Power Stability Management for Renewable Energy Resources using Big Data Analysis

Main Article Content

Ming Shi
Yueping Deng
Jince Wang
Jicheng Wang
Lin Hao

Abstract

The power sector plays a major role in the world’s economic growth. However, the high energy demand and depleting energy resources make the power sector operates in a stressed condition. In recent times, the power sectors are facing various challenges like power instability, high consumption rate, etc. In this article, a Honey Pot-based Recurrent Neural Network (HPbRNN) Big Data Analysis model was presented to predict the power instability in the grid system. Power stability determination is important in a grid system to maintain stable power flow and system operation. In the developed scheme, a huge amount of data is collected from the grid network to predict power stability. The application of big data in the grid network enables the process of this huge collected dataset by analyzing the dataset features. Initially, to make the prediction accurate and easy the dataset is splitted and pre-processed. Then the input and output attributes are tracked and extracted to predict the grid stability. In addition, to achieve the finest results the honey pot fitness solution is integrated into the optimization layer of the proposed model. Furthermore, the outcomes of the developed model are validated and the performance enhancement score is determined from the comparative analysis.

Article Details

Section
Special Issue - High-performance Computing Algorithms for Material Sciences