A Novel ANFIS-Based Islanding Detection for Inverter-Interfaced Microgrids

Mlakić, Dragan; Baghaee, Hamid Reza; Nikolovski, Srete

doi:10.1109/tsg.2018.2859360

Cited by 147 publications

(73 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recently, some computational intelligent methods in combination with modern signal processing techniques have been introduced to get rapid detection of islanding condition, such as artificial neural network, [11][12][13][14][15][16][27][28][29][30][31] fuzzy logic, [15][16][17][18]28 and wavelet. [15][16][17][24][25][26][27][28] In spite of the outstanding features and the capability of these intelligent methods to determine the most proper combination of features, as well as thresholds, that can reduce the NDZ, such intelligent methods need additional software and hardware support and are difficult to implement in practice.…”

Section: Passive Methodsmentioning

confidence: 99%

Zero non‐detection zone assessment for anti‐islanding protection in rotating machines based distributed generation system

Abd-Elkader

Saleh

2020

Int J Energy Res

View full text Add to dashboard Cite

The challenges for a reliable operation of electrical power system have increased due to the presence of multi-distributed generation units (DGs) in the distribution systems in order to meet the increase of the load demand. Detection of unintentional islanding situation is very important as nondetection of islanding situation could result in a cascaded failure of the system. If the islanding situation remains undetected, the instability in the islanded part can lead to a complete failure of the electrical power system. This paper introduces a new passive scheme for islanding detection, which is suitable for multi-distributed generation units based on rotating machines. The proposed method is based on the measurements of the system voltage and frequency to compute two indices called the islanding index and harmonics index. The islanding index is the main index used to discriminate and identify the islanding situation. However, the harmonics index in conjunction with a strategy called speed reduction strategy assists the islanding index to discriminate between islanding situation in case of a close power match and system disturbances. The simulation studies were conducted in MATLAB/SIMULINK environment, and various cases have been considered, such as normal operation, islanding operation, sudden load change, DG tripping, separation of some DG units, faults, etc. The novelty of the proposed strategy is that it provides fast detection and has zero nondetection zone compared with the existing detection methods. Moreover, the proposed strategy has no effect on the power quality, and the maximum detection time is almost 350 ms at a close power match. The results indicate that the proposed scheme is successful in discrimination of the islanding conditions from other grid disturbances, revealing its great potential to be able to detect islanding events. Finally, the proposed method is applied only for rotating machine based DGs, such as wind turbines. Wind farms'

show abstract

Section: Passive Methodsmentioning

confidence: 99%

Zero non‐detection zone assessment for anti‐islanding protection in rotating machines based distributed generation system

Abd-Elkader

Saleh

2020

Int J Energy Res

View full text Add to dashboard Cite

show abstract

“…Intentional islanding is carried out because of the scheduled maintenance, while unintentional islanding can take place as a result of unpredicted issues causing the isolation from the main grid. This can lead to safety hazards, mal-operation of protective devices, power quality disturbances [2]. So the IEEE 1547-2003 standard specifies that the maximum allowable delay for recognizing the unintentional islanding condition is two seconds [3].…”

Section: Nomenclaturementioning

confidence: 99%

Islanding Detection of Microgrid Incorporating Inverter Based DGs Using Long Short-Term Memory Network

Abdelsalam¹,

Salem²,

Oda³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

This paper proposes a new approach for rapid detection of islanding events in a microgrid (MG). The proposed approach is a two-step procedure in which the first step is to extract some valuable features from the voltage and current signals. Such signals are analyzed for finding the second harmonic by the discrete Fourier transform (DFT). Then, the symmetrical components of this second harmonic are calculated for voltage and current, resulting in six features; positive, negative and zero sequence components. In the second step, a novel deep learning classifier based on long short-term memory (LSTM) network to identify the islanding decision is applied. The LSTM is a new artificial intelligence technique which is a distinctive pattern of recurrent neural networks. To evaluate the performance of the proposed approach, simulated and practical voltage and current signals are used. The simulated signals are generated by simulating a MG consisting of inverter based wind DGs using Matlab Simulink, while the practical data are collected from an experimental model consisting of wind and PV DGs. Different intentional and unintentional islanding events are conducted and processed using the proposed approach. The results show that in comparison with other artificial intelligence algorithms such as decision tree (DT), support vector machine (SVM) and artificial neural network (ANN), the proposed approach is efficient and reliable in detecting the islanding with high accuracy, high dependability and small detection time.

show abstract

“…Similar to layer 2, nodes are fixed in layer 3. Next, adaptive nodes in layer 4 calculate values of the rule of the consequent part and finally, layer 5 sums all outputs of layer 4 and contains only one node [27]. Mathematical description of layer 3, layer 4 and layer 5 are given in Equations (6)-(8) respectively.ω…”

Section: Anfismentioning

confidence: 99%

Short-Term Electric Power Demand Forecasting Using NSGA II-ANFIS Model

et al. 2019

View full text Add to dashboard Cite

Load forecasting is of crucial importance for smart grids and the electricity market in terms of the meeting the demand for and distribution of electrical energy. This research proposes a hybrid algorithm for improving the forecasting accuracy where a non-dominated sorting genetic algorithm II (NSGA II) is employed for selecting the input vector, where its fitness function is a multi-layer perceptron neural network (MLPNN). Thus, the output of the NSGA II is the output of the best-trained MLPNN which has the best combination of inputs. The result of NSGA II is fed to the Adaptive Neuro-Fuzzy Inference System (ANFIS) as its input and the results demonstrate an improved forecasting accuracy of the MLPNN-ANFIS compared to the MLPNN and ANFIS models. In addition, genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization (ACO), differential evolution (DE), and imperialistic competitive algorithm (ICA) are used for optimized design of the ANFIS. Electricity demand data for Bonneville, Oregon are used to test the model and among the different tested models, NSGA II-ANFIS-GA provides better accuracy. Obtained values of error indicators for one-hour-ahead demand forecasting are 107.2644, 1.5063, 65.4250, 1.0570, and 0.9940 for RMSE, RMSE%, MAE, MAPE, and R, respectively.

show abstract

A Novel ANFIS-Based Islanding Detection for Inverter-Interfaced Microgrids

Cited by 147 publications

References 38 publications

Zero non‐detection zone assessment for anti‐islanding protection in rotating machines based distributed generation system

Zero non‐detection zone assessment for anti‐islanding protection in rotating machines based distributed generation system

Islanding Detection of Microgrid Incorporating Inverter Based DGs Using Long Short-Term Memory Network

Short-Term Electric Power Demand Forecasting Using NSGA II-ANFIS Model

Contact Info

Product

Resources

About