Details

Autor(en) / Beteiligte

• Baz, Abdullah
• Logeshwaran, J.
• Natarajan, Yuvaraj
• Patel, Shobhit K.

Titel

Deep fuzzy nets approach for energy efficiency optimization in smart grids

Ist Teil von

• Applied soft computing, 2024-08, Vol.161, p.111724, Article 111724

Ort / Verlag

Elsevier B.V

Erscheinungsjahr

2024

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Using smart grids has become crucial for achieving efficient and sustainable energy management. One of the main challenges in smart grids is optimizing energy efficiency by managing and controlling electricity generation, transmission, and distribution. The Deep Fuzzy Nets (DFN) approach has been proposed as a novel technique that combines the capabilities of deep learning and fuzzy login to optimize energy efficiency in smart grids. The proposed approach utilizes a deep learning architecture to learn the complex relationships between various parameters within the smart grid system. The fuzzy logic component handles uncertainties and imprecision’s in the data, making the DFN approach well-suited for real-world energy management applications. The proposed approach can provide accurate and reliable predictions and enhancing energy efficiency in a dynamic and evolving smart grid environment. The proposed deep fuzzy nets approach reached 91% sensitivity, 94.45% specificity, 92/37% prevalence threshold, and 96.54% critical success index. This approach has been tested in various energy systems and has demonstrated capabilities to improve system-level energy efficiency while still giving users control of their energy usage. As energy efficiency optimization in intelligent grids continues to be a primary focus of energy research, deep fuzzy nets could provide a powerful solution for energy optimization. •Combination of deep learning and fuzzy logic to optimize the energy efficiency in smart grids.•Energy efficiency optimization in smart grids by predicting energy demand and accurately controlling energy consumption.•This approach is capable of real-time adaptation to changing environmental and consumption factors.•Higher accuracy and efficiency using deep learning and fuzzy logic.•Sustainable energy consumption using optimization of energy efficiency in smart grids.