According to Moore’s law, computer processing hardware technology performance is doubled every year. To make effective use of this technological development, the algorithmic solutions have to be developed at the same speed. Consequently, it is necessary to design parallel algorithms to be implemented on parallel machines. This helps to exploit the multi-core environment by executing multiple instructions simultaneously on multiple processors. Traveling Salesman (TSP) is a challenging non-deterministic-hard optimization problem that has exponential running time using brute-force methods. TSP is concerned with finding the shortest path starting with a point and returning to that point after visiting the list of points, provided that these points are visited only once. Meta-heuristic optimization algorithms have been used to tackle TSP and find near-optimal solutions in a reasonable time. This paper proposes a parallel River Formation Dynamics Optimization Algorithm (RFD) to solve the TSP problem. The parallelization technique depends on dividing the population into different processors using the Map-Reduce framework in Apache Spark. The experiments are accomplished in three phases. The first phase compares the speedup, running time, and efficiency of RFD on 1 (sequential RFD), 4, 8, and 16 cores. The second phase compares the proposed parallel RFD with three parallel water-based algorithms, namely the Water Flow algorithm, Intelligent Water Drops, and the Water Cycle Algorithm. To achieve fairness, all algorithms are implemented using the same system specifications and the same values for shared parameters. The third phase compares the proposed parallel RFD with the reported results of metaheuristic algorithms that were used to solve TSP in the literature. The results demonstrate that the RFD algorithm has the best performance for the majority of problem instances, achieving the lowest running times across different core counts. Our findings highlight the importance of selecting the most suitable algorithm and core count based on the problem characteristics to achieve optimal performance in parallel optimization.
