Search

To solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross validation (RFECV) algorithm and time convolution network–efficient channel attention mechanism–long short-term memory network (TCN–ECA–LSTM) is presented. First, the load sequence is decomposed into a relatively stable set of modal components using variational mode decomposition. Then, the RFECV-based method filters the feature set of each modal component to construct the best feature set. Finally, a two-stage prediction model based on TCN–ECA–LSTM is established. The first stage predicts each modal component and the second stage reconstructs the load forecast based on the predicted value of the previous stage. This paper takes actual data from New South Wales, Australia, as an example, and the results show that the method proposed in this paper can build the feature set reliably and efficiently and has a higher accuracy than the conventional prediction model. [ABSTRACT FROM AUTHOR]

The current power load exhibits strong nonlinear and stochastic characteristics, increasing the difficulty of short-term prediction. To more accurately capture data features and enhance prediction accuracy and generalization ability, in this paper, we propose an efficient approach for short-term electric load forecasting that is grounded in a synergistic strategy of feature optimization and hyperparameter tuning. Firstly, a dynamic adjustment strategy based on the rate of the change of historical optimal values is introduced to enhance the PID-based Search Algorithm (PSA), enabling the real-time adjustment and optimization of the search process. Subsequently, the proposed Improved Population-based Search Algorithm (IPSA) is employed to achieve the optimal adaptive variational mode decomposition of the load sequence, thereby reducing data volatility. Next, for each load component, a Bi-directional Gated Recurrent Unit network with an attention mechanism (BiGRU-Attention) is established. By leveraging the interdependence between feature selection and hyperparameter optimization, we propose a synergistic optimization strategy based on the Improved Population-based Search Algorithm (IPSA). This approach ensures that the input features and hyperparameters for each component's predictive model achieve an optimal combination, thereby enhancing prediction performance. Finally, the optimal parameter prediction model is used for multi-step rolling forecasting, with the final prediction values obtained through superposition and reconstruction. The case study results indicate that this method can achieve an adaptive optimization of hybrid prediction model parameters, providing superior prediction accuracy compared to the commonly used methods. Additionally, the method demonstrates robust adaptability to load forecasting across various day types and seasons. Consequently, this approach enhances the accuracy of short-term load forecasting, thereby supporting more efficient power scheduling and resource allocation. [ABSTRACT FROM AUTHOR]

The rising adoption of electric vehicles (EVs), driven by carbon neutrality goals, has prompted the need for accurate forecasting of EVs' charging behavior. However, this task presents several challenges due to the dynamic nature of EVs' usage patterns, including fluctuating demand and unpredictable charging durations. In response to these challenges and different from previous works, this paper presents a novel and holistic methodology for day-ahead forecasting of EVs' plugged-in status and power consumption in charging stations (CSs). The proposed framework encompasses data analysis, pre-processing, feature engineering, feature selection, the use and comparison of diverse machine learning forecasting algorithms, and validation. A real-world dataset from a CS in Boulder City is employed to evaluate the framework's effectiveness, and the results demonstrate its proficiency in predicting the EVs' plugged-in status, with XGBoost's classifier achieving remarkable accuracy with an F1-score of 0.97. Furthermore, an in-depth evaluation of six regression methods highlighted the supremacy of gradient boosting algorithms in forecasting the EVs' power consumption, with LightGBM emerging as the most effective method due to its optimal balance between prediction accuracy with a 4.22% normalized root-mean-squared error (NRMSE) and computational efficiency with 5 s of execution time. The proposed framework equips power system operators with strategic tools to anticipate and adapt to the evolving EV landscape. [ABSTRACT FROM AUTHOR]

For the advancement of smart grids, solar power generation predictions have become an important research topic. In the case of using traditional modeling methods, excessive computational costs may be incurred and it is difficult for these methods to learn the multi-variable dependencies of the data. Therefore, in this paper, a deep learning model was used to combine convolutional neural networks and long short-term memory recurrent network predictions. This method enables hourly power generation one day into the future. Convolutional neural networks are used to extract the features of multiple time series, while long short-term memory neural networks predict multivariate outcomes simultaneously. In order to obtain more accurate prediction results, we performed feature selection on meteorological features and combined the selected weather features to train the prediction model. We further distinguished sunny- and rainy-day models according to the predicted daily rainfall conditions. In the experiment, it was shown that the method of combining meteorological features further reduced the error. Finally, taking into account the differences in climate conditions between the northern and southern regions of Taiwan, the experimental results of case studies involving multiple regions were evaluated to verify the proposed method. The results showed that training combined with selected meteorological features can be widely used in regions with different climates in Taiwan. [ABSTRACT FROM AUTHOR]

Accurate prediction of energy consumption in district heating systems plays an important role in supporting effective and clean energy production and distribution in dense urban areas. Predictive models are needed for flexible and cost-effective operation of energy production and usage, e.g., using peak shaving or load shifting to compensate for heat losses in the pipeline. This helps to avoid exceedance of power plant capacity. The purpose of this study is to automate the process of building machine learning (ML) models to solve a short-term power demand prediction problem. The dataset contains a district heating network's measured hourly power consumption and ambient temperature for 415 days. In this paper, we propose a hybrid evolutionary-based algorithm, named GA-SHADE, for the simultaneous optimization of ML models and feature selection. The GA-SHADE algorithm is a hybrid algorithm consisting of a Genetic Algorithm (GA) and success-history-based parameter adaptation for differential evolution (SHADE). The results of the numerical experiments show that the proposed GA-SHADE algorithm allows the identification of simplified ML models with good prediction performance in terms of the optimized feature subset and model hyperparameters. The main contributions of the study are (1) using the proposed GA-SHADE, ML models with varying numbers of features and performance are obtained. (2) The proposed GA-SHADE algorithm self-adapts during operation and has only one control parameter. There is no fine-tuning required before execution. (3) Due to the evolutionary nature of the algorithm, it is not sensitive to the number of features and hyperparameters to be optimized in ML models. In conclusion, this study confirms that each optimized ML model uses a unique set and number of features. Out of the six ML models considered, SVR and NN are better candidates and have demonstrated the best performance across several metrics. All numerical experiments were compared against the measurements and proven by the standard statistical tests. [ABSTRACT FROM AUTHOR]

There are many influencing factors present in different situations of power load. There is also a strong imbalance in the number of load samples. In addition to examining the problem of low training efficiency of existing algorithms, this paper proposes a short-term power load prediction method based on feature selection and error compensation under imbalanced samples. After clustering the load data, we expand some sample data to balance the sample categories and input the load data and filtered feature sequences into the improved GRU for prediction. At the same time, the errors generated during the training process are used as training data. An error correction model is constructed and trained, and the results are used for error compensation to further improve prediction accuracy. The experimental results show that the overall prediction accuracy of the model has increased by 80.24%. After expanding a few samples, the prediction accuracy of the region where the samples are located increased by 59.41%. Meanwhile, due to the improvement of the algorithms, the running time was reduced by approximately 14.92%. [ABSTRACT FROM AUTHOR]

Predictive modeling is important for assessing and reducing energy consumption and CO2 emissions of light-duty vehicles (LDVs). However, LDV emission datasets have not been fully analyzed, and the rich features of the data pose challenges in prediction. This study aims to conduct a comprehensive analysis of the CO2 emission data for LDVs and investigate key prediction model characteristics for the data. Vehicle features in the data are analyzed for their correlations and impact on emissions and fuel consumption. Linear and non-linear models with feature selection are assessed for accuracy and consistency in prediction. The main behaviors of the predictive models are analyzed with respect to vehicle data. The results show that the linear models can achieve good prediction performance comparable to that of nonlinear models and provide superior interpretability and reliability. The non-linear generalized additive models exhibit enhanced accuracy but display varying performance with model and parameter choices. The results verify the strong impact of fuel consumption and powertrain attributes on emissions and their substantial influence on the prediction models. The paper uncovers crucial relationships between vehicle features and CO2 emissions from LDVs. These findings provide insights for model and parameter selections for effective and reliable prediction of vehicle emissions and fuel consumption. [ABSTRACT FROM AUTHOR]

Compared with the pole-to-pole short circuit, the fault characteristics are not obvious when a monopolar grounding fault occurs in a DC distribution network, and it is difficult to locate the fault accurately. To solve this problem, this paper proposes a fault location method based on improved ReliefF and Weighted random forest (WRF). The 24 time and frequency-domain fault features of the postfault aerial mode current are calculated, and the most useful features are selected to form the optimal feature subset for input to the fault location estimator. In this paper, the ReliefF algorithm is utilized for automatic feature selection and obtaining the weights of features. In addition, the WRF algorithm is used to build the fault location estimator. Considering the fault location, fault resistance, noise and time window length, the Matlab/Simulink simulation platform is used to simulate the fault situation and compare it with other algorithms. The simulation results show that the average positioning error of the fault location method is less than 0.1%, which is not affected by the fault resistance and has strong robustness. [ABSTRACT FROM AUTHOR]

Electricity prices are a central element of the electricity market, and accurate electricity price forecasting is critical for market participants. However, in the context of increasingly integrated economic markets, the complexity of the electricity system has increased. As a result, the number of factors required to consider in electricity price forecasting is growing. In addition, the high percentage of renewable energy penetration has increased the volatility of electricity generation, making it more challenging to predict prices accurately. In this paper, we propose a probabilistic forecasting method based on SHAP (SHapley Additive exPlanation) feature selection and LSTNet (long- and short-term time-series network) quantile regression. First, to reduce feature redundancy and overfitting, we use the SHAP method to perform feature selection in a high-dimensional input feature set, and specifically analyze the magnitude and manner in which features affect electricity prices. Second, we apply the LSTNet quantile regression model to predict the electricity value under different quantiles. Finally, the probability density function and the prediction interval of the predicted electricity prices are obtained by kernel density estimation. The case of the Danish electricity market validates the effectiveness and accuracy of our proposed method. The accuracy of the proposed method is better than that of other methods, and we assess the importance and direction of the impact of features on electricity prices. [ABSTRACT FROM AUTHOR]

The rising interest in the security of network infrastructure, including edge devices, the Internet of Things, and smart grids, has led to the development of numerous machine learning-based approaches that promise improvement to existing threat detection solutions. Among the popular methods to ensuring cybersecurity is the use of data science techniques and big data to analyse online threats and current trends. One important factor is that these techniques can identify trends, attacks, and events that are invisible or not easily detectable even to a network administrator. The goal of this paper is to suggest the optimal method for feature selection and to find the most suitable method to compare results between different studies in the context of imbalance datasets and threat detection in ICT. Furthermore, as part of this paper, the authors present the state of the data science discipline in the context of the ICT industry, in particular, its applications and the most frequently employed methods of data analysis. Based on these observations, the most common errors and shortcomings in adopting best practices in data analysis have been identified. The improper usage of imbalanced datasets is one of the most frequently occurring issues. This characteristic of data is an indispensable aspect in the case of the detection of infrequent events. The authors suggest several solutions that should be taken into account while conducting further studies related to the analysis of threats and trends in smart grids. [ABSTRACT FROM AUTHOR]

Lithium-ion batteries play a vital role in many systems and applications, making them the most commonly used battery energy storage systems. Optimizing their usage requires accurate state-of-health (SoH) estimation, which provides insight into the performance level of the battery and improves the precision of other diagnostic measures, such as state of charge. In this paper, the classical machine learning (ML) strategies of multiple linear and polynomial regression, support vector regression (SVR), and random forest are compared for the task of battery SoH estimation. These ML strategies were selected because they represent a good compromise between light computational effort, applicability, and accuracy of results. The best results were produced using SVR, followed closely by multiple linear regression. This paper also discusses the feature selection process based on the partial charging time between different voltage intervals and shows the linear dependence of these features with capacity reduction. The feature selection, parameter tuning, and performance evaluation of all models were completed using a dataset from the Prognostics Center of Excellence at NASA, considering three batteries in the dataset. [ABSTRACT FROM AUTHOR]

The paper presents a novel approach for predicting battery energy consumption in electric city buses (e-buses) by means of a trip-based data-driven regression model. The model was parameterized based on the data collected by running a physical experimentally validated e-bus simulation model, and it consists of powertrain and heating, ventilation, and air conditioning (HVAC) system submodels. The main advantage of the proposed approach is its reliance on readily available trip-related data, such as travel distance, mean velocity, average passenger count, mean and standard deviation of road slope, and mean ambient temperature and solar irradiance, as opposed to the physical model, which requires high-sampling-rate driving cycle data. Additionally, the data-driven model is executed significantly faster than the physical model, thus making it suitable for large-scale city bus electrification planning or online energy consumption prediction applications. The data-driven model development began with applying feature selection techniques to identify the most relevant set of model inputs. Machine learning methods were then employed to achieve a model that effectively balances accuracy, simplicity, and interpretability. The validation results of the final eight-input quadratic-form e-bus model demonstrated its high precision and generalization, which was reflected in the R2 value of 0.981 when tested on unseen data. Owing to the trip-based, mean-value formulation, the model executed six orders of magnitude faster than the physical model. [ABSTRACT FROM AUTHOR]

This paper aims to improve the forecasting of electricity market prices by incorporating the characteristics of electricity market prices that are discretely affected by the fuel cost per unit, the unit generation cost of the large-scale generators, and the demand. In this paper, two new techniques are introduced. The first technique applies feature generation to the label and forecasts the transformed new variables, which are then post-processed by inverse transformation, considering the characteristic of the fuel types of marginal generators or prices through two variables: fuel cost per unit by the representative fuel type and argument of the maximum of Probability Density Function (PDF) calculated by Kernel Density Estimation (KDE) from the previous price. The second technique applies decomposition to the demand, followed by a feature selection process to apply the major decomposed feature. It is verified using gain or SHapley Additive exPlanations (SHAP) value in the feature selection process. In the case study, both showed improvement in all indicators. In the Korean Electricity Market, the unit generation cost for each generator is calculated monthly, resulting in a step-wise change in the electricity market price depending on the monthly fuel cost. Feature generation using the fuel cost per unit improved the forecasting by eliminating monthly volatility caused by the fuel costs and reducing the error that occurs at the beginning of the month. It improved the Mean Squared Percentage Error (MAPE) of 3.83[%]. Using the argument of the maximum PDF calculated by KDE improved the forecasting during the test period, where discrete monthly variations were not included. The resulting MAPE was 3.82[%]. Combining these two techniques resulted in the most accurate performance compared to the other techniques used, which had a MAPE of 3.49[%]. The MAPE of the forecasting with the decomposed data of the original price was 4.41[%]. [ABSTRACT FROM AUTHOR]

Most traditional artificial intelligence-based fault location methods are very dependent on fault signal selection and feature extraction, which is often based on prior knowledge. Further, these methods are usually very sensitive to line parameters and selected fault characteristics, so the generalization performance is poor and cannot be applied to different lines. In order to solve the above problems, this paper proposes a two-terminal fault location fusion model, which combines a convolutional neural network (CNN), an attention module (AM), and multi-head long short-term memory (multi-head-LSTM). First, the CNN is used to accomplish the self-extraction of fault data features. Second, the CBAM (convolutional block attention module) model is embedded into the convolutional neural network to selectively learn fault features autonomously. Furthermore, the LSTM is combined to learn the deep timing characteristics. Finally, a MLP output layer is used to determine the optimal weights to construct a fusion model based on the results of the two-terminal relative fault location model and then output the final location result. Simulation studies show that this method has a high location accuracy, does not require the design of complex feature extraction algorithms, and exhibits good generalization performance for lines with different parameters, which is of great importance for the development of AI-based methods of fault location. [ABSTRACT FROM AUTHOR]

The goal of this work is to give a full review of how machine learning (ML) is used in thermal comfort studies, highlight the most recent techniques and findings, and lay out a plan for future research. Most of the researchers focus on developing models related to thermal comfort prediction. However, only a few works look at the current state of adaptive thermal comfort studies and the ways in which it could save energy. This study showed that using ML control schemas to make buildings more comfortable in terms of temperature could cut energy by more than 27%. Finally, this paper identifies the remaining difficulties in using ML in thermal comfort investigations, including data collection, thermal comfort indices, sample size, feature selection, model selection, and real-world application. [ABSTRACT FROM AUTHOR]

The protection of users of ICT networks, including smart grids, is a challenge whose importance is constantly growing. Internet of Things (IoT) or Internet of Energy (IoE) devices, as well as network resources, store more and more information about users. Large institutions use extensive security systems requiring large and expensive resources. For smart grid users, this becomes difficult. Efficient methods are needed to take advantage of limited sets of traffic features. In this paper, machine learning techniques to verify network events for recognition of Internet threats were analyzed, intentionally using a limited number of parameters. The authors considered three machine learning techniques: Long Short-Term Memory, Isolation Forest, and Support Vector Machine. The analysis is based on two datasets. In the paper, the data preparation process is also described. Eight series of results were collected and compared with other studies. The results showed significant differences between the techniques, the size of the datasets, and the balance of the datasets. We also showed that a more accurate classification could be achieved by increasing the number of analyzed features. Unfortunately, each increase in the number of elements requires more extensive analysis. The work ends with a description of the steps that can be taken in the future to improve the operation of the models and enable the implementation of the described methods of analysis in practice. [ABSTRACT FROM AUTHOR]

The increasing penetration of distributed generation (DG) to power distribution networks mainly induces weaknesses in the sensitivity and selectivity of protection systems. In this manner, conventional protection systems often fail to protect active distribution networks (ADN) in the case of short-circuit faults. To overcome these challenges, the accurate detection of faults in a reasonable fraction of time appears as a critical issue in distribution networks. Machine learning techniques are capable of generating efficient analytical expressions that can be strong candidates in terms of reliable and robust fault detection for several operating scenarios of ADNs. This paper proposes a deep group method of data handling (GMDH) neural network based on a non-pilot protection method for the protection of an ADN. The developed method is independent of the DG capacity and achieves accurate fault detection under load variations, disturbances, and different high-impedance faults (HIFs). To verify the improvements, a test system based on a real distribution network that includes three generators with a capacity of 6 MW is utilized. The extensive simulations of the power network are performed using DIgSILENT Power Factory and MATLAB software. The obtained results reveal that a mean absolute percentage error (MAPE) of 3.51% for the GMDH-network-based protection system is accomplished thanks to formulation via optimized algorithms, without requiring the utilization of any feature selection techniques. The proposed method has a high-speed operation of around 20 ms for the detection of faults, while the conventional OC relay performance is in the blinding mode in the worst situations for faults with HIFs. [ABSTRACT FROM AUTHOR]

Lithium-ion batteries are a key technology for the electrification of the transport sector and the corresponding move to renewable energy. It is vital to determine the condition of lithium-ion batteries at all times to optimize their operation. Because of the various loading conditions these batteries are subjected to and the complex structure of the electrochemical systems, it is not possible to directly measure their condition, including their state of charge. Instead, battery models are used to emulate their behavior. Data-driven models have become of increasing interest because they demonstrate high levels of accuracy with less development time; however, they are highly dependent on their database. To overcome this problem, in this paper, the use of a data augmentation method to improve the training of artificial neural networks is analyzed. A linear regression model, as well as a multilayer perceptron and a convolutional neural network, are trained with different amounts of artificial data to estimate the state of charge of a battery cell. All models are tested on real data to examine the applicability of the models in a real application. The lowest test error is obtained for the convolutional neural network, with a mean absolute error of 0.27%. The results highlight the potential of data-driven models and the potential to improve the training of these models using artificial data. [ABSTRACT FROM AUTHOR]

This paper proposes a novel network anomaly detection framework based on data balance and feature selection. Different from the previous binary classification of network intrusion, the network anomaly detection strategy proposed in this paper solves the problem of multiple classification of network intrusion. Regarding the common data imbalance of a network intrusion detection set, a resampling strategy generated by random sampling and Borderline SMOTE data is developed for data balance. According to the features of the intrusion detection dataset, feature selection is carried out based on information gain rate. Experiments are carried out on three basic machine learning algorithms (K-nearest neighbor algorithm (KNN), decision tree (DT), random forest (RF)), and the optimal feature selection scheme is obtained. [ABSTRACT FROM AUTHOR]

This paper aims to develop a machine-learning model based on a gradient-boosting algorithm to predict the energy-saving awareness of households using a questionnaire survey and 11-month energy data collected from more than 200 smart houses in Kitakyushu, Japan. We utilize the LightGBM (light gradient boosting machine) classifier to perform feature selection for the prediction. By using this approach, we demonstrate that the key features are the standard deviations of electricity purchased between 8 a.m. and 9 a.m. and electricity consumed between 7 p.m. and 9 p.m. Next, by using k-means clustering we split the households based on the obtained features into three groups. Finally, by using statistical hypothesis testing, we prove that these three groups have statistically distinct levels of energy-saving awareness. This model enables us to detect eco-friendly households from their energy data, which may support energy policymaking. [ABSTRACT FROM AUTHOR]

Sustainable energy systems rely on energy yield from renewable resources such as solar radiation and wind, which are typically not on-demand and need to be stored or immediately consumed. Solar irradiance is a highly stochastic phenomenon depending on fluctuating atmospheric conditions, in particular clouds and aerosols. The complexity of weather conditions in terms of many variable parameters and their inherent unpredictability limit the performance and accuracy of solar power forecasting models. As renewable power penetration in electricity grids increases due to the rapid increase in the installation of photovoltaics (PV) systems, the resulting challenges are amplified. A regional PV power prediction system is presented and evaluated by providing forecasts up to 72 h ahead with an hourly time resolution. The proposed approach is based on a local radiation forecast model developed by Blue Sky. In this paper, we propose a novel method of deriving forecast equations by using an irradiance classification approach to cluster the dataset. A separate equation is derived using the GEKKO optimization tool, and an algorithm is assigned for each cluster. Several other linear regressions, time series and machine learning (ML) models are applied and compared. A feature selection process is used to select the most important weather parameters for solar power generation. Finally, considering the prediction errors in each cluster, a weighted average and an average ensemble model are also developed. The focus of this paper is the comparison of the capability and performance of statistical and ML methods for producing a reliable hourly day-ahead forecast of PV power by applying different skill scores. The proposed models are evaluated, results are compared for different models and the probabilistic time series forecast is presented. Results show that the irradiance classification approach reduces the forecasting error by a considerable margin, and the proposed GEKKO optimized model outperforms other machine learning and ensemble models. These findings also emphasize the potential of ML-based methods, which perform better in low-power and high-cloud conditions, as well as the need to build an ensemble or hybrid model based on different ML algorithms to achieve improved projections. [ABSTRACT FROM AUTHOR]

A hybrid feature selection (HFS) algorithm to obtain the optimal feature set to attain optimal forecast accuracy for short-term load forecasting (STLF) problems is proposed in this paper. The HFS employs an elitist genetic algorithm (EGA) and random forest method, which is embedded in the load forecasting algorithm for online feature selection (FS). Using selected features, the performance of the forecaster was tested to signify the utility of the proposed methodology. For this, a day-ahead STLF using the M5P forecaster (a comprehensive forecasting approach using the regression tree concept) was implemented with FS and without FS (WoFS). The performance of the proposed forecaster (with FS and WoFS) was compared with the forecasters based on J48 and Bagging. The simulation was carried out in MATLAB and WEKA software. Through analyzing short-term load forecasts for the Australian electricity markets, evaluation of the proposed approach indicates that the input feature selected by the HFS approach consistently outperforms forecasters with larger feature sets. [ABSTRACT FROM AUTHOR]

In low-voltage AC distribution systems, when a series arc fault occurs in a branch with multiple loads operating in parallel, it will be significantly more difficult to identify. Existing arc fault detection methods make it difficult to effectively detect faults occurring in the lower-level branch. This study introduces a novel series arc fault detection approach based on the improved northern goshawk optimization adaptive base class LogitBoost (INGO-ABCLogitBoost) algorithm. Considering the zero-rest, intermittent, and random fluctuation and high-frequency features of the arc current, the zero-rest coefficient, discrete coefficient, harmonic amplitude, and wavelet entropy are proposed to establish the high-dimensional feature matrix of the arc current. The ReliefF feature selection algorithm is used to optimize feature quality and decrease feature dimensionality. Subsequently, the ABCLogitBoost fault detection model is proposed, with the INGO algorithm applied to optimize the model parameters, thus enhancing the model's diagnostic capabilities. The efficacy of the proposed diagnostic model is validated through the construction of a multi-load arc simulation system. The simulation results show that the overall fault diagnosis accuracy of the proposed method reaches 99.01% and can effectively identify the fault load types, which helps to locate the fault location. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) has a significant role in reliable operation and efficient scheduling of power systems. However, it is still a major challenge to accurately predict power load due to social and natural factors, such as temperature, humidity, holidays and weekends, etc. Therefore, it is very important for the efficient feature selection and extraction of input data to improve the accuracy of STLF. In this paper, a novel hybrid model based on empirical mode decomposition (EMD), a one-dimensional convolutional neural network (1D-CNN), a temporal convolutional network (TCN), a self-attention mechanism (SAM), and a long short-term memory network (LSTM) is proposed to fully decompose the input data and mine the in-depth features to improve the accuracy of load forecasting. Firstly, the original load sequence was decomposed into a number of sub-series by the EMD, and the Pearson correlation coefficient method (PCC) was applied for analyzing the correlation between the sub-series with the original load data. Secondly, to achieve the relationships between load series and external factors during an hour scale and the correlations among these data points, a strategy based on the 1D-CNN and TCN is proposed to comprehensively refine the feature extraction. The SAM was introduced to further enhance the key feature information. Finally, the feature matrix was fed into the long short-term memory (LSTM) for STLF. According to experimental results employing the North American New England Control Area (ISO-NE-CA) dataset, the proposed model is more accurate than 1D-CNN, LSTM, TCN, 1D-CNN–LSTM, and TCN–LSTM models. The proposed model outperforms the 1D-CNN, LSTM, TCN, 1D-CNN–LSTM, and TCN–LSTM by 21.88%, 51.62%, 36.44%, 42.75%, 16.67% and 40.48%, respectively, in terms of the mean absolute percentage error. [ABSTRACT FROM AUTHOR]

Accurate solar radiation forecasting is essential to operate power systems safely under high shares of photovoltaic generation. This paper compares the performance of several machine learning algorithms for solar radiation forecasting using endogenous and exogenous inputs and proposes an ensemble feature selection method to choose not only the most related input parameters but also their past observations values. The machine learning algorithms used are: Support Vector Regression (SVR), Extreme Gradient Boosting (XGBT), Categorical Boosting (CatBoost) and Voting-Average (VOA), which integrates SVR, XGBT and CatBoost. The proposed ensemble feature selection is based on Pearson coefficient, random forest, mutual information and relief. Prediction accuracy is evaluated based on several metrics using a real database from Salvador, Brazil. Different prediction time-horizons are considered: 1 h, 2 h and 3 h ahead. Numerical results demonstrate that the proposed ensemble feature selection approach improves forecasting accuracy and that VOA performs better than the other algorithms in all prediction time horizons. [ABSTRACT FROM AUTHOR]

Increased focus on sustainability and energy decentralization has positively impacted the adoption of nanogrids. With the tremendous growth, load forecasting has become crucial for their daily operation. Since the loads of nanogrids have large variations with sudden usage of large household electrical appliances, existing forecasting models, majorly focused on lower volatile loads, may not work well. Moreover, abrupt operation of electrical appliances in a nanogrid, even for shorter durations, especially in "Peak Hours", raises the energy cost substantially. In this paper, an ANN model with dynamic feature selection is developed to predict the hour-ahead load of nanogrids based on meteorological data and a load lag of 1 h (t-1). In addition, by thresholding the predicted load against the average load of previous hours, peak loads, and their time indices are accurately identified. Numerical testing results show that the developed model can predict loads of nanogrids with the Mean Square Error (MSE) of 0.03 KW, the Mean Absolute Percentage Error (MAPE) of 9%, and the coefficient of variation (CV) of 11.9% and results in an average of 20% daily energy cost savings by shifting peak load to off-peak hours. [ABSTRACT FROM AUTHOR]

Integrating inverter-based generators in power systems introduces several challenges to conventional protection relays. The fault characteristics of these generators depend on the inverters' control strategy, which matters in the detection and classification of the fault. This paper presents a comprehensive machine-learning-based approach for detecting and classifying faults in transmission lines connected to inverter-based generators. A two-layer classification approach was considered: fault detection and fault type classification. The faults were comprised of different types at several line locations and variable fault impedance. The features from instantaneous three-phase current and voltages and calculated swing-center voltage (SCV) were extracted in time, frequency, and time–frequency domains. A photovoltaic (PV) and a Doubly-Fed Induction Generator (DFIG) wind farm plant were the considered renewable resources. The unbalanced data problem was investigated and mitigated using the synthetic minority class oversampling technique (SMOTE). The hyperparameters of the evaluated classifiers, namely decision trees (DT), Support Vector Machines (SVM), k-Nearest Neighbors (k-NN), and Ensemble trees, were optimized using the Bayesian optimization algorithm. The extracted features were reduced using several methods. The classification performance was evaluated in terms of the accuracy, specificity, sensitivity, and precision metrics. The results show that the data balancing improved the specificity of DT, SVM, and k-NN classifiers (DT: from 99.86% for unbalanced data to 100% for balanced data; SVM: from 99.28% for unbalanced data to 99.93% for balanced data; k-NN: from 99.64% for unbalanced data to 99.74% for balanced data). The forward feature selection combined with the Bag ensemble classifier achieved 100% accuracy, sensitivity, specificity, and precision for fault detection (binary classification), while the Adaboost ensemble classifier had the highest accuracy (99.4%), compared to the other classifiers when using the complete set of features. The classification models with the highest performance were further tested using a new dataset test case. They showed high detection and classification capabilities. The proposed approach was compared with the previous methodologies from the literature. [ABSTRACT FROM AUTHOR]

High precision short-term photovoltaic (PV) power prediction can reduce the damage associated with large-scale photovoltaic grid-connection to the power system. In this paper, a combination deep learning forecasting method based on variational mode decomposition (VMD), a fast correlation-based filter (FCBF) and bidirectional long short-term memory (BiLSTM) network is developed to minimize PV power forecasting error. In this model, VMD is used to extract the trend feature of PV power, then FCBF is adopted to select the optimal input-set to reduce the forecasting error caused by the redundant feature. Finally, the input-set is put into the BiLSTM network for training and testing. The performance of this model is tested by a case study using the public data-set provided by a PV station in Australia. Comparisons with common short-term PV power forecasting models are also presented. The results show that under the processing of trend feature extraction and feature selection, the proposed methodology provides a more stable and accurate forecasting effect than other forecasting models. [ABSTRACT FROM AUTHOR]

In fault detection and the diagnosis of large industrial systems, whose chemical processes usually exhibit complex, high-dimensional, time-varying and non-Gaussian characteristics, the classification accuracy of traditional methods is low. In this paper, a kernel limit learning machine (KELM) based on an adaptive variation sparrow search algorithm (AVSSA) is proposed. Firstly, the dataset is optimized by removing redundant features using the eXtreme Gradient Boosting (XGBOOST) model. Secondly, a new optimization algorithm, AVSSA, is proposed to automatically adjust the network hyperparameters of KELM to improve the performance of the fault classifier. Finally, the optimized feature sequences are fed into the proposed classifier to obtain the final diagnosis results. The Tennessee Eastman (TE) chemical process is used to verify the effectiveness of the proposed method through multidimensional diagnostic metrics. The results show that our proposed diagnosis method can significantly improve the accuracy of TE process fault diagnosis compared with traditional optimization algorithms. The average diagnosis rate for 21 faults was 91.00%. [ABSTRACT FROM AUTHOR]

This paper proposes an Intelligent Monitoring System (IMS) for Photovoltaic (PV) systems using affordable and cost-efficient hardware and also lightweight software that is capable of being easily implemented in different locations and having the capability to be installed in different types of PV power plants. IMS uses the Internet of Things (IoT) platform for handling data as well as Interoperability and Communication among the devices and components in the IMS. Moreover, IMS includes a personal cloud server for computing and storing the acquired data of PV systems. The IMS also consists of a web monitor system via some open-source and lightweight software that displays the information to multiple users. The IMS uses deep ensemble models for fault detection and power prediction in PV systems. A remarkable ability of the IMS is the prediction of the output power of the PV system to increase energy yield and identify malfunctions in PV plants. To this end, a long short-term memory (LSTM) ensemble neural network is developed to predict the output power of PV systems under different environmental conditions. On the other hand, the IMS uses machine learning-based models to detect numerous faults in PV systems. The fault diagnostic of IMS is based on the following stages. Firstly, major features are elicited through an analysis of Current–Voltage (I–V) characteristic curve under different faulty and normal events. Second, an ensemble learning model including Naive Bayes (NB), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM) is used for detecting and classifying fault events. To enhance the performance in the process of fault detection, a feature selection algorithm is also applied. A PV system has been designed and implemented for testing and validating the IMS under real conditions. IMS is an interoperable, scalable, and replicable solution for holistic monitoring of PV plant from data acquisition, storing, pre-and post-processing to malfunction and failure diagnosis, performance and energy yield assessment, and output power prediction. [ABSTRACT FROM AUTHOR]

In the current paper, a novel technique is represented to control the liquid petrochemical and petroleum products passing through a transmitting pipe. A simulation setup, including an X-ray tube, a detector, and a pipe, was conducted by Monte Carlo N Particle-X version (MCNPX) code to examine a two-by-two mixture of four diverse petroleum products (ethylene glycol, crude oil, gasoline, and gasoil) in various volumetric ratios. As the feature extraction system, twelve time characteristics were extracted from the received signal, and the most effective ones were selected using correlation analysis to present reasonable inputs for neural network training. Three Multilayers perceptron (MLP) neural networks were applied to indicate the volume ratio of three kinds of petroleum products, and the volume ratio of the fourth product can be feasibly achieved through the results of the three aforementioned networks. In this study, increasing accuracy was placed on the agenda, and an RMSE < 1.21 indicates this high accuracy. Increasing the accuracy of predicting volume ratio, which is due to the use of appropriate characteristics as the neural network input, is the most important innovation in this study, which is why the proposed system can be used as an efficient method in the oil industry. [ABSTRACT FROM AUTHOR]

Wind–solar towers are a relatively new method of capturing renewable energy from solar and wind power. Solar radiation is collected and heated air is forced to move through the tower. The thermal updraft propels a wind turbine to generate electricity. Furthermore, the top of the tower's vortex generators produces a pressure differential, which intensifies the updraft. Data were gathered from a wind–solar tower system prototype developed and established at Kyushu University in Japan. Aiming to predict the power output of the system, while knowing a set of features, the data were evaluated and utilized to build a regression model. Sensitivity analysis guided the feature selection process. Several machine learning models were utilized in this study, and the most appropriate model was chosen based on prediction quality and temporal criteria. We started with a simple linear regression model but it was inaccurate. By adding some non-linearity through using polynomial regression of the second order, the accuracy increased considerably sufficiently. Moreover, deep neural networks were trained and tested to enhance the power prediction performance. These networks performed very well, having the most powerful prediction capabilities, with a coefficient of determination R 2 = 0.99734 after hyper-parameter tuning. A 1-D convolutional neural network achieved less accuracy with R 2 = 0.99647 , but is still considered a competitive model. A reduced model was introduced trading off some accuracy ( R 2 = 0.9916 ) for significantly reduced data collection requirements and effort. [ABSTRACT FROM AUTHOR]

This work identifies the most effective machine learning techniques and supervised learning models to estimate power output from photovoltaic (PV) plants precisely. The performance of various regression models is analyzed by harnessing experimental data, including Random Forest regressor, Support Vector regression (SVR), Multi-layer Perceptron regressor (MLP), Linear regressor (LR), Gradient Boosting, k-Nearest Neighbors regressor (KNN), Ridge regressor (Rr), Lasso regressor (Lsr), Polynomial regressor (Plr) and XGBoost regressor (XGB). The methodology applied starts with meticulous data preprocessing steps to ensure dataset integrity. Following the preprocessing phase, which entails eliminating missing values and outliers using Isolation Feature selection based on a correlation threshold is performed to identify relevant parameters for accurate prediction in PV systems. Subsequently, Isolation Forest is employed for outlier detection, followed by model training and evaluation using key performance metrics such as Root-Mean-Squared Error (RMSE), Normalized Root-Mean-Squared Error (NRMSE), Mean Absolute Error (MAE), and R-squared (R2), Integral Absolute Error (IAE), and Standard Deviation of the Difference (SDD). Among the models evaluated, Random Forest emerges as the top performer, highlighting promising results with an RMSE of 19.413, NRMSE of 0.048%, and an R2 score of 0.968. Furthermore, the Random Forest regressor (the best-performing model) is integrated into a MATLAB application for real-time predictions, enhancing its usability and accessibility for a wide range of applications in renewable energy. [ABSTRACT FROM AUTHOR]

Growing dependence on fossil fuels is one of the critical factors accelerating climate change, a global concern that can destabilize ecosystems and economies worldwide. In this context, renewable energy is emerging as a sustainable and environmentally responsible alternative. Among the options, geothermal energy stands out for its ability to provide heat and electricity consistently and efficiently, offering a feasible solution to reduce the carbon footprint and promote more sustainable development in a globalized economy. In this work, a machine learning approach is proposed to predict the behavior of a horizontal heat exchanger from a bioclimatic house. First, a correlation analysis was conducted for optimal feature selection. Then, several regression techniques were applied to predict the output temperature of the geothermal exchanger. Satisfactory prediction results were obtained in different scenarios over the whole dataset. Also, a significant correlation between several sensors was concluded. [ABSTRACT FROM AUTHOR]

We propose a method for selecting the optimal set of weather features for wind energy prediction. This problem is tackled by developing a wrapper approach that employs binary differential evolution to search for the best feature subset, and an ensemble of artificial neural networks to predict the energy production from a wind plant. The main novelties of the approach are the use of features provided by different weather forecast providers and the use of an ensemble composed of a reduced number of models for the wrapper search. Its effectiveness is verified using weather and energy production data collected from a 34 MW real wind plant. The model is built using the selected optimal subset of weather features and allows for (i) a 1% reduction in the mean absolute error compared with a model that considers all available features and a 4.4% reduction compared with the model currently employed by the plant owners, and (ii) a reduction in the number of selected features by 85% and 50%, respectively. Reducing the number of features boosts the prediction accuracy. The implication of this finding is significant as it allows plant owners to create profitable offers in the energy market and efficiently manage their power unit commitment, maintenance scheduling, and energy storage optimization. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) plays a vital role in ensuring the safe, efficient, and economical operation of power systems. Accurate load forecasting provides numerous benefits for power suppliers, such as cost reduction, increased reliability, and informed decision-making. However, STLF is a complex task due to various factors, including non-linear trends, multiple seasonality, variable variance, and significant random interruptions in electricity demand time series. To address these challenges, advanced techniques and models are required. This study focuses on the development of an efficient short-term power load forecasting model using the random forest (RF) algorithm. RF combines regression trees through bagging and random subspace techniques to improve prediction accuracy and reduce model variability. The algorithm constructs a forest of trees using bootstrap samples and selects random feature subsets at each node to enhance diversity. Hyperparameters such as the number of trees, minimum sample leaf size, and maximum features for each split are tuned to optimize forecasting results. The proposed model was tested using historical hourly load data from four transformer substations supplying different campus areas of the University of Beira Interior, Portugal. The training data were from January 2018 to December 2021, while the data from 2022 were used for testing. The results demonstrate the effectiveness of the RF model in forecasting short-term hourly and one day ahead load and its potential to enhance decision-making processes in smart grid operations. [ABSTRACT FROM AUTHOR]

Feature selection helps improve the accuracy and computational time of solar forecasting. However, FS is often passed by or conducted with methods that do not suit the solar forecasting issue, such as filter or linear methods. In this study, we propose a wrapper method termed Sequential Forward Selection (SFS), with a Kernel Conditional Density Estimator (KCDE) named SFS-KCDE, as FS to forecast day-ahead regional PV power production in French Guiana. This method was compared to three other FS methods used in earlier studies: the Pearson correlation method, the RReliefF (RRF) method, and SFS using a linear regression. It has been shown that SFS-KCDE outperforms other FS methods, particularly for overcast sky conditions. Moreover, Wrapper methods show better forecasting performance than filter methods and should be used. [ABSTRACT FROM AUTHOR]

Fault diagnosis of induction motor anomalies is vital for achieving industry safety. This paper proposes a new hybrid Machine Learning methodology for induction-motor fault detection. Some of the motor parameters such as the stator currents and vibration signals provide a great deal of information about the motor's conditions. Therefore, these signals of the motor were selected to test the proposed model. The induction motor was assessed in a laboratory under healthy, mechanical, and electrical faults with different loadings. In this study a new hybrid model was developed using the collected signals, an optimal features selection mechanism is proposed, and machine learning classifiers were trained for fault classification. The procedure is to extract some statistical features from the raw signal using Matching Pursuit (MP) and Discrete Wavelet Transform (DWT). Then, the Invasive Weed Optimization algorithm (IWO)-based optimal subset was selected to reduce the data dimension and increase the average accuracy of the model. The optimal subset of features was fed into three classification algorithms: k-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Random Forest (RF), which were trained using k-fold cross-validation to distinguish between the induction motor faults. A similar strategy was performed by applying the Genetic Algorithm (GA) to compare with the performance of the proposed method. The suggested fault detection model's performance was evaluated by calculating the Receiver Operation Characteristic (ROC) curve, Specificity, Accuracy, Precision, Recall, and F1 score. The experimental results have proved the superiority of IWO for selecting the discriminant features, which has achieved more than 99.7% accuracy. The proposed hybrid model has successfully proved its robustness for diagnosing the faults under different load conditions. [ABSTRACT FROM AUTHOR]

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]

Critical infrastructures have recently been integrated with digital controls to support intelligent decision making. Although this integration provides various benefits and improvements, it also exposes the system to new cyberattacks. In particular, the injection of false data and commands into communication is one of the most common and fatal cyberattacks in critical infrastructures. Hence, in this paper, we investigate the effectiveness of machine-learning algorithms in detecting False Data Injection Attacks (FDIAs). In particular, we focus on two of the most widely used critical infrastructures, namely power systems and water treatment plants. This study focuses on tackling two key technical issues: (1) finding the set of best features under a different combination of techniques and (2) resolving the class imbalance problem using oversampling methods. We evaluate the performance of each algorithm in terms of time complexity and detection accuracy to meet the time-critical requirements of critical infrastructures. Moreover, we address the inherent skewed distribution problem and the data imbalance problem commonly found in many critical infrastructure datasets. Our results show that the considered minority oversampling techniques can improve the Area Under Curve (AUC) of GradientBoosting, AdaBoost, and kNN by 10–12%. [ABSTRACT FROM AUTHOR]

The paper proposes a novel hybrid feature selection (FS) method for day-ahead electricity price forecasting. The work presents a novel hybrid FS algorithm for obtaining optimal feature set to gain optimal forecast accuracy. The performance of the proposed forecaster is compared with forecasters based on classification tree and regression tree. A hybrid FS method based on the elitist genetic algorithm (GA) and a tree-based method is applied for FS. Making use of selected features, aperformance test of the forecaster was carried out to establish the usefulness of the proposed approach. By way of analyzing and forecasts for day-ahead electricity prices in the Australian electricity markets, the proposed approach is evaluated and it has been established that, with the selected feature, the proposed forecaster consistently outperforms the forecaster with a larger feature set. The proposed method is simulated in MATLAB and WEKA software. [ABSTRACT FROM AUTHOR]

Solar radiation prediction is an important process in ensuring optimal exploitation of solar energy power. Numerous models have been applied to this problem, such as numerical weather prediction models and artificial intelligence models. However, well-designed hybridization approaches that combine numerical models with artificial intelligence models to yield a more powerful model can provide a significant improvement in prediction accuracy. In this paper, novel hybrid machine learning approaches that exploit auxiliary numerical data are proposed. The proposed hybrid methods invoke different machine learning paradigms, including feature selection, classification, and regression. Additionally, numerical weather prediction (NWP) models are used in the proposed hybrid models. Feature selection is used for feature space dimension reduction to reduce the large number of recorded parameters that affect estimation and prediction processes. The rough set theory is applied for attribute reduction and the dependency degree is used as a fitness function. The effect of the attribute reduction process is investigated using thirty different classification and prediction models in addition to the proposed hybrid model. Then, different machine learning models are constructed based on classification and regression techniques to predict solar radiation. Moreover, other hybrid prediction models are formulated to use the output of the numerical model of Weather Research and Forecasting (WRF) as learning elements in order to improve the prediction accuracy. The proposed methodologies are evaluated using a data set that is collected from different regions in Saudi Arabia. The feature-reduction has achieved higher classification rates up to 8.5% for the best classifiers and up to 15% for other classifiers, for the different data collection regions. Additionally, in the regression, it achieved improvements of average root mean square error up to 5.6 % and in mean absolute error values up to 8.3%. The hybrid models could reduce the root mean square errors by 70.2% and 4.3% than the numerical and machine learning models, respectively, when these models are applied to some dataset. For some reduced feature data, the hybrid models could reduce the root mean square errors by 47.3% and 14.4% than the numerical and machine learning models, respectively. [ABSTRACT FROM AUTHOR]

Transient stability assessment (TSA) has always been a fundamental means for ensuring the secure and stable operation of power systems. Due to the integration of new elements such as power electronics, electric vehicles and renewable power generations, dynamic characteristics of power systems are becoming more and more complex, which makes TSA an increasingly urgent task. Since traditional time-domain simulations and direct method cannot meet the actual operation requirements of power systems, data-driven TSA has attracted growing attention from both academia and industry. This paper makes a comprehensive review from the following four aspects: feature extraction and selection, model construction, online learning and rule extraction; and then, summarizes the challenges and prospects for future research; finally, draws the conclusions of this review. This review will be beneficial for relevant researchers to better understand the research status, key technologies, and existing challenges in the field. [ABSTRACT FROM AUTHOR]

Decarbonizing buildings is crucial in addressing pressing climate change issues. Buildings significantly contribute to global greenhouse gas emissions, and reducing their carbon footprint is essential to achieving sustainable and low-carbon cities. Retrofitting buildings to become more energy efficient constitutes a solution. However, building energy retrofits are complex processes that require a significant number of simulations to investigate the possible options, which limits comprehensive investigations that become infeasible to carry out. Surrogate models can be vital in addressing computational inefficiencies by emulating physics-based models and predicting building performance. However, there is a limited focus on investigating feature engineering and selection methods and their effect on the model's performance and optimization. Feature selection methods are considered effective with interpretable models such as multi-variate linear regression (MVLR) and multiple adaptive regression splines (MARS) for achieving stable prediction stability. This study proposes a modelling framework to create, optimize, and improve the performance of surrogate predictive models for energy consumption, carbon emissions, and the associated cost of building energy retrofit processes. The investigated feature selection methods are wrapper and embedded methods such as backward-stepwise feature selection (BSFS), recursive feature elimination (RFE), and Elastic Net embedded regularization in order to provide insights into the model's behavior and optimize the model's performance. The most accurate surrogate models developed achieved a mean absolute percentage error (MAPE) of 0.2–1.8% compared to the used test data. In addition, when calculated for a million samples, all developed surrogate models reduced the computational time by one-thousand-fold compared to physics-based models. The study's findings pave the way towards low-computational accurate models that can comprehensively predict building performance in near real-time, ultimately leading to identifying decarbonization measures at scale. [ABSTRACT FROM AUTHOR]

Conventional numerical solutions and empirical formulae for predicting the initial productivity of oil wells in low-permeability reservoirs are limited to specific reservoirs and relatively simple scenarios. Moreover, the few influencing factors are less considered and the application model is more ideal. A productivity prediction method based on machine learning algorithms is established to improve the lack of application performance and incomplete coverage of traditional mathematical modelling for productivity prediction. A comprehensive analysis was conducted on the JY extra-low-permeability oilfield, considering its geological structure and various factors that may impact its extraction and production. The study collected 13 factors that influence the initial productivity of 181 wells. The Spearman correlation coefficient, ReliefF feature selection algorithm, and random forest selection algorithm were used in combination to rank the importance of these factors. The screening of seven main controlling factors was completed. The particle swarm optimization–extreme learning machine algorithm was adopted to construct the initial-productivity model. The primary control factors and the known initial productivity of 127 wells were used to train the model, which was then used to verify the initial productivity of the remaining 54 wells. In the particle swarm optimization–extreme learning machine (PSO-ELM) algorithm model, the root-mean-square error (RMSE) is 0.035 and the correlation factor (R2) is 0.905. Therefore, the PSO-ELM algorithm has a high accuracy and a fast computing speed in predicting the initial productivity. This approach will provide new insights into the development of initial-productivity predictions and contribute to the efficient production of low-permeability reservoirs. [ABSTRACT FROM AUTHOR]

Gas disasters threaten the safe operation of coal mines. Improving the accuracy of gas concentration predictions can effectively prevent gas disasters and reduce disaster losses. Traditional gas concentration prediction methods poorly couple the gas concentration and its influencing factors when dealing with a great number of features and data, which results in low prediction accuracy and poor efficiency. To solve this problem, we used an innovative Pearson-LSTM prediction model, which uses the Pearson coefficient to select features of gas concentration data. It then uses long short-term memory (LSTM) that has been optimized using adaptive moment estimation (Adam) to predict a time series. In the process of model establishment, the optimal prediction model was obtained by constantly adjusting the number of network layers and batch size based on the fitting effect, performance issues, and result errors. Taking monitoring data from the 2407 working face at Yuhua Coal Mine as the sample, we compared our method with the traditional Bi-RNN and GRU machine learning methods. The results show that, compared with the Bi-RNN and GRU models, the mean square error of the Pearson-LSTM model can be reduced to 0.015 with an error range of 0.005 to 0.04, which has higher prediction accuracy. This method has excellent precision and robustness for forecasting gas concentration time series. The model was able to make predictions 15 min in advance for the 2409 working face of the Yuhua Coal Mine, and the mean square error could be lowered to 0.008, which verifies the applicability and reliability of the model and provides a reference for ensuring the safety of coal mine operations. In summary, Pearson-LSTM models have higher accuracy and robustness and can effectively predict changes in gas concentration, thus allowing for more response time for accidents, which is important for coal mine production safety. [ABSTRACT FROM AUTHOR]

Optimization-based design tools for energy systems often require a large set of parameter assumptions, e.g., about technology efficiencies and costs or the temporal availability of variable renewable energies. Understanding the influence of all these parameters on the computed energy system design via direct sensitivity analysis is not easy for human decision-makers, since they may become overloaded by the multitude of possible results. We thus propose transferring an approach from explaining complex neural networks, so-called locally interpretable model-agnostic explanations (LIME), to this related problem. Specifically, we use variations of a small number of interpretable, high-level parameter features and sparse linear regression to obtain the most important local explanations for a selected design quantity. For a small bottom-up optimization model of a grid-connected building with photovoltaics, we derive intuitive explanations for the optimal battery capacity in terms of different cloud characteristics. For a larger application, namely a national model of the German energy transition until 2050, we relate path dependencies of the electrification of the heating and transport sector to the correlation measures between renewables and thermal loads. Compared to direct sensitivity analysis, the derived explanations are more compact and robust and thus more interpretable for human decision-makers. [ABSTRACT FROM AUTHOR]

Reservoir lithology identification is the basis for the exploration and development of complex lithological reservoirs. Efficient processing of well-logging data is the key to lithology identification. However, reservoir lithology identification through well-logging is still a challenge with conventional machine learning methods, such as Convolutional Neural Networks (CNN), and Long Short-term Memory (LSTM). To address this issue, a fully connected network (FCN) and LSTM were coupled for predicting reservoir lithology. The proposed algorithm (LSTM-FCN) is composed of two sections. One section uses FCN to extract the spatial properties, the other one captures feature selections by LSTM. Well-logging data from Hugoton Field is used to evaluate the performance. In this study, well-logging data, including Gamma-ray (GR), Resistivity (ILD_log10), Neutron-density porosity difference (DeltaPHI), Average neutron-density porosity(PHIND), and (Photoelectric effect) PE, are used for training and identifying lithology. For comparison, seven conventional methods are also proposed and trained, such as support vector machines (SVM), and random forest classifiers (RFC). The accuracy results indicate that the proposed architecture obtains better performance. After that, particle swarm optimization (PSO) is proposed to optimize hyper-parameters of LSTM-FCN. The investigation indicates the proposed PSO-LSTM-FCN model can enhance the performance of machine learning algorithms on identify the lithology of complex reservoirs. [ABSTRACT FROM AUTHOR]

For load forecasting, numerous machine learning (ML) approaches have been published. Besides fully connected feedforward neural networks (FFNNs), also called multilayer perceptron, more advanced ML approaches like deep, recurrent or convolutional neural networks or ensemble methods have been applied. However, evaluating the added benefit by novel approaches is difficult. Statistical or rule-based methods constitute a too low benchmark. FFNNs need extensive tuning due to their manifold design choices. To address this issue, a structured, comprehensible five-step FFNN model creation methodology is presented, which constitutes of initial model creation, internal parameter selection, feature engineering, architecture tuning and final model creation. The methodology is then applied to forecast real world heat load data of a hospital in Germany. The forecast constitutes of 192 values (upcoming 48 h in 15 min resolution) and is composed of a multi-model univariate forecasting strategy, with three test models developed at first. As a result, the test models show great similarities which simplifies creation of the remaining models. A performance increase of up to 18% between initial and final models points out the importance of model tuning. As a conclusion, comprehensible model tuning is vital to use FFNN models as benchmark. The effort needed can be reduced by the experience gained through repeated application of the presented methodology. [ABSTRACT FROM AUTHOR]

The analysis of reliable studies helps to identify the credibility, scope, and limitations of various techniques for condition monitoring of a wind turbine (WT) system's design and development to reduce the operation and maintenance (O&M) costs of the WT. In this study, recent advancements in data-driven models for condition monitoring and predictive maintenance of wind turbines' critical components (e.g., bearing, gearbox, generator, blade pitch) are reviewed. We categorize these models according to data-driven procedures, such as data descriptions, data pre-processing, feature extraction and selection, model selection (classification, regression), validation, and decision making. Our findings after reviewing extensive relevant articles suggest that (a) SCADA (supervisory control and data acquisition) data are widely used as they are available at low cost and are extremely practical (due to the 10 min averaging time), but their use is in some sense nonspecific. (b) Unstructured data and pre-processing remain a significant challenge and consume a significant time of whole machine learning model development. (c) The trade-off between the complexity of the vibration analysis and the applicability of the results deserves further development, especially with regards to drivetrain faults. (d) Most of the proposed techniques focus on gearbox and bearings, and there is a need to apply these models to other wind turbine components. We explain these findings in detail and conclude with a discussion of the main areas for future work in this domain. [ABSTRACT FROM AUTHOR]