Scholarlink

The possibility of incorporating photovoltaics (PV) as part of building design has opened a new approach to energy generation from sustainable resources. An effective method to facilitate the good operation of these systems would be efficient energy-level management. The existing Energy Management of LE-BIPV employs a conventional control strategy, which is inconvenient for operation and fails to properly deal with nonlinearity in the PV system. The proposed model aims to provide a new deep-learning framework for the energy management of LE-BIPV. The proposed neural network framework can learn the intricate relationships between PV generation and battery storage and enable accurate energy management predictions. This proposed deep learning framework can substantially upgrade the global energy control of building-integrated PV systems in low-energy buildings.

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

An Improved Deep Learning Framework for Energy Management in Low-Energy Building Integrated Photovoltaics (LE-BIPV)

  • 章节

  • 发表日期：

    2026年

查看全文
  • J. Logeshwaran,
  • Satya Prakash Yadav,
  • Chadi Altrjman,
  • Fadi Al-Turjman

摘要

The possibility of incorporating photovoltaics (PV) as part of building design has opened a new approach to energy generation from sustainable resources. An effective method to facilitate the good operation of these systems would be efficient energy-level management. The existing Energy Management of LE-BIPV employs a conventional control strategy, which is inconvenient for operation and fails to properly deal with nonlinearity in the PV system. The proposed model aims to provide a new deep-learning framework for the energy management of LE-BIPV. The proposed neural network framework can learn the intricate relationships between PV generation and battery storage and enable accurate energy management predictions. This proposed deep learning framework can substantially upgrade the global energy control of building-integrated PV systems in low-energy buildings.