Parallel Ant Colony Optimization Algorithm for Finding the Shortest Path for Mountain Climbing

Abstract

The problem of finding the shortest path between two nodes is a common problem that requires a solution in many applications like games, robotics, and real-life problems. Since its deals with a large number of possibilities. Therefore, parallel algorithms are suitable to solve this optimization problem that has attracted a lot of researchers from both industry and academia to find the optimal path in terms of runtime, speedup, efficiency, and cost compared to sequential algorithms. In mountain climbing, finding the shortest path from the start node under the mountain to reach the destination node is a fundamental operator, and there are some interesting issues to be studied in mountain climbing that cannot be found in a traditional two-dimensional space search. We present a parallel Ant Colony Optimization (ACO) to find the shortest path in the mountain climbing problem using Apache Spark. The proposed algorithm guarantees the security of the selected path by applying some constraints that take into account the secure slope angle for the path. A generated dataset with variable sizes is used to evaluate the proposed algorithm in terms of runtime, speedup, efficiency, and cost. The experimental results show that the parallel ACO algorithm significantly $(p < 0.05)$ outperformed the best sequential ACO. On the other hand, the parallel ACO algorithm is compared with one of the most recent research from the literature for finding the best path for mountain climbing problems using the parallel A∗ algorithm with Apache Spark. The parallel ACO algorithm with Spark significantly outperformed the parallel A∗ algorithm.