Safety-Constrained Multi-Agent Reinforcement Learning for Power Quality Control in Distributed Renewable Energy Networks

This paper examines the difficulties of managing distributed power systems,notably due to the increasing use of renewable energy sources,and focuses on voltage control challenges exacerbated by their variable nature in modern power grids.To tackle the unique challenges of voltage control in distributed renewable energy networks,researchers are increasingly turning towards multi-agent reinforcement learning(MARL).However,MARL raises safety concerns due to the unpredictability in agent actions during their exploration phase.This unpredictability can lead to unsafe control measures.To mitigate these safety concerns in MARL-based voltage control,our study introduces a novel approach:Safety-ConstrainedMulti-Agent Reinforcement Learning(SC-MARL).This approach incorporates a specialized safety constraint module specifically designed for voltage control within the MARL framework.This module ensures that the MARL agents carry out voltage control actions safely.The experiments demonstrate that,in the 33-buses,141-buses,and 322-buses power systems,employing SC-MARL for voltage control resulted in a reduction of the Voltage Out of Control Rate(%V.out)from0.43,0.24,and 2.95 to 0,0.01,and 0.03,respectively.Additionally,the Reactive Power Loss(Q loss)decreased from 0.095,0.547,and 0.017 to 0.062,0.452,and 0.016 in the corresponding systems.

The Correlation between the Power Quality Indicators and Entropy Production Characteristics of Wind Power+Energy Storage Systems

Power quality improvements help guide and solve the problems of inefficient energy production and unstable power output in wind power systems.The purpose of this paper is mainly to explore the influence of different energy storage batteries on various power quality indicators by adding different energy storage devices to the simulated wind power system,and to explore the correlation between systementropy generation and various indicators,so as to provide a theoretical basis for directly improving power quality by reducing loss.A steady-state experiment was performed by replacing the wind wheel with an electric motor,and the output power qualities of the wind power systemwith andwithout energy storagewere compared and analyzed.Moreover,the improvement effect of different energy storage devices on various indicatorswas obtained.Then,based on the entropy theory,the loss of the internal components of the wind power system generator is simulated and explored by Ansys software.Through the analysis of power quality evaluation indicators,such as current harmonic distortion rate,frequency deviation rate,and voltage fluctuation,the correlation between entropy production and each evaluation indicator was explored to investigate effective methods to improve power quality by reducing entropy production.The results showed that the current harmonic distortion rate,voltage fluctuation,voltage deviation,and system entropy production are positively correlated in the tests and that the power factor is negatively correlated with system entropy production.In the frequency range,the frequency deviationwas not significantly correlated with the systementropy production.

Power Quality Disturbance Identification Basing on Adaptive Kalman Filter andMulti-Scale Channel Attention Fusion Convolutional Network

In light of the prevailing issue that the existing convolutional neural network(CNN)power quality disturbance identification method can only extract single-scale features,which leads to a lack of feature information and weak anti-noise performance,a new approach for identifying power quality disturbances based on an adaptive Kalman filter(KF)and multi-scale channel attention(MS-CAM)fused convolutional neural network is suggested.Single and composite-disruption signals are generated through simulation.The adaptive maximum likelihood Kalman filter is employed for noise reduction in the initial disturbance signal,and subsequent integration of multi-scale features into the conventional CNN architecture is conducted.The multi-scale features of the signal are captured by convolution kernels of different sizes so that the model can obtain diverse feature expressions.The attention mechanism(ATT)is introduced to adaptively allocate the extracted features,and the features are fused and selected to obtain the new main features.The Softmax classifier is employed for the classification of power quality disturbances.Finally,by comparing the recognition accuracy of the convolutional neural network(CNN),the model using the attention mechanism,the bidirectional long-term and short-term memory network(MS-Bi-LSTM),and the multi-scale convolutional neural network(MSCNN)with the attention mechanism with the proposed method.The simulation results demonstrate that the proposed method is higher than CNN,MS-Bi-LSTM,and MSCNN,and the overall recognition rate exceeds 99%,and the proposed method has significant classification accuracy and robust classification performance.This achievement provides a new perspective for further exploration in the field of power quality disturbance classification.

An Improvement in Power Quality and By-Product of the Run-Off River Micro Hydro Power Plant

Utilization of Micro Hydro Power Plant at the Gunung Halu case study type run-off the river is a household use only in the afternoon,around 5 pm until bedtime at about 10 pm.Therefore,more than 75%of the energy is lost.This case study lost power which can be used as a by-product,such as for drying coffee beans.In this case study,a design was carried out to obtain by-products and improve power quality in the electrical system.In addition,they complain about the poor quality of power controlled by frequency using Triac-Based Electronic Dummy Load Control.The heat from the dummy load in the case study is used as a by-product.MHP with a minimum power of 20 kW,and the usage time of customer service is about 6 h.The energy for the by-products is about 360 kWh/day,and the power quality improved by using Triac-Based Electronic Load Control and Hysteresis Current Control for the active filter.As a result,the power factor is close to one,the generator current harmonics is less than 2%,and the voltage harmonics is less than 5%.

Analysis and Power Quality Improvement in Hybrid Distributed Generation System with Utilization of Unified Power Quality Conditioner

This paper presents a comprehensive study that includes the sizing and power flow by series and parallel inverters in a distributed generation system(DGs)that integrates the system of hybrid wind photovoltaic with a unified power quality conditioner(UPQC).In addition to supplying active power to the utility grid,the system of hybrid wind photovoltaic functions as a UPQC,compensating reactive power and suppressing the harmonic load currents.Additionally,the load is supplied with harmonic-free,balanced and regulated output voltages.Since PVWind-UPQC is established on a dual compensation scheme,the series inverter works like a sinusoidal current source,while the parallel inverter works like a sinusoidal voltage source.Consequently,a smooth alteration from interconnected operating modes to island operating modes and vice versa can be achieved without load voltage transients.Since PV-Wind-UPQC inverters handle the energy generated through the hybrid wind photovoltaic system and the energy demanded through the load,the converters should be sized cautiously.A detailed study of the flow of power via the PV-Wind-UPQC is imperative to gain a complete understanding of the system operation and the proper design of the converters.Thus,curves that allow the sizing of the power converters according to the power flow via the converters are presented and discussed.Simulation results are presented to assess both steady state and dynamic performances of the grid connected hybrid system of PV-Wind-UPQC.This investigation is verified by simulating and analyzing the results with Matlab/Simulink.

Power Quality Improvement Using ANN Controller For Hybrid Power Distribution Systems

In this work,an Artificial Neural Network(ANN)based technique is suggested for classifying the faults which occur in hybrid power distribution systems.Power,which is generated by the solar and wind energy-based hybrid system,is given to the grid at the Point of Common Coupling(PCC).A boost converter along with perturb and observe(P&O)algorithm is utilized in this system to obtain a constant link voltage.In contrast,the link voltage of the wind energy conversion system(WECS)is retained with the assistance of a Proportional Integral(PI)controller.The grid synchronization is tainted with the assis-tance of the d-q theory.For the analysis of faults like islanding,line-ground,and line-line fault,the ANN is utilized.The voltage signal is observed at the PCC,and the Discrete Wavelet Transform(DWT)is employed to obtain different features.Based on the collected features,the ANN classifies the faults in an effi-cient manner.The simulation is done in MATLAB and the results are also validated through the hardware implementation.Detailed fault analysis is carried out and the results are compared with the existing techniques.Finally,the Total harmonic distortion(THD)is lessened by 4.3%by using the proposed methodology.

A Review on Intelligent Detection and Classification of Power Quality Disturbances:Trends,Methodologies,and Prospects

With increasing global concerns about clean energy in smart grids,the detection of power quality disturbances(PQDs)caused by energy instability is becoming more and more prominent.It is well acknowledged that the PQD effects on power grid equipment are destructive and hazardous,which causes irreversible damage to underlying electrical/electronic equipment of the concerned intelligent grids.In order to ensure safe and reliable equipment implementation,appropriate PQDdetection technologiesmust be adopted to avoid such adverse effects.This paper summarizes the newly proposed and traditional PQD detection techniques in order to give a quick start to new researchers in the related field,where specific scenarios and events for which each technique is applicable are also clearly presented.Finally,comments on the future evolution of PQD detection techniques are given.Unlike the published review articles,this paper focuses on the new techniques from the last five years while providing a brief recap on traditional PQD detection techniques so as to supply researchers with a systematic and state-of-the-art review for PQD detection.

Regional difference and dynamic evolution of development quality of power industry in China

To achieve the goals of carbon peaking and carbon neutrality and maintain high-quality economic growth,China is currently striving to improve the quality of development of its power sector.In this regard,revealing the regional differences and evolutionary trends in the development quality of China’power sector has a high value to inspire the next improvement direction toward how to integrate regional power recourses to an overall optimization level.Motived by this purpose,this paper uses the entropy method to evaluate the com‐prehensive and subsystem indices of the development quality of the power industry,and reveals their re‐gional differences and evolutionary trends with the help of the Dagum Gini coefficient and Kernel density es‐timation methods.The findings show that:There are obvious regional differences in the development quality of China’s power industry,and the differences are steadily declining in all regions except the West.Regional differences are mainly derived from inter-regional differences,with the largest inter-regional differences in the East-Northeast region.Intra-regional differences show a distribution pattern of East>West>North‐east>Center.

Improving Power Quality by DSTATCOM Based DQ Theory with Soft Computing Techniques

The development of non-linear loads at consumers has significantly impacted power supply systems.Since,the poor power quality has been found in the three-phase distribution system due to unbalanced loads,harmonic current,undesired voltage regulation,and extreme reactive power demand.To overcome this issue,Distributed STATicCOMpensator(DSTATCOM)is implemented.DSTATCOM is a shunt-connected Voltage Source Converter(VSC)that has been utilized in distribution networks to balance the bus voltage in terms of enhancing reactive power control and power factor.DSTATCOM can provide both rapid and continuous capacitive and inductive mode compensation.A rectified resistive and inductive load eliminates current harmonics in a three-phase power supply.The synchronous fundamental DQ frame is a time-domain approach developed from three-phase system space vector transformations has been designed using MATLAB/Simulink.The DQ theory is used to produce the reference signal for the Pulse Width Modulation(PWM)generator.In addition,a traditional Propor-tional Integral Derivative(PID)controller is designed and compared with pro-posed soft computing approaches such as Fuzzy–PID and Artificial Neural Network(ANN-PID)and compared accurate reference current determination for Direct Current(DC)bus through DC link.An Analytical explores the pro-posed control strategies given to establish superior outcomes.Finally,total harmo-nic distortion analysis should be taken for performance analysis of the proposed system with IEEE standards.

Analysis of Power Quality for Distribution Networks Using Active Compensator

This paper concentrates on compensating the power quality issues which have been increased in day-to-day life due to the enormous usage of loads with power electronic control.One such solution is compensating devices like Pension Protection Fund(PPF),Active power filter(APF),hybrid power filter(HPF),etc.,which are used to overcome Power Quality(PQ)issues.The proposed method used here is an active compensator called unified power quality condi-tioner(UPQC)which is a combination of shunt and series type active filter con-nected via a common DC link.The primary objective is to investigate the behavior of the compensators in the distribution networks.The performance of two configurations of UPQC,Right Shunt UPQC(RS-UPQC)and Left Shunt UPQC(LS-UPQC)are tested in the distribution networks under various load con-ditions by connecting them at the source side of harmonic generation using a spe-cially constructed transformer called inductively filtered converter transformer which adopts special wiring scheme at the secondary side.PSCAD(Power Sys-tems Computer Aided Design)/EMTDC(Electromagnetic Transients with DC Analysis)software is used to model the compensators connected to the nonlinear load.Both RS-UPQC and LS-UPQC are tested at the distribution side of the sup-ply system with Hysteresis current controller for shunt and Sinusoidal pulse with modulation controller for series at various locations of power system network and their results are compared.

Research on Power Quality Evaluation Based on Radar Chart Method and Fuzzy Membership Degree

Aiming at the current limit value of six steady-state energy indexes, the current radar method is used for reference. A method of comprehensive evaluation of power quality based on improved radar method is proposed, which improves the power quality index Type radar pattern to represent the steady-state indicator. Each of the main indicators corresponds to a partial ring, and the angle of the annular portion is mainly affected by the size of the weight. Compared with the previous radar map method to maintain the independence of the indicators and a single indicator of the binding data assessment. The method has the advantages of good feasibility.

Compliance verification and probabilistic analysis of state-wide power quality monitoring data

This paper introduces the implementation and data analysis associated with a state-wide power quality monitoring and analysis system in China. Corporation specifications on power quality monitors as well as on communication protocols are formulated for data transmission. Big data platform and related technologies are utilized for data storage and computation. Compliance verification analysis and a power quality performance assessment are conducted, and a visualization tool for result presentation is finally presented.

Bacterial graphical user interface oriented by particle swarm optimization strategy for optimization of multiple type DFACTS for power quality enhancement in distribution system

This study proposes a graphical user interface(GUI) based on an enhanced bacterial foraging optimization(EBFO) to find the optimal locations and sizing parameters of multi-type DFACTS in large-scale distribution systems.The proposed GUI based toolbox,allows the user to choose between single and multiple DFACTS allocations,followed by the type and number of them to be allocated.The EBFO is then applied to obtain optimal locations and ratings of the single and multiple DFACTS.This is found to be faster and provides more accurate results compared to the usual PSO and BFO.Results obtained with MATLAB/Simulink simulations are compared with PSO,BFO and enhanced BFO.It reveals that enhanced BFO shows quick convergence to reach the desired solution there by yielding superior solution quality.Simulation results concluded that the EBFO based multiple DFACTS allocation using DSSSC,APC and DSTATCOM is preferable to reduce power losses,improve load balancing and enhance voltage deviation index to 70%,38% and 132% respectively and also it can improve loading factor without additional power loss.

Classification of power quality combined disturbances based on phase space reconstruction and support vector machines

Power Quality (PQ) combined disturbances become common along with ubiquity of voltage flickers and harmonics. This paper presents a novel approach to classify the different patterns of PQ combined disturbances. The classification system consists of two parts, namely the feature extraction and the automatic recognition. In the feature extraction stage, Phase Space Reconstruction (PSR), a time series analysis tool, is utilized to construct disturbance signal trajectories. For these trajectories, several indices are proposed to form the feature vectors. Support Vector Machines (SVMs) are then implemented to recognize the different patterns and to evaluate the efficiencies. The types of disturbances discussed include a combination of short-term dis-turbances (voltage sags, swells) and long-term disturbances (flickers, harmonics), as well as their homologous single ones. The feasibilities of the proposed approach are verified by simulation with thousands of PQ events. Comparison studies based on Wavelet Transform (WT) and Artificial Neural Network (ANN) are also reported to show its advantages.

Predicting of Power Quality Steady State Index Based on Chaotic Theory Using Least Squares Support Vector Machine

An effective power quality prediction for regional power grid can provide valuable references and contribute to the discovering and solving of power quality problems. So a predicting model for power quality steady state index based on chaotic theory and least squares support vector machine (LSSVM) is proposed in this paper. At first, the phase space reconstruction of original power quality data is performed to form a new data space containing the attractor. The new data space is used as training samples for the LSSVM. Then in order to predict power quality steady state index accurately, the particle swarm algorithm is adopted to optimize parameters of the LSSVM model. According to the simulation results based on power quality data measured in a certain distribution network, the model applies to several indexes with higher forecasting accuracy and strong practicability.

Probabilistic Assessment of Power System Performance Quality

In a recently published work by the authors, a novel framework was developed and applied for assessment of reliability and quality performance levels in real-life power systems with practical large-scale sizes. The new assessment methodology is based on three metaphors (dimensions) representing the relationship between available generation capacities and required demand levels. The developed reliability and performance quality indices were deterministic in nature. That is, they represent one operating state (a snapshot of the system conditions) in which the required demand as well as the generation and transmission capacities are known with 100% certainty. In real life, however, load variations occur randomly so as the contingencies which cause some generation and/or transmission capacities to be lost (become unavailable). In other words, neither the load levels nor the generation or transmission capacities are known with absolute certainty. They are rather subject to random variations and, consequently, the calculated reliability and performance quality indices are all subject to random variations where only expected values of these indices can be evaluated. This paper presents a major extension to the previously published work by developing a theory and formulas for computing the expected values of different system reliability and performance quality indices. In this context, a “contingency scenario” or a system “demand level” are regarded, in a more general sense, as a “state”, which occurs with certain probability and represents a given demand value and availability pattern of various capacities in the system. The work of this paper provides a practical and meaningful methodology for real-life assessment of power system reliability and performance quality levels. Practical applications are also presented, for demonstration purposes, to the Saudi electricity power grid.

Power Quality Disturbance Classification Method Based on Wavelet Transform and SVM Multi-class Algorithms

The accurate identification and classification of various power quality disturbances are keys to ensuring high-quality electrical energy. In this study, the statistical characteristics of the disturbance signal of wavelet transform coefficients and wavelet transform energy distribution constitute feature vectors. These vectors are then trained and tested using SVM multi-class algorithms. Experimental results demonstrate that the SVM multi-class algorithms, which use the Gaussian radial basis function, exponential radial basis function, and hyperbolic tangent function as basis functions, are suitable methods for power quality disturbance classification.

Research and applications of FDMP algorithm for power quality signal analysis

The accuracy of unsteady-state disturbance analysis of power quality signals is reduced by the steadystate components with high amplitudes and energies. In this paper,a novel frequency-domain matching pursuits (FDMP) algorithm is proposed to estimate the parameters of the steady-state components and separate the unsteady-state disturbances from power quality signals. Firstly,the time-frequency atoms and redundant dictionaries are constructed according to the characteristics of power quality signal spectra. Secondly,the steady-state components and unsteady-state disturbances of power quality signals are decomposed by FDMP into two mutually orthogonal subspaces in Hilbert space. Furthermore,the expressions for parameters calculation of steady-state components have been derived. The experiments show that the relative errors of frequency and amplitude estimations of steady-state components are less than 2 × 10 -4 and 5 × 10 -3 respectively,and phase estimation errors are less than 1. 6° under the existence of both interharmonics and unsteady-state disturbances. The steady-state components and unsteady-state disturbances are separated quickly and accurately.

Improve power quality of coal mine power network based on gray system theory

Unified Power Quality Controller（UPQC） was proposed to comprehensively improve power quality of coal mine power network and its basic structure and operation principle was introduced. In order to overcome time lag of Active Power Filter（APF） in compensating harmonic and reactive current, a novel method based on gray system theory was proposed to predict harmonic current and other distortion component. The mathematical model of component to be compensated was constructed by data sequence of distortion component, which could exactly forecast compensation signal of next period. The optimal control strategy was selected according to the principle of output signal approaching component to be compensated as near as possible. Before predicating each time the oldest data was eliminated while the latest data was added to data sequence. Then new predication model was established once again. The results show that the method can always construct mathematical model with variation of system parameters, reflect the latest state of system and not increase calculation quantity. The feasible and effective control strategy can improve power quality of coal mine power network.

A Remote Real-Time Monitoring System for Power Quality

An introduction is made to the composition, design method and engineering application of a remote real time monitoring system of power quality in substations based on internet. With virtual instrument and network technique adopted, this system is characterized by good real time property, high reliability, plentiful functions, and so on. It also can be used to monitor the load of a substation, such as electric locomotives.