Published on Sun Sep 29 2019

Evaluation of Deep Learning-based prediction models in Microgrids

Alexey Györi, Mathis Niederau, Violett Zeller, Volker Stich

Energy has been generated based on forecasts of peak and low demands. Shallow models showed the lowest Mean Absolute Percentage Error (MAPE) A potential decrease of up to 23% in peak energy demand was found.

0
0
0
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).

Tue Aug 24 2021
Machine Learning
Energy time series forecasting-Analytical and empirical assessment of conventional and machine learning models
Deep learning methods have been adopted in the literature as contenders to solve the energy time series forecasting (TSF) problems. This paper provides a comprehensive analytical assessment for conventional,machine learning, and deep learning methods that can be utilized to solve TSF problems.
0
0
0
Wed Jan 20 2021
Machine Learning
Deep Learning for Intelligent Demand Response and Smart Grids: A Comprehensive Survey
Deep Learning (DL) can be leveraged to learn patterns from the generated data and predict the demand for electricity and peak hours. We review the state-of-the-art applications of DL in smart grids and demand response. We highlight the challenges presented in existing research works.
0
0
0
Sat Oct 29 2016
Neural Networks
Building Energy Load Forecasting using Deep Neural Networks
The power grid of the future should provide an unprecedented level of flexibility in energy management. Ensuring sustainability demands more efficient energy management with with minimized energy wastage. To that end, intelligent decision making requires accurate predictions of future energy demand/load.
0
0
0
Mon Feb 05 2018
Machine Learning
On the Feasibility of Generic Deep Disaggregation for Single-Load Extraction
The developed model is evaluated on the publicly available UK-DALE dataset. The model is capable of achieving state-of-art performance in load monitoring for a variety of load categories.
0
0
0
Thu Jun 16 2016
Neural Networks
Improving Power Generation Efficiency using Deep Neural Networks
The main objective is reduction of energy losses and this requires improvements on data acquisition and analysis. We use consumers' electrical smart meter readings to estimate network loading. This information can then be used for better capacity planning.
0
0
0
Wed Nov 25 2020
Machine Learning
Energy Forecasting in Smart Grid Systems: A Review of the State-of-the-art Techniques
Energy forecasting has a vital role to play in smart grid (SG) systems. Managing efficient forecasting while ensuring the least possible prediction error is one of the main challenges posed in the grid. This paper provides a comprehensive review of state-of-the-art forecasting methods for SG systems.
0
0
0