Search

To tune the wave energy converter (WEC) controller parameters such as damping to reduce the line force during extreme wave conditions, future knowledge of the line force is required. To achieve this, the incoming wave and system state should be predicted for a few seconds in the future. It is rather an arduous task to predict the future knowledge of waves and the system's dynamic when dealing with breaking and steep waves, and the system is subject to various nonlinear forces. The classical model-based control strategies often rely on linear assumptions to estimate the WEC dynamics for the sake of simplicity. Unlike the model-based, the data-driven approaches are free from modeling errors and the algorithms are trained over the true and noisy data to predict non-linear system behaviors. Using data-driven approaches, we are able to model nonlinear dynamics. However, new questions emerge on the accuracy of the future wave and system state predictions, and how this uncertainty propagates into the final prediction of the line force. As incorrect damping may lead to excessive line force and detrimental damage to the system, these are the knowledge gaps that need to be addressed. The main purpose of this paper is to answer these questions through a survivability strategy for wave energy converters by providing a realistic perspective on the implementation of the neural network approaches by accounting for the errors in the input data. For this purpose, a series of neural networks is designed that first predicts the surface elevation for 0.36 s ahead, i.e. corresponding to 2 s in the full-scale WEC. This future knowledge of the wave elevation is then used to predict the system state (i.e. power take-off (PTO) translator position) for the same prediction horizon based on the PTO damping. This information is then fed to a convolutional neural network (CNN) that predicts the peak line force 0.36 s ahead. This paper also evaluates the predictive capabilities of neural network (NN) models, comparing them to classical autoregressive (AR) and Kalman filter methods. While the AR model exhibits slightly higher accuracy in fixed PTO system configurations, it falters in providing real-time predictions when system parameters undergo variations. In contrast, the NN prediction model excels by establishing a robust relationship between system configuration and output signals. Especially noteworthy is its ability to outperform classical methods with minimal training on a selective set of system configurations. Then, the sensitivity of the peak line force prediction to the uncertainties in the input data from NN models and the prediction horizon is analyzed. The neural network models are trained over the experimental data subjected to extreme sea states for a point absorber wave energy converter. The results suggest that the accuracy of the surface elevation prediction has an insignificant direct effect on the peak force prediction model. However, these uncertainties are reflected in the PTO translator position prediction, and the model is considerably sensitive to the accuracy of this prediction. This sensitivity nonetheless is less notable for higher PTO damping values. • Predicting wave elevation, PTO position, and mooring force via neural networks. • Finding optimum damping to reduce mooring force in extreme wave conditions. • Predicting the mooring force is sensitive to the PTO position prediction. [ABSTRACT FROM AUTHOR]

The existing decentralized wind farm control incorporating the wind turbine wake interaction has almost all concentrated on the condition of fixed wind speed/direction without considering the variability of wind in nature. Meanwhile, most of the current wake models cannot meet the requirement for wind turbine control optimization research with the high demand of wake calculation speed and accuracy. In this paper, a novel decentralized control strategy, named the wind-interval-based (WIB) control which adopts the uniform operation among the same interval of variable wind speeds/directions, is proposed for the control optimization study of in-line two scaling wind turbines for demonstration. To prove the effectiveness of the new control mechanism, the ideal instantaneous control is introduced for the comparative study. At the same time, a wake model incorporating the two directly controllable parameters (i.e., the tip speed ratio λ and pitch angle γ) is established based on artificial neural network (ANN). The comparative results show that the total power output applying the instantaneous control and the new WIB control mechanisms are increased by 0.1%–4.1% and 0.45%–3.9% depending on the tested wind scenarios, respectively. By comparing the optimized power output with the two controls, it is found that the error between them is generally lower than 3%, while the proposed WIB control reduces the operational difficulty to a large extent facilitating its application to the real wind turbine operation in reality. In summary, this paper shows that the new proposed WIB control not only reduces the difficulties of the wind turbine control mechanism, but maintains the control effectiveness by achieving a comparable total power output with respect to the traditional instantaneous control, which is of great significance to the wind farm developer. [ABSTRACT FROM AUTHOR]

Chemical Looping Combustion (CLC) is a carbon capture technology that uses an oxygen carrier to transfer the oxidizing agent to the fuel for combustion. This study used different machine learning algorithms, Artificial neural network and Response surface methodology to estimate the surface region process performance and optimize the process condition for the CLC of different solid fuels waste paper, plastic waste, and sugarcane bagasse blends. Based on the combustion efficiency, CO 2 yield and CO 2 capture efficiency responses, A high performance correlation (R2 > 0.8) was obtained for all the combustion parameters analyzed. The perturbation plot derived from the RSM analysis indicated that the most significant input parameters include the steam to fixed carbon, blend ratio and the fuel reaction temperature. The CLC process was optimized using RSM. For blends of SCB/WP, the best operating conditions were found to be 800 °C, a solid flow rate of 197.7 kg/h, an oxygen carrier to fuel ratio of 1.1, a steam to fixed carbon ratio of 2.16, and a blend ratio of 1. Similarly, for blends of SCB/PW, the optimal operating conditions were 800 °C, a solid flow rate of 199.4 kg/h, an oxygen carrier to fuel ratio of 1.3, steam to fixed carbon ratio of 2, and a blend ratio of 0.3. The optimum combustion performance was found to be 0.98, 0.78, and 0.96 for SCB/WP and 0.99, 0.62, and 0.96 for SCB/PW, respectively. • The process performance of the CLC of MSW/biomass blend was compared using ANN and RSM. • The optimal blend ratios for SCB/WP and SCB/PW blends were 1 (25% WP) and 0.3 (42.5% PW). • The combustion performance of the WP improved by 6.2% and 3.5% in terms of combustion efficiency and CO 2 yield, respectively. • The most significant input factors were discovered to be the blend of fuels ratio and the steam to fixed carbon ratio. [ABSTRACT FROM AUTHOR]

This paper proposes the use of Artificial Neural Networks (ANNs), specifically Physics-Informed Neural Networks (PINNs), for dynamic surrogate modelling of wind turbines. PINNs offer the flexibility to model complex relationships while incorporating physics-based constraints, enabling accurate representation of wind turbine dynamics. In this paper, a PINN-based surrogate model is developed for the Blade Element Momentum (BEM) aerodynamic model used in state-of-the-art numerical wind turbine simulations. The PINN model replaces the time-consuming root-finding process in BEM with high-dimensional regression, significantly improving computational efficiency. The PINN model is trained using data generated from a numerical model of the IEA-15MW reference wind turbine, and its performance is compared against conventional data-driven Neural Network (DDNN) models. The proposed surrogate model provides more efficient and accurate evaluations of wind turbine responses compared with traditional surrogate modelling approaches. A significant computational advantage is obtained by using the developed surrogate models with a forty-fold speedup demonstrated compared to the BEM model. Replacing the BEM model with the PINN-based surrogate model for load computation in the numerical model used for dynamic analysis results in an overall reduction of 35% in computational time for a complete dynamic simulation. This is a substantial improvement in efficiency without sacrificing accuracy — the maximum Mean Absolute Error (MAE) values for the surrogate models are of the order of 1 0 − 2 , which shows that the surrogate models can predict the angle of attack at any blade node with a discrepancy of less than 0. 5 °. The surrogate models significantly reduce computational time while maintaining high accuracy, making them a promising approach for simulating wind turbine dynamics, especially in fields such as reliability analysis or fatigue estimation where many simulations are necessary. [ABSTRACT FROM AUTHOR]

Wind power ramp is a destructive event accompanied with a sharp change of wind power. Offshore wind power is expected to receive more attention for it can harvest consistent and strong winds. In this paper, a ramp detection framework based on the swinging door algorithm (SDA) and the mergence of correct ramps is proposed. Meanwhile, a trend-based prediction method (T-Method) is proposed to predict offshore wind power ramps. The ramp detection framework is utilized to identify wind power ramp events (WPREs) and label original data according to the detection results. After that, the labeled data is selected as the input of recurrent neural network to produce wind power prediction results. Finally, the prediction results are detected by the ramp detection framework to produce WPREs prediction results. Four recurrent neural network models and two traditional methods are applied to two offshore wind power datasets for corroborating the effectiveness of our method. Comparative experiments show that our proposed method performs excellent in all evaluation indicators. The proposed WPREs prediction method improves the performance of WPREs prediction under the premise of low false alarm rate and missing alarm rate. It provides early warning for power system operators to reduce the harm of WPREs. • This is a novel offshore wind power ramp events (WPREs) forecasting method. • The method can improve the forecasting accuracy of offshore WPREs. • Results are evaluated by the metrics of classification. [ABSTRACT FROM AUTHOR]

The curtailment of renewable energy worsens with increasing penetration in power systems, so it is necessary to explore the upper limit value of the penetration of renewable energy (PRE). This paper uses artificial neural networks (ANN) to study the historical data of California independent system operator (CAISO), analyze the fluctuation balance strategy of wind and solar power, and predict the upper limit value of the PRE, which will peak at 40.5% in 2025. In addition, this paper also simulates the inclusion of energy storage unit (ESU) with an installed capacity of 3 GWh in the grid to reduce curtailments, and analyzes the grid operating conditions and the upper limit value of the PRE, showing that the storage units with an installed capacity of only 3% of the average daily power output of solar energy recover 58% of the annual curtailments (2021), and the maximum PRE is 41.2%. [ABSTRACT FROM AUTHOR]

Wind power has become one of the essential solutions to renewable energy and sustainable development problems. The accuracy of wind speed forecasts primarily determines the utilization of wind energy. Because many factors affect wind speed, high-precision wind speed prediction is still a practical and challenging task. In this paper, we propose multidimensional spatial-temporal graph neural networks (MST-GNN) for wind speed prediction: (1) establish a transformer-based model named Wind-Transformer on temporal perspective for single-point wind speed prediction with multidimensional data (wind speed, wind direction, temperature, air pressure, etc.), (2) apply graph neural network using Wind-Transformer as a node on spatial view to accurately predict the wind speed at local point by comprehensively aggregating the wind speed of local point and surrounding points. Through comprehensive experiments on open source datasets for wind speed prediction, we demonstrate that our model MST-GNN outperforms the state-of-the-art baselines up to 8.96%. The longer the prediction steps, the more improvement relative to other methods. • Wind power is an essential solution to renewable energy. • Wind speed forecasting primarily determines the utilization of wind energy. • Predicting wind speed with multidimensional data at different locations. • Generating wind prediction parallelly rather than in sequence. • Leveraging the advantages of transformer and graph neural network models. [ABSTRACT FROM AUTHOR]

Lithium-ion batteries have been used in all aspects of life for environmental and resource reasons. The accurate estimation of the state of charge (SOC) ensures the proper operation of the battery. However, few methods have focused on the problem of SOC estimation at low temperatures. A hybrid method based on the CNN-BWGRU network is proposed in this paper. The method optimizes the influence of battery information on the results through a "multi-moment input" structure and the bidirectional network. The convolutional neural network (CNN) is used to learn the feature parameters in the input. The bidirectional weighted gated recurrent unit (BWGRU) can improve the fitting performance of the network at low temperatures by changing the weights. The proposed network has a strong generalization capability, estimation accuracy, and robustness. SOC estimation is performed under different conditions to verify the plausibility of the network. The experimental results show that the method has higher accuracy and stability than other networks. In addition, the proposed method can overcome the effect of different initial SOC on the estimation results. Therefore, the CNN-BWGRU network provides a new method in battery SOC estimation while providing helpful guidance for safe and stable battery operation in natural environments. [Display omitted] [ABSTRACT FROM AUTHOR]

Precise power prediction for wind turbines under wake effects is requisite for wind farm wake control to increase the energy production and economic benefits. Wind farm wake effects that have spatial and temporal characteristics significantly complicate the physical modelling. To overcome the modelling difficulties, this paper proposes two new coupled structures of physical process and machine learning to predict wind turbine output power under wake effects. Their structures are fully presented and verified by comparisons to the pure physical model, neural network model alone and existing physical-guided neural network models. One of the new models that couples physical model and transfer learning approach shows the best prediction performance. It uses data generated from physical model and small size real data to establish the model, which makes it adaptive to data with different distribution. The results confirm that a robust hybrid physical and machine learning model can simultaneously inherit the advantages from developments of physical models and machine learning approaches. Important insights into HPML models for output power prediction of WTs under wake effects are provided. [ABSTRACT FROM AUTHOR]

Recent European Community directives introduce Renewable Energy Communities (REC) and Jointly Acting Renewable Self-Consumers (JARSC). Both entities are constituted by communities of residential and/or non-residential prosumers, located in proximity of renewable generators and Electrical Storage Systems (ESS) owned and managed by the REC/JARSCs. These aggregations of prosumers are aimed at providing environmental and economic benefits by maximizing their global self-consumption. In this frame, it is relevant to introduce a control strategy which considers the whole system represented by the REC/JARSCs and performs optimal management of energy production, storage and consumption. The present paper proposes a Model Predictive Control (MPC) based control design, targeted at the minimization of electricity cost and equivalent CO2 emissions, considering the whole ensemble of loads included in the REC/JARSCs over a 24-h prediction horizon. To exploit the MPC ability of including forecasts in the optimization problem, predictors including Artificial Neural Networks (ANN) are developed for solar irradiance, air temperature, electricity price and carbon intensity. The proposed control performance is evaluated considering a case study located in Milan, Italy, and its advantages with respect to traditional control algorithms are highlighted by comprehensive numerical simulations. Lastly, an economic evaluation of the considered system is presented. • RECs and JARSCs are new forms of self-consumption introduced by EU directives. • RECs/JARSCs operation approached as an optimization problem by an MPC Controller. • ANN-based predictors for PV production, electricity price and carbon intensity. • Evaluation of economic revenues and CO2 emission reduction in different Scenarios. [ABSTRACT FROM AUTHOR]

During operation Pelton turbines suffer from erosion and cavitation wear, which decreases the hydraulic efficiency. Welding repair is a cost-effective method for recovering the original bucket geometry but requires templates to ensure proper results. However, those templates may be unavailable for Pelton units with decades of operation. This is the case of one of the 2.8 MW Pelton units at Nima II, a small hydropower plant in Colombia that began operation in 1942. This paper presents the redesign and optimization of the bucket. First, the bucket is rebuilt following both, technical recommendations, and Design of Experiments (DOE) to verify the effects of the basic dimensions on the hydraulic efficiency. Experimental measurements on the eroded turbine validate the two-phase computational fluid dynamics (CFD) modelling to be applied in the optimization process. Second, the best inner surface is found by using a multi-objective optimization based on Artificial Neural Networks trained by the previous DOE and a genetic algorithm. At the end, the CFD results suggest a total hydraulic efficiency recovery of 8 %. Further experimental tests on the optimized runner showed a difference of 0.7 % from the predicted value. [ABSTRACT FROM AUTHOR]

Modeling solar plants, like Linear Fresnel Reflectors, plays an essential role in analyzing plant characteristics, assessing overall efficiency, designing appropriate controllers, and optimizing system's operation. Although physical modeling approaches are widely used, their accuracy when compared to real operational data is deficient. In this context, this paper conducts a novel and comprehensive investigation for an existing Linear Fresnel Reflector using six distinct machine learning algorithms namely, Multilayer Perceptron and LSTM Neural Networks, Random Forest, Decision Trees, Extreme Gradient Boosting, and K-Nearest Neighbours to forecast the useable output power of a linear Fresnel solar plant. Datasets between May 2018 and September 2019 with a 30-s time interval from a linear Fresnel plant located in Nicosia, Cyprus are used in this research. Seven distinct statistical metrics, in conjunction with the computation time are employed to assess the performance of the different machine learning models. The objective of this study is to further improve the prediction of Linear Fresnel Reflectors performance using machine learning model, in order to increase modeling reliability on an annual basis. Outcomes reveal that, among the various models considered, K-Nearest Neighbours demonstrated the most optimal performance with a coefficient of determination 98.81 % and a mean absolute percentage error of 1.975 %. [ABSTRACT FROM AUTHOR]

Harnessing daylight for energy-efficient designs requires the availability of daylight illuminance data. In the absence of measured daylight data, deriving daylight using the luminous efficacy model is an alternative. This paper presents an approach for modeling diffuse and global luminous efficacies using accessible measured climatic data. The methodology explored machine learning, sensitivity analysis and empirical modeling approaches. Twelve (12) luminous efficacy models were proposed. These models consisted of six artificial neural networks (ANN) and six empirical models. All models also cover the all-sky, overcast and non-overcast sky conditions. The intent of using ANN lies in the need for more accurate daylight predictions and its ease in explaining complex relationships between complex atmospheric variables. Findings from the study show that diffuse fraction is crucial in global and diffuse luminous efficacy modeling. Furthermore, the performance of all models was statistically assessed, and the results show that all twelve proposed models could offer acceptable predictions of daylight. In particular, the ANN models outperformed the empirical models. [ABSTRACT FROM AUTHOR]

Energy piles have attracted much attention in recent years because they provide a profitable solution for efficient shallow geothermal energy utilization in different climatic regions. However, the long-term performance design of energy piles under different thermal scenarios currently relies on time-consuming and computationally expensive methods such as numerical simulations, which seriously hinders the further engineering application of energy piles. To this end, this paper provides a high-precision and computationally efficient model for predicting the long-term performance of energy pile design through an artificial neural network machine learning process. First, experimentally validated numerical models are developed. Then, they are utilized to generate the training and evaluate datasets for the proposed model by inputting sixty typical thermal load distributions in different regions of China. Finally, the performance of the proposed model is evaluated by comparing its calculations with those obtained using numerical models. The results show that the proposed model can predict the long-term performance of energy piles and enrich the current methods for the long-term design of energy piles. Furthermore, its features that tremendously reduce the computational time and minimum required resources make it an excellent supplement compared with numerical simulations. [ABSTRACT FROM AUTHOR]

This paper uses a Modern-Era Retrospective analysis for Research and Applications version 2 (MERRA-2) re-analysis to identify long-term Mediterranean Sea Offshore Wind (OW) classification possible locations. In particular, an OW classification based on the last 40-years period OW speeds highlighted the best areas for potential Offshore Wind Turbine Generators (OWTG) installations in the Mediterranean basin. Preliminary, long-term OW classification results show that several Mediterranean basin zones in the Aegean Sea, Gulf of Lyon, the Northern Morocco and Tunisia regions have attractive OW potential. Secondly, a combined forecasting model based on the wavelet decomposition method and long-term memory neural network has been developed to predict the short-term wind speed considering the last ten years of hourly data for Mediterranean areas. The results of the proposed model for wind speed prediction have been compared with other single models, Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM), highlighting a higher level of accuracy. Finally, three Weibull fitting algorithms have been provided to analyze the wind energy potential in the Mediterranean basin. • Offshore wind classification using 40 years of re-analysis data and learning models. • Offshore wind speed assessment and mapping of the Mediterranean Sea hot region's. • A prediction model based on wavelet transform and long short-term memory network. • The evaluated model based on re-analysis data for offshore wind hot region's. [ABSTRACT FROM AUTHOR]

Wind power is becoming a main alternative energy source to meet the growing electricity needs. Forecasting wind speed is important to mitigate generation uncertainty and optimize asset utilization. This paper proposes a hybrid wind speed prediction model with multivariate input and multi-step output capability. The model synthesizes linear time series regression with nonlinear machine learning algorithm. The input neurons of the hybrid model are determined by the number of lag observations in autoregressive integrated moving average (ARIMA), and also by correlated meteorological features, such as wind direction, air pressure, humidity, dew point, and temperature. The output neurons are further derived based on the forecasting horizon. The hybrid model is trained, validated, and tested by using 1.73 million hourly meteorological records from three cities with diverse wind profiles. The performance of the model is compared with several existing methods based on root mean square error and mean absolute error. Though the hybrid model does not show obvious advantage in 1-h ahead prediction, it outperforms persistence model, ARIMA, and univariate neural network models in 3-to-24 h ahead prediction. The hybrid model is able to reduce the prediction error by 20% in comparison with univariate neural networks. [ABSTRACT FROM AUTHOR]

The prediction of wave height and flux of energy is essential for most ocean engineering applications. To simultaneously predict both wave parameters, this paper presents a novel approach using short-term time prediction horizons (6h and 12h). Specifically, the methodology proposed presents a twofold simultaneity: 1) both parameters are predicted by a single model, applying the multi-task learning paradigm, and 2) the prediction tasks are tackled for several neighbouring ocean buoys with such single model by the development of a zonal strategy. Multi-Task Evolutionary Artificial Neural Network (MTEANN) models are applied to two different zones located in the United States, considering measurements collected by three buoys in each zone. Zonal MTEANN models have been compared in a two-phased procedure: 1) against the three individual MTEANN models specifically trained for each buoy of the zone, and 2) against some state-of-the-art regression techniques. Results achieved show that the proposed zonal methodology obtains not only better performance than the individual MTEANN models, but it also requires a lower number of connections. Besides, the zonal MTEANN methodology outperforms state-of-the-art regression techniques. Hence, the proposed approach results in an excellent method for predicting both significant wave height and flux of energy at short-term prediction time horizons. [ABSTRACT FROM AUTHOR]

In this paper, three machine learning (ML) algorithms, Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Extreme Gradient Boosting (XGBoost), are validated to estimate the velocity and turbulence intensity of a wind turbine's wake at distinct downstream distances. To this end, a series of high-fidelity numerical simulations for the NREL Phase VI wind turbine is carried out to generate training and test datasets for the three machine learning algorithms. The predicted wake velocity and turbulence intensity from the ML models are also contrasted with significant existing analytical wake models. Machine learning algorithms estimate velocity and turbulence intensity in the wake in a way commensurate to the Computational Fluid Dynamics (CFD) simulations while running at a similar pace as low-fidelity wake models. The results demonstrate that machine learning-based algorithms can predict velocity and turbulence intensity better with higher precision than the traditional analytical wake models. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the wind speed data collected by wind farms are affected by many factors and easy to introduce noise information, a wind speed prediction method based on data decomposition of improved singular spectrum analysis (ISSA) is proposed. In this paper, the ISSA is used to decompose the wind speed sequence into a series of sub-sequences. Based on the singular spectrum analysis (SSA), the ISSA introduces the singular entropy to judge the noise components of the wind speed series and remove them. Then, the artificial neural network model is used to calculate and compare the prediction results of several data preprocessing decomposition methods using EMD, EEMD, CEEMD, ISSA and the prediction results without data preprocessing. Experimental results show that the proposed method can effectively improve the prediction accuracy of the artificial neural network, and also has higher prediction accuracy than the comparison method, which verifies the effectiveness of the ISSA. [ABSTRACT FROM AUTHOR]

The share of photovoltaic energy is more and more increasing in the World energy mix; the intermittence of this production makes difficult to maintain the stability of the electricity grid and the balance production-consumption. Predicting in advance the solar production facilitates the operation of the grid manager. This paper aims to forecast hourly global solar irradiation for time horizons from h+1 to h+6, using two approaches: multiple linear regression (MLR) and artificial neural network (ANN) models. The choice of inputs in these models is crucial for a good prediction and is investigated here; generally, only endogenous data are used (global solar irradiation), the addition of exogenous ones often improves the accuracy (ambient temperature, humidity, pressure and differential pressure) but they are not always available; the introduction of ordinal variables is studied: four ordinal variables allow to introduce the double seasonality of solar irradiation. The performances of two forecasting models (linear and nonlinear models) with combinations of endogenous, exogenous and ordinal variables are compared on two Algerian sites with different meteorological variabilities. It appears that adding ordinal variables to endogenous data decreases the nRMSE values and enables to reach the same level of reliability than adding exogenous variables while simplifying the implementation. This addition as inputs in ANN models decreased nRMSE by 0.45–1.65% points (2.6–6.2%) for Algiers and by 0.2–0.3% point (1–3%) for Ghardaïa according to the forecasting horizon. [ABSTRACT FROM AUTHOR]

The paper aims to solve drawbacks associated with Gas Turbine GT by integrating a novel cascaded system into a combined cycle simultaneously. Parabolic trough collectors preheat the air at the combustion chamber inlet, then drive an absorption inlet-air cooling cycle that controls the ambient-air temperature at the compressor's inlet. This study uses the 2nd law of thermodynamics to estimate the maximum available energy, calculate the electric exergy efficiency, and explore the maximum irreversible exergy destruction in the system's components. Artificial Neural Network was employed to develop a multi-objective optimization by linking data collected from equations in the Engineering Equation Solver software with Matlab. Spider diagrams investigated the effect of varying several key operating parameters on the performance of the system, identifying gas turbine as the highest irreversibility sub-unit and the solar field parabolic trough collectors as the second. Design improvement for the combustion chamber can reduce 303.6 MW, and for parabolic trough collectors field reduce 58.9 MW. Artificial neural networks with multi-objective optimization maximized the electric exergy destruction to 46.19% and minimized the exergy destruction to 489.4 MW, relative to the corresponding values from the simple design point. • A Novel configuration was proposed and optimized in terms of exergy. • Improved exergy efficiency and reduced exergy destruction were accomplished. • Spider diagrams revealed operating parameters' effect on the model's performance. • A parametric study is used to train, test, and validate an ANN. • The ANN is employed to perform prediction and optimization. [ABSTRACT FROM AUTHOR]

Spatiotemporal assessment of solar potential is one of the most promising solutions to find suitable locations for future photovoltaic systems' placement. However, accurate assessment of solar potential on large areas can be challenging due to missing data or computational complexity. In this paper, a fully convolutional neural network based method for high-resolution spatiotemporal assessment of solar potential by using remote sensing data is presented. The method is trained and validated on the area of 32 km2 of the Maribor city, Slovenia, and tested on the 6 different locations in Slovenia and Germany. The proposed method was tested against the simulation algorithm, which utilized isotropic Liu Jordan diffuse model or anisotropic Perez model with sky view factor based shading. On average, a normalized root mean square error (NRMSE) of 6.06% and mean absolute percentage error (MAPE) of 4.29% was achieved in test locations against the simulation based on Liu-Jordan model. When training the fully convolutional neural network models against the ground truth, generated with more advanced Perez diffuse model, the average NRMSE was 8.37% and MAPE of 10.90% was achieved across all test locations. Additionally, it was shown that the proposed method can assess solar potential in high-resolution from the input in lower resolution with higher accuracy than the simulation algorithm, while being up to 1500-times faster. [ABSTRACT FROM AUTHOR]

Spatiotemporal assessment of solar potential is one of the most promising solutions to find suitable locations for future photovoltaic systems' placement. However, accurate assessment of solar potential on large areas can be challenging due to missing data or computational complexity. In this paper, a fully convolutional neural network based method for high-resolution spatiotemporal assessment of solar potential by using remote sensing data is presented. The method is trained and validated on the area of 32 km2 of the Maribor city, Slovenia, and tested on the 6 different locations in Slovenia and Germany. The proposed method was tested against the simulation algorithm, which utilized isotropic Liu Jordan diffuse model or anisotropic Perez model with sky view factor based shading. On average, a normalized root mean square error (NRMSE) of 6.06% and mean absolute percentage error (MAPE) of 4.29% was achieved in test locations against the simulation based on Liu-Jordan model. When training the fully convolutional neural network models against the ground truth, generated with more advanced Perez diffuse model, the average NRMSE was 8.37% and MAPE of 10.90% was achieved across all test locations. Additionally, it was shown that the proposed method can assess solar potential in high-resolution from the input in lower resolution with higher accuracy than the simulation algorithm, while being up to 1500-times faster. [ABSTRACT FROM AUTHOR]

This paper presents a data-driven wind farm layout optimization framework that uses a machine learning wake model that considers physical control stages. The machine learning wake model is trained using well-validated Computational Fluid Dynamics (CFD) simulation data, and consists of thousands of sub-models, each of which is an artificial neural network (ANN) wake model. The ANN wake models are trained separately for low-speed and high-speed inflows to ensure high accuracy of the predictions, with less than 2% error compared to CFD simulations. The accuracy and efficiency of the framework are validated, and the results show better agreement with CFD simulation than an analytical wake model developed in recent years. A parametric study on the number of wind turbines in the Horns Rev wind farm demonstrates that more wind turbines can be added with a minor decrease in average power, with more even and staggered layouts. Under full-wake uniform inflow, the selected analytical wake model exhibits a power prediction error of 5%–8%, while the differences between optimal layouts searched by different wake models range from 2% to 8%. When introducing a wider range of inflow direction sectors, the discrepancy between optimal layout performances decreases. [ABSTRACT FROM AUTHOR]

This paper addresses the torque and pitch control problems of wind turbines. The main contribution of this work is the development of an innovative reinforcement learning (RL)-based control method targeting wind turbine applications. Our RL-based control framework synergistically combines the advantages of deep neural networks (DNNs) and model predictive control (MPC) technologies. The proposed control strategy is data-driven, adapting to real-time changes in system dynamics and enhancing control performance and robustness. Additionally, the incorporation of an MPC structure within our design improves learning efficiency and reduces the high computational complexity typically found in deep RL algorithms. Specifically, a DNN is designed to approximate the wind turbine dynamics based on a continuously updated dataset composed of state and action measurements taken at specified sampling intervals. The real-time control policy is generated by integrating the online trained DNN into an MPC architecture. The proposed method iteratively updates the DNN and control policy in real-time to optimize performance. As a primary result of this work, the proposed method demonstrates superior robustness and control performance compared to commonly-employed MPC and other baseline wind turbine controllers in the presence of uncertainties and unexpected actuator faults. This effectiveness is showcased through simulations with a high-fidelity wind turbine simulator. • A novel reinforcement learning-based wind turbine control method is developed. • The proposed method is data-driven without relying on analytical turbine models. • This method shows better performance under uncertainties and actuator faults. [ABSTRACT FROM AUTHOR]