Authors: Antonino Capillo, Enrico De Santis, Fabio Massimo Frattale Mascioli, Antonello Rizzi

Published on: January 22, 2024

Impact Score: 8.3

Arxiv code: Arxiv:2402.01688

Summary

• What is new: The paper introduces a novel online Hierarchical Energy Management System (HEMS) for Renewable Energy Communities (RECs) that outperforms traditional self-consumption approaches by approximately 20% in cost savings, incorporating a hybrid Fuzzy Inference System – Genetic Algorithm (FIS-GA) and Explainable AI for better precision and reliability.
• Why this is important: Addressing the need for efficient Energy Management Systems in Smart Grids, particularly for RECs, to enhance energy efficiency and reduce costs while adhering to EU’s renewable energy sharing directives.
• What the research proposes: A synthesized online HEMS for REC cost minimization, implementing a hybrid FIS-GA model for optimized power flows and an LSTM for accurate prediction of power generation and consumption.
• Results: The system achieved significant precision in optimization with short computation times, leading to approximately 20% savings in costs compared to the local self-consumption approach, with added benefits of reliability and easy interpretation through Explainable AI.

Technical Details

Technological frameworks used: Hybrid Fuzzy Inference System – Genetic Algorithm (FIS-GA), LSTM for predictions, Explainable AI for model transparency

Models used: FIS-GA for energy optimization, LSTM for power prediction

Data used: Historical power generation and consumption data

Potential Impact

This breakthrough could disrupt energy management and smart grid solution providers, benefiting energy companies in the EU and potentially worldwide by enabling cost-effective renewable energy sharing within local communities.

Want to implement this idea in a business?

We have generated a startup concept here: SmartRenew.