorganisms, is developed to solve continuous problems. However, DSA proposed for solving problems with continuous search space proposed for solving should be modified for solving binary structured problems. When the DSA is intended for use in binary problems, continuous variables need to be converted into binary format due to solution space structure of this type of problem. In this study, the DSA is modified to solve binary optimization problems by using a conversion approach from continuous values to binary values. The new algorithm has been designated as the binary DSA or BDSA for short. First, when finding donors with the BDSA, four search methods (Bijective, Surjective, Elitist1 and Elitist2) with different iteration numbers are used and tested on 15 UFLP benchmark problems. The Elitist2 approach, which provides the best solution of the four methods, is used in the BDSA, and the results are compared with Continuous Particle Swarm Optimization (CPSO), Continuous Artificial Bee Colony (ABCbin), Improved Binary Particle Swarm Optimization (IBPSO), Binary Artificial Bee Colony (binABC) and Discrete Artificial Bee Colony (DisABC) algorithms using UFLP benchmark problems. Results from the tests and comparisons show that the BDSA is fast, effective and robust for binary optimization.
Wireless sensors (nodes) are devices with built-in batteries, sensors and communication units. Wireless sensor networks (WSNs) are structures that are formed by multiple nodes coming together to transmit the data they collect from each other to the base station. Significant work has been done on WSNs in recent years. One of the important issues that these studies have focused on is increasing the energy efficiency of the nodes forming the network and ensuring their survival for a longer time. In this paper, two-dimensional particle swarm optimization (PSO) is proposed to solve the problem of clustering in WSNs by inspiration from PSO modified by Fan to solve discrete problems such as the traveling salesman problem. The proposed algorithm was analyzed comparatively with the low-energy adaptive clustering hierarchy (Leach) protocol. As a result, an improvement of 4% compared with Leach was achieved in terms of the amount of energy left in the network. The data packets sent in 20 rounds increased by 2000 packets compared to Leach, and a 27% improvement was achieved. In addition, the number of surviving nodes increased by 22%.