Voltage Instability Detection Using Neural Networks

The explosive growth in decision-support systems over the past 30 years has yielded numerous “intelligent” systems that have often produced less-than-stellar results (Michalewicz Z. et al., 2005). The increasing trend in developing intelligent systems based on neural networks is attributed to their capability of learning nonlinear problems offline with selective training, which can lead to sufficiently accurate online response. Artificial neural networks have been used to solve many problems obtaining outstanding results in various application areas such as power systems. Power systems applications can benefit from such intelligent systems; particularly for voltage stabilization, where voltage instability in power distribution systems could lead to voltage collapse and thus power blackouts. This article presents an intelligent system which detects voltage instability and classifies voltage output of an assumed power distribution system (PDS) as: stable, unstable or overload. The novelty of our work is the use of voltage output images as the input patterns to the neural network for training and generalizing purposes, thus providing a faster instability detection system that simulates a trained operator controlling and monitoring the 3-phase voltage output of the simulated PDS.

Download Full-text

A Game-Theoretic Loss Allocation Approach in Power Distribution Systems with High Penetration of Distributed Generations

Mathematics ◽

10.3390/math6090158 ◽

2018 ◽

Vol 6 (9) ◽

pp. 158

Author(s):

Farzaneh Pourahmadi ◽

Payman Dehghanian

Keyword(s):

Power Systems ◽

Power Distribution ◽

Distribution System ◽

Distribution Systems ◽

Power Distribution Systems ◽

Loss Allocation ◽

Distributed Generators ◽

High Penetration ◽

Game Theoretic ◽

Allocation Approach

Allocation of the power losses to distributed generators and consumers has been a challenging concern for decades in restructured power systems. This paper proposes a promising approach for loss allocation in power distribution systems based on a cooperative concept of game-theory, named Shapley Value allocation. The proposed solution is a generic approach, applicable to both radial and meshed distribution systems as well as those with high penetration of renewables and DG units. With several different methods for distribution system loss allocation, the suggested method has been shown to be a straight-forward and efficient criterion for performance comparisons. The suggested loss allocation approach is numerically investigated, the results of which are presented for two distribution systems and its performance is compared with those obtained by other methodologies.

Download Full-text

Artificial Neural Networks to Improve Current Harmonics Identification and Compensation

Advances in Civil and Industrial Engineering - Intelligent Industrial Systems ◽

10.4018/978-1-61520-849-4.ch010 ◽

2010 ◽

pp. 256-290 ◽

Cited By ~ 2

Author(s):

Patrice Wira ◽

Djaffar Ould Abdeslam ◽

Jean Mercklé

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Digital Signal Processor ◽

Power Distribution ◽

Distribution System ◽

Control Laws ◽

Identification Schemes ◽

Learning Capabilities ◽

Artificial Neural ◽

The One

Artificial Neural Networks (ANNs) have demonstrated very interesting properties in adaptive identification schemes and control laws. In this work, they are employed for the on-line control strategy of an Active Power Filter (APF) in order to improve its performance. Indeed, neural-based approaches are synthesized to design adaptive and efficient harmonic identification schemes. The proposed neural approaches are employed for compensating for the changing harmonic distortions introduced in a power distribution system by unknown nonlinear loads. The implementation of the ANNs has been optimized on a digital signal processor for real-time experiments. The feasibility of the implementation has been validated and the neural compensation schemes exhibit good performances compared to conventional approaches. By their learning capabilities, ANNs are able to take into account time-varying parameters such as voltage sags and harmonic content changes, and thus appreciably improve the performance of the APF compared to the one obtained with traditional compensating methods.

Download Full-text

Prediction of International Stock Markets Based on Hybrid Intelligent Systems

Handbook of Research on Innovations in Information Retrieval, Analysis, and Management - Advances in Knowledge Acquisition, Transfer, and Management ◽

10.4018/978-1-4666-8833-9.ch004 ◽

2016 ◽

pp. 110-124

Author(s):

Salim Lahmiri

Keyword(s):

Neural Networks ◽

Time Delay ◽

Stock Market ◽

Intelligent Systems ◽

Fuzzy Inference ◽

Intelligent System ◽

Market Price ◽

Hybrid Intelligent Systems ◽

Out Of Sample ◽

Artificial Neural Network Ann

This paper compares the accuracy of three hybrid intelligent systems in forecasting ten international stock market indices; namely the CAC40, DAX, FTSE, Hang Seng, KOSPI, NASDAQ, NIKKEI, S&P500, Taiwan stock market price index, and the Canadian TSE. In particular, genetic algorithms (GA) are used to optimize the topology and parameters of the adaptive time delay neural networks (ATNN) and the time delay neural networks (TDNN). The third intelligent system is the adaptive neuro-fuzzy inference system (ANFIS) that basically integrates fuzzy logic into the artificial neural network (ANN) to better model information and explain decision making process. Based on out-of-sample simulation results, it was found that contrary to the literature GA-TDNN significantly outperforms GA-ATDNN. In addition, ANFIS was found to be more effective in forecasting CAC40, FTSE, Hang Seng, NIKKEI, Taiwan, and TSE price level. In contrary, GA-TDNN and GA-ATDNN were found to be superior to ANFIS in predicting DAX, KOSPI, and NASDAQ future prices.

Download Full-text

Optimal Power Distribution System Planning and Analysis Using Q-GIS and Soft Computing

International Journal of Decision Support System Technology ◽

10.4018/ijdsst.2020010104 ◽

2020 ◽

Vol 12 (1) ◽

pp. 70-83

Author(s):

Shabbiruddin ◽

Sandeep Chakravorty ◽

Karma Sonam Sherpa ◽

Amitava Ray

Keyword(s):

Power Systems ◽

Power Distribution ◽

Distribution System ◽

Flow Analysis ◽

Integrated Approach ◽

Load Flow ◽

Strategic Decisions ◽

Power Distribution System ◽

Load Flow Analysis ◽

Private And Public

The selection of power sub-station location and distribution line routing in power systems is one of the important strategic decisions for both private and public sectors. In general, contradictory factors such as availability, and cost, affects the appropriate selection which adheres to vague and inexact data. The work presented in this research deals with the development of models and techniques for planning and operation of power distribution system. The work comprises a wider framework from the siting of a sub-station to load flow analysis. Work done also shows the application of quantum- geographic information system (Q-GIS) in finding load point coordinates and existing sub-station locations. The proposed integrated approach provides realistic and reliable results, and facilitates decision makers to handle multiple contradictory decision perspectives. To accredit the proposed model, it is implemented for power distribution planning in Bihar which consists of 9 divisions. A Cubic Spline Function-based load flow analysis method is developed to validate the proposal.

Download Full-text

Planning of Distribution System with High Penetration Level for Distributed Generation in Smart Grid

International Journal of Current Engineering and Technology ◽

10.14741/ijcet/v.8.3.13 ◽

2018 ◽

Vol 8 (3) ◽

Cited By ~ 2

Author(s):

Reza Tajik

Keyword(s):

Smart Grid ◽

Power Systems ◽

Power Distribution ◽

Distribution System ◽

Distribution Systems ◽

Distribution Networks ◽

Planning Problem ◽

Renewable Energy Resources ◽

Power Distribution System ◽

High Penetration

Nowadays, the utilization of renewable energy resources in distribution systems (DSs) has been rapidly increased. Since distribution generation (DG) use renewable resources (i.e., biomass, wind and solar) are emerging as proper solutions for electricity generation. Regarding the tremendous deployment of DG, common distribution networks are undergoing a transition to DSs, and the common planning methods have become traditional in the high penetration level. Indeed, in conformity with the voltage violation challenge of these resources, this problem must be dealt with too. So, due to the high penetration of DG resources and nonlinear nature of most industrial loads, the planning of DG installation has become an important issue in power systems. The goal of this paper is to determine the planning of DG in distribution systems through smart grid to minimize losses and control grid factors. In this regard, the present work intending to propose a suitable method for the planning of DSs, the key properties of DS planning problem are evaluated from the various aspects, such as the allocation of DGs, and planning, and high-level uncertainties. Also depending on these analyses, this universal literature review addressed the updated study associated with DS planning. In this work, an operational design has been prepared for a higher performance of the power distribution system in the presence of DG. Artificial neural network (ANN) has been used as a method for voltage monitoring and generation output optimization. The findings of the study show that the proposed method can be utilized as a technique to improve the process of the distribution system under various penetration levels and in the presence of DG. Also, the findings revealed that the optimal use of ANN method leads to more controllable and apparent DS.

Download Full-text

Probability-Based Customizable Modeling and Simulation of Protective Devices in Power Distribution Systems

Energies ◽

10.3390/en15010199 ◽

2021 ◽

Vol 15 (1) ◽

pp. 199

Author(s):

Chengwei Lei ◽

Weisong Tian

Keyword(s):

Power Systems ◽

Power Distribution ◽

Distribution System ◽

Distribution Systems ◽

Short Circuit ◽

Current Data ◽

System Level ◽

Power Distribution Systems ◽

Power Distribution System ◽

Protective Devices

Fused contactors and thermal magnetic circuit breakers are commonly applied protective devices in power distribution systems to protect the circuits when short-circuit faults occur. A power distribution system may contain various makes and models of protective devices, as a result, customizable simulation models for protective devices are demanded to effectively conduct system-level reliable analyses. To build the models, thermal energy-based data analysis methodologies are first applied to the protective devices’ physical properties, based on the manufacturer’s time/current data sheet. The models are further enhanced by integrating probability tools to simulate uncertainties in real-world application facts, for example, fortuity, variance, and failure rate. The customizable models are expected to aid the system-level reliability analysis, especially for the microgrid power systems.

Download Full-text

Reliability Analysis of A Radial Distributed Generation Distribution System

International Journal of Electronics and Electical Engineering ◽

10.47893/ijeee.2015.1169 ◽

2015 ◽

pp. 279-285

Author(s):

Peyman Mazidi ◽

G.N. Sreenivas

Keyword(s):

Power Systems ◽

Distributed Generation ◽

Power Distribution ◽

Distribution System ◽

Analytical Methodology ◽

Power Distribution System ◽

Demand Growth ◽

Typical Distribution ◽

Transmission And Distribution ◽

Oil Gas

Distributed Generation (DG) plays an important role in current power systems with high demand growth. DG provides an alternative to the traditional electricity sources like oil, gas, coal, water, etc. and can also be used to enhance the current electrical system. DG distribution is likely to improve the reliability of a power distribution system by at least partially minimizing unplanned power interruptions to customers due to loss of utility generators or due to faults in transmission and distribution lines/equipments. In this paper, a typical distribution system is considered and to show the reliability enhancement of the system, different components (fuses, disconnects, DGs) are step by step taken into account and added to the system in five cases. Analytical methodology is used for the analysis. The results demonstrate that DG does improve the reliability of the distribution system.

Download Full-text

Nonlinear Loads Compensation Using a Shunt Active Power Filter Controlled by Feedforward Neural Networks

Applied Sciences ◽

10.3390/app11167737 ◽

2021 ◽

Vol 11 (16) ◽

pp. 7737

Author(s):

Juan L. Flores-Garrido ◽

Patricio Salmerón ◽

Juan A. Gómez-Galán

Keyword(s):

Neural Networks ◽

Power Systems ◽

Fourier Coefficients ◽

Active Power Filter ◽

Nonlinear Problems ◽

Feedforward Neural Networks ◽

Active Power ◽

Accurate Estimation ◽

Shunt Active Power Filter ◽

Power Filter

The shunt active power filter (SAPF) is a widely used tool for compensation of disturbances in three-phase electric power systems. A high number of control methods have been successfully developed, including strategies based on artificial neural networks. However, the typical feedforward neural network, the multilayer perceptron, which has provided effective solutions to many nonlinear problems, has not yet been employed with satisfactory performance in the implementation of the SAPF control for obtaining the reference currents. In order to prove the capabilities of this simple neural topology, this work describes a suitable strategy of use, based on the accurate estimation of the Fourier coefficients corresponding to the fundamental harmonic of any distorted voltage or current. An effective training method has been developed, consisting of the use of many distorted patterns. The new generation procedure uses random combinations of multiple harmonics, including the possible nominal frequency deviations occurring in real power systems. The design of the generation of reference signals through computations based on the Fourier coefficients is presented. The objectives were the harmonic mitigation and power factor correction. Practical cases were tested through simulation and also by using an experimental platform, showing the feasibility of the proposal.

Download Full-text

Review of Steady-State Electric Power Distribution System Datasets

Energies ◽

10.3390/en13184826 ◽

2020 ◽

Vol 13 (18) ◽

pp. 4826

Author(s):

Steffen Meinecke ◽

Leon Thurner ◽

Martin Braun

Keyword(s):

Steady State ◽

Power Systems ◽

Power System ◽

Power Distribution ◽

Distribution System ◽

New Technologies ◽

Electrical Power ◽

Background Information ◽

Electrical Power Systems ◽

Power Distribution System

Publicly available grid datasets with electric steady-state equivalent circuit models are crucial for the development and comparison of a variety of power system simulation tools and algorithms. Such algorithms are essential to analyze and improve the integration of distributed energy resources (DERs) in electrical power systems. Increased penetration of DERs, new technologies, and changing regulatory frameworks require the continuous development of the grid infrastructure. As a result, the number and versatility of grid datasets, which are required in power system research, increases. Furthermore, the used grids are created by different methods and intentions. This paper gives orientation within these developments: First, a concise overview of well-known, publicly available grid datasets is provided. Second, background information on the compilation of the grid datasets, including different methods, intentions and data origins, is reviewed and characterized. Third, common terms to describe electric steady-state distribution grids, such as representative grid or benchmark grid, are assembled and reviewed. Recommendations for the use of these grid terms are made.

Download Full-text