Probabilistic forecasting method for mid-term hourly load time series based on an improved temporal fusion transformer model

Li, Dan; Ya, Tan; Zhang, Yuanhang; Miao, Shuwei; He, Shuai

doi:10.1016/j.ijepes.2022.108743

Cited by 39 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, TFT models have been introduced only recently for multi-horizon time series forecasting in the literature [10]. Nevertheless, they have been used for MTLF predictions over the energy load [39], where they have demonstrated substantial improvements in forecasting accuracy as well as the incorporation of uncertainty estimation in time series forecasting. However, the data that are used for training do not include environmental factors and categorical values and are also performed with sufficient resources in terms of memory, processing power and GPU availability.…”

Section: Discussionmentioning

confidence: 99%

Edge-Based Short-Term Energy Demand Prediction

Lekidis

Papageorgiou

2023

Energies

View full text Add to dashboard Cite

The electrical grid is gradually transitioning towards being an interconnected area of the smart grid, where embedded devices operate in an autonomous manner without any human intervention. An important element for this transition is the energy demand prediction, since the needs for energy have substantially increased due to the introduction of new and heavy consumption sources, such as electric vehicles. Accurate energy demand prediction, especially for short-term durations (i.e., minutes to hours), allows grid operators to produce the substantial amount needed to satisfy the demand–response equilibrium and avoid peak electricity load conditions that may also lead to blackouts in densely populated areas. However, to achieve such an accuracy level, machine learning (ML) models require extensive training with historical measurements, which is usually resource intensive (e.g., in memory and processing power). Hence, deriving accurate predictions for short-term energy demands is challenging due to the absence of external factors such as environmental data from different regions and seasons and categorical values such as bank/bridging holidays in the ML model. Additionally, existing work focuses on ML model execution on Cloud platforms, which usually does not satisfy the real-time requirements of grid operators for short-term energy demand predictions. To address these challenges, this article presents a new method that considers environmental factors and categorical values to build an energy profile for each consumer in a multi-access edge computing (MEC) framework. The method is also based on the Temporal Fusion Transformer (TFT) ML model, which allows it to learn the temporal dependencies of the gathered historical measurements and predict energy demands with satisfying accuracy. The method is applied to a home energy management system testbed containing photovoltaic systems, smart meters, sensors and actuators for detecting environmental factors (i.e., temperature, humidity and radiation) as well as energy storage systems as an additional energy supply source. The MEC framework is deployed in data concentrator devices where the TFT ML model is executed with low resource requirements, ensuring additional security as the data do not leave the location where they are produced.

show abstract

Section: Discussionmentioning

confidence: 99%

Edge-Based Short-Term Energy Demand Prediction

Lekidis

Papageorgiou

2023

Energies

View full text Add to dashboard Cite

show abstract

“…By introducing the self-attention mechanism, the Transformer model can model the relationship between different positions in the sequence more effectively. For knowledge graph construction, it is necessary to extract entities from the knowledge domain and label their knowledge labels so that the knowledge graph can be visualized [21].…”

Section: Model Structure Of Transformermentioning

confidence: 99%

Knowledge Graph-based Diversity Analysis of Supplier Holographic Portraits

Li,

Bian,

Wen

et al. 2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

Fully understand the development of suppliers in order to make better supplier selection. This paper is based on the knowledge graph, through the knowledge updating of the knowledge graph combined with the Transformer model for knowledge extraction of supplier entity relationship, forming the ternary semantic information of supplier entity relationship. Then, based on the big data platform for the construction of supplier holographic portrait and knowledge storage, through information integration, analysis and other links to identify the supplier attributes for label definition. Taking cell phone product suppliers as an example, we use Python technology to obtain relevant data and validate the specific role of supplier holographic portrait in terms of the supplier’s comprehensive strength, behavioral prediction, transaction closeness, and comprehensive evaluation. The results show that: the correlation between the comprehensive strength of suppliers and the amount of winning bids is strong, and its R2 test result is 0.5924, and it can realize the behavioral prediction of suppliers in the supply chain. Supplier H offers a range of cell phone products in 2022, which is 17.62%<unk>21.17% higher than the benchmark market price. The holographic portrait of suppliers based on a knowledge graph combined with a big data platform can meet the need to carry out an all-around analysis of suppliers and provide more accurate support for diversified decision-making on the demand side.

show abstract

“…Consequently, it provides a more precise determination of the upper and lower bounds of PIs. The model introduced in [37] leverages GRU and an enhanced temporal fusion transformer, which significantly improves the model's ability to capture long-term dependencies in the data. Furthermore, this model includes quantile constraints and PI penalty terms to eliminate quantile crossover and generate concise PIs.…”

Section: Probabilistic Stlfmentioning

confidence: 99%

Ensemble Learning by Stacking for Deterministic and Probabilistic Short-term Load Forecasting

Dudek

2023

Preprint

View full text Add to dashboard Cite

In this study, we explore meta-learning for combining forecasts derived from individual base models for both deterministic and probabilistic short-term load forecasting. Unlike conventional approaches that rely on straightforward averaging, we harness the power of machine learning to implement more advanced methods for combining forecasts through meta-learning, consequently increasing the accuracy of forecasts. For deterministic forecasting, we employ a spectrum of meta-learners, including linear regression, k-nearest neighbors, multilayer perceptron, random forest, and long short-term memory. For probabilistic forecasting, we utilize quantile linear regression, quantile regression forest and post-processing involving residual simulation. We introduce both global and local meta-learning variants tailored for time series data characterized by intricate seasonality patterns. Through a comprehensive assessment across various forecasting scenarios, we illustrate the superior performance of meta-learners in comparison to conventional averaging techniques.

show abstract

Probabilistic forecasting method for mid-term hourly load time series based on an improved temporal fusion transformer model

Cited by 39 publications

References 28 publications

Edge-Based Short-Term Energy Demand Prediction

Edge-Based Short-Term Energy Demand Prediction

Knowledge Graph-based Diversity Analysis of Supplier Holographic Portraits

Ensemble Learning by Stacking for Deterministic and Probabilistic Short-term Load Forecasting

Contact Info

Product

Resources

About