Deep learning approaches are increasingly relevant for time series forecasting tasks. Methods such as N-BEATS, which is built on stacks of multilayer perceptrons (MLPs) blocks, have achieved state-of-the-art results on benchmark datasets and competitions. N-BEATS is also more interpretable relative to other deep learning approaches, as it decomposes forecasts into different time series components, such as trend and sea-sonality. In this work, we present N-BEATS-MOE, an extension of N-BEATS based on a Mixture-of-Experts (MoE) layer. N-BEATS-MOE employs a dynamic block weighting strategy based on a gating network which allows the model to better adapt to the characteristics of each time series. We also hypothesize that the gating mechanism provides additional inter-pretability by identifying which expert is most relevant for each series. We evaluate our method across 12 benchmark datasets against several approaches, achieving consistent improvements on several datasets, especially those composed of heterogeneous time series.

The explosion of Time Series (TS) data, driven by advancements in technology, necessitates sophisticated analytical methods. Modern management systems increasingly rely on analyzing this data, highlighting the importance of effcient processing techniques. State-of-the-art Machine Learning (ML) approaches for TS analysis and forecasting are becoming prevalent. This paper briefly describes and compiles suitable algorithms for TS regression task. We compare these algorithms against each other and the classic ARIMA method using diverse datasets: complete data, data with outliers, and data with missing values. The focus is on forecasting accuracy, particularly for long-term predictions. This research aids in selecting the most appropriate algorithm based on forecasting needs and data characteristics.

Accurate MTLF supports informed decision-making across multiple aspects of power system management, including power plant scheduling, infrastructure expansion, market operations, and maintaining grid reliability and security. By anticipating future demand, utilities can optimize maintenance schedules, secure fuel supplies, and plan necessary capacity additions. Additionally, accurate forecasts across various time horizons are crucial for ensuring grid stability by maintaining the balance between supply and demand. Furthermore, precise forecasting enables strategic decision-making in energy markets, guiding the timing of electricity purchases and sales. In summary, load forecasting serves as a cornerstone for efficient, reliable, and resilient power system operations.

Sepsis is a leading cause of mortality in intensive care units (ICUs), representing a substantial medical challenge. The complexity of analyzing diverse vital signs to predict sepsis further aggravates this issue. While deep learning techniques have been advanced for early sepsis prediction, their 'black-box' nature obscures the internal logic, impairing interpretability in critical settings like ICUs. This paper introduces a framework that combines a deep learning model with an attention mechanism that highlights the critical time steps in the forecasting process, thus improving model interpretability and supporting clinical decision-making. We show that the attention mechanism could be adapted to various black box time series forecasting models such as N-HiTS and N-BEATS. Our method preserves the accuracy of conventional deep learning models while enhancing interpretability through attention-weight-generated heatmaps. We evaluated our model on the eICU-CRD dataset, focusing on forecasting vital signs for sepsis patients. We assessed its performance using mean squared error (MSE) and dynamic time warping (DTW) metrics. We explored the attention maps of N-HiTS and N-BEATS, examining the differences in their performance and identifying crucial factors influencing vital sign forecasting.

Short-term load forecasting (STLF) is vital for the effective and economic operation of power grids and energy markets. However, the non-linearity and non-stationarity of electricity demand as well as its dependency on various external factors renders STLF a challenging task. To that end, several deep learning models have been proposed in the literature for STLF, reporting promising results. In order to evaluate the accuracy of said models in day-ahead forecasting settings, in this paper we focus on the national net aggregated STLF of Portugal and conduct a comparative study considering a set of indicative, well-established deep autoregressive models, namely multi-layer perceptrons (MLP), long short-term memory networks (LSTM), neural basis expansion coefficient analysis (N-BEATS), temporal convolutional networks (TCN), and temporal fusion transformers (TFT). Moreover, we identify factors that significantly affect the demand and investigate their impact on the accuracy of each model. Our results suggest that N-BEATS consistently outperforms the rest of the examined models. MLP follows, providing further evidence towards the use of feed-forward networks over relatively more sophisticated architectures. Finally, certain calendar and weather features like the hour of the day and the temperature are identified as key accuracy drivers, providing insights regarding the forecasting approach that should be used per case.

Detecting and predicting septic shock early is crucial for the best possible outcome for patients. Accurately forecasting the vital signs of patients with sepsis provides valuable insights to clinicians for timely interventions, such as administering stabilizing drugs or optimizing infusion strategies. Our research examines N-BEATS, an interpretable deep-learning forecasting model that can forecast 3 hours of vital signs for sepsis patients in intensive care units (ICUs). In this work, we use the N-BEATS interpretable configuration to forecast the vital sign trends and compare them with the actual trend to understand better the patient's changing condition and the effects of infused drugs on their vital signs. We evaluate our approach using the publicly available eICU Collaborative Research Database dataset and rigorously evaluate the vital sign forecasts using out-of-sample evaluation criteria. We present the performance of our model using error metrics, including mean squared error (MSE), mean average percentage error (MAPE), and dynamic time warping (DTW), where the best scores achieved are 18.52e-4, 7.60, and 17.63e-3, respectively. We analyze the samples where the forecasted trend does not match the actual trend and study the impact of infused drugs on changing the actual vital signs compared to the forecasted trend. Additionally, we examined the mortality rates of patients where the actual trend and the forecasted trend did not match. We observed that the mortality rate was higher (92%) when the actual and forecasted trends closely matched, compared to when they were not similar (84%).

Additionally, this approach also falls a bit short from an Explainable AI (XAI) perspective. While these models all have attention mechanisms that can be visualized, many academics have argued that this may not be explainable and this is an active field of debate. Denis Vorotyntsev has made a great article summarizing the debate and I highly encourage checking his article out as well [10]. In contrast to the attention-based approach of transformers, the other primary direction of tackling the forecasting problem is the neural basis expansion analysis approach first proposed by Oreshkin et.

The distribution shift in Time Series Forecasting (TSF), indicating series distribution changes over time, largely hinders the performance of TSF models. Existing works towards distribution shift in time series are mostly limited in the quantification of distribution and, more importantly, overlook the potential shift between lookback and horizon windows. To address above challenges, we systematically summarize the distribution shift in TSF into two categories. Regarding lookback windows as input-space and horizon windows as output-space, there exist (i) intra-space shift, that the distribution within the input-space keeps shifted over time, and (ii) inter-space shift, that the distribution is shifted between input-space and output-space. Then we introduce, Dish-TS, a general neural paradigm for alleviating distribution shift in TSF. Specifically, for better distribution estimation, we propose the coefficient net (CONET), which can be any neural architectures, to map input sequences into learnable distribution coefficients. To relieve intra-space and inter-space shift, we organize Dish-TS as a Dual-CONET framework to separately learn the distribution of input- and output-space, which naturally captures the distribution difference of two spaces. In addition, we introduce a more effective training strategy for intractable CONET learning. Finally, we conduct extensive experiments on several datasets coupled with different state-of-the-art forecasting models. Experimental results show Dish-TS consistently boosts them with a more than 20% average improvement. Code is available.

In power grids, short-term load forecasting (STLF) is crucial as it contributes to the optimization of their reliability, emissions, and costs, while it enables the participation of energy companies in the energy market. STLF is a challenging task, due to the complex demand of active and reactive power from multiple types of electrical loads and their dependence on numerous exogenous variables. Amongst them, special circumstances, such as the COVID-19 pandemic, can often be the reason behind distribution shifts of load series. This work conducts a comparative study of Deep Learning (DL) architectures, namely Neural Basis Expansion Analysis Time Series Forecasting (N-BEATS), Long Short-Term Memory (LSTM), and Temporal Convolutional Networks (TCN), with respect to forecasting accuracy and training sustainability, meanwhile examining their out-of-distribution generalization capabilities during the COVID-19 pandemic era. A Pattern Sequence Forecasting (PSF) model is used as baseline. The case study focuses on day-ahead forecasts for the Portuguese national 15-minute resolution net load time series. The results can be leveraged by energy companies and network operators (i) to reinforce their forecasting toolkit with state-of-the-art DL models; (ii) to become aware of the serious consequences of crisis events on model performance; (iii) as a high-level model evaluation, deployment, and sustainability guide within a smart grid context.

A number of factors, such as the ongoing development of more intelligent mobile phones, the introduction of machine-to-machine connections, and the availability of enticing and data-intensive applications, are driving up the demand for mobile data traffic globally. Effective and precise mobile traffic forecasting is particularly important for 5G networks, which are expected to have much higher levels of traffic compared to previous generations of mobile networks.It has been well known that implementing traffic prediction can improve energy efficiency, ease resource allocation, provide the best user experience, and finally enable intelligent cellular networks. Traffic prediction has emerged as one of the main enabling technologies for autonomous networks, which is supported by the whole telecommunication sector, with the large-scale commercial deployment of the 5G network. Additionally, traffic forecasting is a crucial component of numerous transportation services, including navigation, route planning, and traffic control. By dynamically allocating network resources in accordance with actual traffic demand, precise short-term prediction of future traffic load information improves network energy efficiency, while long-term forecasting is crucial for network planning and base station localization. For many practical applications, such as predicting the demand for mobile data traffic, time-series prediction techniques are essential. Generally speaking, there are two types of data prediction models: traditional and machine learning models[1]. Traditional techniques include statistical methods such as Autoregressive Integrated Moving Average (ARIMA) and its extensions, such as Seasonal ARIMA (SARIMA). Due to numerous aspects, such as user mobility, the arrival pattern, and distinct user requirements, the pattern of network traffic is actually highly complex.