International Journal of Electrical and Computer Engineering (IJECE) Vol. 14, No. 6, December 2024, pp. 6743~6752 ISSN: 2088-8708, DOI: 10.11591/ijece.v14i6.pp6743-6752  6743 Journal homepage: http://ijece.iaescore.com Optimal shortest path selection using an evolutionary algorithm in wireless sensor networks Dhamodharan Udaya Suriya Rajkumar 1 , Krishna Prasad Karani 2 , Rajendran Sathiyaraj 3 , Pellakuri Vidyullatha 4 1 Department of Computer Science and Engineering, Srinivas University, Mangalore, India. 2 Department of Cyber Security and Cyber Forensics, Institute of Engineering and Technology, Srinivas University, Mangalore, India 3 Department of Computer Science and Engineering, GITAM School of Technology, GITAM University, Bangalore, India 4 Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Guntur, India Article Info ABSTRACT Article history: Received Mar 27, 2024 Revised Aug 1, 2024 Accepted Aug 6, 2024 A wireless sensor network comprises of distributed independent devices, called sensors that monitor the physical conditions of the environment for various applications, such as tracking and observing environmental changes. Sensors have the ability to detect information, process it, and forward it to neighboring sensor nodes. Wireless sensor networks are facing many issues in terms of scalability, which necessitates numerous nodes and network range. The route chosen between the source node and the destination node with the shortest distance determines how well the network performs. In this paper, evolutionary algorithm based shortest path selection provides high end accessibility of path nodes for data transmission among source and destination. It employs the best fitness function methodology, which involves the replication of input, mutation, crossover, and mutation methods, to produce efficient outcomes that align with the best fitness function, thereby determining the shortest path. This is a probabilistic technique that receives input from learning models and provides the best results. The execution results are presented well compared with earlier methodologies in terms of path cost, function values, throughput, packet delivery ratio, and computation time. Keywords: Best fitness function Evolutionary algorithm Mutation and crossover mutation Route discovery Wireless sensor network This is an open access article under the CC BY-SA license. Corresponding Author: Dhamodharan Udaya Suriya Rajkumar Post Doctoral Fellow, Department of Computer Science and Engineering, Srinivas University Mukka, Mangalore, Karnataka, India Email: raisingsun82@gmail.com 1. INTRODUCTION In wireless sensor network (WSN), the system is managed by nodes that have built in central processing units (CPUs). These nodes establish connections with each other, the base station, and the internet [1]. The base station (BS) is responsible for gathering, analyzing, and delivering data to the end user for decision-making, while the nodes handle sensing, data processing, and transmission. A WSN is a transient network made up of a group of wireless sensor nodes that may be anywhere necessary with previous centralized or infrastructure nodes [2]. We now use them to observe environmental events, human activity, and natural calamities [3]. WSN’s known for its dynamic nature and mobility. Hence, the secure dispatch of data requires a lot of energy. The real investigation of mobile nodes lies in their limited battery life. Every node in the network has a permanent communication range; therefore, a starting node requires the help of intermediate nodes along the way to an ending node. In the WSN, protocols utilizing cluster-based communication play a critical role in decreasing energy utilization [4].