Pubblicazioni

Time Series Forecasting for Energy Management: NCPs vs. LSTM.

LA SFIDA

Confronto delle Neural Circuit Policies (NCPs) vs Long Short-Term Memory (LSTM) nel prevedere i dati sulle serie temporali di produzione e consumo energetico.

GLI OBIETTIVI

• ottimizzazione energie rinnovabili
• bilanciamento della CER
• riduzione degli sprechi di risorse
• massimizzazione del TIP

IL TEAM

Giulia Palma
Elna Sara Joy Chengalipunath
Antonio Rizzo

Abstract del progetto

This paper investigates the effectiveness of Neural Circuit Policies (NCPs) compared to Long Short-Term Memory (LSTM) networks in forecasting time series data for energy production and consumption in the context of predictive maintenance. Utilizing a dataset generated from the energy production and consumption data of a Tuscan company specialized in food refrigeration, we simulate a scenario where the company employs a 60 kWh storage system and calculate the battery charge and discharge policies to assess potential cost reductions and increased self-consumption of produced energy. Our findings demonstrate that NCPs outperform LSTM networks by leveraging underlying physical models, offering superior predictive maintenance solutions for energy consumption and production.

Scopri i nostri progetti

La nostra piattaforma Sunlink è progettata per abilitare l’Industria 5.0,
facilitando l’ottimizzazione dell’uso delle risorse energetiche e la produzione sostenibile.

Pubblicazione scientifica

A Reinforcement Learning approach to the management of Renewable Energy Communities

Optimal management of renewable energy is an important pillar of...

Progetti di ricerca

Pubblicazione scientifica

Reinforcement Learning for Energy Community Management: A European-Scale Study

Efficient management of renewable energy resources is imperative for promoting...

Pubblicazione scientifica

Optimizing Energy Efficiency in Smart Factories:Battery Energy Storage Systems Integration Analysis

In the rapidly evolving scenario of renewable energy technology, the...

it_IT