Abstract
Performance is the key issue in power big data applications. One of main challenges is how to exploit these technologies in building power big data processing platform and facilitating science discoveries such as those in electric power systems. This paper explores how Spark and Cloud computing can accelerate performance of missive insulator leak current data pattern recognition. We have designed and implemented the Parallel KNN(k-NearestNeighbor) algorithm using Spark and then deployed onto the Aliyun E-MapReduce cloud computing platform. The results from experiments shows the performance and scalability can be enhanced through these advanced technologies.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have