An Efficient Large-Scale Sensor Deployment Using a Parallel Genetic Algorithm Based on CUDA

We have employed evolutionary computation to solve the optimization problem of sensor deployment in battlefield environments. A genetic algorithm has the advantage of delivering results of a higher quality than simple computational algorithms, but it has the drawback of requiring too much computing time. This study aimed not only to shorten the computing time to as close to real-time as possible by using the Compute Unified Device Architecture (CUDA) but also to maintain a solution quality that is as good as or better than the case when the proposed algorithm is not used. In the proposed genetic algorithm, parallelization was applied to speed up the fitness evaluation requiring heavy computation time. The proposed CUDA-based design approach for complex and various sensor deployments is validated by means of simulation. We parallelized two parts in Monte Carlo simulation for the fitness evaluation: moving lots of tested vehicles and calculating the probability of detection (POD) for each vehicle. The experiment was divided into CPU and GPU experiments depending on arithmetic unit types. In the GPU experiment, the results showed similar levels for the detection probability by GPU and CPU, and the computing time decreased by approximately 55-56 times.