The University of Southampton
University of Southampton Institutional Repository

Electrical Load Consumption and Photovoltaic Power Forecasting using Deep CNN

Electrical Load Consumption and Photovoltaic Power Forecasting using Deep CNN
Electrical Load Consumption and Photovoltaic Power Forecasting using Deep CNN
The modern world is highly dependent on electricity and needs a continuous supply of load demand. During the past decades, renewable energies (REs), as clean and economical sources, have been developed to answer the increasing load demand. However, both renewable energy production and electricity consumption have random characteristics caused by different uncertain factors such as weather conditions and customer behavior. Therefore, it is crucial to simultaneously perform load forecasting and RE generation prediction in areas where most of the demand is supplied by REs. This study proposes a forecasting framework based on a deep three-dimensional convolutional neural network for load forecasting and photovoltaic (PV) power prediction. In this way, power system operators can balance demand and supply based on the predicted values. Also, using the same framework, which is capable of forecasting both load and PV power, would significantly reduce computational costs. The comparative analysis for 15-min, 90-min, 3-h, and 6-h ahead horizon shows that the accuracy of the proposed method increased in all time horizons compared to long short-term memory (LSTM), gated recurrent unit (GRU), and two-dimensional convolutional neural network (Conv2D).
Convolutional neural network, Load demand, Photovoltaic power, Forecasting
IEEE
Dehghan, Fariba
e0863ef3-0a6c-467f-87ed-824cbd16408c
Dehghan, Fariba
e0863ef3-0a6c-467f-87ed-824cbd16408c

Dehghan, Fariba (2024) Electrical Load Consumption and Photovoltaic Power Forecasting using Deep CNN. In 2024 11th Iranian Conference on Renewable Energy and Distribution Generation (ICREDG). IEEE.. (doi:10.1109/ICREDG61679.2024.10607776).

Record type: Conference or Workshop Item (Paper)

Abstract

The modern world is highly dependent on electricity and needs a continuous supply of load demand. During the past decades, renewable energies (REs), as clean and economical sources, have been developed to answer the increasing load demand. However, both renewable energy production and electricity consumption have random characteristics caused by different uncertain factors such as weather conditions and customer behavior. Therefore, it is crucial to simultaneously perform load forecasting and RE generation prediction in areas where most of the demand is supplied by REs. This study proposes a forecasting framework based on a deep three-dimensional convolutional neural network for load forecasting and photovoltaic (PV) power prediction. In this way, power system operators can balance demand and supply based on the predicted values. Also, using the same framework, which is capable of forecasting both load and PV power, would significantly reduce computational costs. The comparative analysis for 15-min, 90-min, 3-h, and 6-h ahead horizon shows that the accuracy of the proposed method increased in all time horizons compared to long short-term memory (LSTM), gated recurrent unit (GRU), and two-dimensional convolutional neural network (Conv2D).

This record has no associated files available for download.

More information

Published date: 30 July 2024
Keywords: Convolutional neural network, Load demand, Photovoltaic power, Forecasting

Identifiers

Local EPrints ID: 505443
URI: http://eprints.soton.ac.uk/id/eprint/505443
PURE UUID: d968a489-30c8-4a93-bfb4-a8d47baf57d3
ORCID for Fariba Dehghan: ORCID iD orcid.org/0009-0002-0319-7905

Catalogue record

Date deposited: 08 Oct 2025 16:55
Last modified: 09 Oct 2025 02:22

Export record

Altmetrics

Contributors

Author: Fariba Dehghan ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×