A hybrid classifier for power quality (PQ) problems using wavelets packet transform (WPT) and artificial neural networks (ANN)

This paper presents a classification method for power quality problems in electrical power systems. To improve the electric power quality, sources of disturbances must be known and controlled. Power quality disturbance waveform recognition is often troublesome because it involves a broad range of disturbance categories or classes. This is a study of power quality problem classification using support vector machine. After training support vector machine, the parameter of support vector machine is obtained for using to classify the power quality problems. The support vector machine is able to classify 4 types for power quality problems correctly.

Having an inter-tie between low/medium voltage grid and distributed generation (DG), both exposes to power quality (PQ) problems created by each other. This paper addresses various PQ problems arise due to integration of DG with grid. The major PQ problems are due to unbalanced and non-linear load connected at DG, unbalanced voltage variations on transmission line and unbalanced grid voltages which severely affect the performance of the system. To mitigate the above mentioned PQ problems, a novel integrated control of distribution static shunt compensator (DSTATCOM) is presented in this paper. DSTATCOM control helps in reducing the unbalance factor of PCC voltage. It also eliminates harmonics from line currents and makes them balanced. Moreover, DSTATCOM supplies the reactive power required by the load locally and hence, grid need not to supply the reactive power. To show the efficacy of the proposed controller, several operating conditions are considered and verified through simulation using MATLAB/SIMULINK.

Electric railway power systems (ERPS) as one of the most critical and high-power end-user loads of utility grids are characterized by outlandish power quality (PQ) problems all over the world. The extension and evolution of different supply topologies for these systems has resulted in significant and various forms of distortions in network voltage and current in all ERPS, the connected power system, and adjacent consumers. During the last years, numerous studies have been offered to investigate various aspects of PQs in a specific supplying topology. Variation in the supply structure of the ERPS and different types of locomotives has propelled the observation of different PQ phenomena. This versatility and development have led to confront considerable types of two-way interactive interfaces as well as reliability and PQ problems in ERPS. In addition, the lack of standards explicitly dedicated to ERPS has added to the ambiguity and complexity of this issue. In this paper, an extensive review of PQ distortions and phenomena in different configurations of ERPS is proposed and a systematic classification is presented. More than 140 scientific papers and publications are studied and categorized which can provide a fast review and a perfect perspective on the status of PQ indexes for researchers and experts.

Power quality (PQ) problems include harmonics, voltage flicker, three-phase imbalance, voltage swell/sag, interruption, switching transient and so on. Identification of accurate location and occurrence time of PQ problem is important for understanding the underlying cause and to prevent future occurrence. This study presents a new method for placement of power quality measurement facilities to identify PQ problems. The power harmonics and capacitor switching transients are used as disturbance sources for illustration. The proposed method first utilises harmonic voltages and wavelet coefficients as PQ features. An enhanced genetic algorithm is proposed for solving the modified K-means clustering to place PQ measurement monitors. Simulation results for an 18-bus system show that the proposed approach is effective in comparison with the existing approaches.

Multilevel inverters are currently the subject of extensive investigation and are used primarily for medium and high voltage distribution systems. The work presented in this paper provides a cost-effective and realistic solution to mitigate power quality (PQ) problems. A Cascaded H-Bridge multilevel inverter (CHB-MLI) has been configured as a shunt active power filter (SAPF). It is well reported that large-scale use of power electronics-based devices leads to several PQ problems such as poor power factor, unregulated dc voltage, harmonics, voltage regulation etc. In this paper, an improved immune feedback control algorithm is proposed and developed to mitigate PQ issues by predicting the weighted active component of load current and to generate reference current for the grid. Extensive MATLAB simulation and experimental work have been reported for validation on a single-phase system. A low prototype model is developed in the laboratory to study and compare the steady-state and dynamic results of the proposed controller with conventional Least Mean Square (LMS) and Immune algorithm.

This study deals with the stabilization of grid connected wind farms. Operation of wind turbines has an impact on the power quality and reliability at the connected electric network. Power quality problems such as voltage flicker and harmonic distortion along with reliability issues are some major concern and in this work the flicker & harmonics issues are considered. Wind turbine connected to an induction generator and synchronous generator is modeled using PSCAD software to analyze power quality and reliability problems. Due to continuously varying wind speed components, the active and reactive power along with terminal voltage fluctuates continuously. A new type of static synchronous compensator (STATCOM) unit is developed to inject reactive power by switching IGBT(s) to mitigate power quality problems and to get stable grid operation. By connecting proposed Electro-Mechanical Switched Capacitor (EMSC) based STATCOM into the grid, reactive power and terminal voltage can be controlled effectively with varying wind speed.

The unified power quality conditioner (UPQC) is a power conditioning device, which is a integration of back to back connected shunt active power filter (APF) and series APF to a common DC link voltage. For improvement of power quality (PQ) problems in a three-phase four-wire distribution system, two topologies are proposed in this paper. A comparative analysis of these topologies along with the most common four-leg voltage source inverter (VSI) based topology of four-wire UPQC is discussed in this work. The performance of each topology of UPQC is evaluated for different PQ problems like power-factor correction, load balancing, current harmonic mitigation, voltage harmonic mitigation and source neutral current mitigation. The synchronous reference frame (SRF) theory is used as a control strategy of series and shunt APFs. The simulation results using MATLAB/Simulink enviournment are obtained, which support the effectiveness of these topologies of UPQC for power quality improvement.

This chapter introduces the custom power device to solve the various kinds of power quality (PQ) problems. It is generally known as flexible AC transmission system (FACTS) and D-FACTS (FACTs used for low voltage and low current rating in AC distribution system). The D-FACTS are various types like dynamic voltage restore (DVR), static compensator in distribution system (D-STATCOM), and unified power quality conditioner (UPQC). The third one is combination of DVR and D-STATCOM, which is known as UPQC. The UPQC can compensate all the PQ problems. Comprehensive knowledge of UPQC is presented here to understand the trade value of this device. This chapter is organized as follows: The evaluation of power electronic based devices is presented in the background part of this chapter where custom power devices (CPDs) are also discussed. And operating principle with the Matlab model of UPQC and results are presented in the section titled “Working Principle of Unified Power Quality Conditioner (UPQC).” The scope of the one of the functional power electronic based devices are presented in section titled “Scope of UPQC.” At the end, this chapter is concluded.

Power Quality Problem (PQP) includes several kinds of problems such as harmonics and voltage sag. Locating PQP online can help take countermeasures, and it is very important. With help of mobile agents, PQP can be located with dynamically geographically changed agents. The Power Quality Management System (PQMS) is built on agents, and data transmission is implemented using Person to Person (P2P) and Foundations of Intelligent Physical Agents (FIPA). As PQP location is a Multi-Objective Problem (MOP) system, a Feedback Balanced Genetic Algorithm (FBGA) is used to help decide the location of PQP. The algorithm for actual PQP modeling is not discussed, and FBGA is an important algorithm for data collection and ultimate analysis. In FBGA, feedback messages are used to adjust optimization rules, and balanced genetic algorithm is used to achieve the Patero solution for MOP. Convergence of the algorithm is analyzed. Implementation of the algorithm proves feasibility of the algorithm.

This paper presents an integration of S-Transform and Probabilistic Neural Network (PNN) technique for identifying the location of a switched capacitor causing a power quality problem. The transient caused by the capacitor switching is one of the important power quality (PQ) problems since it may adversely affect the system as well as sensitive loads. S-Transform has the ability to detect the disturbance correctly in the presence of noise riding on the signal. Hence, S-Transform technique is used for locating switched capacitors under noisy environment. In order to extract efficient features, capacitor switching signals are applied to two S-Transform algorithms and they are processed parallely. Those features are then applied to PNN for training and subsequently tested for automatic classification of switching signals. The simulation results reveal that the combination of S-Transform and PNN can effectively locate the switched capacitor even under the noisy environment.

Chapter 1 - Introductory chapter: effects of power quality problems on energy efficiency of power systems

In This work a power quality (PQ) problem in an industrial plant is analyzed and its possible solutions explored, specifically regarding voltage sags. It is analyzed a plant's electrical system sensitivity regarding voltage sags, how does the magnitude depression and its duration affect the performance of the electrical loads (mainly induction motors). Several proposals are discussed and explored for voltage sag mitigation and their feasibility for the plant's PQ problem. Finally, settings of the voltage sag mitigation equipment (timer or latching relay) are made analyzing voltage recovery times after voltage sag has occurred.

Investigation of the states of human brain through the elec-troencephalograph (EEG) is an important application of EEG signals. This paper describes the application of an artificial neural network technique together with a feature extraction technique, the wavelet packet transformation, in classification of EEG signals. Feature vector is extracted by wavelet packet transform. Artificial neural network is used to recognize the brain statues. After training, the BP and RBF neural network are able to correctly classify the brain states, respectively. This method is potentially powerful for brain states classification.

96/00456 Heard a flash. Saw a boom. Power quality monitoring defined in P1159

Power-quality events are of increasing concern for the economy because today's equipment, particularly computers and automated manufacturing devices, is susceptible to these imperceptible voltage changes. A small variation in voltage can cause this equipment to shut down for long periods, resulting in significant business losses. Tiny variations in power quality are difficult to detect except with expensive monitoring equipment used by trained technicians, so many electricity customers are unaware of the role of power-quality events in equipment malfunctioning. This report describes the findings from a pilot study coordinated through the Silicon Valley Manufacturers Group in California to explore the capabilities of I-Grid(R), a new power-quality monitoring system. This system is designed to improve the accessibility of power-quality in formation and to increase understanding of the growing importance of electricity reliability and power quality to the economy. The study used data collected by I-Grid sensors at seven Silicon Valley firms to investigate the impacts of power quality on individual study participants as well as to explore the capabilities of the I-Grid system to detect events on the larger electricity grid by means of correlation of data from the sensors at the different sites. In addition, study participants were interviewed about the value they place on power quality, and their efforts to address electricity-reliability and power-quality problems. Issues were identified that should be taken into consideration in developing a larger, potentially nationwide, network of power-quality sensors.