User-Based Load Visualization of Categorical Forecasted Smart Meter Data Using LSTM Network

User-Based Load Visualization of Categorical Forecasted Smart Meter Data Using LSTM Network

Ajay Kumar (JSS Academy of Technical Education, Noida, India), Parveen Poon Terang (JSS Academy of Technical Education, Noida, India) and Vikram Bali (JSS Academy of Technical Education, Noida, India)
DOI: 10.4018/IJMDEM.2020010103

Abstract

Electrical load forecasting is an essential feature in power systems planning, operation and control. The non-linearity and non-stationary nature of the data, however, poses a challenge in terms of accuracy. This article explores a deep learning technique, a long short-term memory recurrent neural network-based framework to tackle this tricky issue. The proposed machine learning model framework is tested on real time residential smart meter data showing promising results. A web application has also been developed to allow consumers to have access to greater levels of information and facilitate decision-making at their end. The performance of the proposed model is also comprehensively compared to other methods in the field of load forecasting showing more accurate results for the function of forecasting of load on short term basis.
Article Preview
Top

Introduction

Key role in any power system planning, operation and control is played by load forecasting and thus, the accuracy of load forecasting is crucial for any electric utility. Throughout the evolution of the power system, primary focus has always been load forecasting. The paradigm shift from traditional grid to smart grid, allows the smart grid to provide more intelligent and accurate power services by making use of modern machine learning methods. Power system operations can be enhanced with reliable short-term load forecasting at the consumer end. It can effectively strike the balance between demand and supply, by allowing load-balancing reserve, which in turn would greatly enhance load factor, decrease production cost and hedge market costs. This massive infrastructure development and technological development has also allowed flexibility of load forecasting at the consumer level.

Nowadays, the electric load prediction is a vital process with applications that are used in various fields because of large demand of power supply and consumption in an electric power houses and in households respectively. So, there is a need to develop model for accurate electricity load forecasting and visualization. The reasons for accurate electricity load forecasting and visualization are:

  • Purchasing and generating electric power;

  • Transmitting, transferring and distributing electric power;

  • Managing and maintaining the electric power sources;

  • Managing the daily electric load demand;

  • Financial and marketing planning.

Buildings are identified as a major energy consumer worldwide, accounting for 20%-40% of the total energy production. In addition to being a major energy consumer, buildings are shown to account for a significant portion of energy wastage as well. As energy wastage poses a threat to sustainability, making buildings energy efficient is extremely crucial. Therefore, in making building energy consumption more efficient, it is necessary to have accurate predictions of its future energy consumption. Further, demand or load forecasting is crucial for mitigating uncertainties of the future. In that, individual building level demand forecasting is crucial as well as forecasting aggregate loads. In terms of demand response, building level forecasting helps carry out demand response locally since the smart grids incorporate distributed energy generation. Most of the research for prediction of electricity load forecasting concentrate on aggregate load at the system level. However, variation at the individual level also play an important role in determining accuracy of load prediction.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2020): 1 Released, 3 Forthcoming
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing