Here, we propose a new deep learning scheme to solve the energy time series prediction problem. The model implementation is based on the use of Long Short-Term Memory networks and Convolutional Neural Networks. These techniques are combined in such a fashion that inter-dependencies among several different time series can be exploited and used for forecasting purposes by filtering and joining their samples. The resulting learning scheme can be summarized as a superposition of network layers, resulting in a stacked deep neural architecture. We proved the accuracy and robustness of the proposed approach by testing it on real-world energy problems.

This paper reviews non-intrusive load monitoring (NILM) approaches that employ deep neural networks to disaggregate appliances from low frequency data, i.e., data with sampling rates lower than the AC base frequency. The overall purpose of this review is, firstly, to gain an overview on the state of the research up to November 2020, and secondly, to identify worthwhile open research topics. Accordingly, we first review the many degrees of freedom of these approaches, what has already been done in the literature, and compile the main characteristics of the reviewed publications in an extensive overview table. The second part of the paper discusses selected aspects of the literature and corresponding research gaps. In particular, we do a performance comparison with respect to reported mean absolute error (MAE) and F1-scores and observe different recurring elements in the best performing approaches, namely data sampling intervals below 10 s, a large field of view, the usage of generative... [more]

The problem of energy recovery in braking of an electric vehicle is solved here, which ensures high quality blended deceleration using electrical and friction brakes. A model reference controller is offered, capable to meet the conflicting requirements of intensive and gradual braking scenarios at changing road surfaces. In this study, the neural network controller provides torque gradient control without a tire model, resulting in the return of maximal energy to the hybrid energy storage during braking. The torque allocation algorithm determines how to share the driver’s request between the friction and electrical brakes in such a way as to enable regeneration for all braking modes, except when the battery state of charge and voltage levels are saturated, and a solo friction brake has to be used. The simulation demonstrates the effectiveness of the proposed coupled two-layer neural network capable of capturing various dynamic behaviors that could not be included in the simplified phys... [more]

The development of data driven methods for Li-ion battery diagnosis and prognosis is a growing field of research for the battery community. A big limitation is usually the size of the training datasets which are typically not fully representative of the real usage of the cells. Synthetic datasets were proposed to circumvent this issue. This publication provides improved datasets for three major battery chemistries, LiFePO4, Nickel Aluminum Cobalt Oxide, and Nickel Manganese Cobalt Oxide 811. These datasets can be used for statistical or deep learning methods. This work also provides a detailed statistical analysis of the datasets. Accurate diagnosis as well as early prognosis comparable with state of the art, while providing physical interpretability, were demonstrated by using the combined information of three learnable parameters.

Deterministic load flow analyses of power grids do not include the uncertain factors that affect the network elements; hence, their predictions can be very unreliable for distribution system operators and for the decision makers who deal with the expansion planning of the power network. Adding uncertain probability parameters in the deterministic load flow is vital to capture the wide variability of the currents and voltages. This is achieved by probabilistic load flow studies. Photovoltaic systems represent a remarkable source of uncertainty in the distribution network. In this study, we used a Gaussian copula to model the uncertainty in correlated photovoltaic generators. Correlations among photovoltaic generators were also included by exploiting the Gaussian copula technique. The large sets of samples generated with a statistical method (Gaussian copula) were used as the inputs for Monte Carlo simulations. The proposed methodologies were tested on two different networks, i.e., the 1... [more]

Different prediction models (multiple linear regression, vector support machines, artificial neural networks and random forests) are applied to model the monthly global irradiation (MGI) from different input variables (latitude, longitude and altitude of meteorological station, month, average temperatures, among others) of different areas of Galicia (Spain). The models were trained, validated and queried using data from three stations, and each best model was checked in two independent stations. The results obtained confirmed that the best methodology is the ANN model which presents the lowest RMSE value in the validation and querying phases 1226 kJ/(m2∙day) and 1136 kJ/(m2∙day), respectively, and predict conveniently for independent stations, 2013 kJ/(m2∙day) and 2094 kJ/(m2∙day), respectively. Given the good results obtained, it is convenient to continue with the design of artificial neural networks applied to the analysis of monthly global irradiation.

During the development of oil and gas fields, the permeability of the reservoirs decreases due to a decrease in reservoir pressure and an increase in effective pressure, as a result of which significant reserves of oil and gas remain in the reservoir. To predict the rate of decrease in oil production rates during field development and to respond quickly, it is necessary to know the law of permeability decrease with an increase in effective pressure. Existing methods for describing the change in the permeability of rocks were analyzed in the paper. Numerical analysis of the results of core studies from previously published papers and the results of field well testing on the examples of the north Perm region oil fields showed that in both cases, regardless of the type of rock and the type of reservoir, the change in permeability can be described by the same equations (exponential and power-law). Obtained equations can be used to predict changes in the permeability of terrigenous reservoi... [more]

The field of electric vehicle charging load modelling has been growing rapidly in the last decade. In light of the Paris Agreement, it is crucial to keep encouraging better modelling techniques for successful electric vehicle adoption. Additionally, numerous papers highlight the lack of charging station data available in order to build models that are consistent with reality. In this context, the purpose of this article is threefold. First, to provide the reader with an overview of the open datasets available and ready to be used in order to foster reproducible research in the field. Second, to review electric vehicle charging load models with their strengths and weaknesses. Third, to provide suggestions on matching the models reviewed to six datasets found in this research that have not previously been explored in the literature. The open data search covered more than 860 repositories and yielded around 60 datasets that are relevant for modelling electric vehicle charging load. These... [more]

End-use specific residential electricity load profiles are of interest for energy system modelling that requires future load curves or demand-side management. We present a model that is applicable across countries to predict consumption on a regional and national scale, using openly available data. The model uses neural networks (NNs) to correlate measured consumption from one country (United Kingdom) with weather data and daily profiles of a mix of human activity and device specific power profiles. We then use region-specific weather data and time-use surveys as input for the trained NNs to predict unscaled electric load profiles. The total power profile consists of the end-use household load profiles scaled with real consumption. We compare the model’s results with measured and independently simulated profiles of various European countries. The NNs achieve a mean absolute error compared with the average load of 6.5 to 33% for the test set. For Germany, the standard deviation between... [more]

Since bearing deterioration patterns are difficult to collect from real, long lifetime scenarios, data-driven research has been directed towards recovering them by imposing accelerated life tests. Consequently, insufficiently recovered features due to rapid damage propagation seem more likely to lead to poorly generalized learning machines. Knowledge-driven learning comes as a solution by providing prior assumptions from transfer learning. Likewise, the absence of true labels was able to create inconsistency related problems between samples, and teacher-given label behaviors led to more ill-posed predictors. Therefore, in an attempt to overcome the incomplete, unlabeled data drawbacks, a new autoencoder has been designed as an additional source that could correlate inputs and labels by exploiting label information in a completely unsupervised learning scheme. Additionally, its stacked denoising version seems to more robustly be able to recover them for new unseen data. Due to the non-s... [more]

The diffusion of nonprogrammable power plants, together with the decommissioning of conventional, rotating generators, is increasing the need for flexible resources to always ensure the safe and secure operation of the European electric-power system. Beyond technological advances, policy aspects also play a fundamental role in the opening of electricity markets to new players; in this regard, System Operations Guideline EU 2017/1485 and Italian Regulatory Authority documents require the Italian transmission-system operator (TSO; Terna) to publish all exploited algorithms and methodologies for the management of market balancing. In this context, the present paper develops and presents a data-driven methodology to estimate secondary and tertiary reserve needs; a numerical real-life case study, focused on the North Italy geographical zone, is presented. Data for 2017, 2018, and 2019 on electricity consumption and production (forecasted and actual) were gathered. Following the European TSO... [more]

This article presents the problem of diagnostic examination by the (DIAG) diagnostic system of devices of the House on Water (HoW) hybrid electric power system in the multi-valued (2, 3, and 4) state assessment. Forming the basis for the functioning of the (DIAG) diagnostic system is the measurement knowledge base of the object tested. For this purpose, the issues of building a diagnostic knowledge base for a hybrid power system for HoW are presented. The basis for obtaining diagnostic information for the measurement knowledge base is a functional and diagnostic analysis of the hybrid power system tested. The result of this analysis is a functional and diagnostic model of the research object. At the next stage of the work, on the basis of the model created, the sets of basic elements and the sets of measurement signals were determined together with the reference signals assigned. State classification in the (DIAG) system is based on an analysis of the value of the divergence metrics of... [more]

Phase resolved partial discharge patterns (PRPD) are routinely used to assess the condition of power transformers. In the past, classification systems have been developed in order to automate the fault identification task. Most of those systems work with the assumption that only one source is active. In reality, however, multiple PD sources can be active at the same time. Hence, PRPD patterns can overlap and cannot be separated easily, e.g., by visual inspection. Multiple PD sources in a single PRPD represent a multi-label classification problem. We present a system based on long short-term memory (LSTM) neural networks to resolve this task. The system is generally able to classify multiple overlapping PRPD by while only being trained by single class PD sources. The system achieves a single class accuracy of 99% and a mean multi-label accuracy of 43% for an imbalanced dataset. This method can be used with overlapping PRPD patterns to identify the main PD source and, depending on the da... [more]

Modulating the boundary layer velocity profile is a very promising strategy for achieving transition delay and reducing the friction of the plate. By perturbing the flow with counter-rotating vortices that undergo transient, non-modal growth, streamwise-aligned streaks are formed inside the boundary layer, which have been proved (theoretical and experimentally) to be very robust flow structures. In this paper, we employ efficient numerical methods to perform a parametric stability investigation of the three-dimensional incompressible flat-plate boundary layer with finite-amplitude streaks. For this purpose, the Boundary Region Equations (BREs) are applied to solve the nonlinear downstream evolution of finite amplitude streaks. Regarding the stability analysis, the linear three-dimensional plane-marching Parabolized Stability Equations (PSEs) concept constitutes the best candidate for this task. Therefore, a thorough parametric study is presented, analyzing the instability characteristi... [more]

The present paper defines and assesses a new simplified method to represent the photovoltaic (PV) modules’ electrical behavior, based on the commonly used one diode and three parameters (1D + 3P) model, addressing two main objectives. The first one is to quantify and assess, at different operating conditions, the PV modules electrical behavior estimations’ accuracy provided by the well-known 1D + 3P, through a comparison based on experimental and theoretical results. The second one concerns the performance assessment of the 1D + 3P model’s suggested approximation, aiming at simplifying the mathematics instead of solving complex iterative equations, which hinges on higher computational time to obtain accurate results. Hence, experimental and theoretical data were considered, aiming at performing a thorough comparison with more than 17,000 PV modules being assessed, which was achieved by using both the California Energy Commission (CEC) database and PVsyst software. The findings show tha... [more]

The transportation sector is a major contributor to carbon dioxide emissions, and the resulting climate change. The diffusion of alternative fuel vehicles, including hybrid electric vehicles (HEV), is an important solution for these issues. This study aimed to evaluate the factors affecting the ownership ratio of HEVs, particularly passenger vehicles, and the regional differences in the purchase of HEVs in Japan. This study performed a fixed-effects regression analysis with panel data for 47 prefectures during the period 2005−2015 to evaluate the factors affecting the HEV ownership ratio and conducted three cluster analyses to investigate the regional differences in diffusion in terms of price categories, body types, and drive systems of HEVs. Some demographic and social factors were found to affect the ownership ratio in Japan, whereas economic factors, including prefecture-level subsidies for purchasing HEVs, were not. Regarding regional differences, prefectures in urban areas with h... [more]

The influence of a tubular structure PEMFC (proton exchange membrane fuel cell) with different flow patterns is investigated in this study. A complete 3D non-isothermal model is constructed for square and circular tubular PEMFCs, and the distribution of oxygen and water concentration in cathode channels, current density, power density and cell net power are studied. To this end, the four arrangements of tubular PEMFC are square chordal (SC), square peripheral (SP), circular chordal (CC) and circular peripheral (CP). The calculation of the effective area and boundary conditions remains the same when performing all four configurations. The consequent results show that for the tubular structure PEMFC, compared with the co-flow mode, the counter-flow mode has better performance and provides more power. Using a counter-flow pattern, the permeability of the species increases, so a more uniform reaction occurs at the cell. The entire performance of the SP and CP model is not as good as that o... [more]

This paper introduces a new black-box approach for time domain modeling of commercially available single-phase photovoltaic (PV) inverters in low voltage networks. An artificial neural network is used as a nonlinear autoregressive exogenous model to represent the steady state behavior as well as dynamic changes of the PV inverter in the frequency range up to 2 kHz. The data for the training and the validation are generated by laboratory measurements of a commercially available inverter for low power applications, i.e., 4.6 kW. The state of the art modeling approaches are explained and the constraints are addressed. The appropriate set of data for training is proposed and the results show the suitability of the trained network as a black-box model in time domain. Such models are required, i.e., for dynamic simulations since they are able to represent the transition between two steady states, which is not possible with classical frequency-domain models (i.e., Norton models). The demonstr... [more]

Large eddy simulations are performed to analyze the conjugate heat transfer of turbulent flow in a ribbed channel with a heat-conducting solid wall. An immersed boundary method (IBM) is used to determine the effect of heat transfer in the solid region on that in the fluid region in a unitary computational domain. To satisfy the continuity of the heat flux at the solid−fluid interface, effective conductivity is introduced. By applying the IBM, it is possible to fully couple the convection on the fluid side and the conduction inside the solid and use a dynamic subgrid scale model in a Cartesian grid. The blockage ratio (e/H) is set at 0.1, which is typical for gas turbine blades. Through conjugate heat transfer analysis, it is confirmed that the heat transfer peak in front of the rib occurs because of the impinging of the reattached flow and not the influence of the thermal boundary condition. When the rib turbulator acts as a fin, its efficiency and effectiveness are predicted to be 98.... [more]

An experimental investigation is conducted to measure and correlate the impact of the water content on the electrical characteristics of the mineral oil for transformers, particularly the breakdown voltage, the resistivity, and the dielectric dissipation factor. Regression method is carried out to compare the results obtained through laboratory experiments with those predicted using an analytical model. A treatment to reduce water content in oil involving filtration, degassing and dehydration using a SESCO mobile station was applied to the new, regenerated, and used oil samples in service. The breakdown voltage, the resistivity, and the dielectric dissipation factor of the samples were measured. Regression analysis using an exponential model was applied to examine the samples electrical properties. The results show that, after treatment, the breakdown voltage and resistivity increase as the water content decreases, unlike the dielectric dissipation factor which exhibits a decreasing tr... [more]

Tight reservoirs have poor physical properties: low permeability and strong heterogeneity, which makes it difficult to predict productivity. Accurate prediction of oil well production plays a very important role in the exploration and development of oil and gas reservoirs, and improving the accuracy of production prediction has always been a key issue in reservoir characterization. With the development of artificial intelligence, high-performance algorithms make reliable production prediction possible from the perspective of data. Due to the high cost and large error of traditional seepage theory formulas in predicting oil well production, this paper establishes a horizontal well productivity prediction model based on a hybrid neural network method (CNN-LSTM), which solves the limitations of traditional methods and produces accurate predictions of horizontal wells’ daily oil production. In order to prove the effectiveness of the model, compared with the prediction results of BPNN, RBF,... [more]

Workload prediction is essential in cloud data centers (CDCs) for establishing scalability and resource elasticity. However, the workload prediction accuracy in the cloud data center could be better due to noise, redundancy, and low performance for workload prediction. This paper designs a hierarchical tree-based deep convolutional neural network (T-CNN) model with sheep flock optimization (SFO) to enhance CDCs’ power efficiency and workload prediction. The kernel method is used to preprocess historical information from the CDCs. Additionally, T-CNN model weight parameters are optimized using SFO. The suggested TCNN-SFO technology has successfully reduced excessive power consumption while correctly forecasting the incoming demand. Further, the proposed model is assessed using two benchmark datasets: Saskatchewan HTTP traces and NASA. The developed model is executed in a Java tool. Therefore, associated with existing methods, the developed technique has achieved higher accuracy of 20.75... [more]

This paper introduces a comprehensive examination of vector-controlled- (VC-) based techniques intended for induction motor (IM) drives. In addition, the evaluation and critique of modern control techniques that improve the performance of IM drives are discussed by considering a systematic literature survey. Detailed research on variable-speed drive control, for instance, VC and scalar control (SCC), was conducted. The SCC-based systems’ speed and V/f control purposes are clarified in closed and open loops of IM drives. The operations, benefits, and drawbacks of the direct and indirect field-oriented control systems are illustrated. Furthermore, the direct torque control (DTC) method for IMs is reviewed. Numerous VC methods established along with microprocessor/digital control, model reference adaptive control (MRAC), sliding mode control (SMC), and intelligent control (in terms of fuzzy logic (FL) and artificial neural networks (ANNs)) are described and examined. Uncertainties in the... [more]

Energy accounting is a system for regularly measuring, analyzing, and reporting the energy use of various activities. This is done to increase energy efficiency and monitor the impact of energy usage on the environment. Primary energy accounting is now done by determining the amount of fossil fuel energy required to generate it. However, if fossil fuels become scarcer, this strategy becomes less viable. Instead, a new energy accounting approach will be required, one that takes into consideration the intermittent character of the two most prevalent renewable energy sources, wind and solar power. Furthermore, estimation of the energy consumption data collected from household surveys, whether using a recall-based approach or a meter-based one, remains a difficult task. Hence, this paper proposes a novel energy accounting model using Fuzzy Restricted Boltzmann Machine-Recurrent Neural Network (FRBM-RNN). The energy consumption dataset is preprocessed using linear-scaling normalization. The... [more]

A horizontal well in the Wolfcamp Formation within the Delaware Basin exhibits cross-dipole sonic log anisotropy varying from 0.0% to 29.7% over the reservoir interval. Massive limestones exhibit little anisotropy while shales and intervals with high fracture counts have high anisotropy. Integrated analysis of acoustic, image and triple combo open-hole log data indicates that the computed volume of shale log is a strong predictor of anisotropy with a simple linear relationship. However, there is much anisotropy that is not accounted for by this lithologically related linear relationship. We refer to the residual obtained by subtracting the predicted anisotropy using this relationship from the measured anisotropy from a cross-dipole sonic tool as the excess anisotropy. The excess anisotropy is the remaining anisotropy that is not accounted for by linear regression between the volume of shale log and the measured anisotropy. We find that the excess anisotropy is linearly correlated to th... [more]