A hybrid Autoformer framework for electricity demand forecasting

Wang, Ziqian; Chen, Zhihao; Yang, Yang; Liu, Chanjuan; Li, Xian; Wu, Jinran

doi:10.1016/j.egyr.2023.02.083

Cited by 12 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, we have that this group is made up of 13 documents belonging mainly to the energy and retail sectors, whose main characteristic is the use of deep learning in their forecast models. The models proposed by this group are aimed at improving the performance of deep learning algorithms through various resources, among which are: the use of hyper-parameter optimization algorithms, such as the "firefly algorithm" [31] or the " Improved Giza pyramids construction algorithm" [32]; the use of dimensionality reduction techniques such as "Encoders" [33], [34] and "Principal Component Analysis" (PCA) to optimize the model inputs; the use of "cross or transfer learning", that is, the use of data from similar products or services when the data of the product under study is very limited [35], [36], [37]; the use of "clustering" to divide the data into groups of similar behavior and train a neural network for each cluster [38]; the transformation of the data into images and their decomposition to then use a CNN for feature extraction and an LSTM for prediction [39]; the use of complex time series decomposition algorithms using neural networks [40]; the use of parallel computing [41]; and the use of special architectures of convolutional networks [42].…”

Section: ) Groupmentioning

confidence: 99%

“…Complex and nonlinear data Fourteen of the 33 documents analyzed indicate that the main problem that the proposed "machine learning" models are intended to solve is the complexity and non-linearity of the patterns generated by the variables that affect the forecast. [12], [18], [20], [21], [22], [28], [23], [25], [26], [31], [43], [40], [41], [42].…”

Section: Keyword Inputmentioning

confidence: 99%

“…This leads to the need to build models that can perform well in these types of situations. [14], [15], [18], [28], [27], [35], [36], [40].…”

Section: Low Volumen Of Training Datamentioning

confidence: 99%

“…The demand for many products exhibits temporal patterns, such as trend and seasonality, however, other patterns are superimposed on these temporal patterns due to external factors such as the economy, climate, competition, etc. Simultaneously modeling both types of patterns can be a very complex task and a great challenge for forecasting models [16], [20], [29], [28], [30], [26], [40], [41].…”

Section: Temporal Patterns and External Factorsmentioning

confidence: 99%

See 3 more Smart Citations

A Systematic Review of the Literature on the Use of Artificial Intelligence in Forecasting the Demand for Products and Services in Various Sectors

Villar,

Lengua

2024

IJACSA

View full text Add to dashboard Cite

This systematic review, carried out under the PRISMA methodology, aims to identify the recently proposed artificial intelligence models for demand forecasting, distinguishing the problems they try to overcome, recognizing the artificial intelligence methods used, detailing the performance metrics used, recognizing the performance achieved by these models and identifying what is new in them. Studies in the manufacturing, retail trade, tourism and electric energy sectors were considered in order to facilitate the transfer of knowledge from different sectors. 33 articles were analyzed, with the main results being that the proposed models are generally ensembles of various artificial intelligence methods; that the complexity of data and its scarcity are the main problems addressed; that combinations of simple machine learning, "bagging", "boosting" and deep neural networks, are the most used methods; that the performance of the proposed models surpasses the classic statistical methods and other reference models; and that, finally, the proposed novelties cover aspects such as the type of data used, the pattern extraction techniques used, the assembly forms of the applied models and the use of algorithms for automating the adjustment of the models. Finally, a forecast model is proposed that includes the most innovative aspects found in this research.

show abstract

Section: ) Groupmentioning

confidence: 99%

Section: Keyword Inputmentioning

confidence: 99%

“…This leads to the need to build models that can perform well in these types of situations. [14], [15], [18], [28], [27], [35], [36], [40].…”

Section: Low Volumen Of Training Datamentioning

confidence: 99%

Section: Temporal Patterns and External Factorsmentioning

confidence: 99%

See 2 more Smart Citations

A Systematic Review of the Literature on the Use of Artificial Intelligence in Forecasting the Demand for Products and Services in Various Sectors

Villar,

Lengua

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Anticipating the next-hour demand within a bounded location might help cope with challenging situations. Forecasting electricity demand is a worldwide issue; see, for example, [30] , [23] , [32] , [42] , [41] , [37] , [8] . But since our study is performed in the context of the country of Jordan, we focus next on related work on electricity demand in Jordan.…”

Section: Introductionmentioning

confidence: 99%

Forecasting next-hour electricity demand in small-scale territories: Evidence from Jordan

Nofal

2023

Heliyon

View full text Add to dashboard Cite

Early Warning of Energy Storage Battery Fault Based on Improved Autoformer and Adaptive Threshold

Cheng,

Zhang,

Liu

2024

Energy Tech

View full text Add to dashboard Cite

To enhance voltage prediction accuracy in energy storage batteries and address the limitations of fixed threshold warning methods, a fault warning approach based on an improved Autoformer model and adaptive thresholds is proposed. First, a spatiotemporal filtering layer is introduced into the autocorrelation mechanism to analyze the trend features of voltage sequences across different frequency domains. Additionally, an adaptive gating residual connection is used to link the sublayer and current layer output features, which helps to improve the model's adaptive feature selection capability. This innovation enables the development of a robust voltage prediction model based on the enhanced Autoformer. Then, a similarity‐based adaptive threshold, using interval estimation, is employed to rapidly track variations in battery voltage, enabling dynamic adjustment of voltage thresholds. Finally, the proposed method is validated with real voltage data from an operational energy storage station. The experimental results shows that the proposed model has higher accuracy and robustness compared to similar methods. The adaptive threshold can reduce the false alarm rate by ≈18% and issue alarms at three sampling points ahead of the battery management system alarm, improving fault warning accuracy and illustrating that early fault warning is effectively and practically carried out using the method.

show abstract

A hybrid Autoformer framework for electricity demand forecasting

Cited by 12 publications

References 22 publications

A Systematic Review of the Literature on the Use of Artificial Intelligence in Forecasting the Demand for Products and Services in Various Sectors

A Systematic Review of the Literature on the Use of Artificial Intelligence in Forecasting the Demand for Products and Services in Various Sectors

Forecasting next-hour electricity demand in small-scale territories: Evidence from Jordan

Early Warning of Energy Storage Battery Fault Based on Improved Autoformer and Adaptive Threshold

Contact Info

Product

Resources

About