Scholarlink

<p>Addressing the widening energy gap between global energy generation and supply is a significant challenge in contemporary times, and it is likely that this issue will remain critical in the future. Renewable energy resources are playing a crucial role in addressing the energy gap. Household loads consume nearly 40% of global energy production, highlighting the necessity of using available energy resources efficiently. Demand response programs play a pivotal role in managing household loads and energy sources, benefiting both customers and utilities. This paper proposes a multi-objective residential energy management problem aimed at scheduling household appliances to optimize total electricity costs and emissions, incorporating a wind power generator and battery storage system. The study utilizes forecasted weather parameters for wind power generation specifically in the context of Bhuj, Gujarat, India. Error in the forecasting may cause a higher generation cost for the utility. In this paper, the forecasting is conducted using a hybrid model that combines a convolutional neural network and a long short-term memory recurrent neural network. The formulated scheduling problem is meticulously modeled using General Algebraic Modeling System (GAMS) software and solved with the CPLEX solver, employing mixed-integer programming techniques. The numerical results obtained from the study demonstrate a significant reduction in electricity costs, with the calculated payback period for the deployed wind turbine being 6.09&#xa0;years.</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

CNN-LSTM-based wind forecasting for a residential energy management system

  • 期刊论文

  • 发表日期：

    2025年9月16日

查看全文
  • Vikas Deep Juyal,
  • Sandeep Kakran

摘要

Addressing the widening energy gap between global energy generation and supply is a significant challenge in contemporary times, and it is likely that this issue will remain critical in the future. Renewable energy resources are playing a crucial role in addressing the energy gap. Household loads consume nearly 40% of global energy production, highlighting the necessity of using available energy resources efficiently. Demand response programs play a pivotal role in managing household loads and energy sources, benefiting both customers and utilities. This paper proposes a multi-objective residential energy management problem aimed at scheduling household appliances to optimize total electricity costs and emissions, incorporating a wind power generator and battery storage system. The study utilizes forecasted weather parameters for wind power generation specifically in the context of Bhuj, Gujarat, India. Error in the forecasting may cause a higher generation cost for the utility. In this paper, the forecasting is conducted using a hybrid model that combines a convolutional neural network and a long short-term memory recurrent neural network. The formulated scheduling problem is meticulously modeled using General Algebraic Modeling System (GAMS) software and solved with the CPLEX solver, employing mixed-integer programming techniques. The numerical results obtained from the study demonstrate a significant reduction in electricity costs, with the calculated payback period for the deployed wind turbine being 6.09 years.