Search

The Paris Agreement, a landmark international treaty signed in 2016 to limit global warming to 2 ° C , has urged researchers to explore various strategies for achieving its ambitious goals. While Renewable Energy (RE) innovation holds promise, it alone may not be sufficient as critical deadlines approach. This field of research presents numerous challenges, foremost among them being the costliness of materials involved. However, emerging advancements in Machine Learning (ML) technologies provide a glimmer of hope; these sophisticated algorithms can accurately predict the output of energy systems without relying on physical resources and instead leverage available data from diverse energy platforms that have emerged over recent decades. The primary objective of this paper is to comprehensively explore various ML techniques and algorithms in the context of Renewable Energy Systems (RES). The investigation will address several vital inquiries, including identifying and evaluating existing RE technologies, assessing their potential for further advancement, and thoroughly analyzing the challenges and limitations associated with their deployment and testing. Furthermore, this research examines how ML can effectively overcome these obstacles by enhancing RES performance. By identifying future research opportunities and outlining potential directions for improvement, this work seeks to contribute to developing environmentally sustainable energy systems. • Discussed the advantages and limitations of current renewable energy systems. • Reviewed the different machine learning algorithms and their applications in renewable energy systems. • Highlighted existing renewable energy datasets and feature selection methods. • Discussed the use of machine learning and renewable energy in the hydrogen value chain. • Provided future directions for the application of machine learning in the renewable energy sector. [ABSTRACT FROM AUTHOR]

With the increasing complexity of power systems and the proliferation of renewable energy sources, the task of calculating carbon emissions has become increasingly challenging. To address these challenges, we developed a new method for predicting carbon emission factors. Bayesian optimization technique graphical convolutional networks with long- and short-term network (BO-TGNN) is used to predict the carbon emissions of the power system. The method aims to quickly predict the day-ahead carbon emissions of power system nodes with enhanced feature extraction and optimized network training hyperparameters. The effectiveness of the proposed method is demonstrated through simulation tests on three different power systems using four deep learning algorithms. The method provides a tailored solution to the evolving needs of carbon reduction efforts and is a significant step forward in addressing the complexity of carbon emission calculations for modern power systems. [ABSTRACT FROM AUTHOR]

There are global efforts to deploy Electric Vehicles (EVs) because of the role they promise to play in energy transition. These efforts underscore the e-mobility paradigm, representing an interplay between renewable energy resources, smart technologies, and networked transportation. However, there are concerns that these initiatives could burden the electricity grid due to increased demand. Hence, the need for accurate short-term load forecasting is pivotal for the efficient planning, operation, and control of the grid and associated power systems. This study presents robust models for forecasting half-hourly and hourly loads in the UK's power system. The work leverages machine learning techniques such as Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Gaussian Process Regression (GPR) to develop robust prediction models using the net imports dataset from 2010 to 2020. The models were evaluated based on metrics like Root Mean Square Error (RMSE), Mean Absolute Prediction Error (MAPE), Mean Absolute Deviation (MAD), and the Correlation of Determination (R2). For half-hourly forecasts, SVR performed best with an R-value of 99.85%, followed closely by GPR and ANN. But, for hourly forecasts, ANN led with an R-value of 99.71%. The findings affirm the reliability and precision of machine learning methods in short-term load forecasting, particularly highlighting the superior accuracy of the SVR model for half-hourly forecasts and the ANN model for hourly forecasts. [ABSTRACT FROM AUTHOR]

Highlights: What are the main findings? The use of machine learning algorithms in energy management services can lead to a significant increase in the implementation rate of energy performance, power quality and renewable energy sources projects; Integrating machine learning algorithms in the process of assessing the energy saving potential can accelerate the deployment of energy performance contracting; What is the implication of the main finding? Digitization of the energy services sector could support end-users in achieving their targets regarding the transition towards environmental sustainability Policy makers could also use the proposed methodology to evaluate the global energy performance of the relevant energy sectors, thus increasing the performance of the available financing mechanisms. Current targets, which have been set at both the European and the international level, for reducing environmental impacts and moving towards a sustainable circular economy make energy efficiency and digitization key elements of all sectors of human activity. The authors proposed, developed, and tested a complex methodology for real-time statistical analysis and forecasting of the following main elements contributing to the energy and economic performance of an end user: energy performance indicators, power quality indices, and the potential to implement actions to improve these indicators, in an economically sustainable manner, for the end user. The proposed methodology is based on machine learning algorithms, and it has been tested on six different energy boundaries. It was thus proven that, by implementing an advanced energy management system (AEMS), end users can achieve significant energy savings and thus contribute to the transition towards environmental sustainability. [ABSTRACT FROM AUTHOR]

Demand for energy is increasing as the world's population grows, fossil fuels deplete on a daily basis, and climate conditions change. Renewable energy is more important than ever. Solar energy is the most accessible and cost-effective renewable energy source available today. Photovoltaic (PV) cells are the most promising way to convert solar energy into electricity. Wind speed, ambient temperature, incident radiation rate, and dust deposition are some of the internal and external variables that affect photovoltaic panel performance. Unwanted heat from the sun's rays raises panel temperatures, reduces the amount of energy that solar cells can produce, and lowers conversion efficiency. Solar panels must be adequately cooled. The current research is focused on improving photovoltaic panel performance. The experimental system includes a fully automated photovoltaic panel, a microcontroller (NodeMCU8266), a DC pump, voltage and temperature sensors. The experiment was carried out with and without cooling of the PV panel. The findings suggest that keeping PV panel temperatures close to ambient temperatures improves performance. The Wi-Fi module collects real-time data on PV panel temperature, irradiation, ambient temperature, water temperature, and PV panel power output. The collected data was analyzed using machine learning. The PV panel's performance was analyzed using the linear regression method. [ABSTRACT FROM AUTHOR]

For the past few years, the addition of renewable energy sources has been on the rise, but the unregulated addition of these sources can cause severe harm to the grid. Therefore, it is necessary to have a predefined limit for a grid, beyond which no further addition of renewables should be allowed without reinforcement. That limit is called the hosting capacity (HC), which is addressed in the literature by search‐based methods with heavy computational burdens. This manuscript first presents a framework to find the HC for a grid. The same framework is then applied to 503 different simulated but realistic LV distribution feeders in Finland to find their HCs and the most effective network parameters in defining a network specific HC. Next, different machine learning models, that is, Decision Tree (DT), Random Forest (RF), Linear Regression (LR), K nearest neighbours (KNN), Logistic Regression, and Support Vector Machine (SVM) are implemented on the generated data. For the classification case, the accuracy values for logistic regression, KNN, and SVM were 0.89, 0.84, and 0.81, respectively. The findings demonstrate that the developed machine learning based technique will enable distribution network operators in finding the HC without applying any deterministic or probabilistic approaches. [ABSTRACT FROM AUTHOR]

The integration of photovoltaic (PV) systems into the global energy landscape has been boosted in recent years, driven by environmental concerns and research into renewable energy sources. The accurate prediction of temperature and solar irradiance is essential for optimizing the performance and grid integration of PV systems. Machine learning (ML) has become an effective tool for improving the accuracy of these predictions. This comprehensive review explores the pioneer techniques and methodologies employed in the field of ML-based forecasting of temperature and solar irradiance for PV systems. This article presents a comparative study between various algorithms and techniques commonly used for temperature and solar radiation forecasting. These include regression models such as decision trees, random forest, XGBoost, and support vector machines (SVM). The beginning of this article highlights the importance of accurate weather forecasts for the operation of PV systems and the challenges associated with traditional meteorological models. Next, fundamental concepts of machine learning are explored, highlighting the benefits of improved accuracy in estimating the PV power generation for grid integration. [ABSTRACT FROM AUTHOR]

Rare earth elements (REEs including Sc, Y) are critical minerals for developing sustainable energy sources. The gradual transition adopted in developed and developing countries to meet energy targets has propelled the need for REEs in addition to critical metals (CMs). The rise in demand which has propelled REEs into the spotlight is driven by the crucial role these REEs play in technologies that aim to reduce our carbon footprint in the atmosphere. Regarding decarbonized technologies in the energy sector, REEs are widely applied for use in NdFeB permanent magnets, which are crucial parts of wind turbines and motors of electric vehicles. The underlying motive behind exploring the energy and carbon footprint caused by REEs production is to provide a more complete context and rationale for REEs usage that is more holistic. Incorporating artificial intelligence (AI)/machine learning (ML) models with empirical approaches aids in flowsheet validation, and thus, it presents a vivid holistic picture. The energy needed for REEs production is linked with the source of REEs. The availability of REEs varies widely across the globe. REEs are either produced from ores with associated gangue or impurities. In contrast, in other scenarios, REEs can be produced from the waste of other mineral deposits or discarded REEs-based products. These variations in the source of feed materials, and the associated grade and mineral associations, vary the process flowsheet for each type of production. Thus, the ability to figure out energy outcomes from various scenarios, and a knowledge of energy requirements for the production and commercialization of multiple opportunities, is needed. However, this type of information concerning REEs production is not readily available as a standardized value for a particular material, according to its source and processing method. The related approach for deciding the energy and carbon footprint for different processing approaches and sources relies on the following three sub-processes: mining, beneficiation, and refining. Some sources require incorporating all three, whereas others need two or one, depending on resource availability. The available resources in the literature tend to focus on the life cycle assessment of REEs, using various sources, and they focus little on the energy footprint. For example, a few researchers have focused on the cumulative energy needed for REE production without making assessments of viability. Thus, this article aims to discuss the energy needs for each process, rather than on a specific flowsheet, to define process viability more effectively regarding energy need, availability, and the related carbon footprint. [ABSTRACT FROM AUTHOR]

In recent years, advancements in rooftop solar panel technology have sparked a revolution in the electricity markets. This has given rise to a new concept of energy exchange—the ability for consumers and producers to trade localized energy. This concept has been made possible by the emergence of blockchain technology, which has gained significant traction in the energy markets. Its unique ability to facilitate peer-to-peer (P2P) energy transactions has made it a promising solution for the trilemma of scalability, security, and decentralization. However, while blockchain technology has shown great potential, it is still in its early stages of development and has yet to reach its full potential. To fully understand the potential of blockchain technology in P2P energy trading, it is important to explore the trilemma in depth. This study proposes a blockchain-based scalability solution with a focus on P2P energy trading. This strategy is supported by empirical modeling, utilizing data gathered from a trial case study. The results of this study demonstrate that the suggested technique outperforms base-layer models in terms of scalability while still maintaining the essential elements of security and decentralization. This proposed solution not only has the potential to revolutionize the energy markets but also has broader implications. By providing a more secure and decentralized platform for P2P energy trading, it has the potential to address issues of energy distribution inequality and promote the adoption of renewable energy. With blockchain technology, individuals and communities have the opportunity to take control of their energy usage and production, reducing their reliance on traditional centralized energy systems. This not only has the potential to lower energy costs for consumers but also contributes to the overall goal of reducing carbon emissions and mitigating the effects of climate change. The combination of rooftop solar panel technology and blockchain applications has the potential to create a significant shift toward decentralized and sustainable energy systems. This will not only benefit individuals and communities but also have a positive impact on the environment and the global energy market. However, for this transition to occur, it is crucial that governments and energy companies continue to support and invest in these advancements. [ABSTRACT FROM AUTHOR]

The increasing penetration of renewable energy poses intractable uncertainties in cascade hydropower systems, such that excessively conservative operations and unnecessary curtailment of clean energies can be incurred. To address these challenges, a quantum neural network (QNN)-based coordinated predictive control approach is proposed. It manipulates coordinated dispatch of multiple clean energy sources, including hydro, wind, and solar power, leverages QNN to conquer intricate multi-uncertainty and learn intraday predictive control patterns, by taking renewable power, load, demand response (DR), and optimal unit commitment as observations. This enables us to exploit the stability and exponential memory capacity of QNN to extrapolate diversified dispatch policies in a reliable manner, which can be hard to reach for traditional learning algorithms. A closed-loop warm start framework is finally presented to enhance the dispatch quality, where the decisions by QNN are fed to initialize the optimizer, and the optimizer returns optimal solutions to quickly evolve the QNN. A real-world case in the ZD sub-grid of the Sichuan power grid in China demonstrates that the proposed method hits a favorable balance between operational cost, accuracy, and efficiency. It realizes second-level elapsed time for intraday predictive control. [ABSTRACT FROM AUTHOR]

The energy sector is currently undergoing a significant shift, driven by the growing integration of renewable energy sources and the decentralization of electricity markets, which are now extending into local communities. This transformation highlights the pivotal role of prosumers within these markets, and as a result, the concept of Renewable Energy Communities is gaining traction, empowering their members to curtail reliance on non-renewable energy sources by facilitating local energy generation, storage, and exchange. Also in a community, management efficiency depends on being able to predict future consumption to make decisions regarding the purchase, sale and storage of electricity, which is why forecasting the consumption of community members is extremely important. This study presents an innovative approach to manage community energy balance, relying on Machine Learning (ML) techniques, namely eXtreme Gradient Boosting (XGBoost), to forecast electricity consumption. Subsequently, a decision algorithm is employed for energy trading with the public grid, based on solar production and energy consumption forecasts, storage levels and market electricity prices. The outcomes of the simulated model demonstrate the efficacy of incorporating these techniques, since the system showcases the potential to reduce both the community electricity expenses and its dependence on energy from the centralized distribution grid. ML-based techniques allowed better results specially for bi-hourly tariffs and high storage capacity scenarios with community bill reductions of 9.8%, 2.8% and 5.4% for high, low, and average photovoltaic (PV) generation levels, respectively. [ABSTRACT FROM AUTHOR]

The ability to forecast electricity generation for a small wind turbine is important both on a larger scale where there are many such turbines (because it creates problems for networks managed by distribution system operators) and for prosumers to allow current energy consumption planning. It is also important for owners of small energy systems in order to optimize the use of various energy sources and facilitate energy storage. The research presented here addresses an original, rarely predicted 48 h forecasting horizon for small wind turbines. This topic has been rather underrepresented in research, especially in comparison with forecasts for large wind farms. Wind speed forecasts with a 48 h horizon are also rarely used as input data. We have analyzed the available data to identify potentially useful explanatory variables for forecasting models. Eight sets with increasing data amounts were created to analyze the influence of the types and amounts of data on forecast quality. Hybrid, ensemble and single methods are used for predictions, including machine learning (ML) solutions like long short-term memory (LSTM), multi-layer perceptron (MLP), support vector regression (SVR) and K-nearest neighbours regression (KNNR). Original hybrid methods, developed for research of specific implementations and ensemble methods based on hybrid methods' decreased errors of energy generation forecasts for small wind turbines in comparison with single methods. The "artificial neural network (ANN) type MLP as an integrator of ensemble based on hybrid methods" ensemble forecasting method incorporates an original combination of predictors. Predictions by this method have the lowest mean absolute error (MAE). In addition, this paper presents an original ensemble forecasting method, called "averaging ensemble based on hybrid methods without extreme forecasts". Predictions by this method have the lowest root mean square error (RMSE) error among all tested methods. LSTM, a deep neural network, is the best single method, MLP is the second best one, while SVR, KNNR and, especially, linear regression (LR) perform less well. We prove that lagged values of forecasted time series slightly increase the accuracy of predictions. The same applies to seasonal and daily variability markers. Our studies have also demonstrated that using the full set of available input data and the best proposed hybrid and ensemble methods yield the lowest error. The proposed hybrid and ensemble methods are also applicable to other short-time generation forecasting in renewable energy sources (RES), e.g., in photovoltaic (PV) systems or hydropower. [ABSTRACT FROM AUTHOR]

Abstract Sedentary, inadequate sleep and exercise can affect human health. Artificial intelligence (AI) and Internet of Things (IoT) create the Artificial Intelligence of Things (AIoT), providing the possibility to solve these problems. This paper presents a novel approach to monitor various human behaviors for AIoT‐based health management using triboelectric nanogenerator (TENG) sensors. The insole with solely one TENG sensor, creating a most simplified system that utilizes machine learning (ML) for personalized motion monitoring, encompassing identity recognition and gait classification. A cushion with 12 TENG sensors achieves real‐time identity and sitting posture recognition with accuracy rates of 98.86% and 98.40%, respectively, effectively correcting sedentary behavior. Similarly, a smart pillow, equipped with 15 sensory channels, detects head movements during sleep, identifying 8 sleep patterns with 96.25% accuracy. Ultimately, constructing an AIoT‐based health management system to analyze these data, displaying health status through human‐machine interfaces, offers the potential to help individuals maintain good health.

In this paper, we applied the artificial intelligence technique (SVM Classifier) to compare the performance of two different technologies of PV modules (class to class and backsheet to glass) after five (05) months of operation in Algeria under the same weather conditions (moderate and humid climate) . We have a database for the outdoor monitoring of these two PV modules, consisting of data (Isc, Voc, Pmax, Imp, Vmp, Tm, Tamb, G, WD, WS, Date, Time) which are variables data, where the SVM creates the groups or class according to the conditions that we entered, after which it produces heatmaps that help us in reading the results and making the decision easily, unlike the classic methods which are very difficult. This method is applicable for comparison between several solar panels or several photovoltaic PV plants. It is enough just to give the database.

Numerous research works establish the high efficacy of Machine Learning (ML) based power system fault diagnosis over conventional analytical methods. The ongoing integration of renewable energy sources (RES) into the existing transmission networks alters the system topology, potentially resulting in significant changes in fault signatures depending on the size of the newly added RES. However, there is a notable absence of studies in the literature analyzing the impact of new RES integration on the fault diagnosis performances of ML models. Therefore, to assess the fault classification and localization performance of potential ML models, this paper proposes to analyze two practical scenarios arising from new RES integrations: 1) when no-fault data is available for the changed system and 2) when the changed system data is available over time. The proposed performance and adaptability testing of potential ML models has been conducted by optimally integrating different sizes of RES into ‘IEEE 9-Bus System’. The integrated solar-based RES has been modeled incorporating standard temperature and irradiance variations. A diverse fault database was generated considering actual field variations of fault attributes. Impact analysis revealed significant degradation in the fault diagnosis performances of all tested models post RES integrations. The adaptability testing was performed by extensive analysis of the learning trends of ML models with gradual data availability. The proposed Bayesian ridge regression has emerged as the fastest learning model for locating transmission line faults, whereas XGBoost, Extra Tree, and Random Forest classifiers gave comparable results for fault classification.

There is a rapid increase in the utilization of renewable sources such as solar and wind to provide power and electricity. The reason for this trend is to reduce costs and preserve the environment. However, the challenge is to efficiently use and store the energy from these sources. One approach is to optimize the decision when to charge or discharge a battery. The objective is to generate the greatest monetary gain. More charge/discharge cycles will reduce the life of a battery, thereby increasing the cost. A strategy to reduce the number of charge cycles while maintaining the effectiveness of electricity distribution from battery storage will improve battery life. With the inevitable proliferation of electric vehicles (EVs) in the market, strategies specific to electric vehicle battery profitability will be explored. An additional concern which threatens the financial feasibility of battery energy storage systems (BESSs) is the requirement of secure operation. There is currently little research study on strategies to detect cyberattacks on such systems. In this paper, we have presented a novel taxonomy for battery optimization, survey representative BESS utilization strategies, and classify these schemes within the taxonomy. Within our classification, we outline the battery optimization methods that have been discussed, analyze their ability to address issues that arise when implementing a BESS, and describe alternative research that could be explored. Future research could refer to this information to create unique battery optimization schemes to provide more efficiency and optimal revenue for a BESS when compared to current strategies.

This editorial discusses the need for clean and reliable energy sources in response to increasing electricity consumption and environmental concerns. The integration of wind and solar power into the existing power grid presents challenges due to their variability and dependence on weather conditions. The research presented in this collection focuses on key technologies for planning and operating hybrid energy systems, which combine wind and solar power with controllable sources like hydropower, thermal power, and battery storage. The articles cover topics such as wind turbine control, market decision-making methods, optimization models, and short-term prediction models. These studies propose innovative approaches and models to improve the reliability, efficiency, and sustainability of hybrid energy systems. [Extracted from the article]

Power generation comprises high environmental and ecological impacts. The global power industry is under pressure to develop more efficient ways to operate and reduce the impacts of inherent process variability. With the rapid development of technologies within the energy sector, large volumes of data are available due to in-time operational measurements. With increased computer processing capabilities, machine learning is applied to explore these in-time operational measurements for improved process understanding. This research paper investigates machine learning algorithms for energy efficiency improvement at coal-fired thermal power plants by conducting a systematic literature review. This research is essential since it provides guidelines for applying machine learning towards sustainable energy supply and improved decision-making. Subsequently, efficient processes result in the reduction of fuel usage, which results in lower emission levels for equivalent power generation capacity. Furthermore, this study contributes towards future research by providing valuable insights from academic and industry-related studies.

The rapid depletion of fossil fuel resources and vast demands for electricity has prompted scientists to think of increased reliance on renewable energy sources and, therefore, next-generation energy storage devices (including supercapacitors). A supercapacitor's performance depends on its intrinsic features such as electrode materials, type of electrolytes, etc. This paper uses machine learning algorithms to find a correlation between these inherent features and supercapacitor performances in terms of cyclic stability. A considerable amount of data on supercapacitor cyclic stability and other relevant features from 400+ published papers are collected, and different ML algorithms have been used to build models. Attribute prioritization and Principal Component Analysis (PCA) are performed to remove redundant features, reduce the computation time, and increase the interpretability of the dataset. Key material insights based on this study are (i) Ni and Co-based materials are among the most studied materials, (ii) electrodeposited Ni(OH) 2 on Ni foam is a combination that is industrially relevant, exhibits high initial specific capacitance but has poor capacity retention, and (iii) 3 dimensional nanoparticles are preferable to lower dimensions as electrode materials for cyclability. These insights, among others given here, offer ways forward to pursue new materials combinations for achieving high cyclic stability. [Display omitted] • Machine learning (ML) is used to predict highly cyclable supercapacitor materials. • Data-driven insights are offered to guide material design for supercapacitors. • The models are evaluated based on prediction accuracy and build-up time. • Presented ML-models are computationally lite yet practically significant. [ABSTRACT FROM AUTHOR]

Energy has a strategic role in the economic and social development of countries. In the last few decades, energy demand has been increasing exponentially across the world, and predicting energy demand has become one of the main concerns in many countries. The residential and commercial sectors constitute about 34.7% of global energy consumption. Anticipating energy demand in these sectors will help governments to supply energy sources and to develop their sustainable energy plans such as using renewable and non-renewable energy potentials for the development of a secure and environmentally friendly energy system. Modeling energy consumption in the residential and commercial sectors enables identification of the influential economic, social, and technological factors, resulting in a secure level of energy supply. In this paper, we forecast residential and commercial energy demands in Iran using three different machine learning methods, including multiple linear regression, logarithmic multiple linear regression methods, and nonlinear autoregressive with exogenous input artificial neural networks. These models are developed based on several factors, including the share of renewable energy sources in final energy consumption, gross domestic production, population, natural gas price, and the electricity price. According to the results of the three machine learning methods applied in our study, by 2040, Iranian residential and commercial energy consumption will be 76.97, 96.42 and 128.09 Mtoe, respectively. Results show that Iran must develop and implement new policies to increase the share of renewable energy supply in final energy consumption. [ABSTRACT FROM AUTHOR]

In today's world, renewable energy sources are increasingly integrated with nonrenewable energy sources into electric grids and pose new challenges because of their intermittent and variable nature. Energy prediction using soft-computing techniques plays a vital role in addressing these challenges. As electricity consumption is closely linked to other energy sources such as natural gas and oil, forecasting electricity consumption is essential for making national energy policies. In this paper, we utilize various data mining techniques, including preprocessing historical load data and the load time series's characteristics. We analyzed the power consumption trends from renewable energy sources and nonrenewable energy sources and combined them. A novel machine learning-based hybrid approach, combining multilayer perceptron (MLP), support vector regression (SVR), and CatBoost, is proposed in this paper for power forecasting. A thorough comparison is made, taking into account the results obtained using other prediction methods. [ABSTRACT FROM AUTHOR]

Biotechnology has revolutionized the development of sustainable energy sources by harnessing biomass as a feedstock for energy production. However, challenges such as recalcitrant feedstocks and inefficient metabolic pathways hinder the large-scale integration of renewable energy systems. Enzyme engineering has emerged as a powerful tool to address these challenges by enhancing enzyme activity, specificity, and stability. Generative machine learning (ML) models have shown great promise in accelerating protein design, allowing for the generation of novel protein sequences with desired properties by navigating vast spaces. This review paper aims to summarize the state of the art in generative models for protein design and how they can be applied to bioenergy applications, including the underlying architectures and training strategies. Additionally, it highlights the importance of high-quality datasets for training and evaluating generative models, organizes available datasets for generative protein design, and discusses the potential of applying generative models to strain design for bioenergy production. • Challenges in renewable energy production require novel bioengineering approaches. • Generative models for novel enzymes present a big advancement in enzyme engineering. • We discuss how VAEs, GANs, and transformers enable improved enzyme production. • The potential of generative model integration into strain design is emphasized. • The role of high-quality, diverse datasets in training & evaluation is highlighted. [ABSTRACT FROM AUTHOR]

This paper presents a novel, unified approach for generating high-quality datasets for training machine-learned models for real-time security assessment in power systems. Synthetic data generation methods that extrapolate beyond historical data can be inefficient in generating feasible and rare operating conditions (OCs). The proposed approach balances the trade-off between historically relevant OCs and rare but feasible OCs. Unlike conventional methods that rely on historical records or generic sampling, our approach results in datasets that generalise well beyond similar distributions. The proposed approach is validated through experiments on the IEEE 118-bus system, where a decision tree model trained on data generated using our approach achieved 97 % accuracy in predicting the security label of rare OCs, outperforming baseline approaches by 41 % and 20 %. This work is crucial for deploying reliable machine-learned models for real-time security assessment in power systems undergoing decarbonisation and integrating renewable energy sources. • Machine-learned models as surrogates to predict real-time security of power systems. • Quality datasets are crucial to train high performing Machine Learning (ML) models. • Method trades-off historically relevant operating conditions (OCs) and 'rare' feasible OCs. • Method generates datasets that generalise well beyond similar distributions. • Studies carried out on the IEEE 118-bus validate the proposed method. [ABSTRACT FROM AUTHOR]

Future electricity generation systems must be optimized to provide flexibility that counteracts the variability of non-dispatchable renewable energy sources and ensures the reliability and safety of critical infrastructure, including the electric grid. The current state-of-the-art is to co-optimize the design and operation of integrated energy systems (IES) treating historical or predicted time-series electricity prices as fixed parameters. Recent literature has shown the limitations of this price taker assumption, which neglects how IES optimization decisions influence market outcomes. As such, this paper proposes a new optimization formulation that uses machine learning surrogate models, trained from a library of annual market operation simulations, to embed IES market interactions into the co-optimization problem directly. Using a thermal generator example built in the open-source IDAES computational environment, we show that the price taker approach routinely over-predicts annual revenues by 8% or more compared to a validation simulation, where the proposed approach has a typical relative error of 1% or less. • Multiscale simulations reveal complex interactions between IESs and energy markets. • Standard price taker formulations are not predictive in realistic design scenarios. • Neural network surrogates accurately predict IES/market interactions. • Optimization with market surrogates is tractable and accurate. • Computational design framework is built entirely from open-source tools. [Display omitted] [ABSTRACT FROM AUTHOR]

Accurate lifetime prediction of transformers operated in power grids with renewable energy systems is a challenging task because it requires a large amount of data that is not usually available. In the case of wind energy, this complexity is intensified with the stochastic ageing process influenced by the intermittency of the wind and weather conditions. Existing models make use of detailed power topologies to evaluate transformer stress profiles and associated degradation. However, this modelling approach requires high computational resources and long simulation times. In this context, this paper presents a lifetime prediction model for transformers designed through probabilistic machine learning, thermal modelling and ageing analysis. The proposed model is compared with synthetic wind-to-power detailed simulations of a wind farm and validated with real data. The lifetime prediction is evaluated with different mission profile estimates and results show that the accuracy of the probabilistic machine learning model is very high, with an error of 0.47% for the median value and 80% prediction interval errors within 6%–7% with respect to observations. Moreover, there is a substantial reduction in the simulation time and memory requirements when compared to the synthetic model. A detailed sensitivity analysis demonstrates the influence on transformer ageing of different overloading strategies, thermal constants and the geographic location of the wind farm. • Probabilistic ML-aided lifetime prediction in transformers for wind energy. • Detailed wind-to-power models validated with real wind power data. • Very high model accuracy with substantial reduction in simulation time and memory. • Capture prediction uncertainty and connect with transformer lifetime estimation. • Detailed sensitivity analysis: overloading strategy, thermal constants and location. [ABSTRACT FROM AUTHOR]

Biogas is a renewable energy source that comes from biological waste. In the biogas generation process, various factors such as feedstock composition, digester volume, and environmental conditions are vital in ensuring promising production. Accurate prediction of biogas yield is crucial for improving biogas operation and increasing energy yield. The purpose of this research was to propose a novel approach to improve the accuracy in predicting biogas yield using the stacking ensemble machine learning approach. This approach integrates three machine learning algorithms: light gradient-boosting machine (LightGBM), categorical boosting (CatBoost), and an evolutionary strategy to attain high performance and accuracy. The proposed model was tested on environmental data collected from biogas production facilities. It employs optimum parameter selection and stacking ensembles and showed better accuracy and variability. A comparative analysis of the proposed model with others such as k-nearest neighbor (KNN), random forest (RF), and decision tree (DT) was performed. The study's findings demonstrated that the proposed model outperformed the existing models, with a root-mean-square error (RMSE) of 0.004 and a mean absolute error (MAE) of 0.0024 for the accuracy metrics. In conclusion, an accurate predictive model cooperating with a fermentation control system can significantly increase biogas yield. The proposed approach stands as a pivotal step toward meeting the escalating global energy demands. [ABSTRACT FROM AUTHOR]

Accurate short-term solar irradiance forecasting is crucial for the efficient operation of solar energy-driven photovoltaic (PV) power plants. In this research, we introduce a novel hybrid ensemble forecasting model that amalgamates the strengths of machine learning tree-based models and deep learning neuron-based models. The hybrid ensemble model integrates the interpretability of tree-based models with the capacity of neuron-based models to capture complex temporal dependencies within solar irradiance data. Furthermore, stacking and voting ensemble strategies are employed to harness the collective strengths of these models, significantly enhancing the prediction accuracy. This integrated methodology is enhanced by incorporating pixels from satellite images provided by the European Organization for the Exploitation of Meteorological Satellites (EUMETSAT). These pixels are converted into structured data arrays and employed as exogenous inputs in the algorithm. The primary objective of this study is to improve the accuracy of short-term solar irradiance predictions, spanning a forecast horizon up to 6 h ahead. The incorporation of EUMETSAT satellite image pixel data enables the model to extract valuable spatial and temporal information, thus enhancing the overall forecasting precision. This research also includes a detailed analysis of the derivation of the GHI using satellite images. The study was carried out and the models tested across three distinct locations in Austria. A detailed comparative analysis was carried out for traditional satellite (SAT) and numerical weather prediction (NWP) models with hybrid models. Our findings demonstrate a higher skill score for all of the approaches compared to a smart persistent model and consistently highlight the superiority of the hybrid ensemble model for a short-term prediction window of 1 to 6 h. This research underscores the potential for enhanced accuracy of the hybrid approach to advance short-term solar irradiance forecasting, emphasizing its effectiveness at understanding the intricate interplay of the meteorological variables affecting solar energy generation worldwide. The results of this investigation carry noteworthy implications for advancing solar energy systems, thereby supporting the sustainable integration of renewable energy sources into the electrical grid. [ABSTRACT FROM AUTHOR]

This study presents a meticulous examination of the solar energy potential of five selected metropolitan cities (Abakaliki, Awka, Enugu, Owerri, and Umuahia) in Eastern part of Nigeria using deep learning algorithm, specifically the Long Short-Term Memory (LSTM) model. These cities, despite being characterized by extended rainy seasons and a high level of cloudiness, are suitable environment for solar power generation and investment opportunities. The employed methodology capitalized on the LSTM deep learning approach to analyze and predict energy generation, utilizing comprehensive hourly weather data from the National Airspace Agency (NASA). The data set comprised various parameters, such as date/time, solar azimuth angle, temperature, humidity, wind speed, wind direction, cloud cover, and power, enabling a thorough analysis of each city. To ensure accuracy, energy prediction capabilities were benchmarked against real-time datasets from a solar power plant in Ulsan, South Korea, thereby training and fine-tuning the model for precision. The LSTM model's performance metrics were maintained at a learning rate of 0.07, a batch size of 150, and a train-test split ratio of 0.8 to 0.2. Data validation exhibited a mean square error (MSE) of 0.01, demonstrating the model's reliability. Results showed Enugu as having the highest solar energy potential, averaging 6.25 kWh/day, while Awka registered the most substantial electricity demand across various sectors. These findings highlight the substantial potential for photovoltaic (PV) power systems and advocate for the immediate implementation of renewable energy policy in the selected cities. These are expected to bring about significant implications for future renewable energy environmentally friendly investments in Nigeria and globally. [ABSTRACT FROM AUTHOR]

Demand for electric power, especially amidst limited fossil fuel-based generation capacity, has elevated renewable energy sources to a forefront solution for the growing energy needs. Solar energy, a key renewable source through photovoltaic (PV) panels, faces challenges such as intermittency and non-dispatchability. Thus, recent research has focused on developing programs to predict near-future solar energy generation, with machine learning being a pivotal approach. This article details the creation of an effective machine-learning pipeline for predicting future hourly power generation based on weather data (e.g. temperature, humidity, irradiance). The pipeline, aimed at a scheduling system in a farm equipped with a Solar Power System (SPS) in Al-Salt, Jordan, was optimized using Genetic Algorithm and Grid Search methods. The objective of this article is to create an optimal pipeline with minimal loss. The evaluation shows that ensemble regressors, especially Gradient Boosting Regressors, are effective. This is evidenced in the grid search pipeline, which outperformed the TPOT optimization pipeline-derived pipeline, the latter including stacked ensemble regressors and sequential preprocessors. [ABSTRACT FROM AUTHOR]

This study aims to propose a wind power prediction method that achieves high accuracy in order to minimize the impact of wind power on the power system and reduce scheduling difficulties in systems incorporating wind power. The importance of developing renewable energy has been recognized by society due to the increasing severity of the energy crisis. Wind energy offers advantages such as efficiency, cleanliness, and ease of development. However, the random nature of wind energy poses challenges to power systems and complicates the scheduling process. Therefore, accurate wind power prediction is of utmost importance. A wind power prediction model was constructed based on an improved tunicate swarm algorithm-extreme learning machine (ITSA-ELM). The improved tunicate swarm algorithm (ITSA) optimizes the random parameters of extreme learning machine (ELM), resulting in the best prediction performance. ITSA is an enhancement of the tunicate swarm algorithm (TSA), which introduces a reverse learning mechanism, a non-linear self-learning factor, and a Cauchy mutation strategy to address the drawbacks of poor convergence and susceptibility to local optima in TSA. Two different scenarios were used to verify the effectiveness of ITSA-ELM. The results showed that ITSA-ELM has a decrease of 1.20% and 21.67% in MAPE, compared with TSA-ELM, in May and December, respectively. This study has significant implications for promoting the development of renewable energy and reducing scheduling difficulties in power systems. [ABSTRACT FROM AUTHOR]

The issue of global warming imposes a change of paradigm in the energy sector to mitigate the human impact on the environment. In this perspective, hydrogen can be produced through water electrolysis and used in fuelcell systems with near-zero pollutant emissions. Nevertheless, the distribution system represents one of the main bottlenecks for a future transition to a hydrogen economy. The possibility of transporting hydrogen through the existing pipeline network is economically attractive. Nevertheless, most pipeline steels are prone to hydrogen-induced damage, and their mechanical properties are degraded by hydrogen gas to an extent that could result in sudden component failures. Hydrogen embrittlement can be responsible for undesired releases with potentially catastrophic consequences. This study evaluates the safety of existing European natural gas pipelines for hydrogen transport through machine learning tools. The material susceptibility to hydrogen embrittlement is predicted under different working conditions in order to prevent loss of material integrity and eventual releases. This study aims at bridging the gap between safety and material science, as it can optimize predictive maintenance of hydrogen pipelines, thus promoting the widespread utilization of hydrogen in the forthcoming years. [ABSTRACT FROM AUTHOR]

Renewable energy resources are becoming more appealing as energy demand and fossil fuel costs increase. The hybridization of these resources has the potential to reduce unpredictability and intermittency while increasing efficiency. The accuracy of size optimization of hybrid renewable energy systems (HRES) can be improved by using accurate weather data that can be obtained through forecasting. Thus, to increase the precision of the size optimization, hourly forecasting of global horizontal irradiation, temperature, and wind speed for one year has been performed using Gaussian process regression (GPR), Support Vector Regression, Extreme Gradient Boosting, and Decision Tree techniques. The results of all four forecasting models (FM) are then compared and revealed that the results obtained from GPR are better than those of other FM; therefore, the forecasted data for solar, wind, and temperature obtained from GPR are used for sizing the HRES. The net present cost is utilized to analyze the viability of the HRES while considering system reliability. Furthermore, recently developed optimization algorithms, namely the Colony Predation Algorithm (CPA), Tunicate Swarm Algorithm (TSA), and Aquila Optimization (AO) algorithms have been applied to the sizing of a grid-connected HRES to meet the energy needs of a remote site in the Indian province of Haryana. A comparison of CPA, AO, and TSA has been carried out and revealed that TSA offers more promising outcomes. In addition, the simulation results demonstrate a 0.42% reduction in per unit cost of energy when forecasted data has been used for size optimization. [ABSTRACT FROM AUTHOR]

This systematic review investigates the role of artificial intelligence (AI) in advancing clean energy technologies within Europe, based on a literature survey from 2006 to 2023. The assessment reveals that AI, particularly through deep learning and neural networks, enhances the efficiency, optimization, and management of clean energy systems. Noteworthy is AI's capacity to improve short-term energy forecasts, essential for smart cities and IoT applications. Our findings indicate that AI drives innovation in renewable energy, contributing to the development of smart grids and enabling collaborative energy-sharing models. While the research underscores AI's substantial influence in Europe's energy sector, it also identifies gaps, such as varied AI algorithm applications in different renewable energy sectors. The study emphasizes the need for integrating AI with emerging clean energy innovations, advocating for interdisciplinary research to navigate the socio-economic, environmental, and policy dimensions. This approach is crucial for guiding a sustainable and balanced advancement in the clean energy landscape, signifying AI's pivotal role in Europe's energy transition. [ABSTRACT FROM AUTHOR]

The prevalence of substantial inductive/capacitive loads within the industrial sectors induces variations in reactive energy levels. The imbalance between active and reactive energy within the network leads to heightened losses, diminished network efficiency, and an associated escalation in operating costs. Therefore, the forecasting of active and reactive energy in the industrial sector confers notable advantages, including cost reduction, heightened operational efficiency, safeguarding of equipment, enhanced energy consumption management, and more effective assimilation of renewable energy sources. Consequently, a range of specialized forecasting methods for different applications have been developed to address these challenges effectively. This research proposes a stacked ensemble methodology, denoted as Stack-XGBoost, leveraging three distinct machine learning (ML) methods: extra trees regressor (ETR), adaptive boosting (AdaBoost), and random forest regressor (RFR), as foundational models. Moreover, the incorporation of an extreme gradient boosting (XGBoost) algorithm as a meta-learner serves to amalgamate the predictions generated by the base models, enhancing the precision of the active/reactive energy consumption forecasting using real time data for steel industry. To assess the efficacy of the proposed model, diverse performance metrics were employed. The results show that the proposed Stack-XGBoost model outperformed other forecasting methods. Additionally, a sensitivity analysis was conducted to assess the robustness of the proposed method against variations in input parameters. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) systems are environmentally friendly, generate green energy, and receive support from policies and organizations. However, weather fluctuations make large-scale PV power integration and management challenging despite the economic benefits. Existing PV forecasting techniques (sequential and convolutional neural networks (CNN)) are sensitive to environmental conditions, reducing energy distribution system performance. To handle these issues, this article proposes an efficient, weather-resilient convolutional-transformer-based network (CT-NET) for accurate and efficient PV power forecasting. The network consists of three main modules. First, the acquired PV generation data are forwarded to the pre-processing module for data refinement. Next, to carry out data encoding, a CNNbased multi-head attention (MHA) module is developed in which a single MHA is used to decode the encoded data. The encoder module is mainly composed of 1D convolutional and MHA layers, which extract local as well as contextual features, while the decoder part includesMHA and feedforward layers to generate the final prediction. Finally, the performance of the proposed network is evaluated using standard error metrics, including the mean squared error (MSE), root mean squared error (RMSE), and mean absolute percentage error (MAPE). An ablation study and comparative analysis with several competitive state-of-the-art approaches revealed a lower error rate in terms of MSE (0.0471), RMSE (0.2167), and MAPE (0.6135) over publicly available benchmark data. In addition, it is demonstrated that our proposed model is less complex, with the lowest number of parameters (0.0135 M), size (0.106 MB), and inference time (2 ms/step), suggesting that it is easy to integrate into the smart grid. [ABSTRACT FROM AUTHOR]

With the continual deployment of power-electronics-interfaced renewable energy resources, increasing privacy concerns due to deregulation of electricity markets, and the diversification of demand-side activities, traditional knowledge-based power system dynamic modeling methods are faced with unprecedented challenges. Data-driven modeling has been increasingly studied in recent years because of its lesser need for prior knowledge, higher capability of handling large-scale systems, and better adaptability to variations of system operating conditions. This paper discusses about the motivations and the generalized process of data-driven modeling, and provides a comprehensive overview of various state-of-the-art techniques and applications. It also comparatively presents the advantages and disadvantages of these methods and provides insight into outstanding challenges and possible research directions for the future.

Renewable energy sources (RES) are seen as a means of the fuel and energy complex carbon footprint reduction but the stochastic nature of generation complicates RES integration with electric power systems. Therefore, it is necessary to develop and improve methods for forecasting of the power plants generation using the energy of the sun, wind and water flows. One of the ways to improve the accuracy of forecast models is a deep analysis of meteorological conditions as the main factor affecting the power generation. In this paper, a method for adapting of forecast models to the meteorological conditions of photovoltaic stations operation based on machine learning algorithms was proposed and studied. In this case, unsupervised learning is first performed using the k-means method to form clusters. For this, it is also proposed to use studied the feature space dimensionality reduction algorithm to visualize and estimate the clustering accuracy. Then, for each cluster, its own machine learning model was trained for generation forecasting and the k-nearest neighbours algorithm was built to attribute the current conditions at the model operation stage to one of the formed clusters. The study was conducted on hourly meteorological data for the period from 1985 to 2021. A feature of the approach is the clustering of weather conditions on hourly rather than daily intervals. As a result, the mean absolute percentage error of forecasting is reduced significantly, depending on the prediction model used. For the best case, the error in forecasting of a photovoltaic plant generation an hour ahead was 9 %.

This Special Issue was intended as a forum to advance research and apply machine-learning and data-mining methods in order to facilitate the development of modern electric power systems, grids and devices, smart grids and protection devices, as well as to develop tools for more accurate and efficient power system analysis. Machine learning algorithms, optimization techniques and efficient numerical algorithms, distributed signal processing, machine learning, data-mining statistical signal detection, and estimation may help in solving contemporary challenges in modern power systems. To conclude, with reference to presented papers, we have seen a broad spectrum of data-mining and modern machine-learning techniques applied to recent problems of operation of power systems. [Extracted from the article]

Nowadays, the energy sector is experiencing a profound transition. Among all renewable energy sources, wind energy is the most developed technology across the world. To ensure the profitability of wind turbines, it is essential to develop predictive maintenance strategies that will optimize energy production while preventing unexpected downtimes. With the huge amount of data collected every day, machine learning is seen as a key enabling approach for predictive maintenance of wind turbines. However, most of the effort is put into the optimization of the model architectures and its parameters, whereas data-related aspects are often neglected. The goal of this paper is to contribute to a better understanding of wind turbines through a data-centric machine learning methodology. In particular, we focus on the optimization of data preprocessing and feature selection steps of the machine learning pipeline. The proposed methodology is used to detect failures affecting five components on a wind farm composed of five turbines. Despite the simplicity of the used machine learning model (a decision tree), the methodology outperformed model-centric approach by improving the prediction of the remaining useful life of the wind farm, making it more reliable and contributing to the global efforts towards tackling climate change. [ABSTRACT FROM AUTHOR]

Due to concerns about energy use in production systems, energy-efficient processes have received much interest from the automotive industry recently. Remote laser welding is an innovative assembly process, but has a critical issue with the energy consumption. Robot companies provide only the average energy use in the technical specification, but process parameters such as robot movement, laser use, and welding path also affect the energy use. Existing literature focuses on measuring energy in standardized conditions in which the welding process is most frequently operated or on modularizing unified blocks in which energy can be estimated using simple calculations. In this paper, the authors propose an integrated approach considering both process variation and machine specification and multiple methods' comparison. A deep learning approach is used for building the neural network integrated with the effects of process parameters and machine specification. The training dataset used is experimental data measured from a remote laser welding robot producing a car back door assembly. The proposed estimation model is compared with a linear regression approach and shows higher accuracy than other methods. [ABSTRACT FROM AUTHOR]

Predictive analytics play a significant role in ensuring optimal and secure operation of power systems, reducing energy consumption, detecting fault and diagnosis, and improving grid resilience. However, due to system nonlinearities, delay, and complexity of the problem because of many influencing factors (e.g., climate, occupants' behaviour, occupancy pattern, building type), it is a challenging task to get accurate energy consumption prediction. This paper investigates the accuracy and generalisation capabilities of deep highway networks (DHN) and extremely randomized trees (ET) for predicting hourly heating, ventilation and air conditioning (HVAC) energy consumption of a hotel building. Their performance was compared with support vector regression (SVR), a most widely used supervised machine learning algorithm. Results showed that both ET and DHN models marginally outperform the SVR algorithm. The paper also details the impact of increasing the deep highway network's complexity on its performance. The paper concludes that all developed models are equally applicable for predicting hourly HVAC energy consumption. Possible reasons for the minimum impact of DHN complexity and future research work are also highlighted in the paper. [ABSTRACT FROM AUTHOR]

The distributed generation in smart grids has become highly prevalent due to its inherent characteristics like robust, reachable, lossless and emission less. The increased usage of sensor devices, wireless and network communication, cloud computing and IoT (Internet of things) explores the merge of smartness in energy field which results in an extensive collection of data getting populated in the electricity sector. This paper proposes a hybrid machine learning with big data analytic techniques for optimized distribution of available energy resources targeting smart energy management. The system aims in handling smart energy management using the data received from conventional sources and various distributed generation sources like photovoltaic, wind, small hydro and biomass. For unsupervised power data an efficient clustering methodology such as grid based clustering has been incorporated for optimal distribution of energy received from the nodal and zone regions. For structured power data, support vector machine algorithm of supervised learning is used for smart distribution which performs classification and regression of the vast electricity data. Regressive analysis over electricity data across the country with respect to various regions is carried out to understand the energy consumption which gives the insight of energy deficit. Thus the machine learning hybrid techniques were performed over the collected data to validate the smart distribution and the result obtained ensures a substantial gain which leads to conservation of generated energy through smart energy management. [ABSTRACT FROM AUTHOR]

The prediction of wind speed plays a significant role in wind energy systems. An accurate prediction of wind speed is more important for wind energy systems, but it is difficult due to its uncertain nature. This paper presents three artificial neural networks namely, Back Propagation Network (BPN), Radial Basis Function (RBF) and Nonlinear AutoRegressive model process with eXogenous inputs(NARX) with Mutual Information (MI) feature selection for wind speed prediction. The MI feature selection identifies the significant features and reduces the complexity of wind speed prediction model without loss of information content. The performance of prediction model is evaluated in terms of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The results show that the performance of all three neural network models are highly satisfied. Moreover, NARX model with mutual information feature selection is more accurate in dealing with wind speed prediction. [ABSTRACT FROM AUTHOR]

An ocean turbine generator will be subject to variations in water current velocity at one end and resistive load at the other. Measurements acquired during bench testing of the turbine's drivetrain can be used to predict the effect of these variables on the turbine during deployment. This paper outlines an ongoing series of tests involving vibration data captured at various velocities and loads. This data is analyzed to detect the machine's state using two approaches. In the first approach, machine learning techniques are used to discern between states given adjacent values for velocity or load. The purpose of that approach is to assess a learner's ability to draw the fine distinctions needed for subsequent fault identification. The second approach computes a power spectrum for each velocity and load combination over enough trials as to construct an operating envelope. The purpose of that approach is to identify as abnormal, incoming data having parts of its spectrum that fall outside that envelope. A case study applies each approach to baseline data and data for a deterioration scenario. The rationale behind each approach, their assumptions, and their limitations are also discussed. [ABSTRACT FROM AUTHOR]

The high penetration of renewable energy sources, coupled with decommissioning of conventional power plants, leads to the reduction of power system inertia. This has negative repercussions on the transient stability of power systems. The purpose of this paper is to review the state-of-the-art regarding the application of artificial intelligence to the power system transient stability assessment, with a focus on different machine, deep, and reinforcement learning techniques. The review covers data generation processes (from measurements and simulations), data processing pipelines (features engineering, splitting strategy, dimensionality reduction), model building and training (including ensembles and hyperparameter optimization techniques), deployment, and management (with monitoring for detecting bias and drift). The review focuses, in particular, on different deep learning models that show promising results on standard benchmark test cases. The final aim of the review is to point out the advantages and disadvantages of different approaches, present current challenges with existing models, and offer a view of the possible future research opportunities. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicle (UAV)-assisted cellular networks over the millimeter-wave (mmWave) frequency band can meet the requirements of a high data rate and flexible coverage in next-generation communication networks. However, higher propagation loss and the use of a large number of antennas in mmWave networks give rise to high energy consumption and UAVs are constrained by their low-capacity onboard battery. Energy harvesting (EH) is a viable solution to reduce the energy cost of UAV-enabled mmWave networks. However, the random nature of renewable energy makes it challenging to maintain robust connectivity in UAV-assisted terrestrial cellular networks. Energy cooperation allows UAVs to send their excessive energy to other UAVs with reduced energy. In this paper, we propose a power allocation algorithm based on energy harvesting and energy cooperation to maximize the throughput of a UAV-assisted mmWave cellular network. Since there is channel-state uncertainty and the amount of harvested energy can be treated as a stochastic process, we propose an optimal multi-agent deep reinforcement learning algorithm (DRL) named Multi-Agent Deep Deterministic Policy Gradient (MADDPG) to solve the renewable energy resource allocation problem for throughput maximization. The simulation results show that the proposed algorithm outperforms the Random Power (RP), Maximal Power (MP) and value-based Deep Q-Learning (DQL) algorithms in terms of network throughput. [ABSTRACT FROM AUTHOR]

Traditional power generating technologies rely on fossil fuels, which contribute to worldwide environmental issues such as global warming and climate change. As a result, renewable energy sources (RESs) are used for power generation where battery energy storage systems (BESSs) are widely used to store electrical energy for backup, match power consumption and generation during peak hours, and promote energy efficiency in a pollution-free environment. Accurate battery state of health (SOH) prediction is critical because it plays a key role in ensuring battery safety, lowering maintenance costs, and reducing BESS inconsistencies. The precise power consumption forecasting is critical for preventing power shortage and oversupply, and the complicated physicochemical features of batteries dilapidation cannot be directly acquired. Therefore, in this paper, a novel hybrid architecture called 'CL-Net' based on convolutional long short-term memory (ConvLSTM) and long short-term memory (LSTM) is proposed for multi-step SOH and power consumption forecasting. First, battery SOH and power consumption-related raw data are collected and passed through a preprocessing step for data cleansing. Second, the processed data are fed into ConvLSTM layers, which extract spatiotemporal features and form their encoded maps. Third, LSTM layers are used to decode the encoded features and pass them to fully connected layers for final multi-step forecasting. Finally, a comprehensive ablation study is conducted on several combinations of sequential learning models using three different time series datasets, i.e., national aeronautics and space administration (NASA) battery, individual household electric power consumption (IHEPC), and domestic energy management system (DEMS). The proposed CL-Net architecture reduces root mean squared error (RMSE) up to 0.13 and 0.0052 on the NASA battery and IHEPC datasets, respectively, compared to the state-of-the-arts. These experimental results show that the proposed architecture can provide robust and accurate SOH and power consumption forecasting compared to the state-of-the-art. [ABSTRACT FROM AUTHOR]

In recent years, the overwhelming growth of solar photovoltaics (PV) energy generation as an alternative to conventional fossil fuel generation has encouraged the search for efficient and more reliable operation and maintenance practices, since PV systems require constant maintenance for consistent generation efficiency. One option, explored recently, is artificial intelligence (AI) to replace conventional maintenance strategies. The growing importance of AI in various real-life applications, especially in solar PV applications, cannot be over-emphasized. This study presents an extensive review of AI-based methods for fault detection and diagnosis in PV systems. It explores various fault types that are common in PV systems and various AI-based fault detection and diagnosis techniques proposed in the literature. Of note, there are currently fewer literatures in this area of PV application as compared to the other areas. This is due to the fact that the topic has just recently been explored, as evident in the oldest paper we could obtain, which dates back to only about 15 years. Furthermore, the study outlines the role of AI in PV operation and maintenance, and the main contributions of the reviewed literatures. [ABSTRACT FROM AUTHOR]

Microgrids are empowered by the advances in renewable energy generation, which enable the microgrids to generate the required energy for supplying their loads and trade the surplus energy to other microgrids or the macrogrid. Microgrids need to optimize the scheduling of their demands and energy levels while trading their surplus with others to minimize the overall cost. This can be affected by various factors such as variations in demand, energy generation, and competition among microgrids due to their dynamic nature. Thus, reaching optimal scheduling is challenging due to the uncertainty caused by the generation/consumption of renewable energy and the complexity of interconnected microgrids and their interplay. Previous works mainly rely on modeling-based approaches and the availability of precise information on microgrid dynamics. This paper addresses the energy trading problem among microgrids by minimizing the cost while uncertainty exists in microgrid generation and demand. To this end, a Bayesian coalitional reinforcement learning-based model is introduced to minimize the energy trading cost among microgrids by forming stable coalitions. The results show that the proposed model can minimize the cost up to 23% with respect to the coalitional game theory model. [ABSTRACT FROM AUTHOR]

The purpose of this study is to highlight approaches for predicting a system's future behavior and estimating its remaining useful life (RUL) to define an effective maintenance schedule. Indeed, prognosis and health management (PHM) strategies for renewable energy systems, with a focus on wind turbine generators, are given, as well as publications published in the recent ten years. As a result, some prognostic applications in renewable energy systems are emphasized, such as power converter devices, battery capacity degradation, and damage in wind turbine high-speed shaft bearings. The paper not only focuses on the methodologies adopted during the early research in the area of PHM but also investigates more current challenges and trends in this domain [ABSTRACT FROM AUTHOR]