A. Bandyopadhyay, Bishal Dey Sarkar, M. Hossain, Soumen Rej, Mohidul Alam Mallick
{"title":"利用人工神经网络模拟和预测印度的用电量","authors":"A. Bandyopadhyay, Bishal Dey Sarkar, M. Hossain, Soumen Rej, Mohidul Alam Mallick","doi":"10.1111/opec.12295","DOIUrl":null,"url":null,"abstract":"Precise electricity forecasting is a pertinent challenge in effectively controlling the supply and demand of power. This is due to the inherent volatility of electricity, which cannot be stored and must be utilised promptly. Thus, this study develops a framework integrating canonical cointegrating regressions (CCR), time series artificial neural network (ANN) and a multilayer perceptron ANN model for analysing and projecting India's gross electricity consumption to 2030. Annual data for the years 1961–2020 have been collected for variables like gross domestic product (GDP), population, inflation GDP deflator (annual %), annual average temperature and electricity consumption. The study was conducted in three phases. In the first phase of the study, the CCR method was used to check the significance of the selected variables. In the second phase, the projected values of independent variables (GDP, population, inflation GDP deflator [annual %] and annual average temperature) were predicted using the time series ANN model. Finally, a multilayer perceptron ANN model with independent variables was used to forecast the gross electricity consumption in India by 2030. The result shows that the electricity consumption in India will increase by around 50% in the next 10 years, reaching over 1800 TWh in 2030. The proposed approach can be utilised to effectively implement energy policies, as an accurate prediction of energy consumption can help capture future demand.","PeriodicalId":44992,"journal":{"name":"OPEC Energy Review","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2024-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Modelling and forecasting India's electricity consumption using artificial neural networks\",\"authors\":\"A. Bandyopadhyay, Bishal Dey Sarkar, M. Hossain, Soumen Rej, Mohidul Alam Mallick\",\"doi\":\"10.1111/opec.12295\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Precise electricity forecasting is a pertinent challenge in effectively controlling the supply and demand of power. This is due to the inherent volatility of electricity, which cannot be stored and must be utilised promptly. Thus, this study develops a framework integrating canonical cointegrating regressions (CCR), time series artificial neural network (ANN) and a multilayer perceptron ANN model for analysing and projecting India's gross electricity consumption to 2030. Annual data for the years 1961–2020 have been collected for variables like gross domestic product (GDP), population, inflation GDP deflator (annual %), annual average temperature and electricity consumption. The study was conducted in three phases. In the first phase of the study, the CCR method was used to check the significance of the selected variables. In the second phase, the projected values of independent variables (GDP, population, inflation GDP deflator [annual %] and annual average temperature) were predicted using the time series ANN model. Finally, a multilayer perceptron ANN model with independent variables was used to forecast the gross electricity consumption in India by 2030. The result shows that the electricity consumption in India will increase by around 50% in the next 10 years, reaching over 1800 TWh in 2030. The proposed approach can be utilised to effectively implement energy policies, as an accurate prediction of energy consumption can help capture future demand.\",\"PeriodicalId\":44992,\"journal\":{\"name\":\"OPEC Energy Review\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2024-01-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"OPEC Energy Review\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1111/opec.12295\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ECONOMICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"OPEC Energy Review","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1111/opec.12295","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ECONOMICS","Score":null,"Total":0}
引用次数: 0
摘要
精确的电力预测是有效控制电力供需的一项相关挑战。这是因为电力本身具有波动性,无法储存,必须及时利用。因此,本研究开发了一个整合了典型协整回归(CCR)、时间序列人工神经网络(ANN)和多层感知器 ANN 模型的框架,用于分析和预测印度到 2030 年的总用电量。研究收集了 1961-2020 年的年度数据,包括国内生产总值 (GDP)、人口、通货膨胀 GDP 平减指数(年百分比)、年平均气温和用电量等变量。研究分三个阶段进行。在研究的第一阶段,使用 CCR 方法检查所选变量的显著性。在第二阶段,使用时间序列 ANN 模型预测自变量(国内生产总值、人口、通货膨胀国内生产总值平减指数[年百分比]和年平均气温)的预测值。最后,使用包含自变量的多层感知方差网络模型预测印度到 2030 年的总用电量。结果表明,未来 10 年印度的用电量将增加约 50%,到 2030 年将超过 1800 太瓦时。所提出的方法可用于有效实施能源政策,因为准确预测能源消耗有助于把握未来需求。
Modelling and forecasting India's electricity consumption using artificial neural networks
Precise electricity forecasting is a pertinent challenge in effectively controlling the supply and demand of power. This is due to the inherent volatility of electricity, which cannot be stored and must be utilised promptly. Thus, this study develops a framework integrating canonical cointegrating regressions (CCR), time series artificial neural network (ANN) and a multilayer perceptron ANN model for analysing and projecting India's gross electricity consumption to 2030. Annual data for the years 1961–2020 have been collected for variables like gross domestic product (GDP), population, inflation GDP deflator (annual %), annual average temperature and electricity consumption. The study was conducted in three phases. In the first phase of the study, the CCR method was used to check the significance of the selected variables. In the second phase, the projected values of independent variables (GDP, population, inflation GDP deflator [annual %] and annual average temperature) were predicted using the time series ANN model. Finally, a multilayer perceptron ANN model with independent variables was used to forecast the gross electricity consumption in India by 2030. The result shows that the electricity consumption in India will increase by around 50% in the next 10 years, reaching over 1800 TWh in 2030. The proposed approach can be utilised to effectively implement energy policies, as an accurate prediction of energy consumption can help capture future demand.