Generating Synthetic Data to Reduce Prediction Error of Energy Consumption

作     者：Debapriya Hazra Wafa Shafqat Yung-Cheol Byun 

作者机构：Department of Computer EngineeringJeju National UniversityJeju-siKorea 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第70卷第2期

页      面：3151-3167页

核心收录：

学科分类：08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This research was financially supported by the Ministry of Small and Mediumsized Enterprises(SMEs)and Startups(MSS) Korea under the“Regional Specialized Industry Development Program(R&D S3091627)”supervised by Korea Institute for Advancement of Technology(KIAT) 

主　　题：Energy consumption generative adversarial networks synthetic data time series data TGAN WGAN-GP TGAN-skip prediction error augmentation 

摘      要：Renewable and nonrenewable energy sources are widely incorporated for solar and wind energy that produces electricity without increasing carbon dioxide *** industries worldwide are trying hard to predict future energy consumption that could eliminate over or under contracting energy resources and unnecessary *** learning techniques for predicting energy are the trending solution to overcome the challenges faced by energy *** basic need for machine learning algorithms to be trained for accurate prediction requires a considerable amount of *** critical factor is balancing the data for enhanced *** Augmentation is a technique used for increasing the data available for *** data are the generation of new data which can be trained to improve the accuracy of prediction *** this paper,we propose a model that takes time series energy consumption data as input,pre-processes the data,and then uses multiple augmentation techniques and generative adversarial networks to generate synthetic data which when combined with the original data,reduces energy consumption prediction *** propose TGAN-skip-Improved-WGAN-GP to generate synthetic energy consumption time series tabular *** modify TGANwith skip connections,then improveWGANGPby defining a consistency term,and finally use the architecture of improved WGAN-GP for training *** used various evaluation metrics and visual representation to compare the performance of our proposed *** also measured prediction accuracy along with mean and maximum error generated while predicting with different variations of augmented and synthetic data with original *** mode collapse problemcould be handled by TGAN-skip-Improved-WGAN-GP model and it also converged faster than existing GAN models for synthetic data *** experiment result shows that our proposed technique of combining synthetic data with original data could significantly red