2021
DOI: 10.3390/info12120516
|View full text |Cite
|
Sign up to set email alerts
|

Short-Term Load Forecasting Based on the Transformer Model

Abstract: From the perspective of energy providers, accurate short-term load forecasting plays a significant role in the energy generation plan, efficient energy distribution process and electricity price strategy optimisation. However, it is hard to achieve a satisfactory result because the historical data is irregular, non-smooth, non-linear and noisy. To handle these challenges, in this work, we introduce a novel model based on the Transformer network to provide an accurate day-ahead load forecasting service. Our mod… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
14
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 35 publications
(14 citation statements)
references
References 31 publications
0
14
0
Order By: Relevance
“…Wu et al [39] previously presented an adaptation of the transformer model for time series predictions; however, they did so to predict influenza cases rather than load forecasting and did not include many contextual features in their work. Zhao et al [40] presented a transformer implementation for load forecasting tasks, however the contextual features were handled outside of the transformer and therefore added another processing complexity layer to the solution. Additionally, their work provided little details in terms of implementation, and the evaluation was conducted on a single data stream and limited to one-day-ahead predictions.…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…Wu et al [39] previously presented an adaptation of the transformer model for time series predictions; however, they did so to predict influenza cases rather than load forecasting and did not include many contextual features in their work. Zhao et al [40] presented a transformer implementation for load forecasting tasks, however the contextual features were handled outside of the transformer and therefore added another processing complexity layer to the solution. Additionally, their work provided little details in terms of implementation, and the evaluation was conducted on a single data stream and limited to one-day-ahead predictions.…”
Section: Related Workmentioning
confidence: 99%
“…These results are also highlighted in Figure 8b. Zhao et al [40] also employed the transformer for load forecasting; however, they used similar days' load data as the input for the transformer, while our approach uses previous load readings together with contextual features. Consequently, in contrast to the approach proposed by Zhao et al [40], our approach is flexible with regard to the number of lag readings considered for the forecasting [40], as demonstrated in experiments.…”
Section: Overall Performancementioning
confidence: 99%
See 1 more Smart Citation
“…In [16], an MTLF model based on the neural network approach is presented without any climatic information. The transformer models are suggested in [17,18] for load forecasting.…”
Section: Literature Reviewmentioning
confidence: 99%
“…The forecasting method can be the way to solve the problem. Forecasting is a process of predicting based on historical data and extracting trends that can be approached using statistical or machine learning [2]. In [3]they study the GPU NVIDIA GTX 1060, which is affected by the bitcoin price.…”
Section: Introductionmentioning
confidence: 99%