The \textit{Temporal Fusion Transformer} (TFT), proposed by Lim \textit{et al.}, published in \textit{International Journal of Forecasting} (2021), is a state-of-the-art attention-based deep neural network architecture specifically designed for multi-horizon time series forecasting. It has demonstrated significant performance improvements over existing benchmarks. In this work, we introduce the Quantum Temporal Fusion Transformer (QTFT), a quantum-enhanced hybrid quantum-classical architecture that extends the capabilities of the classical TFT framework. The core idea of this work is inspired by the foundation studies, \textit{The Power of Quantum Neural Networks} by Amira Abbas \textit{et al.} and \textit{Quantum Vision Transformers} by El Amine Cherrat \textit{et al.}, published in \textit{ Nature Computational Science} (2021) and \textit{Quantum} (2024), respectively. A key advantage of our approach lies in its foundation on a variational quantum algorithm, enabling implementation on current noisy intermediate-scale quantum (NISQ) devices without strict requirements on the number of qubits or circuit depth. Our results demonstrate that QTFT is successfully trained on the forecasting datasets and is capable of accurately predicting future values. In particular, our experimental results on two different datasets display that the model outperforms its classical counterpart in terms of both training and test loss. These results indicate the prospect of using quantum computing to boost deep learning architectures in complex machine learning tasks.

Precise short-term price prediction in the highly volatile cryptocurrency market is critical for informed trading strategies. Although Temporal Fusion Transformers (TFTs) have shown potential, their direct use often struggles in the face of the market's non-stationary nature and extreme volatility. This paper introduces an adaptive TFT modeling approach leveraging dynamic subseries lengths and pattern-based categorization to enhance short-term forecasting. We propose a novel segmentation method where subseries end at relative maxima, identified when the price increase from the preceding minimum surpasses a threshold, thus capturing significant upward movements, which act as key markers for the end of a growth phase, while potentially filtering the noise. Crucially, the fixed-length pattern ending each subseries determines the category assigned to the subsequent variable-length subseries, grouping typical market responses that follow similar preceding conditions. A distinct TFT model trained for each category is specialized in predicting the evolution of these subsequent subseries based on their initial steps after the preceding peak. Experimental results on ETH-USDT 10-minute data over a two-month test period demonstrate that our adaptive approach significantly outperforms baseline fixed-length TFT and LSTM models in prediction accuracy and simulated trading profitability. Our combination of adaptive segmentation and pattern-conditioned forecasting enables more robust and responsive cryptocurrency price prediction.

This study proposes a novel approach for dynamic load balancing in Software-Defined Networks (SDNs) using a Transformer-based Deep Q-Network (DQN). Traditional load balancing mechanisms, such as Round Robin (RR) and Weighted Round Robin (WRR), are static and often struggle to adapt to fluctuating traffic conditions, leading to inefficiencies in network performance. In contrast, SDNs offer centralized control and flexibility, providing an ideal platform for implementing machine learning-driven optimization strategies. The core of this research combines a Temporal Fusion Transformer (TFT) for accurate traffic prediction with a DQN model to perform real-time dynamic load balancing. The TFT model predicts future traffic loads, which the DQN uses as input, allowing it to make intelligent routing decisions that optimize throughput, minimize latency, and reduce packet loss. The proposed model was tested against RR and WRR in simulated environments with varying data rates, and the results demonstrate significant improvements in network performance. For the 500MB data rate, the DQN model achieved an average throughput of 0.275 compared to 0.202 and 0.205 for RR and WRR, respectively. Additionally, the DQN recorded lower average latency and packet loss. In the 1000MB simulation, the DQN model outperformed the traditional methods in throughput, latency, and packet loss, reinforcing its effectiveness in managing network loads dynamically. This research presents an important step towards enhancing network performance through the integration of machine learning models within SDNs, potentially paving the way for more adaptive, intelligent network management systems.

Organizing and managing cryptocurrency portfolios and decision-making on transactions is crucial in this market. Optimal selection of assets is one of the main challenges that requires accurate prediction of the price of cryptocurrencies. In this work, we categorize the financial time series into several similar subseries to increase prediction accuracy by learning each subseries category with similar behavior. For each category of the subseries, we create a deep learning model based on the attention mechanism to predict the next step of each subseries. Due to the limited amount of cryptocurrency data for training models, if the number of categories increases, the amount of training data for each model will decrease, and some complex models will not be trained well due to the large number of parameters. To overcome this challenge, we propose to combine the time series data of other cryptocurrencies to increase the amount of data for each category, hence increasing the accuracy of the models corresponding to each category.

We introduce a novel digital twin framework for predictive maintenance of long-term physical systems. Using monitoring tire health as an application, we show how the digital twin framework can be used to enhance automotive safety and efficiency, and how the technical challenges can be overcome using a three-step approach. Firstly, for managing the data complexity over a long operation span, we employ data reduction techniques to concisely represent physical tires using historical performance and usage data. Relying on these data, for fast real-time prediction, we train a transformer-based model offline on our concise dataset to predict future tire health over time, represented as Remaining Casing Potential (RCP). Based on our architecture, our model quantifies both epistemic and aleatoric uncertainty, providing reliable confidence intervals around predicted RCP. Secondly, to incorporate real-time data, we update the predictive model in the digital twin framework, ensuring its accuracy throughout its life span with the aid of hybrid modeling and the use of discrepancy function. Thirdly, to assist decision making in predictive maintenance, we implement a Tire State Decision Algorithm, which strategically determines the optimal timing for tire replacement based on RCP forecasted by our transformer model. This approach ensures our digital twin accurately predicts system health, continually refines its digital representation, and supports predictive maintenance decisions. Our framework effectively embodies a physical system, leveraging big data and machine learning for predictive maintenance, model updates, and decision-making.

Increasingly, homeowners opt for photovoltaic (PV) systems and/or battery storage to minimize their energy bills and maximize renewable energy usage. This has spurred the development of advanced control algorithms that maximally achieve those goals. However, a common challenge faced while developing such controllers is the unavailability of accurate forecasts of household power consumption, especially for shorter time resolutions (15 minutes) and in a data-efficient manner. In this paper, we analyze how transfer learning can help by exploiting data from multiple households to improve a single house's load forecasting. Specifically, we train an advanced forecasting model (a temporal fusion transformer) using data from multiple different households, and then finetune this global model on a new household with limited data (i.e. only a few days). The obtained models are used for forecasting power consumption of the household for the next 24 hours~(day-ahead) at a time resolution of 15 minutes, with the intention of using these forecasts in advanced controllers such as Model Predictive Control. We show the benefit of this transfer learning setup versus solely using the individual new household's data, both in terms of (i) forecasting accuracy ($\sim$15\% MAE reduction) and (ii) control performance ($\sim$2\% energy cost reduction), using real-world household data.

Wind energy is a widely distributed, renewable, and environmentally friendly energy source that plays a crucial role in mitigating global warming and addressing energy shortages. Nevertheless, wind power generation is characterized by volatility, intermittence, and randomness, which hinder its ability to serve as a reliable power source for the grid. Accurate wind power forecasting is crucial for developing a new power system that heavily relies on renewable energy sources. However, traditional wind power forecasting systems primarily focus on ultra-short-term or short-term forecasts, limiting their ability to address the diverse adjustment requirements of the power system simultaneously. To overcome these challenges, We propose an automatic framework capable of forecasting wind power across multi-time scale. The framework based on the tree-structured Parzen estimator (TPE) and temporal fusion transformer (TFT) that can provide ultra-short-term, short-term and medium-term wind power forecasting power.Our approach employs the TFT for wind power forecasting and categorizes features based on their properties. Additionally, we introduce a generic algorithm to simultaneously fine-tune the hyperparameters of the decomposition method and model. We evaluate the performance of our framework by conducting ablation experiments using three commonly used decomposition algorithms and six state-of-the-art models for forecasting multi-time scale. The experimental results demonstrate that our proposed method considerably improves prediction accuracy on the public dataset Engie https://opendata-renewables.engie.com. Compared to the second-best state-of-the-art model, our approach exhibits a reduction of 31.75% and 28.74% in normalized mean absolute error (nMAE) for 24-hour forecasting, and 20.79% and 16.93% in nMAE for 48-hour forecasting, respectively.

Reliable estimates of Gross Primary Productivity (GPP), crucial for evaluating climate change initiatives, are currently only available from sparsely distributed eddy covariance tower sites. This limitation hampers access to reliable GPP quantification at regional to global scales. Prior machine learning studies on upscaling \textit{in situ} GPP to global wall-to-wall maps at sub-daily time steps faced limitations such as lack of input features at higher temporal resolutions and significant missing values. This research explored a novel upscaling solution using Temporal Fusion Transformer (TFT) without relying on past GPP time series. Model development was supplemented by Random Forest Regressor (RFR) and XGBoost, followed by the hybrid model of TFT and tree algorithms. The best preforming model yielded to model performance of 0.704 NSE and 3.54 RMSE. Another contribution of the study was the breakdown analysis of encoder feature importance based on time and flux tower sites. Such analysis enhanced the interpretability of the multi-head attention layer as well as the visual understanding of temporal dynamics of influential features.

Prognosis of the reactor accident is a crucial way to ensure appropriate strategies are adopted to avoid radioactive releases. However, there is very limited research in the field of nuclear industry. In this paper, we propose a method for accident prognosis based on the Temporal Fusion Transformer (TFT) model with multi-headed self-attention and gating mechanisms. The method utilizes multiple covariates to improve prediction accuracy on the one hand, and quantile regression methods for uncertainty assessment on the other. The method proposed in this paper is applied to the prognosis after loss of coolant accidents (LOCAs) in HPR1000 reactor. Extensive experimental results show that the method surpasses novel deep learning-based prediction methods in terms of prediction accuracy and confidence. Furthermore, the interference experiments with different signal-to-noise ratios and the ablation experiments for static covariates further illustrate that the robustness comes from the ability to extract the features of static and historical covariates. In summary, this work for the first time applies the novel composite deep learning model TFT to the prognosis of key parameters after a reactor accident, and makes a positive contribution to the establishment of a more intelligent and staff-light maintenance method for reactor systems.

Semiconductor device models are essential to understand the charge transport in thin film transistors (TFTs). Using these TFT models to draw inference involves estimating parameters used to fit to the experimental data. These experimental data can involve extracted charge carrier mobility or measured current. Estimating these parameters help us draw inferences about device performance. Fitting a TFT model for a given experimental data using the model parameters relies on manual fine tuning of multiple parameters by human experts. Several of these parameters may have confounding effects on the experimental data, making their individual effect extraction a non-intuitive process during manual tuning. To avoid this convoluted process, we propose a new method for automating the model parameter extraction process resulting in an accurate model fitting. In this work, model choice based approximate Bayesian computation (aBc) is used for generating the posterior distribution of the estimated parameters using observed mobility at various gate voltage values. Furthermore, it is shown that the extracted parameters can be accurately predicted from the mobility curves using gradient boosted trees. This work also provides a comparative analysis of the proposed framework with fine-tuned neural networks wherein the proposed framework is shown to perform better.