JournalTOCs

Journal of Control, Automation and Electrical Systems
Journal Prestige (SJR): 0.274

Citation Impact (citeScore): 1
Number of Followers: 11

Hybrid journal (It can contain Open Access articles)
ISSN (Print) 2195-3880 - ISSN (Online) 2195-3899
Published by Springer-Verlag

[2468 journals]

Comparative Analysis of Active Impedance Matching Interfaces for
Piezoelectric Energy Harvesters
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract This paper conducts a comparative study of the output energy generated by two compensation approaches for piezoelectric energy harvesters. These transducers are typically coupled to a cantilevered beam, and the compensation circuitry enhances the harvester’s performance under an input mechanical vibration stimulus. The output power of the piezoelectric transducer relies on both the reflected and intrinsic mechanical impedance, along with the total output load. The electrical equivalent circuit of the structure, incorporating the transducer, is primarily capacitive, leading to an out-of-phase relationship between current and voltage in the electrical domain, resulting in the generation of reactive power and a subsequent reduction in the overall system efficiency. The system’s first vibration mode, corresponding to a very low frequency, requires a significant passive inductor for impedance matching to ensure maximum power transfer to the load. In the first approach, a non-Foster circuit is implemented as a reactance for impedance matching, employing a Negative Impedance Converter (NIC) circuit. In another approach, the output of the cantilever beam is assessed using a synchronized switched inductor (SSHI). Both approaches are examined, and their feasibility limits are evaluated, taking into account the energy balance generated by the piezoelectric transducer. Experimental results illustrate that the active matching approach with a non-Foster reactance shows a greater enhancement in energy compared to the SSHI compensation method under conditions of harmonic mechanical oscillations.
  PubDate: 2024-08-23
Data-Driven Approach for Distributed Generation Impacts Assessment in the
Brazilian Regulatory Framework
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract The electric distribution sector is facing significant challenges in integrating distributed energy resources (DERs), with most assessment methodologies being primarily tested on standard feeders. However, given the nature of electric distribution systems, each feeder is unique and constantly changing, emphasizing the need for customized and updated feeder models for local quantitative studies. These studies encompass network operation, expansion planning, and DER integration. In response to this context, this paper proposes a methodology for extracting and processing information from public data to model up-to-date electric feeders. As these feeder models represent real operating circuits, they can be utilized by utilities, investors, and consumers. The proposed approach involves processing data from the Brazilian utilities’ geographic database (BDGD, in Portuguese) to develop structured simulations of distribution feeders using OpenDSS software. The BDGD standards are established by the Brazilian National Electric Energy Agency (ANEEL). In order to validate the methodology, two case studies are presented evaluating the impacts of distributed generation on real feeders from the Brazilian utilities: Minas Gerais Electric Power Company (CEMIG) and Bahia State Electricity Company (Neoenergia COELBA).
  PubDate: 2024-08-17
Fault-MTL: A Multi-task Deep Learning Approach for Simultaneous Fault
Classification and Localization in Power Systems
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Power system interruptions, though brief, carry significant costs and adverse consequences. Ensuring a reliable power supply necessitates accurate fault detection and swift resolution through fault classification and localization. The existing individual and joint approaches for fault classification and localization involve comprehensive expert-guided feature engineering and pre-processing algorithms depending on the selected classifier. This research proposes a fully automated, integrated multi-task deep learning-based framework called the Fault-MTL (multi-task learning) model for performing fault classification and localization at the same time. The multi-task feature interdependency accelerates the conduction of tasks with better performance. To the best of our knowledge, this is the first-of-its-kind study where the multi-task learning (MTL)-based deep model is developed for power system studies. To evaluate the model, we tested it on three state-of-the-art transmission line topologies, each with various initial conditions and simulated fault data variations in terms of fault type, distance, inception angle, and resistance. The tenfold cross-validation is used to measure the performance. The simulation experiments exhibit an exemplary performance by attaining the perfect validation in fault classification and the minimal mean average error of 1.59% in fault localization, across all three adapted topologies. For investigating the feasibility of the model, the ablation studies including the effect of noise, comparison with the existing state-of-the-art methods and the performance comparison of the work with the studies from the literature are performed in individual and combined simulation experiments of fault classification and fault localization.
  PubDate: 2024-08-11
Nonlinear Data-Driven Control Part II: qLPV Predictive Control with
Parameter Extrapolation
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract We present a novel data-driven Model Predictive Control (MPC) algorithm for nonlinear systems. The method is based on recent extensions of behavioural theory and Willem’s Fundamental Lemma for nonlinear systems by the means of adequate Input–Output (IO) quasi-Linear Parameter-Varying (qLPV) embeddings. Thus, the MPC is formulated to ensure regulation and IO constraints satisfaction, based only on measured datasets of sufficient length (and under persistent excitation). The main innovation is to consider the knowledge of the function that maps the qLPV realisation, and apply an extrapolation procedure in order to generate the corresponding future scheduling trajectories, at each sample. Accordingly, we briefly discuss the issues of closed-loop IO stability and recursive feasibility certificates of the method. The algorithm is tested and discussed with the aid of a numerical application.
  PubDate: 2024-08-06
Edge Device for the Classification of Photovoltaic Faults Using Deep
Neural Networks
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract The use of photovoltaic panels for sustainable electricity generation is increasing worldwide. Hence, large solar power plants must be monitored to find defects quickly and easily, avoiding prolonged interruptions in electricity generation. The present study aims to analyse the incorporation of transfer learning in convolutional neural network models to classify defects in visible spectral images of solar panels. Deep learning with convolutional neural networks is known for their precise classification of images, but they need a significant volume of images and training time. Transfer learning is intended to help the training process become faster and more precise. In addition, a publicly available image dataset was constructed using 36,000 images containing three classes of defects and a class without defects to evaluate tested network models. In this study, 17 networks were tested as potential classification models. The best network exhibited an accuracy higher than 99%. This accuracy was obtained with the MobileNetV3 network, which was optimised with Nvidia Tensor RT to run on an edge device with low power consumption and low weight, enabling the real-time classification of the defects presented in this study and allowing the classification of an image in an average of 50 ms. This approach has yet to be explored in the literature, and this paper aims to contribute to this discussion. The presented work has the limitation of not making image segmentation, where the image obtained by the camera is directly classified. From experiments with a large dataset close to an in-field solar plant inspection, trained models successfully classified the defined classes. These findings help solar plant operation and maintenance teams make quick and accurate decisions about scheduled maintenance.
  PubDate: 2024-08-05
Improving Distribution System State Estimation by Including Volt-Var
Control Information
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract The increasing penetration of distributed energy resources poses new challenges for operating distribution systems, as high penetration levels are causing adverse grid impacts. In this context, active grid regulation, such as the smart inverters functions recommended in IEEE 1547–2018, has become necessary. In this regard, advanced monitoring techniques, such as state estimation, are promising alternatives to enhance the operation of active distribution networks. However, the lack of reliable information is a technical limitation for applying estimation algorithms to distribution circuits. Therefore, knowledge of the control mode of distributed energy resources may be valuable information to enhance the accuracy of the estimates. This paper proposes to include the volt-var smart inverter function in WLS three-phase state estimation via iterative adjustment. The volt-var control variables are introduced as pseudo-measurements in the first stage, and the second one ensures the control and state variables’ compliance with the control model. The validation and benefits of the proposed method are presented via simulation results in the IEEE 34-node test feeder.
  PubDate: 2024-08-05
Nonlinear Data-Driven Control Part I: An Overview of Trajectory
Representations
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract In the literature, a recent debate has been brought up regarding how linear time-invariant systems can be represented by trajectories features. That is, how a single input–output (IO) data dictionary can be exploited to span all possible system trajectories, as long as the input is persistently exciting. Indeed, the so-called behavioural framework is a promising alternative for controller synthesis without the necessity of system identification procedures. In this paper, we provide an overview of the available results. In particular, we focus on how quasi-Linear Parameter Varying (qLPV) embeddings, in the data-driven context, can be used to represent nonlinear dynamical systems along suitable IO coordinates. We debate the topics of nonlinear data-driven simulation and predictions, as proposed in recent works. The effectiveness of the surveyed tools is tested in practice and shown to provide accurate descriptions of the nonlinear dynamics by the means of a linear representation structure. For such, we consider a high-fidelity nonlinear simulator of a rotational pendulum benchmark simulator and an electro-mechanical positioning experimental validation test-bench. We also debate that, even if the qLPV scheduling function is erroneously selected, the framework is still able to offer a reasonably trustworthy representation of the system.
  PubDate: 2024-08-03
Volt/Var Strategy Implementation in the Three-Phase Current Injection
Power Flow Employed for Microgrid Studies in a Global Power Flow
Environment
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Power flow studies are essential for planning and operating microgrids (MGs). However, power flow is generally calculated separately for MGs and medium voltage (MV) systems, which tends to overlook some characteristics of the joint MG-MV system. In this context, the literature proposes methods to simulate MG and MV systems in a unique power flow structure. However, some Volt/Var controls must be considered when solving the MG power flow, which increases the power flow iterations. This paper proposes a method to include the Volt/Var strategy in the three-phase Newton–Raphson current injection (NRCI) power flow. The Volt/Var strategy is included in the Jacobian matrix and solved with each power flow iteration. The CIGRE benchmark MV and LV networks and the European LV test Feeder are used to validate the proposed methodology. The conventional Newton–Raphson is employed for the MV system, and the NRCI for the MG systems. Three cases are considered: the first evaluates the MG with the Volt/Var strategy; the second compares the implementation; and the last evaluates the global power flow with the Volt/Var. The results show that the proposed implementation can converge smoothly with few iterations.
  PubDate: 2024-08-02
Information Theoretic Learning Applied to Daily Streamflow Forecast and
Its Impact on the Brazilian Hourly Energy Spot Prices
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract The Brazilian energy spot price is obtained through a chain of dynamic stochastic optimization models that works with the uncertainties related to its continental hydrogeneration-based power system. In that sense, this paper presents an information theoretic learning neural forecasting model for daily streamflow prediction of Brazilian hydroelectric power plants. More precisely, the maximum correntropy criterion was used as the error function of a multilayer perceptron. After the prediction stage, the generated outputs were used as one of the inputs of the model chain that is used to compute the hourly energy spot price in Brazil. To the best of the authors’ knowledge, it is the first paper that aims to analyze the impact of the streamflow prediction on the Brazilian hourly energy spot price formation. In terms of streamflow forecast, results indicated that the predictions originated from the proposed forecasting model were equivalent to the ones from the official models, especially in the first predicted day. In the spot price graph analysis, the main result pointed that the curves provided from the modeled structure were closer to the values obtained using the actual flows than the official prices, which shows that the proposed work could produce prices more aligned to the real hydrological system conditions. From that, the study’s relevance is due to the conclusion that the official process of streamflow forecasting can be improved to generated outputs more consistent with the actual system conditions, to avoid further expenses in the system operation due to potential unscheduled hydrothermal dispatches.
  PubDate: 2024-08-01
A Visible Light Positioning Technique Based on Artificial Neural Network
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract This paper presents an indoor positioning strategy based on Visible Light Communication that relies on LED luminaires as transmitters, whose luminous flux is modulated at different frequencies, and a light sensor as a receiver. Then, a previously trained Artificial Neural Network (ANN) uses the illuminance signal gathered by the receiver as input to estimate the sensor’s position. The main contribution of the technique is that the ANN is trained by using an illuminance estimator based on the lighting distribution of the luminaires, which is obtained through the IES file provided by the luminaire’s manufacturer, without the need to collect data from the environment. In this work, the designed illuminance estimator is validated by comparing it to the well-known commercial software DIALux and Relux. The algorithm’s setting and the performance evaluation of the ANN are explained. Then, the impact of the lighting uniformity and the environment’s number of divisions on the accuracy of the results is analyzed. Error analyses are also made by adding uncertainty to the illuminance measurements obtained by the sensor. Finally, the work is compared to several papers in the field.
  PubDate: 2024-08-01
Measuring Rotational and Translational Movements in Rotating Machines
Using a Computer Vision Approach
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract For a variety of production and development processes, there is a need for precise and reliable measurements of rotating machinery or objects. In this article, an alternative approach is introduced to assess both rotational and translational movements in a rotor by employing the technique known as “visual encoder.” This methodology combines principles of computer vision with visual components, operating analogously to conventional optical encoders. Non-contact measurements provided by visual encoders offer several advantages, including the ability to withstand free movements and oscillations along the rotation axis, as well as application in hostile environments, such as high-temperature conditions that might pose challenges for conventional measurement methods. The proposed method incorporates translational motion tracking into rotational velocity measurement using cost-effective conventional equipment. Experimental tests demonstrate that the developed system exhibited high precision and robustness under various operating conditions, successfully operating even at rotational frequencies close to the sampling rate. The results validate the developed technique as a viable alternative for measuring rotation and translational movement in rotor applications.
  PubDate: 2024-08-01
Voltage Vector Classification-Based Duty Cycle-Modulated PCC for OEW-PMSM
Drive with Three-Level Inversion
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract The permanent magnet synchronous motor (PMSM) is extensively used in electric vehicles. The predictive current control (PCC) technique is most popularly employed in the control of open-end winding interior PMSM (OEW-IPMSM) drives. It is the simplest method with less complexity and is more easily understandable than other predictive control techniques. PCC involves optimization and evaluation of the cost function to reduce the errors in stator currents. The dual inverter-fed OEW-IPMSM drive using conventional PCC with 19 voltage vectors (VVs) performs poorly as one Active VV is applied for the complete control interval which yields in over-regulation with high switching frequency. In proposed PCC (P-PCC), initially voltage vectors were segregated into two groups based on machine operating speed and these vectors are applied for the evaluation of cost function which reduces the computational burden as well as switching frequency of the inverter. The obtained voltage vector (from CF minimization) and a null vector are used in one control cycle to minimize the q-axis stator current ripples and common mode voltage. In P-PCC, the cost function is modified which utilizes flux weights which reduces flux ripples for better performance. The efficacy of P-PCC is verified through MATLAB simulation results and validated using experimentation with a 3.7 kW OEW-IPMSM drive with d-SPACE controller.
  PubDate: 2024-08-01
Robust Collision-Free Guidance for Multirotor Aerial Vehicles Under
Short-Range Sensors
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract This paper is concerned with the translational guidance of multirotor aerial vehicles with uncertain dynamics and equipped with short-range detection sensors in a scenario containing disturbances/uncertainties, multiple accelerated obstacles, and velocity constraints. To address this problem, we propose a robust guidance strategy based on the continuous control obstacles method. To handle disturbances and uncertainties, the proposed method tightens the position and velocity admissible sets according to the respective tracking errors. Moreover, a hybrid prescribed-time arbitrary-order differentiator is employed to robustly estimate the obstacles’ velocities and accelerations within a prescribed time interval using measurements from a short-range sensor. As a result, the proposed method can fit into the available time for executing an avoidance maneuver upon the detection and tracking of obstacles. Then, we build a set of possible future positions for the obstacles according to their observed velocities and accelerations, and use this set to calculate a position command for the guided vehicle. The proposed method is experimentally evaluated using an augmented-reality setup composed of a Crazyflie quadcopter, motion capture cameras, and virtual obstacles. The results show that the proposed method is viable for real-time implementation and effective in providing collision avoidance and satisfying velocity constraints.
  PubDate: 2024-08-01
A Model for a Lithium-Polymer Battery Based on a Lumped Parameter
Representation of the Charge Diffusion
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract This paper proposes a model of the diffusion and electrical dynamics of lithium-polymer batteries through a lumped parameter approach. Discharge experiments were performed on a set of three battery cells using a programmable DC load. The resulting data sets were used to obtain several model parameters using different optimization approaches. A comparison of the performance of such optimization approaches to estimate the model parameters from experimental tests was also conducted. The resulting models had an overall good performance, proving that the chosen modeling approach applies to lithium-polymer batteries.
  PubDate: 2024-08-01
Review of Power System State Estimation and Maturity Level of Market
Solutions: Preceding Steps
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Power system state estimation (PSSE) is a control center application that comprises a collection of algorithms aimed at providing essential information about the current operating condition of the power grid. As such, PSSE plays a vital role in the real-time operation of power systems. Accuracy and reliability of the estimator are closely connected to both quality and quantity of the real-time data that feed it. Therefore, such applications can benefit from functions that pre-filter the dataset, removing obvious spurious measurements or complementing it with reliable information. Moreover, some functionalities intended to analyze the dataset are desirable, since they indicate if state estimation can be performed with the currently available measurement set and if its vulnerabilities can be identified. Such analysis tools can assist in the design of measurement sets, or strengthen an existing one. They constitute preceding steps for PSSE and have drawn growing interest in recent years, with the evolution of computational techniques and the advent of new technologies. This paper provides a review of the literature on such preceding steps, namely pre-filtering, observability analysis, redundancy/criticality analysis, and metering system design, along with a market evaluation of existing solutions, with main focus on transmission systems.
  PubDate: 2024-08-01
High-Speed Motion Planning with Object Acceleration Constraint for
Industrial Robots
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract In this paper, we propose a new approach to efficiently plan trajectories for industrial robots, where total trajectory time is reduced while limiting the robot end-effector acceleration to a safe threshold, which guarantees an object to be transported safely without damage or spills. We also propose to solve the optimization problem in two steps by utilizing both the quadratic programming algorithm and sparse sequential quadratic programming method. The proposed two-step procedure empirically proves that computing time of solving the optimization problem is significantly reduced. Effectiveness of the proposed approach was verified in Drake, where the obtained results are highly promising.
  PubDate: 2024-08-01
Generalized Harmonic State Estimation: An Approach Considering Measurement
and Parameter Errors
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Harmonic state estimation (HSE) is an useful technique for determining harmonic voltages and currents in electric power systems based on synchronized measurements and network impedances parameters. However, measurements and parameters data can be corrupted by gross errors yielding unsatisfactory estimation results. Despite recent methods have been proposed for HSE in power systems, there are few works considering both harmonic state variables and parameters estimation. In order to solve this problem, this paper presents a generalized harmonic state estimation considering uncertain network parameters and synchronized measurements. In the proposed approach, harmonic voltage and current phasors are obtained by measurement units allocated along the system. Network parameters, such as line and load impedances, are treated as inequality constraints in an optimization problem formulation considering both system state variables and parameters to be determined by the proposed HSE. The main contribution of this research paper is the use of a deterministic approach for estimating both harmonic state variables and parameters with reduced estimation errors when compared with the traditional weighted least squares (WLS) technique. Computational simulations are carried out using the IEEE test systems and results are also validated using RSCAD (Real-Time Simulation Software Package) software.
  PubDate: 2024-06-26
The Evaluation of Transmission Line Modeling on Lightning Performance
Considering Surger Arresters: Impact in the Energy and Backflashover Rates
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract This paper investigates the impact of transmission line parameter calculation formulations on surge arrester performance in response to lightning strikes. This evaluation consists of comparing power and energy dissipated in surge arresters, as well as critical currents and line backflashover rates. The lightning performance of surge arrester installed in a typical Brazilian 138 kV transmission line is assessed by simulations in ATP software, while transmission line parameters are calculated in 3 different ways, namely: (i) Carson formulation, (ii) Nakagawa formulation considering the electrical parameters of the ground constant with the frequency, and (iii) Nakagawa formulation considering the frequency-dependent characteristics of the soil. Taking as reference the results determined by Carson’s formulation (since this formulation is the most used in programs for calculating transients, such as ATP), it is shown that Nakagawa’s formulations considering both constant and frequency-dependent soil parameters can lead to differences for the cases of unprotected lines, partially protected (lightning arresters in one or two phases) and fully protected (lightning arresters in all phases), resulting in an inaccurate prevision of insulation failure, leading to an increase in the backflashover rate.
  PubDate: 2024-06-23
Tracking Defective Panel on Photovoltaic Strings with Non-Intrusive
Monitoring and Deep Learning
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Photovoltaic (PV) generation systems are susceptible to various types of faults. Our objective is to identify unusual operating conditions in a photovoltaic string using only the voltage and current generated at its terminals. To achieve this, we collected voltage and current samples produced by a PV string consisting of six panels during typical operation and four possible types of faults: full panel shading, partial panel shading, panel short-circuits, and electrical arcs in conductor cables. The first three fault groups were further subdivided into six faults, one for each PV panel, resulting in 20 different operating conditions. We collected samples of the electrical system’s generation under each state in different climatic situations. We used the resulting dataset to train a convolutional neural network (CNN) and a classic machine learning method, K-Nearest Neighbors (KNN). The results showed that the CNN’s ability to learn the characteristics that identify each of the 20 operating conditions resulted in an average accuracy of 95.78%, while the KNN, taking into account previously defined features, achieved an accuracy of 86.34%.
  PubDate: 2024-06-18
  DOI: 10.1007/s40313-024-01103-y
Day-Ahead Photovoltaic Power Forecasting Using Deep Learning with an
Autoencoder-Based Correction Strategy
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Accurate forecasting is crucial for successfully integrating photovoltaic (PV) power plants into electrical grids and microgrids. Accordingly, this work presents a hybrid methodology for day-ahead PV power forecasting (PPF). It begins by examining three deep learning (DL) techniques, long short-term memory (LSTM), gated recurrent unit (GRU), and multilayer perceptron (MLP), as potential forecasting models. To find a robust forecasting model, feature selection is employed to select the most relevant input features, and additionally, hyperparameter optimization is performed using the Chu–Beasley genetic algorithm to automatically set the hyperparameters for each technique. An initial day-ahead PPF is computed recursively after selecting the optimal forecasting model. Subsequently, this initial forecast is refined using a long-short-term memory autoencoder (LSTM-AE) that corrects the initial PPF. To further enhance the interpretability of the final forecast, the k-means algorithm, incorporating a soft-dynamic time warping (DTW) metric, is utilized. The efficacy of the methodology is validated using real data from a solar farm at the State University of Campinas (UNICAMP) in Brazil. Empirical results demonstrate that the proposed methodology improves the forecast accuracy by more than 3.5% when LSTM-AE is applied for correction compared to state-of-the-art models.
  PubDate: 2024-06-07
  DOI: 10.1007/s40313-024-01099-5

HOME > Browse the 73 Subjects covered by JournalTOCs
Subject	Total Journals