Scholarlink

<p>To keep the grid stable, improve energy planning, and promote long-term economic growth, it is important to be able to accurately predict how much renewable energy will be produced in the future. The main goal of this project is to create a new model based on artificial intelligence that will take the place of the current one. The model now uses cointegration analysis and adaptive evolutionary optimization, which has greatly improved its capacity to predict energy use over long periods of time. I used a new framework that is based on artificial intelligence and a wide range of regression and time-series models, such as linear, ridge, ARIMA, ARMA, and LSRM, to look at two datasets. The first set of data was about making energy, while the second set was about weather. The proposed model outperformed the existing one during the investigation, demonstrating a substantial decrease in error rates (MAPE = 4.28%). This technique, which used a wide range of energy sources, such as renewables, fossil fuels, wind, and biomass, among others, was more effective than the way things are now. According to the study’s results, China’s energy use is expected to reach 13 trillion kWh by 2030, which would be an increase of more than 55% each year. Using artificial intelligence to validate and optimize econometric models resulted in far more accurate estimates. Now that they have a solid tool, energy planners and policymakers may be able to make decisions that will help them find a long-term balance between supply, demand, and sustainability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Renewable Energy Using an Improved Derivative Model

  • 期刊论文

  • 发表日期：

    2025年12月8日

查看全文
  • Ahmed A. F. Osman,
  • Ramgopal Kashyap,
  • Rajit Nair,
  • Mosleh Hmoud Al-Adhaileh,
  • Mohammed Ataelfadiel

摘要

To keep the grid stable, improve energy planning, and promote long-term economic growth, it is important to be able to accurately predict how much renewable energy will be produced in the future. The main goal of this project is to create a new model based on artificial intelligence that will take the place of the current one. The model now uses cointegration analysis and adaptive evolutionary optimization, which has greatly improved its capacity to predict energy use over long periods of time. I used a new framework that is based on artificial intelligence and a wide range of regression and time-series models, such as linear, ridge, ARIMA, ARMA, and LSRM, to look at two datasets. The first set of data was about making energy, while the second set was about weather. The proposed model outperformed the existing one during the investigation, demonstrating a substantial decrease in error rates (MAPE = 4.28%). This technique, which used a wide range of energy sources, such as renewables, fossil fuels, wind, and biomass, among others, was more effective than the way things are now. According to the study’s results, China’s energy use is expected to reach 13 trillion kWh by 2030, which would be an increase of more than 55% each year. Using artificial intelligence to validate and optimize econometric models resulted in far more accurate estimates. Now that they have a solid tool, energy planners and policymakers may be able to make decisions that will help them find a long-term balance between supply, demand, and sustainability.