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.

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.

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.

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 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.

非隔离单相半桥UPQC直流纹波分析及其影响抑制

非隔离单相半桥统一电能质量调节器(UPQC)两侧变换器的脉动功率差将在直流电容及分电容上产生复杂的多倍频电压纹波,各次电压纹波会对串联侧变换器的补偿电压有不同的影响,降低串联侧变换器的补偿效果。为了抑制直流电压纹波影响,利用等效电容电流模型计算直流电容电压表达式,分析直流纹波及非线性负载对补偿电压的影响路径,并仿真验证其正确性。针对分电容电压纹波和非线性负载对电压补偿效果的影响,提出一种抑制多倍频纹波影响的补偿电压特定次谐波控制策略。最后,基于SiC器件建立了非隔离单相半桥UPQC实验平台进行实验验证,实验结果表明在非线性工况下,所提控制策略将补偿电压THD从12.2%降低至2.4%,相比于传统控制可以减少约70%的直流电容需求。

Fuzzy Logic Controller Implementation of Power Quality Improvement Using UPQC

This paper presents a gross examination about Unified Power Quality Conditioner (UPQC) to invigorate the power issues at the distribution level of the electrical system. Nowadays power electronics research has added the importance of power quality studies, for concrete illustration, Custom Power Devices (CPD) and Flexible AC Transmission position (FACTS) devices. The approach offered in this paper utilizes the series and shunt compensator of Unified Power Quality Conditioner (UPQC) to inject a compensation voltage in-phase with the source current over voltage fluctuations. The execution of two structures of UPQC, left-shunt (L-UPQC) and right-shunt (R-UPQC) are investigated under diverse operating conditions based on the fuzzy logic controller to raise the value of power quality of a single feeder distribution system by MATLAB/Simulink programming. Various power quality issues have been analyzed in this study. Finally, the right shunt UPQC is outperformed in this proposed power system.

基于FCS MPC的TNPC UPQC补偿策略研究

针对传统统一电能质量控制器(UPQC)控制策略存在控制性能不佳的问题,以三电平变流器为对象提出基于有限集模型预测控制(FCS MPC)的TNPC UPQC的补偿策略。设计了补偿量检测环节,研究了串并联侧补偿量控制策略;并通过进一步优化分区,在减少控制器计算量的同时,兼顾了三电平变流器中点电位平衡的控制效果。最后在MATLAB/Simulink仿真实验平台搭建模型,仿真结果证明了所提出的设计方法的正确性和可行性。

基于五桥臂MMC-UPQC的复合模型预测控制研究

针对模块化多电平统一电能质量调节器(modular multilevel unified power quality conditioner, MMC-UPQC)六桥臂结构下的单相桥臂故障问题,提出了一种五桥臂拓扑,这种新型拓扑可实现故障情况下的电能质量补偿。首先,对MMC-UPQC串并联侧的数学模型进行分析,提出了一种复合模型预测控制(hybrid model predictive control,H-MPC),所提控制方法结合了有限集模型预测控制(finite-control-set model predictive control, FCS-MPC)以及快速模型预测控制(fast model predictive control, F-MPC)。然后,通过构建两侧独立的价值函数减少了控制方法的计算量,同时也实现了五桥臂解耦控制。最后,相比传统线性(例如PI)和非线性(例如无源控制passivity-based control,PBC)的控制策略,所提复合模型预测控制在电压补偿、负序电压抑制以及谐波电流补偿等方面具有一定优势,并在一定程度上避免了复杂的参数整定及坐标变化环节。仿真实验结果证明了所提控制方法的可行性和优越性。

面向脉冲负载的基于超级电容储能UPQC设计及控制策略研究

针对带有脉冲负载电网的电压畸变和电流畸变问题,设计了带有超级电容储能的三电平统一电能质量调节器,提出了基于人工神经网络的方法对串联和并联补偿单元进行控制,基于双闭环PI控制的方法对超级电容储能单元进行控制。其中,串联补偿单元进行电压补偿,以维持负载电压的稳定,保证负载的用电需求;并联补偿单元进行电流补偿,以维持电源电流的稳定,避免电网受到持续大幅冲击;超级电容储能单元对直流侧进行充放电,以维持直流侧电压的恒定,保证串、并联侧的正常工作。所提方法省去了繁琐的坐标变换过程,避免了多个滤波器造成相位滞后的问题。仿真实验结果表明,所提拓扑和控制策略有助于改善带有脉冲负载电网的电能质量。

基于不对称正负反馈效应的PQ功率控制并网逆变器稳定性分析

针对弱电网下PQ功率控制并网逆变器的稳定性问题,该文通过构建有功/无功环的小信号控制框图,首次揭示弱电网下PQ功率控制是一种不对称控制的本质,即无功环控制器会在有功和无功控制环中形成不对称的正负反馈环路。同时,基于PQ功率环小信号控制框图的不对称现象,揭示有功/无功环控制器参数变化对并网逆变器稳定性影响存在差异性的机理,指出无功环控制器参数变化对并网系统稳定性的影响程度要明显强于有功环控制器参数变化。在此基础上,借助有功与无功环小信号控制框图中的正负反馈效应,分析并网逆变器稳定性随无功环控制器参数增加而出现先增强后减弱的“拐点”现象。最后,通过仿真与实验验证了该文理论分析的正确性。

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.

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.