Search

This paper develops a trustworthy deep learning model that considers electricity demand (G) and local climate conditions. The model utilises Multi-Head Self-Attention Transformer (TNET) to capture critical information from G, to attain reliable predictions with local climate (rainfall, radiation, humidity, evaporation, and maximum and minimum temperatures) data from Energex substations in Queensland, Australia. The TNET model is then evaluated with deep learning models (Long-Short Term Memory LSTM, Bidirectional LSTM BILSTM, Gated Recurrent Unit GRU, Convolutional Neural Networks CNN, and Deep Neural Network DNN) based on robust model assessment metrics. The Kernel Density Estimation method is used to generate the prediction interval (PI) of electricity demand forecasts and derive probability metrics and results to show the developed TNET model is accurate for all the substations. The study concludes that the proposed TNET model is a reliable electricity demand predictive tool that has high accuracy and low predictive errors and could be employed as a stratagem by demand modellers and energy policy-makers who wish to incorporate climatic factors into electricity demand patterns and develop national energy market insights and analysis systems.

Prediction problems in timed datasets related to human activities are especially difficult to solve, because of the specific characteristics and the scarce number of predictive (input) variables available to tackle these problems. In this paper, we try to find out whether Machine Learning (ML) approaches can be successfully applied to these problems. We deal with timed datasets with human activity patterns, in which the input variables are exclusively related to the day or type of day when the prediction is carried out and, usually, to the meteorology of those days. These problems with a marked human activity pattern frequently appear in mobility and traffic-related problems, delivery prediction (packets, food), and many other activities, usually in cities. We evaluate the performance in these problems of different ML methods such as artificial neural networks (multi-layer perceptrons, extreme learning machines) and support vector regression algorithms, together with an Analogue-type (KNN) approach, which serves as a baseline algorithm and provides information about when it is expected that ML approaches will fail, by looking for similar situations in the past. The considered ML algorithms are evaluated in four real prediction problems with human activity patterns, such as school absences, bike-sharing demand, parking occupation, and packets delivered in a post office. The results obtained show the good performance of the ML algorithms, revealing that they can deal with scarce information in all the problems considered. The results obtained have also revealed the importance of including meteorology as the input variables, showing that meteorology is frequently behind demand peaks or valleys in this kind of problem. Finally, we show that having a number of similar situations in the past (training set) prevents ML algorithms from making important mistakes in the prediction obtained.

We review the latest modeling techniques and propose new hybrid SAELSTM framework based on Deep Learning (DL) to construct prediction intervals for daily Global Solar Radiation (GSR) using the Manta Ray Foraging Optimization (MRFO) feature selection to select model parameters. Features are employed as potential inputs for Long Short-Term Memory and a seq2seq SAELSTM autoencoder Deep Learning (DL) system in the final GSR prediction. Six solar energy farms in Queensland, Australia are considered to evaluate the method with predictors from Global Climate Models and ground-based observation. Comparisons are carried out among DL models (i.e., Deep Neural Network) and conventional Machine Learning algorithms (i.e., Gradient Boosting Regression, Random Forest Regression, Extremely Randomized Trees, and Adaptive Boosting Regression). The hyperparameters are deduced with grid search, and simulations demonstrate that the DL hybrid SAELSTM model is accurate compared with the other models as well as the persistence methods. The SAELSTM model obtains quality solar energy prediction intervals with high coverage probability and low interval errors. The review and new modelling results utilising an autoencoder deep learning method show that our approach is acceptable to predict solar radiation, and therefore is useful in solar energy monitoring systems to capture the stochastic variations in solar power generation due to cloud cover, aerosols, ozone changes, and other atmospheric attenuation factors.

This work presents a full statistical analysis and accurate prediction of low-visibility events due to fog, at the A-8 motor-road in Mondoñedo (Galicia, Spain). The present analysis covers two years of study, considering visibility time series and exogenous variables collected in the zone affected the most by extreme low-visibility events. This paper has then a two-fold objective: first, we carry out a statistical analysis for estimating the fittest probability distributions to the fog event duration, using the Maximum Likelihood method and an alternative method known as the L-moments method. This statistical study allows association of the low-visibility depth with the event duration, showing a clear relationship, which can be modeled with distributions for extremes such as Generalized Extreme Value and Generalized Pareto distributions. Second, we apply a neural network approach, trained by means of the ELM (Extreme Learning Machine) algorithm, to predict the occurrence of low-visibility events due to fog, from atmospheric predictive variables. This study provides a full characterization of fog events at this motor-road, in which orographic fog is predominant, causing important traffic problems during all year. We also show how the ELM approach is able to obtain highly accurate low-visibility events predictions, with a Pearson correlation coefficient of 0.8, within a half-hour time horizon, enough to initialize some protocols aiming at reducing the impact of these extreme events in the traffic of the A-8 motor road.

This work presents an analysis of low-visibility event persistence and prediction at Villanubla Airport (Valladolid, Spain), considering Runway Visual Range (RVR) time series in winter. The analysis covers long- and short-term persistence and prediction of the series, with different approaches. In the case of long-term analysis, a Detrended Fluctuation Analysis (DFA) approach is applied in order to estimate large-scale RVR time series similarities. The short-term persistence analysis of low-visibility events is evaluated by means of a Markov chain analysis of the binary time series associated with low-visibility events. We finally discuss an hourly short-term prediction of low-visibility events, using different approaches, some of them coming from the persistence analysis through Markov chain models, and others based on Machine Learning (ML) techniques. We show that a Mixture of Experts approach involving persistence-based methods and Machine Learning techniques provides the best results in this prediction problem.

Wind, being a clean and sustainable resource, boasts environmental advantages. However, its electricity generation faces challenges due to unpredictable variations in wind speed (WS). Accurate predictions of these variations would allow mixed grids to adjust their energy mix in real-time, ensuring overall stability. For this purpose, the paper develops a new hybrid gated additive tree ensemble (H-GATE) model for accurate multi-step-ahead WS predictions. First, the multivariate empirical mode decomposition (MEMD) simultaneously demarcates the multivariate data into intrinsic mode functions (IMFs) and residuals. These components represent underlying trends, periodicity, and stochastic patterns in WS variations. The IMF and residual components are pooled in respective sets, and an opposition-based whale optimization algorithm (OBWOA) is applied for dimensionality reduction. The selected features are used by GATE tuned with Bayesian optimization (BO) to forecast the individual IMF and residual components. The outputs are summed to obtain the final multi-step-ahead WS forecasts. The proposed H-GATE is benchmarked against standalone (S-GATE, S-CLSTM, and S-ABR) and hybrid (H-CLSTM and H-ABR) models. Based on all statistical metrics and diagnostic plots, H-GATE outperforms all comparative models at all forecast horizons, accumulating the lowest mean absolute percentage error (MAPE) of 6.13 - 9.93% (at $t_{L+1}$ ), 8.67 - 14.07% (at $t_{L+2}$ ), and 11.60 - 18.37% (at $t_{L+3}$ ) across all three sites. This novel multi-step-ahead WS forecasting strategy can significantly benefit grid operators by helping anticipate fluctuations in wind power generation. This can assist in optimizing energy dispatch schedules, reducing reliance on backup power sources, and enhancing overall grid stability. Practical implementation of this method can help meet the rising energy demands through renewable wind energy.

For bifacial solar photovoltaic panels, surface albedo plays a crucial role in estimating the radiant energy. Since land surfaces are heterogeneous, the actual albedo of the surface where the solar photovoltaic panel is placed can vary widely and its temporality and sparsity present a significant challenge for renewable energy engineers. This paper develops a new image super-resolution deep learning model based on convolutional neural network to generate high resolution spatial representations of surface albedo from coarse resolution remote sensing-based data. For selected Australian locations, we generated a higher resolution surface albedo using imagery from PROBA-V/SPOT Earth Observation satellites. We proposed a Deep Downscaling Spectral Model with Attention (DDSA) with the capability of processing 10-day albedo images captured at a relatively low (≈ 1 km) resolution. The proposed DDSA was then applied to downscale observed surface albedo and generate predicted albedo at 500 m, 333 m and 250 m resolutions. The proposed model was benchmarked with alternative deep learning, super-resolution approaches: Super-Resolution Convolution Neural Network (SRCNN), Enhanced Deep Super-Resolution network (EDSR), Efficient Sub-Pixel Convolutional Neural Network (ESPCN) and Residual Dense Network (RDN). The results showed that the proposed DDSA model outperformed all comparative models in terms of the mean square error (MSE) $\approx ~0.0041$ , signal-to-noise ratio (PSNR) $\approx ~39.471$ , Structural Similarity Index (SSIM) $\approx ~0.999$ vs. an MSE $\approx $ [0.0140-0.0387], PSNR $\approx $ [29.761-33.850], SSIM $\approx $ [0.9994-0.999]). We also cross-validated the downscaled images with satellite imagery and ground-based observations, which reaffirmed the proposed DDSA model’s ability to produce high resolution surface albedo maps and its potential applications for granular scale tracking and mapping solar energy where bifacial solar photovoltaic panels are placed.

Shape-from-Template (SfT) solves the registration and 3D reconstruction of a deformable 3D object, represented by the template, from a single image. Recently, methods based on deep learning have been able to solve SfT for the wide-baseline case in real-time, clearly surpassing classical methods. However, the main limitation of current methods is the need for fine tuning of the neural models to a specific geometry and appearance represented by the template texture map. We propose the first texture-generic deep learning SfT method which adapts to new texture maps at run-time, without the need for texture specific fine tuning. We achieve this by dividing the problem into a segmentation step and a registration and reconstruction step, both solved with deep learning. We include the template texture map as one of the neural inputs in both steps, training our models to adapt to different ones. We show that our method obtains comparable or better results to previous deep learning models, which are texture specific. It works in challenging imaging conditions, including complex deformations, occlusions, motion blur and poor textures. Our implementation runs in real-time, with a low-cost GPU and CPU.

In conventional networks, there was a tight bond between the control plane and the data plane. The introduction of Software-Defined Networking (SDN) separated these planes, and provided additional features and tools to solve some of the problems of traditional network (i.e., latency, consistency, efficiency). SDN is a flexible networking paradigm that boosts network control, programmability and automation. It proffers many benefits in many areas, including routing. More specifically, for efficiently organizing, managing and optimizing routing in networks, some intelligence is required, and SDN offers the possibility to easily integrate it. To this purpose, many researchers implemented different machine learning (ML) techniques to enhance SDN routing applications. This article surveys the use of ML techniques for routing optimization in SDN based on three core categories (i.e. supervised learning, unsupervised learning, and reinforcement learning). The main contributions of this survey are threefold. Firstly, it presents detailed summary tables related to these studies and their comparison is also discussed, including a summary of the best works according to our analysis. Secondly, it summarizes the main findings, best works and missing aspects, and it includes a quick guideline to choose the best ML technique in this field (based on available resources and objectives). Finally, it provides specific future research directions divided into six sections to conclude the survey. Our conclusion is that there is a huge trend to use intelligence-based routing in programmable networks, particularly during the last three years, but a lot of effort is still required to achieve comprehensive comparisons and synergies of approaches, meaningful evaluations based on open datasets and topologies, and detailed practical implementations (following recent standards) that could be adopted by industry. In summary, future efforts should be focused on reproducible research rather than on new isolated ideas. Otherwise, most of these applications will be barely implemented in practice.

In this paper we propose a novel path-loss model, the Weighted ABG (WABG), which suitably allows integrating or combine different available datasets, or previously proposed 5G propagation path-loss models from the state-of-the-art. Our proposal is therefore a new ABG-based approach which integrates other existing models, leading to the best possible approximation in least-square sense, considering different weighting policies. We evaluate the performance of the WABG in several 5G scenarios, and we carry out a complete comparison of the proposed method against several recently published ABG models, showing that the WABG obtains the best results in terms of model's accuracy.