Details
| Original language | English |
|---|---|
| Title of host publication | CANDO-EPE 2023 - Proceedings |
| Subtitle of host publication | IEEE 6th International Conference and Workshop Obuda on Electrical and Power Engineering |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 83-88 |
| Number of pages | 6 |
| ISBN (electronic) | 9798350328752 |
| ISBN (print) | 979-8-3503-2876-9 |
| Publication status | Published - 2023 |
| Event | 6th IEEE International Conference and Workshop Obuda on Electrical and Power Engineering, CANDO-EPE 2023 - Budapest, Hungary Duration: 19 Oct 2023 → 20 Oct 2023 |
Publication series
| Name | IEEE 6th International Conference and Workshop Obuda on Electrical and Power Engineering |
|---|---|
| ISSN (Print) | 2831-4492 |
| ISSN (electronic) | 2831-4506 |
Abstract
The imbalance between supply and demand is a crucial factor in the operation of the power system therefore, it is essential to be able to predict its value from historical, measured, and prediction data. This work proposes a multistep version of the autoregressive distributed lag model for the short-term forecast of imbalance. The proposed forecast model has been compared to a Long Short-Term Memory network-based procedure using real data. The results show that the proposed multistep autoregressive forecast model outperforms the others in all three evaluation metrics. Since, in many cases, it is sufficient to specify the sign of the imbalance, this paper introduces the concept of sign accuracy as a function of the forecasted imbalance and evaluates it for the investigated solutions.
Keywords
- autoregressive distributed lag model, balancing energy, system imbalance, time series forecast
ASJC Scopus subject areas
- Engineering(all)
- Electrical and Electronic Engineering
- Engineering(all)
- Safety, Risk, Reliability and Quality
- Mathematics(all)
- Control and Optimization
- Computer Science(all)
- Artificial Intelligence
- Computer Science(all)
- Information Systems
- Computer Science(all)
- Software
- Decision Sciences(all)
- Information Systems and Management
- Energy(all)
- Energy Engineering and Power Technology
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
CANDO-EPE 2023 - Proceedings: IEEE 6th International Conference and Workshop Obuda on Electrical and Power Engineering. Institute of Electrical and Electronics Engineers Inc., 2023. p. 83-88 (IEEE 6th International Conference and Workshop Obuda on Electrical and Power Engineering).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Short-Term System Imbalance Forecast Using Autoregressive Distributed Lag Method
AU - Magyar, Attila
N1 - Funding Information: Project no. 131501 has been implemented with the support provided from the National Research, Development and Innovation Fund of Hungary, financed under the K 19 funding scheme.
PY - 2023
Y1 - 2023
N2 - The imbalance between supply and demand is a crucial factor in the operation of the power system therefore, it is essential to be able to predict its value from historical, measured, and prediction data. This work proposes a multistep version of the autoregressive distributed lag model for the short-term forecast of imbalance. The proposed forecast model has been compared to a Long Short-Term Memory network-based procedure using real data. The results show that the proposed multistep autoregressive forecast model outperforms the others in all three evaluation metrics. Since, in many cases, it is sufficient to specify the sign of the imbalance, this paper introduces the concept of sign accuracy as a function of the forecasted imbalance and evaluates it for the investigated solutions.
AB - The imbalance between supply and demand is a crucial factor in the operation of the power system therefore, it is essential to be able to predict its value from historical, measured, and prediction data. This work proposes a multistep version of the autoregressive distributed lag model for the short-term forecast of imbalance. The proposed forecast model has been compared to a Long Short-Term Memory network-based procedure using real data. The results show that the proposed multistep autoregressive forecast model outperforms the others in all three evaluation metrics. Since, in many cases, it is sufficient to specify the sign of the imbalance, this paper introduces the concept of sign accuracy as a function of the forecasted imbalance and evaluates it for the investigated solutions.
KW - autoregressive distributed lag model
KW - balancing energy
KW - system imbalance
KW - time series forecast
UR - http://www.scopus.com/inward/record.url?scp=85185711817&partnerID=8YFLogxK
U2 - 10.1109/CANDO-EPE60507.2023.10417995
DO - 10.1109/CANDO-EPE60507.2023.10417995
M3 - Conference contribution
AN - SCOPUS:85185711817
SN - 979-8-3503-2876-9
T3 - IEEE 6th International Conference and Workshop Obuda on Electrical and Power Engineering
SP - 83
EP - 88
BT - CANDO-EPE 2023 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th IEEE International Conference and Workshop Obuda on Electrical and Power Engineering, CANDO-EPE 2023
Y2 - 19 October 2023 through 20 October 2023
ER -