Search

In trainable wireless communications systems, the use of deep learning for over-the-air training aims to address the discontinuity in backpropagation learning caused by the channel environment. The primary methods supporting this learning procedure either directly approximate the backpropagation gradients using techniques derived from reinforcement learning, or explicitly model the channel environment by training a generative channel model. In both cases, over-the-air training of transmitter and receiver requires a feedback channel to sound the channel environment and obtain measurements of the learning objective. The use of continuous feedback not only demands extra system resources but also makes the training process more susceptible to adversarial attacks. Conversely, opting for a feedback-free approach to train the models over the forward link, exclusively on the receiver side, could pose challenges to reliably end the training process without intermittent testing over the actual channel environment. In this article, we propose a novel method for the over-the-air training of wireless communication systems that does not require a feedback channel to train the transmitter and receiver. Random samples are transmitted through the channel environment to train a mixture density network to approximate the channel distribution on the receiver side of the network. The transmitter and receiver models are trained with the resulting channel model, and the transmitter can be deployed after training. We show that the block error rate measurements obtained with the simulated channel are suitable for monitoring as a stopping criterion during the training process. The resulting method is demonstrated to have equivalent performance to the end-to-end autoencoder training on small message sequences. [ABSTRACT FROM AUTHOR]

Atmospheric extreme events cause severe damage to human societies and ecosystems. The frequency and intensity of extremes and other associated events are continuously increasing due to climate change and global warming. The accurate prediction, characterization, and attribution of atmospheric extreme events is, therefore, a key research field in which many groups are currently working by applying different methodologies and computational tools. Machine learning and deep learning methods have arisen in the last years as powerful techniques to tackle many of the problems related to atmospheric extreme events. This paper reviews machine learning and deep learning approaches applied to the analysis, characterization, prediction, and attribution of the most important atmospheric extremes. A summary of the most used machine learning and deep learning techniques in this area, and a comprehensive critical review of literature related to ML in EEs, are provided. The critical literature review has been extended to extreme events related to rainfall and floods, heatwaves and extreme temperatures, droughts, severe weather events and fog, and low-visibility episodes. A case study focused on the analysis of extreme atmospheric temperature prediction with ML and DL techniques is also presented in the paper. Conclusions, perspectives, and outlooks on the field are finally drawn. [ABSTRACT FROM AUTHOR]

Wireless communications systems are traditionally designed by independently optimising signal processing functions based on a mathematical model. Deep learning-enabled communications have demonstrated end-to-end design by jointly optimising all components with respect to the communications environment. In the end-to-end approach, an assumed channel model is necessary to support training of the transmitter and receiver. This limitation has motivated recent work on over-the-air training to explore disjoint training for the transmitter and receiver without an assumed channel. These methods approximate the channel through a generative adversarial model or perform gradient approximation through reinforcement learning or similar methods. However, the generative adversarial model adds complexity by requiring an additional discriminator during training, while reinforcement learning methods require multiple forward passes to approximate the gradient and are sensitive to high variance in the error signal. A third, collaborative agent-based approach relies on an echo protocol to conduct training without channel assumptions. However, the coordination between agents increases the complexity and channel usage during training. In this article, we propose a simpler approach for disjoint training in which a local receiver model approximates the remote receiver model and is used to train the local transmitter. This simplified approach performs well under several different channel conditions, has equivalent performance to end-to-end training, and is well suited to adaptation to changing channel environments. [ABSTRACT FROM AUTHOR]

In this paper, we propose different explicable forecasting approaches, based on inductive and evolutionary decision rules, for extreme low-visibility events prediction. Explicability of the processes given by the rules is in the core of the proposal. We propose two different methodologies: first, we apply the PRIM algorithm and evolution to obtain induced and evolved rules, and subsequently these rules and boxes of rules are used as a possible simpler alternative to ML/DL classifiers. Second, we propose to integrate the information provided by the induced/evolved rules in the ML/DL techniques, as extra inputs, in order to enrich the complex ML/DL models. Experiments in the prediction of extreme low-visibility events in Northern Spain due to orographic fog show the good performance of the proposed approaches. [ABSTRACT FROM AUTHOR]

Adaptive modulation and coding schemes play a crucial role in ensuring robust data transfer in wireless communications, especially when faced with changes or interference in the transmission channel. These schemes involve the use of variable coding rates, which can be achieved normally through code puncturing or shortening, and have been adopted in 4G and 5G communication standards. In recent works, auto-encoders for wireless communications have demonstrated the ability to learn short code representations that achieve gains over conventional codes. Such a methodology is attractive as it can learn optimal representations under a variety of channel conditions. However, due to its structure the auto-encoder does not currently support multiple code rates with a single model. This article draws upon the discipline of multi-task learning, as it applies to deep learning and therefore devises a branching architecture for the auto-encoder and custom training algorithm in training transmitter and receiver for adaptive modulation and coding. In this article we aim to demonstrate improvements in Block Error Rate over conventional methods in the Additive White Gaussian Noise channel, and to analyse the performance of the model under Rayleigh fading channels without retraining the auto-encoder on the new channel. This article demonstrates a novel approach towards training auto-encoder models to jointly learn adaptive modulation and coding schemes framed as a multi-task learning problem. The research outcomes extend end-to-end learning approaches to the design of adaptive wireless communications systems. [Display omitted] • Proposes an end-to-end machine learning architecture enabling multiple code rates. • Custom training/multi-task learning produces competitive error-rate performance. • Proposed approach outperforms several traditional coding techniques for short codes. • Proposed approach is versatile in adapting to varying channels without retraining. • Demonstrates machine learning design methods for resilient wireless communications. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Exposure to solar ultraviolet (UV) radiation can cause malignant keratinocyte cancer and eye disease. Developing a user-friendly, portable, real-time solar UV alert system especially or wearable electronic mobile devices can help reduce the exposure to UV as a key measure for personal and occupational management of the UV risks. This research aims to design artificial intelligence-inspired early warning tool tailored for short-term forecasting of UV index (UVI) integrating satellite-derived and ground-based predictors for Australian hotspots receiving high UV exposures. The study further improves the trustworthiness of the newly designed tool using an explainable artificial intelligence approach. An enhanced joint hybrid explainable deep neural network model (called EJH-X-DNN) is constructed involving two phases of feature selection and hyperparameter tuning using Bayesian optimization. A comprehensive assessment of EJH-X- DNN is conducted with six other competing benchmarked models. The proposed model is explained locally and globally using robust model-agnostic explainable artificial intelligence frameworks such as Local Interpretable Model-Agnostic Explanations (LIME), Shapley additive explanations (SHAP), and permutation feature importance (PFI). The newly proposed model outperformed all benchmarked models for forecasting hourly horizons UVI , with correlation coefficients of 0.900, 0.960, 0.897, and 0.913, respectively, for Darwin, Alice Springs, Townsville, and Emerald hotspots. According to the combined local and global explainable model outcomes, the site-based results indicate that antecedent lagged memory of UVI and solar zenith angle are influential features. Predictions made by EJH-X-DNN model are strongly influenced by factors such as ozone effect, cloud conditions, and precipitation. With its superiority and skillful interpretation, the UVI prediction system reaffirms its benefits for providing real-time UV alerts to mitigate risks of skin and eye health complications, reducing healthcare costs and contributing to outdoor exposure policy. • Explainable artificial intelligence xAI for 1-hr ahead solar ultraviolet UV index prediction. • xAI model is optimized with the Bayesian feature selection algorithm. • xAI methods provide physical understandings of model prediction outcomes. • xAI model is significantly accurate for solar UV index predictions. • xAI model can help in sun exposure risk mitigation, skin and eye health protection. [ABSTRACT FROM AUTHOR]

Electricity demand prediction is crucial to ensure the operational safety and cost-efficient operation of the power system. Electricity demand has predominantly been predicted deterministically, while uncertainty analysis has been usually overlooked. To address this research gap, an integrated Neural Facebook Prophet (NFBP) model and Gaussian Kernel Density Estimation (KDE) model is proposed in this paper, as a way to obtain point and interval predictions of electricity demand, quantifying this way the uncertainty in the predictions. First, historical lagged data, created by utilizing the Partial Auto-correlation Function and Mutual Information Test, is applied to train a prediction model based on NFBP, Deep Learning (DL) as well as Statistical Models. Second, the model Prediction Errors (PE) are derived from the difference between actual and predicted values. A splitting strategy based on the mean and standard deviation of PE is proposed. Finally, electricity demand prediction intervals are obtained by applying Gaussian KDE on split PE. To verify the effectiveness of the proposed model, simulation studies are carried out for three prediction horizons on freely available datasets for the Bulimba sub-station in Southeast Queensland, Australia. Compared with DL models (Long-Short Term Memory Network and Deep Neural Network), the Root Mean Square Error of the NFBP model was reduced by 6.1% and 11.3% for 0.5-hr ahead, 22.7% and 26.3% for 6-hr ahead, and 31.8% and 29.9% for daily prediction. In addition, the Prediction Interval normalized Interval width is smaller in magnitude for the proposed NFBP-KDE model compared to other DL and Statistical models. [Display omitted] • A novel method is proposed for interval prediction of electricity demand. • Kernel density estimation with Gaussian function is applied to obtain interval prediction based on point prediction error. • Parameter of KDE distribution is optimized by minimizing Mean Integrated Square Error. • Deterministic and probabilistic metrics verify the superiority of the proposed prediction model. [ABSTRACT FROM AUTHOR]

Global Solar Radiation (GSR) prediction models are critical to improve the dispatch, control, and stabilization of solar renewable power, and to integrate the solar energy into the electrical grid system. GSR, especially on a short-term scale, can have important fluctuations, which may affect the total energy expected to be supplied to the grid. To overcome this issue, prediction models with a high forecasting performance are needed. In this paper a novel framework based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Deep Residual Network with Bidirectional long short-term memory, i.e., DRESNET model, is proposed for obtaining accurate multi-step ahead GSR predictions. To train the proposed ICEEMDAN-DRESNET hybrid model, minute-level daylight data from Energy Sector Management Assistance Program in Nepalgunj (mid-western Nepal) are used. The results demonstrate ICEEMDAN-DRESNET model is an excellent tool for short-term solar energy monitoring, yielding excellent predictions, in all metrics such as MAE 9.769 W/m2, MAPE 5.657 % , TIC 1.143, CPI 4.739, and TIC 0.023 for 5-min time-horizon predictions, improving the results from the benchmark models. As the forecasting time-horizon is increased, the ICEEMDAN-DRESNET model accuracy drops, with MAE 33.672 W/m2; MAPE 31.749 % for 1-hr, MAE 22.625 W/m2; MAPE 18.312 % (30-min) and MAE 14.897 W/m2; MAPE 10.358 % (15-min), also better than the benchmark models. The results confirm the competitive merit of ICEEMDAN and DRESNET integration to improve deep learning and the potential of proposed model for the monitoring of solar or other renewable (e.g., wind or solar) energies. [Display omitted] • A deep learning algorithm for short-term solar prediction is proposed. • The system considers deep residual and bidirectional long short-term memory network models. • Nepal (a solar-rich region) is selected to evaluate the deep learning algorithm. • Tests are carried out at multi-step ahead horizons of 5-min, 10-min, 30-min and 1-h. • Excellent performance of the proposed deep learning system is reported. [ABSTRACT FROM AUTHOR]

Digital technologies with predictive modelling capabilities are revolutionizing electricity markets, especially in demand-side management. Accurate electricity price prediction is essential in deregulated markets; however, developing effective models is challenging due to high-frequency fluctuations and price volatility. This study introduces a hybrid prediction system that addresses these challenges through a comprehensive data processing and modelling framework for half-hourly electricity price predictions. The preprocessing stage employs the Maximum Overlap Discrete Wavelet Transform (MoDWT) to enhance input quality by reducing overlap and revealing underlying price patterns. The prediction model integrates Convolutional Neural Networks with Random Vector Functional Link (CRVFL) in a deep learning hybrid approach. Bayesian Optimization fine-tunes the MoDWT-CRVFL model for optimal performance. Validation of the model is conducted using half-hourly electricity prices from New South Wales. The results highlight the efficacy of the MoDWT-CRVFL model, achieving high accuracy with superior Global Performance Indicator (G P I) values of approximately 1.61, 1.33, 1.85, 1.30, and 0.78 for Summer, Autumn, Winter, Spring, and Annual (Year 2022), respectively, outperforming alternative models. Similarly, the Kling–Gupta Efficiency (K G E) metrics for the proposed model consistently surpassed those of both decomposition-based and standalone models. For instance, the K G E value for MoDWT-CRVFL was approximately 0.972, significantly higher than values of approximately 0.958, 0.899, 0.963, 0.943, 0.930, 0.661, 0.708, 0.696, 0.739, and 0.738 for MoDWT-LSTM, MoDWT-DNN, MoDWT-XGB, MoDWT-RF, MoDWT-MLP, Bi-LSTM, LSTM, DNN, RF, XGB, and MLP, respectively. The methodologies proposed in this study optimize energy resource allocation, market prices, and network management, empowering market operators to make informed decisions for a resilient and efficient electricity market. • Designs deep hybrid Convolutional Neural-Random Vector Functional Link-Wavelet data decomposition model. • Performs half-hourly electricity price predictions over seasonal and annual periods. • Performs detailed appraisal of proposed deep hybrid decomposition model with visual and statistical predictive analytics. • Proposed deep hybrid decomposition model outperforms data decomposition and standalone predictive models. • Demonstrates a practical method for seasonal/annual electricity market insight analysis. [ABSTRACT FROM AUTHOR]

Implementing key engineering solutions to optimise the operation of energy industries requires daily electricity demand forecasting and including uncertainty, to promote markets insight analysis as part of their strategic planning, regulating and supplying electricity to consumers. This paper proposes hybrid artificial intelligence models combining convolutional neural networks (CNN) as a feature extraction algorithm with extreme learning machines (ELM) as a framework to predict electricity demand with confidence intervals generated by Kernel Density Estimation (KDE) approaches. In order to develop CELM-KDE model, time-lagged series of daily electricity demand with local climate variables based on the air temperature, atmospheric vapour pressure, evaporation, solar radiation, humidity and sea level pressures are used to train the proposed CELM-KDE hybrid model. In order to fully evaluate the newly developed model from a point-based, as well as a probabilistic prediction strategy, the observed and predicted electricity demand as well as the probability distribution of errors are analysed using KDE method that operates without prior data distribution assumptions. Based on observed and predicted electricity demand and the relevant probabilistic confidence intervals generated by the CELM-KDE model, the final results show that the proposed method attains significantly better probability interval predictions than traditionally-used point-based models. The proposed CELM-KDE model is demonstrated to be highly effective in providing a comprehensive coverage of predicted errors, as well as providing greater insights into the average bandwidth and detailed predicted electricity demand in the testing stage. The results also indicate that the proposed hybrid model is a reliable decision support tool to develop engineering solutions in area of energy modelling, monitoring and forecasting, which could potentially be useful to the industry policymakers. We show that the point-and probabilistic-based electricity demand predictive models can be employed as an effective tool to improve accuracy of forecasting and provision of insights for national electricity markets and key energy industry stakeholder application tools. [Display omitted] • A hybrid deep learning model for daily electricity demand prediction is proposed. • A Kernel Density Estimation is applied to derive probabilistic prediction intervals. • The algorithm quantifies uncertainties in point-based electricity demand predictions. • The proposed model outperforms deep learning models using statistical uncertainty indicators. [ABSTRACT FROM AUTHOR]

Wind energy is an environment friendly, low-carbon, and cost-effective renewable energy source. It is, however, difficult to integrate wind energy into a mixed energy grid due to its high volatility and intermittency. For wind energy conversion systems to be reliable and efficient, accurate wind speed (WS) forecasting is fundamental. This study cascades a convolutional neural network (CNN) with a bidirectional long short-term memory (BiLSTM) in order to obtain a model for hourly WS forecasting by utilizing several meteorological variables as model inputs to study their effects on predicted WS. For input selection, the mutation grey wolf optimizer (TMGWO) is used. For efficient optimization of CBiLSTM hyperparameters, a hybrid Bayesian Optimization and HyperBand (BOHB) algorithm is used. The combined usage of TMGWO, BOHB, and CBiLSTM leads to a three-phase hybrid model (i.e., 3P-CBiLSTM). The performance of 3P-CBiLSTM is benchmarked against the standalone and hybrid BiLSTMs, LSTMs, gradient boosting (GBRs), random forest (RFRs), and decision tree regressors (DTRs). The statistical analysis of forecasted WS reveals that the 3P-CBiLSTM is highly effective over the other benchmark forecasting methods. This objective model also registers the highest percentage of forecasted errors (≈ 53.4 – 81.8%) within the smallest error range ≤ | 0. 25 | ms − 1 amongst all tested study sites. Despite the remarkable results achieved, the CBiLSTM model cannot be generally understood, so the eXplainable Artificial Intelligence (xAI) technique was used for explaining local and global model outputs, based on Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). Both of the xAI methods determined that the antecedent WS is the most significant predictor of the short-term WS forecasting. Therefore, we aver that the proposed model can be employed to help wind farm operators in making quality decisions in maximizing wind power integration into the grid with reduced intermittency. • Explainable hybrid deep learning model proposed for hourly wind speed forecasting. • Grey wolf optimizer with a two-phase mutation designed for feature selection. • Bayesian Optimization and HyperBand used for efficient hyperparameter tuning. • Local Interpretable Model-Agnostic Explanations offer local model interpretation. • SHapley Additive exPlanations provide global model interpretation. [Display omitted] [ABSTRACT FROM AUTHOR]

In this paper the performance of different Machine Learning and Deep Learning approaches is evaluated in problems related to green mobility in big cities. Specifically, the forecasting of bike sharing demand in Madrid and Barcelona (Spain) is approached, for different prediction time-horizons, and also a problem of cable car demand forecasting in Madrid city. An important number of predictive variables are considered, which are grouped into four different sets (categorical/calendrical, persistence-based, meteorological and, as a novelty of the paper, information about analogue past instances), whose relevance is studied for all cases. A feature selection mechanism is also incorporated in order to improve the prediction accuracy of the proposed algorithms. A total of 12 different multivariate regression techniques are implemented, covering from Machine Learning methods to time-series Deep Learning approaches. Excellent results in all the prediction problems approached are reported. Finally, the consequences of obtaining accurate prediction in these three problem of green mobility in big cities are discussed. In addition, it is studied how the results could be exported to other similar cases in more general urban mobility studies. Novelties of the work include: (1) Addressing the forecast problem of passenger flow on a cable car using ML and DL multivariate techniques; (2) using the demand of analogous past instances as an additional feature to solve the demand prediction problems; and (3) the extraction of global conclusions about feature relevance when addressing a demand forecasting problem in green mobility. [ABSTRACT FROM AUTHOR]

Reliable forecast of electricity demand is crucial to stability, supply, and management of electricity grids. Short-term hourly and sub-hourly demand forecasts are difficult due to the stochastic nature of electricity demand. To improve the electricity demand forecasts, artificial neural networks are combined with attention-based bi-directional neural network as well as Error Correction methods, and Bayesian hyperparameter optimizations. As part of the hybrid VMD-CABLSTM-ANN-EC model, the intrinsic mode functions, representing distinct predictive features, are separated from electricity demand data using variational mode decomposition algorithm. For predicting each intrinsic mode function and respective error time series, convolutional neural networks-bi-directional long short-term memory algorithms are applied. In a second stage, error time series are split, followed by a model to predict the error series' intrinsic mode functions, and a final integration stage to predict the error. The results of the proposed VMD-CABLSTM-ANN-EC model are benchmarked against decomposition-based and standalone models at substations in Queensland, Australia. The proposed VMD-CABLSTM-ANN-EC model outperformed all benchmark models. By splitting the predictor and target variables, it will be shown that the variational model decomposition method improves error corrections by revealing key features of historical demand data. Using error correction method in short-term electricity demand modelling can provide greater confidence in the prediction of electricity demand. The models can be used by energy providers for market analysis and insight research, to manage power failure risk, and make financial decisions. [Display omitted] • Proposes double decomposition method for electricity demand error correction. • Decomposition method generate significant important predictive features. • Integrates convolutional neural, attention long short term memory and artificial neural networks. • Hybrid model adopts Bayesian optimization, outperforms benchmark models. • Our model is useful for energy market insights/electricity demand forecasting. [ABSTRACT FROM AUTHOR]

Prediction of electricity price is crucial for national electricity markets supporting sale prices, bidding strategies, electricity dispatch, control and market volatility management. High volatility, non-stationarity and multi-seasonality of electricity prices make it significantly challenging to estimate its future trend, especially over near real-time forecast horizons. An error compensation strategy that integrates Long Short-Term Memory (LSTM) network, Convolution Neural Network (CNN) and the Variational Mode Decomposition (VMD) algorithm is proposed to predict the half-hourly step electricity prices. A prediction model incorporating VMD and CLSTM is first used to obtain an initial prediction. To improve its predictive accuracy, a novel error compensation framework, which is built using the VMD and a Random Forest Regression (RF) algorithm, is also used. The proposed VMD-CLSTM-VMD-ERCRF model is evaluated using electricity prices from Queensland, Australia. The results reveal highly accurate predictive performance for all datasets considered, including the winter, autumn, spring, summer, and yearly predictions. As compared with a predictive model without error compensation (i.e., the VMD-CLSTM model), the proposed VMD-CLSTM-VMD-ERCRF model outperforms the benchmark models. For winter, autumn, spring, summer, and yearly predictions, the average Legates and McCabe Index is seen to increase by 15.97%, 16.31%, 20.23%, 10.24%, and 14.03%, respectively, relative to the benchmark models. According to the tests performed on independent datasets, the proposed VMD-CLSTM-VMD-ERCRF model can be a practical stratagem useful for short-term, half-hourly electricity price forecasting. Therefore the research outcomes demonstrate that the proposed error compensation framework is an effective decision-support tool for improving the predictive accuracy of electricity price. It could be of practical value to energy companies, energy policymakers and national electricity market operators to develop their insight analysis, electricity distribution and market optimization strategies. [Display omitted] • We propose an error compensation strategy to predict half-hourly electricity prices. • Two-step hybrid deep learning model built with Neural Network and Variation Mode Decomposition. • Variation Mode Decomposition captures fluctuating characteristics of predictors. • Bayesian hyperparameter optimization leads to accurate electricity price forecasts. • The proposed model provides in-depth analysis of national electricity markets. [ABSTRACT FROM AUTHOR]

Predicting electricity demand (G) is crucial for electricity grid operation and management. In order to make reliable predictions, model inputs must be analyzed for predictive features before they can be incorporated into a forecast model. In this study, a hybrid multi-algorithm framework is developed by incorporating Artificial Neural Networks (ANN), Encoder-Decoder Based Long Short-Term Memory (EDLSTM) and Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICMD). Following the partitioning of data, the G time-series are decomposed into multiple time-series using the ICEEMDAN algorithm, with partial autocorrelation applied to training sets to determine lagged features. We combine lagged inputs into a predictive framework where G components with the highest frequency are predicted with an ANN model, while remaining components are predicted with an EDLSTM model. To generate the results, all IMF components' predictions are merged using ICMD-ANN-EDLSTM hybrid models. A comparison is made between this objective model and standalone models (ANN, RFR, LSTM), hybrid models (CLSTM), and three decomposition-based hybrid models. Based on the results, the Relative Mean Absolute Error at Duffield Road substation was ≈ 2. 82 % , ≈ 4. 15 % , ≈ 3. 17 % , ≈ 6. 41 % , ≈ 6. 60 % , ≈ 6. 49 % , and ≈ 6. 602 % , compared to ICMD-RFR-LSTM, ICMD-RFR-CLSTM, LSTM, CLSTM, RFR, and ANN. According to statistical score metrics, the hybrid ICMD-ANN-EDLSTM model performed better than other benchmark models. Further, the results show that the hybrid ICMD-ANN-EDLSTM model can not only detect seasonality in G data, but also predict and analyze electricity market demand to add valuable insight to market analysis. [Display omitted] • Predicting electricity demand is challenging due to non-linear and non-stationary features. • A hybrid deep-leaning based multi-method approach is proposed in this paper. • Data decomposition-based encoder–decoder neural networks algorithm is proposed. • The algorithm adopts a neural network for high frequency and a deep LSTM model for low frequency input data. [ABSTRACT FROM AUTHOR]

Predicting electricity demand data is considered an essential task in decisions taking, and establishing new infrastructure in the power generation network. To deliver a high-quality electricity demand prediction, this paper proposes a hybrid combination technique, based on a deep learning model of Convolutional Neural Networks and Echo State Networks, named as CESN. Daily electricity demand data from four sites (Roderick, Rocklea, Hemmant and Carpendale), located in Southeast Queensland, Australia, have been used to develop the proposed hybrid prediction model. The study also analyzes five other machine learning-based models (support vector regression, multilayer perceptron, extreme gradient boosting, deep neural network, and Light Gradient Boosting) to compare and evaluate the outcomes of the proposed deep learning approach. The results obtained in the experimental study showed that the proposed hybrid deep learning model is able to obtain the highest performance compared to other existing models developed for daily electricity demand data forecasting. Based on the statistical approaches utilized in this study, the proposed hybrid approach presents the highest prediction accuracy among the compared models. The obtained results showed that the proposed hybrid deep learning algorithm is an excellent and accurate electricity demand forecasting method, which outperformed the state of the art algorithms that are currently used in this problem. [Display omitted] • A Hybrid deep learning model is proposed for daily electricity demand prediction. • Convolutional Neural Networks and Echo State Networks are integrated into a single forecasting algorithm. • The proposed deep learning-based approach is excellent in electricity demand prediction. • The proposed algorithm has practical use in inter-daily electricity demand prediction. [ABSTRACT FROM AUTHOR]

Global solar radiation (GSR) prediction plays an essential role in planning, controlling and monitoring solar power systems. However, its stochastic behaviour is a significant challenge in achieving satisfactory prediction results. This study aims to design an innovative hybrid prediction model that integrates a feature selection mechanism using a S lime-Mould algorithm, a C onvolutional-Neural-Network (CNN), a L ong–Short-Term-Memory Neural Network (LSTM) and a final CNN with Multilayer-Perceptron output (SCLC algorithm hereafter). The proposed model was applied to six solar farms in Queensland (Australia) at daily temporal horizons in six different time steps. The comprehensive benchmarking of the obtained results with those from two Deep-Learning (CNN-LSTM, Deep-Neural-Network) and three Machine-Learning (Artificial-Neural-Network, Random-Forest, Self-Adaptive Differential-Evolutionary Extreme-Learning-Machines) models highlighted a higher performance of the proposed prediction model in all the six selected solar farms. From the results obtained, this work establishes that the designed SCLC algorithm could have a practical utility for applications in renewable and sustainable energy resource management. [Display omitted] • A novel deep learning model for Global Solar Radiation prediction is proposed. • The model integrates deep networks with Slime Mould Algorithm for feature selection. • Meteorological data at solar farms in Australia are considered as variables. • Error analysis and statistical metrics show the model's practicality. [ABSTRACT FROM AUTHOR]

This paper presents a new hybrid approach for Global Solar Radiation (GSR) prediction problems, based on deep learning approaches. Predictive models are useful ploys in solar energy industries to optimize the performance of photovoltaic power systems. Specifically, in this work we develop a new 4-phase hybrid CXGBRFR framework, which includes a deep learning Convolutional Neural Network, an Extreme Gradient Boosting with Random Forest Regression, and a Harris Hawks Optimization for initial feature selection. The proposed system has been tested in a problem of daily GSR prediction at six solar farms in Australia. Data from three global climate models (GCM) (CSIRO-BOM ACCESS1-0, MOHC Hadley-GEM2-CC and MRI MRI-CGCM3) have been considered as predictive (input) variables for the proposed approach. The variables from these GCMs contain enough information to obtain an accurate prediction of the GSR at each solar farm. The performance of the proposed approach is compared against different deep and shallows learning approaches: Deep Belief Network, Deep Neural Network, Artificial Neural Network, Extreme Learning Machine and Multivariate Auto-Regressive Spline models. We show that the proposed approach exhibits an excellent performance in GSR prediction, against all alternative approaches in all solar farms considered. [Display omitted] • We develop hybrid deep learning model to predict solar radiation • We optimize the algorithm with Harris Hawks, gradient boosting and random forest • We adopt global climate model and observed predictors as learning model inputs • We build an expert system with relevant knowledge in context of solar application • Our methods benefit solar photovoltaic power monitoring in solar engineering problems. [ABSTRACT FROM AUTHOR]

This study proposes a new hybrid deep learning (DL) model, the called CSVR, for Global Solar Radiation (GSR) predictions by integrating Convolutional Neural Network (CNN) with Support Vector Regression (SVR) approach. First, the CNN algorithm is used to extract local patterns as well as common features that occur recurrently in time series data at different intervals. Then, the SVR is subsequently adopted to replace the fully connected CNN layers to predict the daily GSR time series data at six solar farms in Queensland, Australia. To develop the hybrid CSVR model, we adopt the most pertinent meteorological variables from Global Climate Model and Scientific Information for Landowners database. From a pool of Global Climate Models variables and ground-based observations, the optimal features are selected through a metaheuristic Feature Selection algorithm, an Atom Search Optimization method. The hyperparameters of the proposed CSVR are optimized by mean of the HyperOpt method, and the overall performance of the objective algorithm is benchmarked against eight alternative DL methods, and some of the other Machine Learning approaches (LSTM, DBN, RBF, BRF, MARS, WKNNR, GPML and M5TREE) methods. The results obtained shows that the proposed CSVR model can offer several predictive advantages over the alternative DL models, as well as the conventional ML models. Specifically, we note that the CSVR model recorded a root mean square error/mean absolute error ranging between ≈ 2.172–3.305 MJ m2/1.624–2.370 MJ m2 over the six tested solar farms compared to ≈ 2.514–3.879 MJ m2/1.939–2.866 MJ m2 from alternative ML and DL algorithms. Consistent with this predicted error, the correlation between the measured and the predicted GSR , including the Willmott's, Nash-Sutcliffe's coefficient and Legates & McCabe's Index was relatively higher for the proposed CSVR model compared to other DL and Machine Learning methods for all of the study sites. Accordingly, this study advocates the merits of CSVR model to provide a viable alternative to accurately predict GSR for renewable energy exploitation, energy demand or other forecasting-based applications. [Display omitted] • This paper presents a hybrid CSVR algorithm for global solar radiation prediction. • The proposed approach combines Convolutional Neural Network with a Support Vector Machine. • An Atom Search-based feature selection is applied to improve the performance of the system. • Experiments are carried out in data at six solar energy farms in Queensland, Australia. • The results show the efficacy of deep learning CSVR for solar energy prediction problems. [ABSTRACT FROM AUTHOR]