With an increasing share of renewable energy resources participating in electricity markets, there is a growing dependence between renewable power production and clearing prices of spot markets. Modeling this dependence using bivariate analysis can result in underestimation of market risks and adverse effects for stakeholders’ risk management. To enable an undistorted risk assessment, we are using a copula approach to precisely and jointly model electricity prices and infeed volumes of wind power. We simulate the case of wind farm operators using power purchase agreements (PPAs) to shift the price risk to an energy trader, who integrates the infeed into its portfolio. The trader’s portfolio can either be geographically dispersed, or highly localized. Based on its portfolio, the energy trader can decide to use derivatives such as futures to manage its risk exposure. The trader decides on future volumes subject to its portfolio’s inherent volatility. With a given risk averse strategy, a... [more]

With the development of micro-grids including PV production and storage, the need for efficient energy management strategies arises. One of their key components is the forecast of the energy production from very short to long term. The forecast time-step is an important parameter affecting not only its accuracy but also the optimal control time discretization, hence its efficiency and computational burden. To quantify this trade-off, four machine learning forecast models are tested on two geographical locations for time-steps varying from 2 to 60 min and horizons from 10 min to 6 h, on global irradiance horizontal and tilted when data was available. The results are similar for all the models and indicate that the error metric can be reduced up to 0.8% per minute on the time-step for forecasts below one hour and up to 1.7% per ten minutes for forecasts between one and six hours. In addition, it is shown that for short term horizons, it may be advantageous to forecast with a high resolut... [more]

The present study proposes a model to predict the heat transfer coefficient in R134a liquid−vapor two-phase pulsating flow boiling in an evaporator using the experimental data and response surface methodology (RSM). The model is based on the current existing empirical correlation for R134a liquid−vapor two-phase continuous flow with an imposed modification factor. The model for the imposed modification factor is the function of the pulsating period and inlet/outlet vapor quality, which is obtained using the limited experimental data. An analysis of variance (ANOVA) is carried out to test the significance of the model and normal probability of residuals is analyzed as well. Results show that the regression model produces a mean error of −4.3% and a standard deviation of 15.4%, compared to experimental results. Of the data 95.1% is contained inside a ±50% error window, which indicates that the proposed model could predict the heat transfer coefficient of R134a liquid−vapor two-phase puls... [more]

For a safe drilling operation with the of minimum borehole instability challenges, building a mechanical earth model (MEM) has proven to be extremely valuable. However, the natural complexity of reservoirs along with the lack of reliable information leads to a poor prediction of geomechanical parameters. Shear wave velocity has many applications, such as in petrophysical and geophysical as well as geomechanical studies. However, occasionally, wells lack shear wave velocity (especially in old wells), and estimating this parameter using other well logs is the optimum solution. Generally, available empirical relationships are being used, while they can only describe similar formations and their validation needs calibration. In this study, machine learning approaches for shear sonic log prediction were used. The results were then compared with each other and the empirical Greenberg−Castagna method. Results showed that the artificial neural network has the highest accuracy of the prediction... [more]

Because the penetration level of renewable energy sources has increased rapidly in recent years, uncertainty in power system operation is gradually increasing. As an efficient tool for power system analysis under uncertainty, probabilistic power flow (PPF) is becoming increasingly important. The point-estimate method (PEM) is a well-known PPF algorithm. However, two significant defects limit the practical use of this method. One is that the PEM struggles to estimate high-order moments accurately; this defect makes it difficult for the PEM to describe the distribution of non-Gaussian output random variables (ORVs). The other is that the calculation burden is strongly related to the scale of input random variables (IRVs), which makes the PEM difficult to use in large-scale power systems. A novel approach based on principal component analysis (PCA) and high-dimensional model representation (HDMR) is proposed here to overcome the defects of the traditional PEM. PCA is applied to decrease t... [more]

Concentrator photovoltaic (CPV) is used to obtain cheaper and more stable renewable energy. Methods which predict the energy production of a power system under specific circumstances are highly important to reach the goal of using this system as a part of a bigger one or of making it integrated with the grid. In this paper, the development of a model to predict the energy of a High CPV (HCPV) system using an Artificial Neural Network (ANN) is described. This system is located at the University of Rabat. The performed experiments show a quick prediction with encouraging results for a very short-term prediction horizon, considering the small amount of data available. These conclusions are based on the processes of obtaining the ANN models and detailed discussion of the results, which have been validated using real data.

Convolutional Neural Networks (CNN) possess many positive qualities when it comes to spatial raster data. Translation invariance enables CNNs to detect features regardless of their position in the scene. However, in some domains, like geospatial, not all locations are exactly equal. In this work, we propose localized convolutional neural networks that enable convolutional architectures to learn local features in addition to the global ones. We investigate their instantiations in the form of learnable inputs, local weights, and a more general form. They can be added to any convolutional layers, easily end-to-end trained, introduce minimal additional complexity, and let CNNs retain most of their benefits to the extent that they are needed. In this work we address spatio-temporal prediction: test the effectiveness of our methods on a synthetic benchmark dataset and tackle three real-world wind prediction datasets. For one of them, we propose a method to spatially order the unordered data.... [more]

Charging a group of series-connected batteries of a PV-battery hybrid system exhibits an imbalance issue. Such imbalance has severe consequences on the battery activation function and the maintenance cost of the entire system. Therefore, this paper proposes an active battery balancing technique for a PV-battery integrated system to improve its performance and lifespan. Battery state of charge (SOC) estimation based on the backpropagation neural network (BPNN) technique is utilized to check the charge condition of the storage system. The developed battery management system (BMS) receives the SOC estimation of the individual batteries and issues control signal to the DC/DC Buck-boost converter to balance the charge status of the connected group of batteries. Simulation and experimental results using MATLAB-ATMega2560 interfacing system reveal the effectiveness of the proposed approach.

The paper firstly summarizes a simple analytical model of the air gap flux-density distribution for isotropic permanent magnet (PM) synchronous machines, in the presence of static eccentricity. The model was proposed by the authors in a previous paper and is based on an efficacious analytical expression of the variable length of air gap magnetic field lines which occur in eccentric brushless machines with surface-mounted permanent magnets. The approximate expression of the air gap field makes it possible to achieve a mathematical model with concentrated parameters close to that of a PM machine without eccentricity. The expression of the armature voltages and electromagnetic torque are found, also with reference to steady-state operating conditions at fixed rotor speed and impressed currents. The differences introduced by the considered type of eccentricity are evaluated and highlighted especially with reference to the air gap inductance and to waveforms and frequency spectra of voltage... [more]

Condition monitoring for wind turbines is tailored to predict failure and aid in making better operation and maintenance (O&M) decisions. Typically the condition monitoring approaches are concerned with predicting the remaining useful lifetime (RUL) of assets or a component. As the time-based measures can be rendered absolute when changing the operational set-point of a wind turbine, we propose an alternative in a power-based condition monitoring framework for wind turbines, i.e., the remaining power generation (RPG) before a main bearing failure. The proposed model utilizes historic wind turbine data, from both run-to-failure and non run-to-failure turbines. Comprised of a recurrent neural network with gated recurrent units, the model is constructed around a censored and uncensored data-based cost function. We infer a Weibull distribution over the RPG, which gives an operator a measure of how certain any given prediction is. As part of the model evaluation, we present the hyper-parame... [more]

Appliance recognition is one of the vital sub-tasks of NILM in which a machine learning classier is used to detect and recognize active appliances from power measurements. The performance of the appliance classifier highly depends on the signal features used to characterize the loads. Recently, different appliance features derived from the voltage−current (V−I) waveforms have been extensively used to describe appliances. However, the performance of V−I-based approaches is still unsatisfactory as it is still not distinctive enough to recognize devices that fall into the same category. Instead, we propose an appliance recognition method utilizing the recurrence graph (RG) technique and convolutional neural networks (CNNs). We introduce the weighted recurrent graph (WRG) generation that, given one-cycle current and voltage, produces an image-like representation with more values than the binary output created by RG. Experimental results on three different sub-metered datasets show that the... [more]

The presented paper deals with the metal foams, which have a wide application potential ranging from power engineering, through catalysts to impact energy absorbers. The main aim of the paper is to propose an economical non-destructive method of determining the basic characteristics and dimensions using affordable devices. The basic principle of the proposed method lies in the image capture of metal foam and their subsequent analysis in image analysis software. An important element of the work is a comparison of results obtained by the proposed method with results obtained by high-resolution X-ray microtomography. The proposed method was evaluated in terms of measurement uncertainty and propagation of error in overall results. The use of the method is limited to the metal foams, characterized by an ordered structure, which are produced mainly by the electrophoretic deposition process. Based on the descriptive statistical analysis of results, it is possible to state, that the proposed m... [more]

This work aims at exploring the potential contribution of the Italian residential sector in implementing load flexibility for Demand Response activities. In detail, by combining experimental and statistical approaches, a method to estimate the load profile of a dwelling cluster of 751 units has been presented. To do so, 14 dwelling archetypes have been defined and the algorithm to categorise the sample units has been built. Then, once the potential flexible loads for each archetype have been evaluated, a control strategy for applying load time shifting has been implemented. That strategy accounts for both the power demand profile and the hourly electricity price. Specifically, it has been assumed that end users access a pricing mechanism following the hourly trend of electricity economic value, which is traded day by day in the Italian spot market, instead of the current Time of Use (TOU) system. In such a way, it is possible to flatten the dwellings cluster profile, limiting undesired... [more]

Defects in high voltage transmission line components such as cracked insulators, broken wires rope, and corroded power line joints, are very common due to continuous exposure of these components to harsh environmental conditions. Consequently, they pose a great threat to humans and the environment. This paper presents a real-time aerial power line inspection system that aims to detect power line components such as insulators (polymer and porcelain), splitters, damper-weights, power lines, and then analyze these transmission line components for potential defects. The proposed system employs a deep learning-based framework using Jetson TX2 embedded platform for the real-time detection and localization of these components from a live video captured by remote-controlled drone. The detected components are then analyzed using novel defect detection algorithms, presented in this paper. Results show that the proposed detection and localization system is robust against highly cluttered environm... [more]

The extensive use of finite element models accurately simulates the temperature distribution of electrical machines. The simulation model can be quickly modified to reflect changes in design. However, the long runtime of the simulation prevents any direct application of the optimization algorithm. In this paper, research focused on improving efficiency with which expensive analysis (finite element method) is used in generator temperature distribution. A novel surrogate model based optimization method is presented. First, the Taguchi orthogonal array relates a series of stator geometric parameters as input and the temperatures of a generator as output by sampling the design decision space. A number of stator temperature designs were generated and analyzed using 3-D multi-physical field collaborative finite element model. A suitable shallow neural network was then selected and fitted to the available data to obtain a continuous optimization objective function. The accuracy of the functio... [more]

Due to the ever-increasing environmental pollution becoming progressively more serious, wind power has been widely used around the world in recent years. However, because of their randomness and intermittence, the accurate prediction of wind speeds is difficult. To address this problem, this article proposes a hybrid system for short-wind-speed prediction. The system combines the autoregressive differential moving average (ARIMA) model with a three-layer feedforward neural network. An ARIMA model was employed to predict linear patterns in series, while a feedforward neural network was used to predict the nonlinear patterns in series. To improve accuracy of the predictions, the neural network models were trained by using two methods: first-order transition rules and fuzzy first-order transition rules. The Levenberg−Marquardt (LM) algorithm was applied to update the weight and deviation of each layer of neural network. The dominance matrix method was employed to calculate the weight of t... [more]

This paper explores a way to apply Item Response Theory (IRT), one of the popular statistical methodologies in measurement and psychometrics, to evaluate Financial Transmission Rights (FTR) paths in the U.S. electricity market. FTR is an energy derivative product to hedge congestion cost risks inherent in constrained transmission lines. In New England, with about 1200 pricing locations, the theoretical combinations of FTR paths amount to 1.4 million in prevailing flows alone. With capital constraints, it is imperative that FTR market participants build the capability to evaluate FTR paths to bid on. IRT provides a framework of how well tests work, and how individual items work on tests, estimating respondents’ latent abilities, and individual item parameters. IRT is utilized to analyze historical electricity data of 2019 for a daily congestion cost of eight customer load zones and one hub in the U.S., New England, for the evaluation of FTR paths. In the analysis, an item represents an... [more]

Though the full AC power flow model can accurately represent the physical power system, the use of this model is limited in practice due to the computational complexity associated with its non-linear and non-convexity characteristics. For instance, the AC power flow model is not incorporated in the unit commitment model for practical power systems. Instead, an alternative linearized DC power flow model is widely used in today’s power system operational and planning tools. However, DC power flow model will be useless when reactive power and voltage magnitude are of concern. Therefore, a linearized AC (LAC) power flow model is needed to address this issue. This paper first introduces a traditional LAC model and then proposes an enhanced data-driven linearized AC (DLAC) model using the regression analysis technique. Numerical simulations conducted on the Tennessee Valley Authority (TVA) system demonstrate the performance and effectiveness of the proposed DLAC model.

The common analog approach and ensemble methods in photovoltaic (PV) power forecasting are based on the forecasts from several numerical weather prediction (NWP) models. These may be not applicable to the very-short-term PV power forecasting, since forecasts based on NWP models are reliable in horizons longer than six hours. In this paper, a methodology for one-hour-ahead PV power forecasting is proposed. Instead of the NWP models, the persistence method is applied in the analog approach to produce meteorological forecasts. The historical data with meteorological predictions similar to the target forecast hour are identified to train the forecast model. Then, the feed forward neural networks (FNNs) act as the base predictors of the neural network ensemble method to replace the NWP-based PV power prediction methods. The forecast results produced by the FNNs are combined by the random forest (RF) algorithm. The performance of the proposed method is evaluated on a real grid-connected PV p... [more]

Estimating the additional power losses caused by an inter-laminar short circuit in electromagnetic devices using thermal measurements depends on many parameters such as thermal conductivity, heat capacity, convective heat coefficient, and size of the fault points. This paper presents a method for estimating these parameters using experimental measurement and a numerical model. The surface temperature rise due to inter-laminar short circuit fault was obtained using an infrared camera. Based on the initial temperature rise method, the least square non-linear approximation technique was used to determine the best fitting parameters of the fault region from the numerical model. To validate the results obtained, the fault region temperature rise and the total loss of the experimental sample were compared with the numerical model using the obtained parameters for different current supply conditions. The study shows that surface temperature distribution can be used to estimate the inter-lamin... [more]

Transverse jets in crossflow are widely used in energy systems, especially as dilution air jets, fuel/air mixers, and combustion equipment, and have received extensive attention and plenty of research. However, the studies of the circular transverse jet issued from a circular gap at the circumferential direction of a tube in crossflow are very limited. This paper studies a relatively new jet: the circular transverse jet. Firstly, numerical calculations are conducted under different turbulence models but with the same boundary conditions. By comparing the numerical results of different turbulence models with the existing experimental data, the turbulence model which is most suitable for the numerical calculation of the circular transverse jet is selected. Then, this turbulence model is used to calculate and analyze the flow field structure and its characteristics. It is found that due to the aerodynamic barrier effect of the high-velocity jet, a negative pressure zone is formed behind t... [more]

This paper proposes an analytical model for natural convection in a closed rectangular enclosure filled by a fluid, with imposed heat fluxes at the vertical walls and adiabatic horizontal walls. The analytical model offers a simplified, but easy to handle, description of the temperature and velocity fields. The predicted temperature, velocity, and pressure fields are shown to be in agreement with those obtained from a reliable numerical model. The Nusselt numbers for both the analytical and numerical solutions are then calculated and compared, varying both the aspect ratio of the enclosure and the Rayleigh number. Based on the comparisons, it is possible to assess the dependence of the reliability of the analytical model on the aspect ratio of the enclosure, showing that the prediction error rapidly decreases with the increase of the enclosure slenderness.

This paper intends to prepare a nanofluid sample by suspending Multi-walled Carbon Nanotubes (MWCNTs) at 0.005g/L concentration and analyze the behavior of electrical and dielectric properties based on the International Electrotechnical Commision test method. In order to validate the effectiveness of MWCNT nanofluid, alternating current breakdown voltage (BDV), negative polarity lightning impulse (LI), dielectric permittivity, dissipation factor (DF), DC resistivity and Raman structural measurement are executed accordingly. In the following, an analysis of the statistical distribution using the two-parameter Weibull distribution law of BDV and LI are evaluated at four experimental conditions to predict the probability of breakdown occurring at different percentages. Based on the observation, the MWCNT filler has a substantial effect in improving the BDV and LI characteristics of disposed mineral oil. The permittivity, DF and resistivity performance of MWCNT nanofluid from 25 °C to 90 °... [more]

This study aimed to develop a building-integrated photovoltaic (BIPV) device and optimal control methods that increase the photovoltaic (PV) efficiency and visual comfort of the indoor space. A louver-type PV-integrated shading device was suggested and an artificial neural networks (ANN) model was developed to predict PV electricity output, work plane illuminance, and daylight glare index (DGI). The slat tilt angle of the shading device was controlled to maximize PV electricity output based on three different strategies: one without visual comfort constraints, and the other two with visual comfort constraints: work plane illuminance and DGI. Optimal tilt angle was calculated using predictions of the ANN. Experiments were conducted to verify the system modeling and to evaluate the performance of the shading device. Experiment results revealed that the ANN model successfully predicted the PV output, work plane illuminance, and DGI. The PV-integrated shading device was more efficient in p... [more]

The use of low-emission combustion techniques in pulverized coal-fired (PC) boilers are usually associated with the formation of a reduced-gas atmosphere near evaporator walls. This increases the risk of high temperature (low oxygen) corrosion processes in coal-fired boilers. The identification of the dynamics and the locations of these processes, and minimizing negative consequences are essential for power plant operation. This paper presents the diagnostic system for determining corrosion risks, based on continuous measurements of flue gas composition in the boundary layer of the combustion chamber, and artificial intelligence techniques. Experience from the implementation of these measurements on the OP-230 hard coal-fired boiler, to identify the corrosion hazard of one of the evaporator walls, has been thoroughly described. The results obtained indicate that the continuous controlling of the concentrations of O2 and CO near the water wall, in combination with the use of neural netw... [more]