Achieving load-balancing in power system parallel contingency analysis using X10 programming language

Due to recent trends of expansion and deregulation in power systems, the stress level of power systems has increased which has highlighted the importance of conducting stability analysis. Further, due to increasing emphasis on analyzing N -- k contingency, the number of contingencies which are required to be analyzed has greatly increased. To address this challenge, researchers have used parallel computing resources, however, in absence of efficient load-balanced scheduling, parallelization leads to wastage of computation resources. In this paper, we present an approach to parallelize power system contingency analysis using X10 language. We discuss the features of X10 which enable us to achieve high performance gains. Our approach is evaluated using a large 13029-bus power systems. We parallelize contingency analysis over 2, 4, 8 and 16 threads and use efficient work-stealing algorithm to achieve load-balancing. The results have shown that our approach scales effectively with the number of cores and provides large computational gains. Also, it outperforms a conventional scheduling technique, namely master-slave scheduling.