Random forest (RF) is one of the most popular machine learning (ML) models used for both classification and regression problems. As an ensemble model, it demonstrates high predictive accuracy and low variance, while being easy to learn and optimize. In this study, we use RF for short-term load forecasting (STLF), focusing on data representation and training modes. We consider seven methods of defining input patterns and three training modes: local, global and extended global. We also investigate key RF hyperparameters to learn about their optimal settings. The experimental part of the work demonstrates on four STLF problems that our model, in its optimal variant, can outperform both statistical and ML models, providing the most accurate forecasts.

The aim of this paper is to present a novel approach to energy use forecasting. We propose a nested fuzzy cognitive map in which each concept at a higher level can be decomposed into another fuzzy cognitive map, multilayer perceptron artificial neural network or long short-term memory network. Historical data related to energy consumption are used to construct a nested fuzzy cognitive map in order to better understand energy use behavior. Through the experiments, the usefulness of the nested structure in energy demand prediction is demonstrated, by calculating three popular metrics: Mean Square Error, Mean Absolute Error and the correlation coefficient. A comparative analysis is performed, applying classic multilayer perceptron artificial neural networks, long short-term memory networks and fuzzy cognitive maps. The results confirmed that the proposed approach outperforms the classic methods in terms of prediction accuracy. Moreover, the advantage of the proposed approach is the abilit... [more]

Neural networks have been applied to seismic inversion problems since the 1990s. More recently, many publications have reported the use of Deep Learning (DL) neural networks capable of performing seismic inversion with promising results. However, when solving a seismic inversion problem with DL, each author uses, in addition to different DL models, different datasets and different metrics for performance evaluation, which makes it difficult to compare performances. Depending on the data used for training and the metrics used for evaluation, one model may be better or worse than another. Thus, it is quite challenging to choose the appropriate model to meet the requirements of a new problem. This work aims to review some of the proposed DL methodologies, propose appropriate performance evaluation metrics, compare the performances, and observe the advantages and disadvantages of each model implementation when applied to the chosen datasets. The publication of this benchmark environment wi... [more]

Renewable energy sources (RES) are currently the main alternative to fossil fuels and are also seen as an important contributor to slowing down the dangerous climate change on our planet. Energy supplied from renewable sources can reduce the consumption of primary raw materials and reduce emissions of harmful substances that enter the atmosphere in the process of producing electricity and heat, having a negative impact on the environment. This paper provides a multivariate comparative analysis of EU countries in terms of the use of renewable energy. The empirical research used seven variables defining the complex phenomenon under study, collected for 27 EU countries between 2011 and 2020. The research method used was the dynamic version of the non-model method, with a normalisation method based on zero unitarisation. The results of the study confirm that there was a positive change in the use of renewable energy in most EU countries between 2011 and 2020. High levels of renewable energ... [more]

This work focuses on the geometry effects over the performance of oscillating water column (OWC)-type wave energy converter (WEC) systems and searches for the OWC geometries that enhance the energy efficiencies under the same wave conditions. To analyze the hydrodynamic performances of the WEC systems, an in-house smoothed particle hydrodynamics (SPH) code based on weakly compressible fluid approach is utilized. The energy efficiency enhancement studies of the determined OWC device are carried out with a two-step geometry modification procedure. The first step starts with the validation of the free-surface elevation and orbital velocity time histories. Then, a three-by-three simulation matrix that depends on the geometrical design parameters of chamber length and front wall draft is run at three different wave conditions, and the OWC geometry that produces the maximum energy efficiency is determined. In the second step, the corner regions of the obtained optimal geometry are chamfered,... [more]

The large-scale, nonlinear and uncertain factors of hybrid power systems (HPS) have always been difficult problems in dynamic stability control. This research mainly focuses on the dynamic and transient stability performance of large HPS under various operating conditions. In addition to the traditional synchronous power generator, wind-driven generator and ocean wave generator, the hybrid system also adds battery energy storage system and unified power flow controller (UPFC), making the system more diversified and more consistent with the current actual operation mode of the complex power grid. The purpose of this study is to propose an adaptive least squares Petri fuzzy probabilistic neural network (ALTS-PFPNN) for UPFC installed in the power grid to enhance the behavior of HPS operation. The proposed scheme improves the active power adjustment and dynamic performance of the integrated wave power generation and offshore wind system under a large range of operating conditions. Through... [more]

This paper introduces a novel machine learning (ML) model for the lightning performance analysis of overhead distribution lines (OHLs), which facilitates a data-centrist and statistical view of the problem. The ML model is a bagging ensemble of support vector machines (SVMs), which introduces two significant features. Firstly, support vectors from the SVMs serve as a scaffolding, and at the same time give rise to the so-called curve of limiting parameters for the line. Secondly, the model itself serves as a foundation for the introduction of the statistical safety factor to the lightning performance analysis of OHLs. Both these aspects bolster an end-to-end statistical approach to the OHL insulation coordination and lightning flashover analysis. Furthermore, the ML paradigm brings the added benefit of learning from a large corpus of data amassed by the lightning location networks and fostering, in the process, a “big data” approach to this important engineering problem. Finally, a rela... [more]

Renewable energy penetration in the global energy sector is in a state of steady growth. A major criterion imposed by the regulatory boards in the wake of electronic-driven power systems is frequency regulation capability. As more rooftop PV systems are under installation, the inertia response of the power utility system is descending. The PV systems are not equipped inherently with inertial or governor control for unseen frequency deviation scenarios. In the proposed method, inertial and droop frequency control is implemented by creating the necessary power reserve by the derated operation of the PV system. While, traditionally, PV systems operate in normal MPPT mode, a derated PV system follows a flexible power point tracking (FPPT) algorithm for creating virtual energy storage. The point of operation for the FPPT of the PV is determined by using a neural network block set available in MATLAB. For the verification of the controller, it is applied to a PV array in a modified IEEE-13 b... [more]

This study develops a geometry adaptive, physical field predictor for the combined forced and natural convection flow of a nanofluid in horizontal single or double-inner cylinder annular pipes with various inner cylinder sizes and placements based on deep learning. The predictor is built with a convolutional-deconvolutional structure, where the input is the annulus cross-section geometry and the output is the temperature and the Nusselt number for the nanofluid-filled annulus. Profiting from the proven ability of dealing with pixel-like data, the convolutional neural network (CNN)-based predictor enables an accurate end-to-end mapping from the geometry input and the desired nanofluid physical field. Taking the computational fluid dynamics (CFD) calculation as the basis of our approach, the obtained results show that the average accuracy of the predicted temperature field and the coefficient of determination R2 are more than 99.9% and 0.998 accurate for single-inner cylinder nanofluid-f... [more]

In this research, we introduce an artificial gorilla troop optimizer for use in artificial neural networks that manage energy consumption in DC−AC hybrid distribution networks. It is being proposed to implement an energy management system that takes into account distributed generation, load demand, and battery-charge level. Using the profile data, an artificial neural network was trained on the charging and discharging characteristics of an energy storage system under a variety of distribution-network power situations. As an added bonus, the percentage of mistakes was maintained far below 10%. An artificial neural network is used in the proposed energy management system, and it has been taught to operate in the best possible manner by using an optimizer inspired by gorillas called artificial gorilla troops. The artificial gorilla troops optimizer optimize the weights and bias of the neural network based on the power of the distributed generator, the power of the grid, and the reference... [more]

Research in asymmetric light transmission interfaces has been recently gaining traction. While traditionally considered for optical circuitry applications, there is a new interest to use these interfaces in luminescent solar concentrators. Previous studies have shown that applying them to the top surface of a concentrator could mitigate surface losses. This paper presents experimental results for proof-of-concept asymmetric light transmission interfaces that may have potential applications in luminescent solar concentrators. The interfaces and the underneath substrate were created in a single step from polydimethylsiloxane using silicon molds fabricated on wafers via anisotropic wet etching. The resulting structures were pyramidal in shape. Large surface areas of nanostructures repeating at 800 nm, 900 nm, and 1000 nm were tested for backward and forward transmission using a spectrometer. Results showed a 21%, 10%, and 0% average transmissivity difference between the forward and backw... [more]

Partial discharge (PD) online monitoring is a common technique for high-voltage equipment diagnosis. However, due to field interference, the monitored PD signal contains a lot of noise. Therefore, this paper proposes a novel method by integrating the flower pollination algorithm, variational mode decomposition, and Savitzky−Golay filter (FPA-VMD-SG) to effectively suppress white noise and narrowband noise in the PD signal. Firstly, based on the mean envelope entropy (MEE), the decomposition number and quadratic penalty term of the VMD were optimized by the FPA. The PD signal containing noise was broken down into intrinsic mode functions (IMFs) by optimized parameters. Secondly, the IMFs were classified as the signal component, the noise dominant component, and the noise component according to the kurtosis value. Thirdly, the noise dominant component was denoised using the SG filter, and the denoised signal was mixed with the signal component to reconstruct a new signal. Finally, thresh... [more]

In the context of international carbon neutrality, energy prices are affected by several nonlinear and nonstationary factors, making it challenging for traditional forecasting models to predict energy prices effectively. The existing literature mainly uses linear models or a combination of multiple models to forecast energy prices. For the nonlinear relationship between variables and the mining of historical data information, the prediction strategy and accuracy of the existing literature need to be improved. Thus, this paper improves the prediction accuracy of energy prices by developing a “decomposition-reconstruction-integration” thinking strategy that affords medium- and short-term energy price prediction based on carbon constraint, eigenvalue transformation and deep learning neural networks. Considering 2011−2020 as the research period, the prices for traditional energy resources and polysilicon in clean photovoltaic energy raw materials are selected as representatives. Based on e... [more]

Low-grade faults play an important role in controlling oil and gas accumulations, but their fault throw is small and difficult to identify. Traditional low-grade fault recognition methods are time-consuming and inaccurate. Therefore, this study proposes a combination of a simulated low-grade fault sample set and a self-constructed convolutional neural network to recognize low-grade faults. We used Wu’s method to generate 500 pairs of low-grade fault samples to provide the data for deep learning. By combining the attention mechanism with UNet, an SE-UNet with efficient allocation of limited attention resources was constructed, which can select the features that are more critical to the current task objective from ample feature information, thus improving the expression ability of the network. The network model is applied to real data, and the results show that the SE-UNet model has better generalization ability and can better recognize low-grade and more continuous faults. Compared with... [more]

Power quality (PQ) becomes a more and more pressing issue for the operation stability of power systems with renewable energy sources. An important aspect of PQ monitoring of distribution networks is to compare the PQ indicators in different operating conditions. This paper evaluates the impact of a microgrid implementation in a real distribution network on power quality indicators at the point of common coupling in an LV network. The study includes a classical assessment of the long-term PQ parameters according to the EN 50160 standard, such as nominal frequency deviations, voltage RMS variations, voltage fluctuations (represented by long-term flicker severity), voltage unbalance and total harmonic distortion. The PQ evaluation is extended in statistical assessment based on cluster analysis. The case study contains 5 weeks of power quality observation results obtained at the assessment point in two different working conditions of the distribution system: before and after implementing t... [more]

Fluid−structure interactions (FSI) can significantly affect flow and the acoustic field generated by it. In this article, simulations of the flow over a rectangular cavity are conducted with and without taking FSI into account. The aim of this research is to conduct a numerical study of the flow over a cavity and to verify whether interactions between the flow and the elastic structure can significantly affect the flow itself or the acoustic pressure field. Four cases involving flexible walls with different material parameters and one reference case with rigid walls were analysed. The two-directional fluid−structure coupling between the flow and cavity walls was simulated. The simulations were performed with the volume and finite element methods using OpenFOAM software to solve the fluid field, CalculiX software to solve the displacement of the structure, and the preCICE library to couple the codes and computed fields. The acoustic analogy of Ffowcs-Williams and Hawkings and the libAco... [more]

Overhead line ice-shedding causes line breakage and results in electrical faults occurring between transmission lines, which seriously affects the safe operation of the power grid. In this paper, a risk assessment method for ice-shedding on 500 kV compact overhead lines is proposed. Two ratios were used to assess the discharge risk and mechanical failure risk of a line. A 500 kV compact overhead line in southern China was taken as an example, the proposed risk assessment method was used to carry out a risk assessment of the ice-shedding line with an ice thickness of 15 mm, and the suppression effects of different spacer arrangement schemes on the ice-shedding line were analyzed. The results showed that the impact coefficient of the conductor reached 1.88, the maximum jump height of the lower phase conductor reached 22.596 m, and the interphase clearance of the conductor decreased sharply when the lower phase conductor of 500 kV case line underwent full-span ice-shedding synchronously.... [more]

Mixed obstacles have a great influence on the deflagration process of liquefied petroleum gas (LPG)-air premixed combustible gas with concentration gradient. The arrangement of mixed obstacles may further stimulate overpressure and flame propagation. In this work, based on experimental and numerical simulations, this paper analyzes the flame and overpressure, and mainly studies the coupling relationship among the explosion overpressure characteristics, the structure of flame and the speed of flame propagation. The result shows that when the rectangular obstacle is 100 mm away from the ignition source, not only the speed of flame is the fastest, but also the time required to reach the maximum over-pressure is the shortest. In this configuration, an elongated flame is formed between a rectangular obstacle and a flat obstacle, and an obvious backflow structure appears. In addition, the average growth rate of overpressure has a minimum value, reaching at −35 MPa/s. The existence of rectang... [more]

Heat enhancement has been addressed by studying flow in channels with different shapes. The present paper investigates a particular channel shape with divergent and convergent forms. Two configurations are addressed: wall channels and pin-fin walls forming divergent/convergent shapes. The flow is assumed to be in a laminar and steady-state condition. The numerical model investigated the heat enhancement for different flow rates represented by Reynolds numbers. The average Nusselt number and the performance evaluation criterion revealed that wall channels outperformed the pin-fin shape. The performance evaluation criterion is higher than 1 for the wall channels. The main reason for this is that the flow passes through and above the wall creating mixing. This flow configuration happened since the wall height is shorter than the test cavity height. It is important to emphasize that pin-fins forming convergent channels did not improve heat enhancement when compared to convergent channels.... [more]

The Korean government is committed to advance the country’s energy transition to greener energy by increasing the share of renewable electricity to 20 percent by 2030 and to 30−35 percent by 2040. Achieving these goals will necessitate flexibility in energy markets as well as innovative business models and technological solutions. Peer-to-peer (P2P) electricity trading platforms (ETPs) are rapidly gaining traction, as they enable the integration of distributed energy sources into power systems. This study explores whether South Koreans are willing to participate in a hypothetical P2P ETP, which allows prosumers (who both consume and produce electricity) to trade electricity surpluses with their neighbours or with KEPCO (Korea Electric Power Corporation). We employ a choice experiment (CE) to examine respondent heterogeneous preferences and their willingness to pay (WTP) for a hypothetical P2P ETP in South Korea. Our findings indicate that two-thirds of total respondents in our CE are i... [more]

This paper presents the ANN (Artificial Neural Networks) approach to obtaining complete P-V curves of electrical power systems subjected to contingency. Two networks were presented: the MLP (multilayer perceptron) and the RBF (radial basis function) networks. The differential of our methodology consisted in the speed of obtaining all the P-V curves of the system. The great advantage of using ANN models is that they can capture the nonlinear characteristics of the studied system to avoid iterative procedures. The applicability and effectiveness of the proposed methodology have been investigated on IEEE test systems (14 buses) and compared with the continuation power flow, which obtains the post-contingency loading margin starting from the base case solution. From the results, the ANN performed well, with a mean squared error (MSE) in training below the specified value. The network was able to estimate 98.4% of the voltage magnitude values within the established range, with residues arou... [more]

The analyses presented in the publication allowed, on the basis of the data collected, development of an econometric model for the Polish steel industry from the point of view of the relationship between heat and energy management in the steel production process. The developed model is the main novelty of the paper. The main objective of the study was to develop an econometric model of Poland’s heat and energy economy. The following research questions were raised: Is there an econometric model describing heat consumption (intensity) in the steel industry in Poland in relation to steel production and the energy economy? What are the relations between heat intensity and energy prices and steel production in Poland? How might the current energy crisis affect steel production? In the analysis we used data of energy and heat management in the Polish steel industry. An econometric model was developed of the dependence of heat consumption (Yt) on electricity prices (X1t) and steel production... [more]

Physics-informed neural networks (PINNs) are an emerging technology in the scientific computing domain. Contrary to data-driven methods, PINNs have been shown to be able to approximate and generalize well a wide range of partial differential equations (PDEs) by imbedding the underlying physical laws describing the PDE. PINNs, however, can struggle with the modeling of hyperbolic conservation laws that develop shocks, and a classic example of this is the Buckley−Leverett problem for fluid flow in porous media. In this work, we explore specialized neural network architectures for modeling the Buckley−Leverett shock front. We present extensions of the standard multilayer perceptron (MLP) that are inspired by the attention mechanism. The attention-based model was, compared to the multilayer perceptron model, and the results show that the attention-based architecture is more robust in solving the hyperbolic Buckley−Leverett problem, more data-efficient, and more accurate. Moreover, by utili... [more]

Increasing economic and population growth has led to a rise in electricity consumption. Consequently, electrical utility firms must have a proper energy management strategy in place to improve citizens’ quality of life and ensure an organization’s seamless operation, particularly amid unanticipated circumstances such as coronavirus disease (COVID-19). There is a growing interest in the application of artificial intelligence models to electricity prediction during the COVID-19 pandemic, but the impacts of clustering methods and parameter selection have not been explored. Consequently, this study investigates the impacts of clustering techniques and different significant parameters of the adaptive neuro-fuzzy inference systems (ANFIS) model for predicting electricity consumption during the COVID-19 pandemic using districts of Lagos, Nigeria as a case study. The energy prediction of the dataset was examined in relation to three clustering techniques: grid partitioning (GP), subtractive cl... [more]

A fiber-optic gyroscope (FOG) with lower precision but higher cost advantage is typically selected according to working conditions and engineering budget. Thermal drift is the main factor affecting FOG precision. External thermal calibration methods by algorithms can effectively weaken the influence of thermal drift. This paper presents a thermal calibration method of a two-dimensional N-order polynomial (TDNP) and compares it with artificial neural network (ANN) methods to determine a software FOG thermal calibration method for landslide displacement monitoring. The TDNP thermal calibration coefficient matrix was established, and the thermal calibration capability of the TDNP method with different orders N was evaluated on the basis of error analysis. The ANN model with 1 to 18 hidden neural layers was established on the basis of LM, BR, and SCG algorithms to choose a suitable ANN. Finally, the mean absolute errors of FOG thermal calibration through the TDNP with different orders and... [more]