Better reliability of power supply is assured with the inculcation of distributed generators (DGs) in a distribution network. Smart sensors and latest grid communication protocols have played a ...crucial role in the development of intelligent microgrids (MGs). Conventional protection schemes do not provide reliable performance when implemented in MGs. This article proposes an approach which requires root mean square value of one cycle three -phase voltage and current measurements during fault. These data are treated as inputs for developing a fault isolation and locator module. This module is supposed to be available at central protection system, and is designed using machine learning (ML) based techniques viz. Gaussian process regression for fault location prediction and support vector machine for fault identification. Effectiveness of the proposed methodology is evaluated by considering practical grid scenarios with load variation and different DG penetration level. Furthermore, the robustness of the proposed model is assessed by performing sensitivity analysis with consideration of variation in line parameters and load as well as effect of DG correlation. A 7-bus meshed ac MG test system consisting of three DGs and two grid sources is modeled in SIMULINK platform, and is used to demonstrate the proposed module. Data analytics tools of MATLAB 2020a has been explored to develop an ML-based fault isolation and location module for MGs. The proposed scheme has also been validated with real-time MG data obtained from OPAL Real time (OPAL-RT) real-time simulator OP-4510. The accuracy in predicted results proves that the proposed scheme is pertinent for real-time practical applications.
Modern distribution systems consist of various distributed generators (DG) to make reliable power systems. In these DG integrated distribution systems, coordination of overcurrent relays is a big ...challenge for protection engineers. With the addition of DG, distribution system experiences change in the short-circuit level of the system and thus earlier relay settings causes mal operation of relays. Nowadays, various programming optimization techniques are frequently used to find optimal relay settings of overcurrent relays. This paper presents a comparative study of particle swarm optimization and Gravitational Search Algorithm for the coordination of overcurrent relay for a system containing DG. A proper combination of primary and backup relay is selected to avoid mal operation of relays and unwanted outages when DG is penetrated. Practical cases with different DG penetration level and fault types are also thoroughly discussed. A 4-bus radial system is simulated in PSCAD/Simulink platform and programming is done using MATLAB software.
Abstract-Microgrids usually operate in grid-connected or islanded mode. Due to substantial variation in fault current, same protection coordination scheme cannot be applied in both modes. Moreover, ...network topology keeps on changing due to momentary events. In this paper, an adaptive protection strategy is proposed to avoid any miscoordination between numerical directional overcurrent relays under a fault instance. Through this scheme, the relay settings can be updated online as per the operating mode and prevailing topology. The proposed tactic employs a central protection center with data storage and programming capability, smart electronic devices and communication channels to acquire and transfer real-time data. The relay coordination problem is formulated as a non-linear optimization function, with coordination time interval constraints. The optimal relay settings under both operating modes are obtained through non-linear programming and hybrid genetic algorithm non-linear programming method. To handle contingencies of communication channel failure, a novel inclusive mode settings are also introduced to protect the system in both modes even with line or DG outages. The proposed adaptive approach is tested on a nine bus radial distribution system with DGs. It has been found that the proposed scheme provides reliable system protection under different operating scenario.
•Voltage data processing based fault detection and its isolation is proposed in multiple operating modes of Micro grid.•A fault locator module is designed using Gaussian process regression which can ...predict the exact fault location using simple measurements at source buses.•No complex signal processing is involved in designing the ML model which makes the FLM fast and efficient.
Modern intelligent digital relays embedded with phasor measurement units have facilitated easy access and collection of electrical signals in a microgrid. In this paper, a model for detection, location and isolation of faults in AC microgrid is presented. The real time voltage, frequency and current data are processed via simple formulations to detect the fault. The tripping command is promptly communicated to the incumbent line relays within fault tolerance time, after fault detection. The proposed scheme assures reliable protection in grid connected and islanded mode of operation with added security in case of primary protection failure. Post tripping, the exact location of fault in any distribution line from utility grid is predicted using a fault locator module. This module is designed and developed by gaussian process regression technique. Further, various machine learning techniques used for fault location has been explored and compared to establish the superiority of GPR method over others. Also the features extracted for model training is quite simpler, which imposes less computational burden on central protection computer. An IEEE 15 bus distribution system with synchronous and solar photo voltaic based DG is simulated in EMTP-RV platform to generate the electrical data. Further the required calculations are performed in MATLAB 2020a
This article presents a hybrid optimization technique particle swarm optimization-gravitational search algorithm for optimal over-current relay coordination. The main contribution of this article is ...to find the optimized relay settings during variation in environmental factors that affect distributed generation performance. The detailed model of wind and photovoltaic source, modeled in a PSCAD/EMTDC platform is penetrated in a 13-bus distribution system. The optimal relay settings are found for different cases, including change in wind speed, change in penetration level, change in cell temperature, and insolation level of photovoltaic. A comparison of particle swarm optimization-gravitational search algorithm with particle swarm optimization and gravitational search algorithm technique is also done, and it is shown that the particle swarm optimization-gravitational search algorithm is a superior method that can be applied in relay coordination tasks.
Better reliability of power is assured with the inculcation of distributed generations in a distribution network. Smart sensors and latest grid communication protocols has led to the development of ...intelligent microgrids (MG). Protection of such grids are a key concern for power engineers, as conventional protection schemes fails while operating in microgrids. This paper presents, data analysis based fault isolation and its location prognosis. The proposed approach takes post fault, one cycle three phase voltage and current measurements as the inputs for developing a fault isolation module (FIM) and fault locator module (FLM). These modules are supposed to be available at central protection system (CPS), designed through meticulous data training, using Gaussian process regression (GPR) for fault location prediction and support vector machine (SVM) for fault identification. The effectiveness of proposed methodology is represented by considering practical grid scenarios such as varying load and DG penetration. A 14 bus meshed AC microgrid structure has been modelled in SIMULINK having three DGs and two grid sources. Data analytics tools of MATLAB 2018a has been explored to develop machine learning based protection strategy for microgrids.
In today's electrical grid, micro grid concept employing Distributed Generation is being implemented rigorously. With change in penetration level of DG, distribution system experiences variation in ...the short circuit level of the system. Therefore the relay settings should be revised at every level. This paper discusses the application of Gravitational Search Algorithm to find optimal relay settings in order to attain coordination of overcurrent relays. Relay settings required for an adaptive numerical relay is obtained for practical cases like system with different DG penetration level and fault types. A four bus radial system with DG and overcurrent protection is simulated in SIMULINK platform and programming is done using MATLAB software.
Electrical microgrids are quite vulnerable to fault conditions because of being in close proximity to the load centres. Due to differences in operating dynamics of microgrids as compared to ...conventional distribution system, designing reliable protection is a major concern for protection engineers. Therefore, detection and localization of fault in microgrids has become difficult and less trustworthy using traditional overcurrent relay based protection schemes. This paper presents a new protection scheme where faulted line number and its exact location from substation is determined using Random forest algorithm. A microgrid model has been created in MATLAB/SIMULINK platform having various distributed generation sources along with the substation grid. Common types of shunt faults have been created at different locations and the root mean square value of post fault one cycle faulted voltage and current signal is collected from each of the source buses. Further various practical cases such as islanded mode, change in DG(distributed generation) penetration level, increment and decrement of loads by 50% has also been taken into consideration while creating the training data. The collected data is then used for designing a machine learning (ML) model. Three types of prediction are being made by this model i.e. (i) type of fault, (ii) line in which fault has occurred and (iii) distance of fault from substation. Two different approaches are used for model, first simply training the model on all the data set that has been collected and the second one is by filtering out the data according to type of fault and then on the filtered data the faulted data set training is done. Random forest method which is implemented using Python coding stands out to be the best algorithm for all the three problem in terms of accuracy and time of execution of model even with simplified measurement.
This work describes a preliminary research investigation to access the feasibility of using advanced machine learning techniques for predicting and diagnosing fault type and fault location in a power ...distribution network consisting distributed generation. The proposed approach uses three phase voltage and current measurements data, assumed to be available at all the source bus. To understand the potential of the machine learning methodology, practical scenarios in a distribution grid such as all types of faults i.e. SLG, LLG, LL, and LLL with different fault locations are addressed in this work. Initially, the fault data is generated which is used to train a fault locator module. Further same data is used to design a fault type detector model in offline mode. The online real time data when fed to these models are able to give exact location and type of fault. The results are obtained from seven techniques of machine learning and their comparison is also done. The approach is proved to be a feasible tool for fault analysis.
The complexity of an active distribution system with distributed generation (DG) is increasing day-by-day. Therefore, a reliable protection system is very necessary to satisfy customer demand. Apart ...from main grid supply, active sources are also available near load centers due to which traditional protection schemes fails to function properly. The magnitude of fault current during grid connected mode of microgrid, is much higher than islanded operation. Therefore, in most of the previous works, overcurrent protection crashes if its pickup current value is not changed when microgrid is shifted to islanded mode. In this paper, the current, voltage and frequency data sampled through PMU is processed to protect the system in both the operating modes. A centralized protection scheme is employed that takes frequency data and voltage phasor to differentiate between islanding and fault condition. Further, it detects the faulted feeder and sends trip command to respective relays within a tolerant time. This method is devised to work as backup protection when main utility grid is available. However, it can work as a primary protection during islanded mode, when local overcurrent relay fails to operate due to settings based on grid connected mode. A standard IEEE 15 bus system modeled in EMTP-RV is taken as test system for every analysis.
