Evaluation of Deep Learning-based prediction models in Microgrids

TL;DR

This paper evaluates deep learning models for energy demand forecasting in microgrids, demonstrating their effectiveness in reducing peak demand and CO2 emissions, especially suitable for SMEs due to low hardware costs.

Contribution

It provides an empirical assessment of deep learning models for energy prediction in microgrids, highlighting their accuracy and practical benefits for renewable energy integration.

Findings

Shallow models outperform persistence baseline in MAPE across all forecast horizons.

Up to 23% reduction in peak energy demand achieved.

Potential annual CO2 emission reduction of 3,091 kg.

Abstract

It is crucial today that economies harness renewable energies and integrate them into the existing grid. Conventionally, energy has been generated based on forecasts of peak and low demands. Renewable energy can neither be produced on demand nor stored efficiently. Thus, the aim of this paper is to evaluate Deep Learning-based forecasts of energy consumption to align energy consumption with renewable energy production. Using a dataset from a use-case related to landfill leachate management, multiple prediction models were used to forecast energy demand.The results were validated based on the same dataset from the recycling industry. Shallow models showed the lowest Mean Absolute Percentage Error (MAPE), significantly outperforming a persistence baseline for both, long-term (30 days), mid-term (7 days) and short-term (1 day) forecasts. A potential decrease of up to 23% in peak energy demand was found that could lead to a reduction of 3,091 kg in CO2-emissions per year. Our approach requires low finanacial investments for energy-management hardware, making it suitable for usage in Small and Medium sized Enterprises (SMEs).