PowerNet: a smart energy forecasting architecture based on neural networks. Issue 4 (5th November 2020)

• Record Type: Journal Article
• Authors: Cheng, Yao; Xu, Chang; Mashima, Daisuke; Biswas, Partha P.; Chipurupalli, Geetanjali; Zhou, Bin; Wu, Yongdong
• Is Part Of: IET smart cities. Volume 2:Issue 4(2020)
• Page Start: 199
• Page End: 207
• Publication Date: 2020-11-05
• Subjects: power engineering computing -- demand forecasting -- load forecasting -- learning (artificial intelligence) -- power grids -- support vector machines -- energy consumption -- regression analysis -- neural net architecture; reliable operation -- economical operation -- power grid -- smart cities -- grid operators -- neural network architecture PowerNet -- historical energy consumption data -- weather data -- calendar information -- real‐world smart meter dataset -- machine learning -- support vector regression -- worst‐case prediction errors -- forecasting demands -- PowerNet demand forecasting -- smart energy forecasting architecture; Smart cities -- Periodicals; City planning -- Technological innovations -- Periodicals; Cities and towns -- Growth -- Periodicals; Sustainable urban development -- Periodicals; Sustainable development; City planning -- Technological innovations; Cities and towns -- Growth; Periodicals; 307.76
• DOI: 10.1049/iet-smc.2020.0003
• Languages: English
• ISSNs: 2631-7680

Abstract

Abstract : Electricity demand forecasting is a critical task for efficient, reliable and economical operation of the power grid, which is one of the most essential building blocks of smart cities. Accurate forecasting allows grid operators to properly maintain the balance of supply and demand as well as to optimize operational cost for generation and transmission. This article proposes a novel neural network architecture PowerNet which can incorporate multiple heterogeneous features such as historical energy consumption data, weather data and calendar information for the demand forecasting task. Using real‐world smart meter dataset, we conduct an extensive evaluation to show the advantages of PowerNet over recently‐proposed machine learning methods such as Gradient Boosting Tree (GBT), Support Vector Regression (SVR), Random Forest (RF) and Gated Recurrent Unit (GRU). PowerNet demonstrates notable performance in reducing both the median and worst‐case prediction errors when forecasting demands of individual residential households. We further provide empirical results concerning the two operational considerations that are crucial when using PowerNet in practice: the time horizon the model can predict with a decent accuracy and the frequency of training the model to retain its modeling capability. Finally, we briefly discuss a multi‐layer anomaly/electricity‐theft detection approach based on PowerNet demand forecasting.