Search

Inverse model predictive control (IMPC) is a control technique that was recently proposed for power electronic converters. IMPC inherits the advantages of model predictive control (MPC) in terms of ability to handle complex and nonlinear systems and achieving multiple control objectives, while adhering to various constraints. Unlike MPC, IMPC offers a significantly reduced computational burden by omitting the iterative computations of the cost functions and states predictions. Nevertheless, both IMPC and MPC rely significantly on the dynamic model of the power converter. This makes them susceptible to uncertainties and disturbances. This article presents a novel technique to enhance the reliability and robustness of the IMPC for electric vehicle chargers by treating the converter's dynamic model as a black box. Then, an adaptive estimation strategy employing a recursive least square algorithm is proposed for online dynamic model estimation, which is then used by the IMPC for optimal switching states prediction. The key benefit of the proposed technique is the utilization of an accurate and real-time estimated dynamic model, which facilitates a reliable states prediction by the IMPC. The effectiveness of the proposed technique is demonstrated through extensive simulations and experimental validation for a three-phase three-level T-type rectifier.

The transient power grid stability is greatly affected by the unpredictability of inverter-based resources of today's interconnected power grids. This article introduces an efficient transient stability status prediction method based on deep temporal convolutional networks (TCNs). A grey wolf optimizer (GWO) is utilized to fine-tune the TCN hyperparameters to improve the proposed model's accuracy. The proposed model provides critical information on the transient grid status in the early stages of fault occurrence, which may lead to taking the proper action. The proposed TCN-GWO uses both synchronously sampled values and synthetic values from various bus systems. In a postfault scenario, a copula of processing blocks is implemented to ensure the reliability of the proposed method where high-importance features are incorporated into the TCN-GWO model. The proposed algorithm unlocks scalability and system adaptability to operational variability by adopting numeric imputation and missing-data-tolerant techniques. The proposed algorithm is evaluated on the 68-bus system and the Northeastern United States 25k-bus synthetic test system with credible contingencies using the PowerWorld simulator. The obtained results prove the enhanced performance of the proposed technique over competitive state-of-the-art transient stability assessment methods under various contingencies with an overall accuracy of 99% within 0.64 s after the fault clearance.

Transient stability assessment (TSA) is critical to the reliable operation of a power system against severe fault conditions. In practice, TSA based on deep learning is preferable for its high accuracy but often overlooks challenges in maintaining data privacy while coping with network topology changes. This article proposes an innovative focal loss-based multihead attention convolutional network (FLACON) for accurate post-disturbance TSA under both symmetrical and asymmetrical smart grid faults. The proposed approach effectively incorporates cross-domain deep federated transfer learning (FTL) to leverage local operating data for TSA in a decentralized fashion. By introducing convolutional layers alongside multi-head attention mechanisms, the FLACON framework significantly improves learning efficiency across geographically distributed datasets. To address the challenge of class imbalance, the model integrates a balance factor-enhanced focal loss function. The FTL architecture enables decentralized model training across various clients, thus preserving data privacy and reducing the burden of communication overhead. To avoid the constant adjustment of hyperparameters, the FLACON employs an inductive transfer learning approach for hyperparameter tuning of the pre-trained model, markedly decreasing training time. Extensive experiments on datasets from the IEEE 39-bus system and the IEEE 68-bus system demonstrate FLACON's exceptional accuracy of 98.98% compared to some competitive alternatives.

In this paper, a new control technique called inverse model predictive control (IMPC) is proposed for power electronic converters. The proposed IMPC technique is primarily based on the inverse of the conventional finite set model predictive control. The key advantage of this design is that it avoids predicting the controlled states for all possible switching-state vectors, while maintaining the advantage of adhering to multiple constraints and achieving multiple objectives. IMPC predicts the optimal control signal that minimizes the cost function and converts it into a switching vector. Unlike classical MPC, the computational time required for IMPC is significantly reduced which makes it easily applicable to all types and levels of power electronics converters. The proposed method does not depend on the number of possible switching vectors and is compatible with low-cost microcontrollers commonly used for industrial applications. Additionally, the proposed control inherits the benefits of MPC, such as the ability to achieve its objectives while adhering to various constraints, minimal parameters tuning requirements, and reduced computational time. To demonstrate the effectiveness of the proposed technique, experimental results are presented for a five-level active neutral point clamped flying capacitor inverter (ANPC-FC) as a case study.

Lithium-ion battery prognostics and health management (BPHM) systems are vital to the longevity, economy, and environmental friendliness of electric vehicles and energy storage systems. Recent advancements in deep learning (DL) techniques have shown promising results in addressing the challenges faced by the battery research and innovation community. This review article analyzes the mainstream developments in BPHM using DL techniques. The fundamental concepts of BPHM are discussed, followed by a detailed examination of the emerging DL techniques. A case study using a data-driven DLinear model for state of health estimation is introduced, achieving accurate forecasts with minimal data and high computational efficiency. Finally, the potential future pathways for research and development in BPHM are explored. This review offers a holistic understanding of emerging DL techniques in BPHM and provides valuable insights and guidance for future research endeavors.

This article introduces a set of innovative solutions designed to enhance the scalability of ac–dc side operations in fast electric vehicle (EV) charging stations. The proposed solutions focus on streamlining and regulating the connection process for integrating a new active front-end rectifier (AFR) with existing AFRs at the high-voltage dc-link side, without requiring detailed knowledge of their specifications, such as control algorithms, switching frequencies, topologies, and modulation techniques. Neglecting these specifications can result in significant adverse effects, particularly on grid currents within the ac–dc side of the charging station. Conversely, these specifications have minimal impact on the dc–dc side. Therefore, this article primarily concentrates on addressing the scalability challenges associated with the ac–dc side of fast EV charging stations. Experimental analysis is conducted to assess the consequences of underestimating any specification, followed by the proposal of a general solution to compensate for or reduce each effect. The proposed methods effectively address the critical demand for scalability in fast EV chargers. Furthermore, these techniques are implemented using low-cost microcontrollers and validated experimentally through the utilization of three parallel-connected AFRs.

This article proposes an adaptive and fault-tolerant communication method for controlling parallel-connected active front-end rectifiers (AFRs). The proposed method relies on the principle of master-slave communication based on the controller area network bus protocol. The master unit is responsible for generating current reference signal and for sharing it with the slaves, while the slave units are solely responsible for generating the power based on the received reference set points. The master can be selected and changed automatically based on a negotiation algorithm among the connected rectifiers. Then, if a communication fault occurs in the master, another master is chosen by the slaves. On the other hand, slaves’ communication faults are tolerated by switching to communication-less mode of operation with online estimation of the current reference signal instead of receiving it over the communication network. The proposed algorithms are validated by simulation and experimentally on a prototype with three parallel AFRs.

The widespread penetration of inverter-based resources has profoundly impacted the electrical stability of power systems (PSs). Deepening grid integration of photovoltaic and wind systems is introducing unforeseen uncertainties for the electricity sector. As a cutting-edge machine learning technology, deep reinforcement learning (DRL) breakthroughs have been in the spotlight over the last few years with potential contributions to PS stability (PSS). The ubiquitous DRL architecture, by learning from the dynamism inherent in PSs, produces near-optimal actions for PSS. This article provides a rigorous review of the latest research efforts focused on DRL to derive PSS policies while accounting for the unique properties of power grids. Furthermore, this paper highlights the theoretical advantages and the key tradeoffs of the emerging DRL techniques as powerful tools for optimal power flow. For all methods outlined, a discussion on their bottlenecks, research challenges, and potential opportunities in large-scale PSS is also presented. This review aims to support research in this area of DRL algorithms to embrace PSS against unseen faults and different PS topologies.

Peer-to-peer (P2P) energy trading has gained significant importance in recent years due to the growing energy needs worldwide. To ensure the effective and efficient implementation of P2P energy trading, it is necessary to analyze the concept from multiple dimensions. This study aims to investigate the challenges that may hinder the smooth flow of P2P energy trading and identify strategies to overcome them. Technical, cybersecurity, renewable energy integration, economic, pricing mechanisms, and regulatory challenges are among the key obstacles that may curtail the full potential of P2P energy trading. In addition, the full achievement of the P2P energy trading potential requires a global response from stakeholders to ensure widespread acceptance and adoption. Game theory and agent-based modeling can effectively address these challenges and facilitate the successful implementation of P2P energy trading.

This article proposes a digital twin (DT)-based diagnosis and fault-tolerant control for T-type three-level rectifiers. To develop the DT, a dense deep neural network (DNN) machine learning approach is used. The DT is trained offline using a set of experimental data and updated online to get the maximum possible accuracy. Then, the DT is used for the diagnosis and tolerance of open-switch faults (OSFs) and faults related to voltage and current sensors or for sensorless control. The OSF detection and localization algorithm is implemented based on the dynamic response difference between the physical system and its DT. First, the OSF is detected and localized based on the grid current dynamics, where each switch fault generates a specific pattern in the current dynamics. OSF is tolerated by changing the switching function based on the location of the fault. Second, the voltage and current sensor fault is detected when the DT provides a specific amplitude of currents while the physical sensors do not provide a correct measurement. This case is tolerated by feeding back the grid currents or voltages from the DT as an alternative to the physical sensors. The proposed technique has low overhead, enhances the reliability of the power converter, and is applicable for sensorless mode of control. Experimental investigations are conducted to validate the proposed concept.

This paper proposes an adaptive control technique (ACT) for a three-phase, three-level, T-type rectifier based on online disturbance estimation and compensation. The proposed solution also regulates the DC-link voltage and grid currents under uncertainties, disturbances, measurement noises, and unbalanced grid voltages without cascaded control. The proposed controller consists of two layers; the first one is responsible for estimating nonlinearities and model uncertainties based on Kalman Filter Algorithm (KFA). The second layer is responsible for controlling both grid currents and DC link voltage using Linear Quadratic Regulator (LQR). The proposed controller is analyzed theoretically, validated experimentally, and the performance of the proposed controller is compared with two other controllers. The simulation and experimental results prove the superiority of the proposed controller and show that the proposed controller can ensure fast-tracking performance with almost zero steady-state error. The proposed controller has the ability to overcome severe disturbances such as AC and DC side disturbances, measurement noises, and mathematical model’s uncertainties even up to 400%.

The hierarchical control structure was introduced to allow the integration of power-electronics-based distributed generation into the microgrid in a smart and flexible manner. The main aim of the primary controller in such a structure is to achieve accurate active and reactive power sharing, whereas the secondary control aims to ensure voltage and frequency (V/f) stability. Generally, converter-level secondary controllers utilize classical nested loop control that suffer from a slow dynamic response and cumbersome parameter tuning. The existing-model-based and estimation-based secondary controllers are fast, but require complex design methodology, high communication bandwidth, and, consequently, higher data analysis and computational burden. This article presents a simple predictive-based secondary control for the ac microgrid that is fast and robust and has a low design complexity, low communication bandwidth, and no parameter tuning requirement in the secondary control layer. The proposed predictive control optimally restores voltage and frequency in the microgrid by predicting their trajectory deviations and leveraging the droop characteristic curves. Experimental tests performed with three parallel-connected grid-forming inverters in an islanded operation validate that the controller can accurately maintain V/f stability, while ensuring active and reactive power sharing.

Abstract Here, a finite‐control‐set sliding‐mode control (FCS‐SMC) method is proposed for single‐phase three‐level T‐type inverter‐based transformerless dynamic voltage restorers (TDVRs). The inherent advantages of SMC (fast dynamic response and high robustness) are combined with FCS concept to increase the effectiveness of the method in achieving the desired control objectives. First, the use of FCS eliminates the modulator requirement, which reduces the design complexity in the practical implementation. Second, an effective method based on charging/discharging conditions of DC capacitors is proposed for balancing capacitor voltages using relevant switching state rather than combining DC voltage error with the inductor current error through a suitable weighting factor in forming the cost function. Therefore, the weighting factor necessity in the control algorithm is eliminated. Finally, the steady‐state error in the compensation voltage is eliminated by the proportional‐resonant (PR) controller. The studied T‐type inverter‐based TDVR topology offers an alternative solution to the existing DVR topologies. Experimental results are carried out to demonstrate the effectiveness of the proposed FCS‐SMC method in maintaining the load voltage at the desired level despite the voltage sags, swells, and distortions occurring in the grid voltage.

In this article, we investigate the problem of electricity theft attacks on smart meters when malicious customers (i.e., adversaries) claim injecting more generated energy into the grid to get more profits from utility companies. These attacks can be applied by accessing the smart meters monitoring renewable-based distributed generation (DG), and manipulating the reading. In this article, we propose approaches that rely on data sources with only a single generator (i.e., solar only) and multifuel type; and address the crucial effects of slight perturbations that the attacker can add, which can deceive the detector. In particular, this article introduces an efficient multitask deep-learning-based detector that offers a higher detection rate, copes with different fuel types, and uses only single data sources. The proposed detector incorporates months and days as two additional features to boost the performance and properly guide the model to successful detection. The proposed method is then extended to consider small perturbations that attackers may use to launch successful attacks. We conduct extensive simulations for two different detectors, one for solar DG and the other for multiple fuel types (i.e., solar and wind). Using a realistic dataset, the results reveal that the proposed recurrent neural network-based detectors identify adversaries at a higher rate than the existing solutions, even with minimal perturbations and different fuel types.

Model Predictive Control (MPC) provides various advantages over traditional controllers in power electronics applications. However, reducing the complexity and computational burden of the Finite-control set-model predictive control (FCS-MPC) in multi-leg multilevel inverters is still a challenging task. In this paper, a simplified model predictive direct power control (MPDPC) for a three-level, four-leg grid-connected converter (4L-GCC) is proposed. The main idea of the proposed strategy is to reduce the computational burden of the control algorithm by using only the switching vectors of the first sector to optimize the cost function. The proposed control method can ensure accurate control of active and reactive powers, control of zero-sequence current, as well as DC capacitor voltages balancing without using any weighting factors. Simulation and experimental results are provided to prove the effectiveness and simplicity of the proposed MPC algorithm compared with most-recently proposed solutions.

This paper proposes an enhanced Deadbeat Controller (DBC) for a grid-tied Flying Capacitors Inverter (FCI). The proposed DBC guarantees the balancing of the capacitors’ voltages while injecting current to the grid with lower Total Harmonics Distortion (THD). The proposed controller has the following advantages: 1) Improved current tracking quality even at zero crossing instants by using a weighted state-space model, 2) Superior steady-state performance (lower current THD) compared to other prediction-based control techniques such as Finite-Control-Set Model Predictive Control, 3) The generated duty cycles are normalized to the common base when the desired state is out of reach within the sampling time, 4) Voltage Ride-Through (VRT) capability, and 5) Robustness to parameters variation. Theoretical analysis, simulation, and experimental results are presented to show the effectiveness of the proposed control technique in ensuring uninterruptible and smooth transfer of energy to the grid during normal/abnormal operating conditions (severe voltage sags, parameters variation, etc.).

This paper describes a novel single-phase thirteen-level packed E-cell inverter (PEC13) for grid-tied photovoltaic (PV) systems. PEC13 topology contains six power switches, two four-quadrant switches and four DC capacitors. The main advantage offered by the proposed PEC13 is the ability to produce different voltage levels without any modifications in power circuit when open circuit fault occurs on one or two four-quadrant switches. In faulty condition, PEC13 can continue its operation and behaves as PEC9 or PUC7 inverter configuration. Furthermore, a reconfigurable finite-control set model predictive control (R-FCS-MPC) is designed to control the proposed grid-connected PV systems based PEC13 inverter. The proposed R-FCS-MPC assures the transition between PEC13 to PEC9 or PUC7 configuration through the adjustment of DC-link capacitor voltages balancing. The effectiveness of the R-FCS-MPC with the proposed PEC13 topology is evaluated through experimental validations using real-time hardware in the loop (HIL) setup. Provided experimental results demonstrate that the R-FCS-MPC enables to achieve the normal operation, multi-functionality, besides the high performance of the novel PEC13 inverter topology under step change in solar irradiance and faulty operation of four-quadrant switches.

Having a reduced number of switches and isolated DC sources yet generating a higher number of voltage levels has been always the challenge when selecting the appropriate Multilevel Inverter (MLI) topology. Nowadays, Single-DC-Source Multilevel Inverter (SDCS-MLI) topologies are being considered as more suitable for many power system applications such as Renewable Energy (RE) conversion systems and electrified transportations compared to the Multiple-DC-Source MLIs (MDCS-MLIs). Moreover, increasing the power rating and minimizing the switching frequency while maintaining reasonable power quality using a SDCS-MLI is an important requirement and a persistent challenge for the industry. Thus, this paper presents a general review on the available SDCS-MLI topologies and future trends. Existing solutions are discussed and analyzed based on their topologies, number of output voltage levels, number of active/passive components, advantages/limitations, maturity, and industrial applications. Furthermore, recommendations for future research and development are suggested in this paper.

An efficient and cost-effective power converter is a pre-requisite for the modern power applications. With the evolvement of matured medium power self-commutated switching devices, multilevel inverters (MLIs) are emerged as a promising solution for high-power medium-voltage applications. Though, MLIs are performing a promising role in industrial applications, their high device count, size, cost and control complexities have restricted their market penetration. To address the disadvantages of MLIs, researchers are continuously contributing to new generation topologies under the name of reduced switch count (RSC) MLIs. From the past decade, numerous RSC-MLIs topologies have been reported for various applications. Therefore, this paper presents a comprehensive review and classification of RSC-MLI topologies, in terms of their structure, features, limitations, suitability and selection for specific applications.

For the utility to plan the resources accurately and balance the electricity supply and demand, accurate and timely forecasting is required. The proliferation of smart meters in the grids has resulted in an explosion of energy datasets. Processing such data is challenging and usually takes a longer time than the requirement of a short-term load forecast. The paper addresses this concern by utilizing parallel computing capabilities to minimize the execution time while maintaining highly accurate load forecasting models. In this paper, a thousand smart meter energy datasets are analyzed to perform day ahead, hourly short-term load forecast (STLF). The paper utilizes multi-processing to enhance the overall execution time of the forecasting models by submitting simultaneous jobs to all the processors available. The paper demonstrates the efficacy of the proposed approach through the choice of machine learning (ML) models, execution time, and scalability. The proposed approach is validated on real energy consumption data collected at distribution transformers' level in Spanish Electrical Grid. Decision trees have outperformed the other models accomplishing a tradeoff between model accuracy and execution time. The methodology takes only 4 minutes to train 1,000 transformers for an hourly day-ahead forecast of (~24 million records) utilizing 32 processors.

Forecasting of energy consumption in Smart Buildings (SB) and using the extracted information to plan and operate power generation are crucial elements of the Smart Grid (SG) energy management. Prediction of electrical loads and scheduling the generation resources to match the demand enable the utility to mitigate the energy generation cost. Different methodologies have been employed to predict energy consumption at different levels of distribution and transmission systems. In this paper, a novel hybrid deep learning model is proposed to predict energy consumption in smart buildings. The proposed framework consists of two stages, namely, data cleaning, and model building. The data cleaning phase applies pre-processing techniques to the raw data and adds additional features of lag values. In the model-building phase, the hybrid model is trained on the processed data. The hybrid deep learning (DL) model is based on the stacking of fully connected layers, and unidirectional Long Short Term Memory (LSTMs) on bi-directional LSTMs. The proposed model is designed to capture the temporal dependencies of energy consumption on dependent features and to be effective in terms of computational complexity, training time, and forecasting accuracy. The proposed model is evaluated on two benchmark energy consumption datasets yielding superior performance in terms of accuracy when compared with widely used hybrid models such as Convolutional (Conv) Neural Network-LSTM, ConvLSTM, LSTM encoder-decoder model, stacking models, etc. A mean absolute percentage error (MAPE) of 2.00% for case study 1 and a MAPE of 3.71% for case study 2 is obtained for the proposed forecasting DL model in comparison with LSTM-based models that yielded 7.80% MAPE and 5.099% MAPE for two datasets respectively. The proposed model has also been applied for multi-step week-ahead daily forecasting with an improvement of 8.368% and 20.99% in MAPE against the LSTM-based model for the utilized energy consumption datasets respectively.

This paper proposes an effective Photovoltaic (PV) Power Forecasting (PVPF) technique based on hierarchical learning combining Nonlinear Auto-Regressive Neural Networks with exogenous input (NARXNN) with Long Short-Term Memory (LSTM) model. First, the NARXNN model acquires the data to generate a residual error vector. Then, the stacked LSTM model, optimized by Tabu search algorithm, uses the residual error correction associated with the original data to produce a point and interval PVPF. The performance of the proposed PVPF technique was investigated using two real datasets with different scales and locations. The comparative analysis of the NARX-LSTM with twelve existing benchmarks confirms its superiority in terms of accuracy measures. In summary, the proposed NARX-LSTM technique has the following major achievements: 1) Improves the prediction performance of the original LSTM and NARXNN models; 2) Evaluates the uncertainties associated with point forecasts with high accuracy; 3) Provides a high generalization capability for PV systems with different scales. Numerical results of the comparison of the proposed NARX-LSTM method with two real-world PV systems in Australia and USA demonstrate its improved prediction accuracy, outperforming the benchmark approaches with an overall normalized Rooted Mean Squared Error (nRMSE) of 1.98% and 1.33% respectively.

The current electric power system witnesses a significant transition into Smart Grids (SG) as a promising landscape for high grid reliability and efficient energy management. This ongoing transition undergoes rapid changes, requiring a plethora of advanced methodologies to process the big data generated by various units. In this context, SG stands tied very closely to Deep Learning (DL) as an emerging technology for creating a more decentralized and intelligent energy paradigm while integrating high intelligence in supervisory and operational decision-making. Motivated by the outstanding success of DL-based prediction methods, this article attempts to provide a thorough review from a broad perspective on the state-of-the-art advances of DL in SG systems. Firstly, a bibliometric analysis has been conducted to categorize this review’s methodology. Further, we taxonomically delve into the mechanism behind some of the trending DL algorithms. We then showcase the DL enabling technologies in SG, such as federated learning, edge intelligence, and distributed computing. Finally, challenges and research frontiers are provided to serve as guidelines for future work in the futuristic power grid domain. This study’s core objective is to foster the synergy between these two fields for decision-makers and researchers to accelerate DL’s practical deployment for SG systems.

Different aggregation levels of the electric grid’s big data can be helpful to develop highly accurate deep learning models for Short-term Load Forecasting (STLF) in electrical networks. Whilst different models are proposed for STLF, they are based on small historical datasets and are not scalable to process large amounts of big data as energy consumption data grow exponentially in large electric distribution networks. This paper proposes a novel hybrid clustering-based deep learning approach for STLF at the distribution transformers’ level with enhanced scalability. It investigates the gain in training time and the performance in terms of accuracy when clustering-based deep learning modeling is employed for STLF. A k-Medoid based algorithm is employed for clustering whereas the forecasting models are generated for different clusters of load profiles. The clustering of the distribution transformers is based on the similarity in energy consumption profile. This approach reduces the training time since it minimizes the number of models required for many distribution transformers. The developed deep neural network consists of six layers and employs Adam optimization using the TensorFlow framework. The STLF is a day-ahead hourly horizon forecasting. The accuracy of the proposed modeling is tested on a 1,000-transformer substation subset of the Spanish distribution electrical network data containing more than 24 million load records. The results reveal that the proposed model has superior performance when compared to the state-of-the-art STLF methodologies. The proposed approach delivers an improvement of around 44% in training time while maintaining accuracy using single-core processing as compared to non-clustering models.

Machine learning algorithms have been intensively applied to perform load forecasting to obtain better accuracies as compared to traditional statistical methods. However, with the huge increase in data size, sophisticated models have to be created which require big data platforms. Optimal and effective use of the available computational resources can be attained by maximizing the effective utilization of the cluster nodes. Parallel computing is demanded to allow for optimal resource utilization in dealing with smart grid big data. In this paper, a master-slave parallel computing paradigm is utilized and experimented with for load forecasting in a multi-AMI environment. The paper proposes a concurrent job scheduling algorithm in a multi-energy data source environment using Apache Spark. An efficient resource utilization strategy is proposed for submitting multiple Spark jobs to reduce job completion time. The optimal value of clustering is used in this paper to cluster the data into groups to be able to reduce the computational time additionally. Multiple tree-based machine learning algorithms are tested with parallel computation to evaluate the performance with tunable parameters on a real-world dataset. One thousand distribution transformers’ real data from Spain for three years are used to demonstrate the performance of the proposed methodology with a trade-off between accuracy and processing time.

Smart grids have been gradually replacing the traditional power grids since the last decade. Such transformation is linked to adding a large number of smart meters and other sources of information extraction units. This provides various opportunities associated with the collected big data. Hence, the triumph of the smart grid energy paradigm depends on the factor of big data analytics. This includes the effective acquisition, transmission, processing, visualization, interpretation, and utilization of big data. The paper provides deep insights into various big data technologies and discusses big data analytics in the context of the smart grid. The paper also presents the challenges and opportunities brought by the advent of machine learning and big data from smart grids.

This paper proposes a sensorless field-oriented control (FOC) of an open-end stator winding five-phase induction motor (OESW-FPIM). The FOC technique used is associated with dual Space Vector Modulation (SVM) to provide a constant switching frequency and lower harmonics distortion. Furthermore, a simple hybrid observer is proposed which combines a model reference adaptive system (MRAS) and a sliding mode (SM) observer. The examined observer is designed for the estimation of the rotor flux and rotational speed as well as for the estimation of the load torque disturbances. Lyapunov theorem is used in this paper to prove the observer's stability. The work presented in this paper aims to enhance the researched motor's sensorless control and its robustness against external load disturbances and parameters variation. In the proposed MRAS-SM observer, the reference model is replaced by a SM model which uses a sigmoid function as a switching function to overcome the chattering problem. This combination is intended to make use of the advantages of both strategies. At the same time, to preserve the high-level performance of the sensorless FOC technique and to reduce system uncertainties, an estimation algorithm is developed to identify the rotor resistance and the stator resistance simultaneously during motor operation. The parameter estimation algorithm is combined with the proposed control to improve the speed estimation and control accuracy, particularly at low-speed operation. Finally, the effectiveness of the proposed control is validated in real-time by utilizing a hardware-in-the-loop (HIL) platform.

The high voltage power transformer is the critical element of the power system, which requires continuous monitoring to prevent sudden catastrophic failures and to ensure an uninterrupted power supply. The most common failures in the transformer are due to partial discharge (PD) in electrical insulations which are the results of the insulation degradation over time. Different approaches have been proposed to monitor, detect, and locate the partial discharge in power transformers. This paper reviews and evaluates the current state-of-the-art methods for PD detection and localization techniques, and methodologies in power transformers. Detailed comparisons of PD detection techniques have been identified and discussed in this paper. The drawbacks and challenges of different partial discharge measurement techniques have been elaborated. Finally, brief reviews of PD denoising signals, feature extraction of PD signals, and classification of partial discharge sources have been addressed.

Smart grids are re-engineering the electricity transmission and distribution system throughout the world. It is an amalgam of increased digital information with the electrical power grids. Managing the data generated from the grid efficiently is the key to successful knowledge extraction from the smart grid big data. Most of the scientific advancements are becoming data-driven and becoming an interesting area of research for data scientists. It is challenging the world computationally enough to develop new storage methods and data processing technologies. Managing big data involves data cleaning, integration of varied data sources, and decision-making applications. This paper focuses on the study of big data management and proposes a management process to help manage the data in the grid. Data management tools and techniques have been leveraged in understanding the sources and data types in the grid. The paper emphasizes the limitations of the existing solutions inclined towards applications of the smart grid big data.

Deep learning (DL)-based PV Power Forecasting (PVPF) emerged nowadays as a promising research direction to intelligentize energy systems. With the massive smart meter integration, DL takes advantage of the large-scale and multi-source data representations to achieve a spectacular performance and high PV forecastability potential compared to classical models. This review article taxonomically dives into the nitty-gritty of the mainstream DL-based PVPF methods while showcasing their strengths and weaknesses. Firstly, we draw connections between PVPF and DL approaches and show how this relation might cross-fertilize or extend both directions. Then, fruitful discussions are conducted based on three classes: discriminative learning, generative learning, and deep reinforcement learning. In addition, this review analyzes recent automatic architecture optimization algorithms for DL-based PVPF. Next, the notable DL technologies are thoroughly described. These technologies include federated learning, deep transfer learning, incremental learning, and big data DL. After that, DL methods are taxonomized into deterministic and probabilistic PVPF. Finally, this review concludes with some research gaps and hints about future challenges and research directions in driving the further success of DL techniques to PVPF applications. By compiling this study, we expect to help aspiring stakeholders widen their knowledge of the staggering potential of DL for PVPF.

The grid integration of a photovoltaic solar system operating with maximum power point tracking is being presented in this paper. The system uses a dc-dc converter for power tracking while employing finite control set model predictive control (FCS-MPC) to govern the dc-ac inverter. An effective control scheme that employs only FCS-MPC in the entirety of its control layer is proposed, where three control objectives; the regulation of the dc-link voltage, the injection of active power, and the injection of reactive power to the main grid have been achieved within a single cost function. The controller avoids translating dc-link voltage deviations to the active power reference and controls all variables directly in the cost function. The controller’s feasibility has been evaluated through experiments where experimental testing using OPAL-RT has been carried out to prove the concept. The results show that all three control objectives can be achieved efficiently using the proposed method, with minimal error in the controlled variables. Furthermore, the controller shows high robustness against parameter mismatch and grid inductance variations.

The random fluctuation and non-uniformity of Photovoltaic (PV) power generation greatly affect the power grids’ stability and operation. This paper addresses the high volatility of PV power by proposing a precise and reliable ensemble learning model for short-term PV power generation forecasting. The proposed forecasting tool incorporates a base model and meta-model layers. The first-layer base learner combines extreme learning machines, extremely randomized trees, k-nearest neighbor, and mondrian forest models. The meta-model layer exploits deep belief network to generate the final outputs. The hyper-parameters of the proposed stacking ensemble are carefully tuned using the tree-structured of parzen estimators algorithm to achieve top-notch predictive performance. The proposed model is thoroughly assessed through an empirical study using a real data set from Australia. The simulation results confirm the performance superiority of the proposed model over the existing forecasting models with the lowest average root mean square error and mean absolute percentage error of 3.88kW and 2.30%, respectively.

With the ever-increasing number of blackouts in distribution systems arising from a variety of natural and manmade disasters, the frequent and necessary isolation/reconnection of loads without power deviations/fluctuations has become an important issue. Grid of microgrids (MG)s is a promising solution towards a highly resilient and efficient power grid operation. To facilitate this implementation, seamless transition with the utility grid is a key feature the today's MG control needs to possess. This transition ability is of great prominence, especially after the accelerated adaptation of distributed renewable energy sources (RES) in MGs. This ability of the MGs should ensure uninterrupted energy services to critical loads and infrastructures. Thus, the implementation of MG control strategies to enable smooth transition between grid-connected (GC) and islanded (IS) operation modes is mandatory. The control scheme implemented should therefore be capable of mitigating the stirring voltage/current deviations due to frequency/phase misalignment during the transition process. This paper provides an overview of the various MG control schemes that enable seamless transition between GC and IS modes of operation. The main purpose of this paper is to provide a generic overview of the challenges and existing techniques available in literature to mitigate the voltage and frequency (V-f) fluctuations at the MG's point of common coupling (PCC) and that of the utility grid; during the transition process. It aims at motivating the development of advanced control schemes in this area of MG related research.

This paper presents a method for improving the reliability of DC nanogrids by decreasing the input capacitance requirement. The nanogrid DC bus capacitance requirement is reduced by utilizing the zero-sequence operation mode of the solid state converter (SSC). This SSC is often considered as the main DC nanogrid energy control unit that is linking the nanogrid with the main utility AC grid and managing the nanogrid elements. The proposed method injects a zero-sequence voltage in the SSC AC filter capacitors to compensate the low frequency power ripples that are imposed on the DC bus. The proposed method compensates power ripple due to non-linear loads, linear loads, distorted grids, and load variations. Moreover, the compensation method does not require additional components that are commonly used with the existing power ripple compensators. Furthermore, practical considerations of the proposed control are discussed in the paper regarding stabilization of the nanogrid in case of lack of critical damping. The analysis and results demonstrated that a 50 μF total capacitance is sufficient at the DC bus for 500V/5kW DC nanogrid to achieve negligible DC bus voltage ripple. Thereby, with such small DC nanogrid input capacitance, the DC link capacitor can be a film type capacitor to enhance the reliability of the nanogrid.

Recently, nanofluids are introduced in the power utilities for the dielectric performance enhancement of power transformer oil. The compactness and fault improvement of the power transformers has resulted in the necessity of next-generation insulating fluid with inflated dielectric properties. This article investigates the dielectric performance of the novel ester oil-based magnetic nanofluids with different nanoparticles under different electric stress conditions. Two biodegradable fluids used as the base liquid for the experiment are synthetic ester oil and natural ester oil while three magnetic nanoparticles used to synthesize nanofluids are iron (II, III) oxide, cobalt (II, III) oxide, and iron phosphide. The concentrations of the nanoparticles are varied to optimize the characteristics of the prepared nanofluids. The dielectric breakdown and relative permittivity of the nanofluids have been experimentally investigated. Further, the breakdown predictions have been performed using Weibull statistical distribution-based regression analysis. The experimental results show the improvement in the characteristics of prepared nanofluids with the change in nanoparticle concentration as compared with the host fluids.

This paper proposes new average model based control strategies for a 5-level Packed U-cell (PUC5) inverter in both standalone and grid-connected modes of operation. First, a simple feedforward controller (FFC) is designed, using only two pulse width modulation (PWM) carrier signals, for the PUC5 inverter operating in standalone mode. This proposed control technique ensures self-balanced operation with high steady-state performance. Moreover, the employment of the proposed FFC leads to a decrease in the capacitor's value as well as the minimization of the Total Harmonic Distortion (THD). Then, a feedback linearizing control technique is designed to improve the transient and steady-state performances. In grid-connected mode, a reduced-sensor technique based on the FFC and the state feedback (FC) techniques was applied. Simulations and experimental results are presented to prove the high performance of the proposed solutions for standalone and grid-connected operating modes.

This paper presents a decoupled active and reactive power control scheme for grid-tied quasi-impedance source cascaded multilevel inverter (qZS-CMI). For photovoltaic (PV) applications, the proposed control scheme is based on an enhanced finite-set model predictive control (MPC) to harvest the desired active power from the PV modules with the ability to provide the ancillary services for the grid. The proposed control scheme has two modes of operation: normal grid mode and low voltage ride through (LVRT) mode. In normal grid mode, the controller commands the qZS-CMI to operate at the global maximum power point (MPP). The proposed technique regulates the impedance network's current and voltage according to the MPP of PV strings and grid current/voltage requirements. In LVRT mode, the controller commands the qZS-CMI to provide the required reactive power to the grid during voltage sags as an ancillary service from the inverter as imposed by the grid codes. The main features of the proposed system include the global MPP operation during normal grid condition, LVRT capability during a grid voltage sag, mitigation of the PV modules mismatch effect on overall energy harvesting, seamless transition between a normal grid and LVRT modes of operation, and an efficient predictive controller that exploits the model redundancies in the control objectives. Several real-time experiments are conducted to verify the system performance with transients in both the solar irradiance and the grid voltage.

The rapid growth of gas insulated switchgears as a compact, efficient, and reliable device has recently been given great attention. Albeit gas insulated switchgears can seldom suffer from failure due to the high resiliency and robustness, some severe damages have been experienced by such devices particularly in the event of partial discharge. Thus, monitoring such accidents has become a vital part of power systems reliability. The ultra-high frequency techniques have recently shown superior performance in the detection and classification of electromagnetic waves produced by partial discharge. This is mainly due to the great immunity to the noise of the ultra-high frequency detection techniques compared with the very-high-frequency counterparts. This review paper highlights the mathematical aspects of the electromagnetic waves generated by partial discharge. It also delivers an overview of the electromagnetic wave behavior in the complex structure of gas insulated switchgears, and outlines the important characteristics of the internal and external partial discharge detection using ultra-high frequency methods.

In this study, a Lyapunov energy function based control method with output voltage feedback loops is proposed for three-phase uninterruptible power supply (UPS) inverters. The presented paper demonstrates that the traditional Lyapunov-energy-function-based control method not only leads to considerable steady-state error in the output voltage, but also distorts the output voltage waveforms. Therefore, a modification has been performed on the traditional Lyapunov-energy-function-based control by incorporating the output voltage feedback loops in the control variables. The robustness of the proposed control method has been studied analytically through transfer functions which are expressed as the ratio of the output voltage to its reference. These analytical results are validated experimentally. In addition, the steady-state and dynamic performances of the proposed control method are also tested experimentally on a three-phase UPS inverter operating with linear (resistive) and nonlinear (diode-bridge rectifier) loads. As a consequence of incorporating output voltage feedback loops into the control variables, the proposed control method offers strong robustness against variations in LC filter parameters, high-quality sinusoidal output voltage along with acceptable total harmonic distortion (THD) values under linear and nonlinear loads, fast dynamic response under abrupt load changes, and negligibly small steady-state error in the output voltage.

This paper is focusing on 3D Finite Elements Analysis (FEA) based modelling of protrusions as defects or imperfections in the XLPE high voltage cable. This study is aiming to examine the impact, protrusions have on the initiation of partial discharges. Spherical and ellipsoidal protrusions with different sizes at the conductor screen of the high voltage cable is an essential content of this paper. In addition, a spherical gas-filled void is placed inside and outside the protrusions, and a water tree produced from protrusions is under consideration. The partial discharge influence taking place at the protrusions and the stress enhancement factor is determined for all the variations mentioned to quantify the rise in the inception of partial discharges due to the protrusions.

In this study, the performance of fault tolerant single-phase capacitor start capacitor run induction motor powered using seven-level quasi-impedance source inverter (qZSI) is analysed. The seven-level inverter consists of three units of qZSI connected in cascade. When one of the qZSI module fails (due to semiconductor failure), the resultant rms voltage applied to the motor will be reduced by one-third. This leads to reduction in both mechanical speed and electromagnetic torque of the motor. To restore the performance of the motor to pre-fault condition, the voltage deficit must be compensated. In conventional CHB inverter, it is not possible to achieve the pre-fault voltage. However, in qZSI, it is possible to achieve required voltage boost by application of shoot through duty cycle. Here, voltage of other two healthy operating modules can be boosted to reach pre-fault inverter output voltage during post-fault condition. The maximum voltage boost achievable is limited by the maximum shoot-through duty cycle which is related with modulation index. To verify the concept, simulation results of single-phase capacitor-start capacitor-run induction motor with or without proposed control algorithm are discussed. Experimental results for the proposed algorithm with RL load are discussed.

This paper proposes an effective deep learning framework for Short-Term Load Forecasting (STLF) of multivariate time series. The proposed model consists of a hybrid Convolutional neural network-Bidirectional Long Short-Term Memory (CBiLSTM) based on the Evolution Strategy (ES) method and the Savitzky–Golay (SG) filter (SG-CBiLSTM). The adopted methodology incorporates the virtue of different prepossessing blocks to enhance the performance of the CBiLSTM model. In particular, a data-augmentation strategy is employed to synthetically improve the feature representation of the CBiLSTM model. The augmented data is forwarded to the Partial Least Square (PLS) method to select the most informative features above the predefined threshold. Next, the SG algorithm is computed for smoothing the load to enhance the learning capabilities of the underlying system. The structure of the SG-CBiLSTM for the ISO New England dataset is optimized using the ES technique. Finally, the CBiLSTM model generates output forecasts. The proposed approach demonstrates a remarkable improvement in the performance of the original CBiLSTM model. Furthermore, the experimental results strongly confirm the high effectiveness of the proposed SG-CBiLSTM model compared to the state-of-the-art techniques.

The tuning of weighting factor has been considered as the most challenging task in the implementation of multi-objective model predictive control (MPC) techniques. Thus, this paper proposes an artificial intelligence (AI)-based weighting factor autotuning in the design of a finite control set MPC (FCS-MPC) applied to a grid-tied seven-level packed U-cell (PUC7) multilevel inverter (MLI). The studied topology is capable of producing a seven-level output voltage waveform and inject sinusoidal current to the grid with high power quality while using a reduced number of components. The proposed cost function optimization algorithm ensures auto-adjustment of the weighting factor to guarantee low injected grid current total harmonic distortion (THD) at different power ratings while balancing the capacitor voltage. The optimal weighting factor value is selected at each sampling time to guarantee a stable operation of the PUC inverter with high power quality. The weighting factor selection is performed using an artificial neural network (ANN) based on the measured injected grid current. Simulation and experimental results are presented to show the high performance of the proposed strategy in handling multi-objective control problems.

Hand-in-hand with the smart-grid paradigm development, power converters used in high-power applications are facing important challenges related to efficiency and power quality. To overcome these issues, the pre-programmed Pulse-Width Modulation (PWM) methods have been extensively applied to reduce the harmonic distortion with very low power switching losses for high-power converters. Among the pre-programmed PWM techniques, Selective Harmonic Elimination (SHE) has been the prevailing solution, but recently, Selective Harmonic Mitigation (SHM) stands as a superior alternative to provide further control of the harmonic spectrum with similar losses. However, the large computational burden required by the SHM method to find a solution confines it as an off-line application, where the switching set valid solutions are pre-computed and stored in a memory. In this paper, for the first time, a real-time implementation of SHM using an off-the-shelf mid-range microcontroller is presented and tested. The Exchange Market Algorithm (EMA), initially focused on optimizing financial transactions, is considered and executed to achieve the SHM targets. The performance of the EMA-based SHM is presented showing experimental results considering a reduced number of switching angles applied to a specific three-level converter, but the method can be extrapolated to any other three-level converter topology.

Fault Detection and Isolation (FDI) in Heating, Ventilation, and Air Conditioning (HVAC) systems is an important approach to guarantee the human safety of these systems. Therefore, the implementation of a FDI framework is required to reduce the energy needs for buildings and improving indoor environment quality. The main goal of this paper is to merge the benefits of multiscale representation, Principal Component Analysis (PCA), and Machine Learning (ML) classifiers to improve the efficiency of the detection and isolation of Air Conditioning (AC) systems. First, the multivariate statistical features extraction and selection is achieved using the PCA method. Then, the multiscale representation is applied to separate feature from noise and approximately decorrelate autocorrelation between available measurements. Third, the extracted and selected features are introduced to several machine learning classifiers for fault classification purposes. The effectiveness and higher classification accuracy of the developed Multiscale PCA (MSPCA)-based ML technique is demonstrated using two examples: synthetic data and simulated data extracted from Air Conditioning systems.

For high-voltage (HV) applications, the designers mostly prefer the classical DC–DC boost converter. However, it lacks due to the limitation of the output voltage by the gain transfer ratio, decreased efficiency and its requirement of two sensors for feedback signals, which creates complex control scheme with increased overall cost. Furthermore, the output voltage and efficiency are reduced due to the self-parasitic behavior of power circuit components. To overcome these drawbacks, this manuscript provides, the theoretical development and hardware implementation of DC–DC step-up (boost) power converter circuit for obtaining extra output-voltage high-performance. The proposed circuit substantially improves the high output-voltage by voltage-lift technology with a closed loop proportional–integral controller. This complete numerical model of the converter circuit including closed loop P-I controller is developed in simulation (Matlab/Simulink) software and the hardware prototype model is implemented with digital signal processor (DSP) TMS320F2812. A detailed performance analysis was carried out under both line and load regulation conditions. Numerical simulation and its verification results provided in this paper, prove the good agreement of the circuit with theoretical background.