Islanding event detection technique based on change in apparent power in microgrid environment

Kumar, Munna; Kumar, Jitendra

doi:10.1007/s00202-023-01750-5

Cited by 8 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[52] Additionally, research optimizing the eXtreme Gradient Boosting (XGB) model for solar radiation forecasting has demonstrated remarkable accuracy enhancements, highlighting the efficacy of hyperparametric tuning in this field. [53] However, it is important to acknowledge the inherent challenges associated with each model type. RNNs, for example, may face training difficulties due to vanishing gradients [54] and numerical instability, [55] while CNNs often require extensive training data and complex architectures to achieve comprehensive receptive fields.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Solar Forecasting Accuracy with Sequential Deep Artificial Neural Network and Hybrid Random Forest and Gradient Boosting Models across Varied Terrains

Hanif,

Siddique,

et al. 2024

Advcd Theory and Sims

View full text Add to dashboard Cite

Effective solar energy utilization demands improvements in forecasting due to the unpredictable nature of solar irradiance (SI). This study introduces and rigorously tests two innovative forecasting models across different locations: the Sequential Deep Artificial Neural Network (SDANN) and the Deep Hybrid Random Forest Gradient Boosting (RFGB). SDANN, leveraging deep learning, aims to identify complex patterns in weather data, while RFGB, combining Random Forest and Gradient Boosting, proves more effective by offering a superior balance of efficiency and accuracy. The research highlights the SDANN model's deep learning capabilities along with the RFGB model's unique blend and their comparative success over existing models such as eXtreme Gradient Boosting (XGBOOST), Categorical Boosting (CatBOOST), Gated Recurrent Unit (GRU), and a K‐Nearest Neighbors (KNN) and XGBOOST hybrid. With the lowest Mean Squared Error (147.22), Mean Absolute Error (8.77), and a high R2 value (0.80) in a studied region, RFGB stands out. Additionally, detailed ablation studies on meteorological feature impacts on model performance further enhance accuracy and adaptability. By integrating cutting‐edge AI in SI forecasting, this research not only advances the field but also sets the stage for future renewable energy strategies and global policy‐making.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing Solar Forecasting Accuracy with Sequential Deep Artificial Neural Network and Hybrid Random Forest and Gradient Boosting Models across Varied Terrains

Hanif,

Siddique,

et al. 2024

Advcd Theory and Sims

View full text Add to dashboard Cite

show abstract

“…In case of contingencies, the existing technique is adaptable enough to take into account the DG effect on any point on the network and its islanded operation. In [32,33], the author uses combinatorial optimization to determine the best type of switches for a radial distribution system while taking into account the overall cost and reliability criterion. Based on prior failures, repair times are taken into account for each failure.…”

Section: Associated Research Workmentioning

confidence: 99%

Economic Analysis of Isolator Placement in the Radial Network for Enhancement of Reliability Indicators

Madhav

Yadav

2023

Preprint

View full text Add to dashboard Cite

This paper presents a novel technique to upgrade the distribution network reliability indices in the radial electrical distribution system. The genetic algorithm (GA) technique is used to determine the optimum position and number of isolators in the electrical distribution network. The problem formulation of this real problem is formulated with the product of unavailability and the total number of consumers affected under the constraints of the optimal number of switches. Among various reliability indices system average interruption duration index is selected to realize the problem. The technique is applied on 34 and 59 load point systems and the results show the acceptance of the suggested method in the paper. This algorithm is compared with particle swarm optimization on 22 and 34 bus system and found GA provide better result. It is also analyzed that the customer-oriented and energy-oriented indices upgraded sharply and consumers service indices are very good so that profit of the distribution company enhanced. All reliability indices improve after optimum switch placement in a radial distribution network. Diminution in Energy not served (ENS) shows that the last end of customers is satisfied with the performance of service provided in their area.

show abstract

“…[87]. Görünür gücün pozitif bileşenindeki değişimi dikkate alan bir diğer ada çalışma tespit yönteminde de sonuçlar OPAL-RT simülatör kullanılarak doğrulanmıştır [88]. Önerilen yöntemin simülasyon ve deneysel sonuçları arasındaki benzerlik önerilen yöntemin gerçek zamanlı olarak uygulanabilirliğini ortaya koymuştur.…”

Section: Sinyal İşlemeye Dayalı Metotlar (Signal Processing Based Sc...unclassified

A Comprehensive Review of Intelligent Islanding Detection Methods for Grid Integrated Distributed Generation Systems

Özcanlı

2023

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım Ve Teknoloji

View full text Add to dashboard Cite

Mikro şebekeler fotovoltaik, rüzgâr ve hidrolik gibi enerji kaynaklarının şebekeye entegrasyonunu sağlayan ve şebekeye bağlı ve şebekeden bağımsız çalışabilen, geleceğin enerji sisteminin önemli bir parçasını oluşturmaktadır. Mikro şebeke konsepti; fosil yakıt kullanımı, hat kayıpları, karbon ayak izi, emisyon azaltma ve enerji verimliliğini arttırma hedefi ile geleceğin akıllı şebekeleri için büyük bir potansiyele sahiptir. Bununla birlikte dağıtık üretimin güç sistemine entegrasyonu, güç sisteminin kontrolü işletilmesi ve korunmasında bazı dezavantajlara ve risklere neden olabilmektedir. Bu konudaki en büyük problemlerden biri, şebekeye bağlı çalışan mikro şebekenin herhangi bir arıza durumunda ana şebekeden ayrılarak çalışmaya devam ettiği istenmeyen ada çalışma durumudur. İstenmeyen ada çalışma durumu, güç sisteminde frekans kararsızlığına neden olarak, personel güvenliği ve güç sistemindeki ekipmanları için tehdit unsuru oluşturabilir. Bu durumu önlemek amacıyla ada çalışmanın ivedilikle tespit edilerek ana şebeke ile mikro şebekenin bağlantısı fiziksel olarak kesilmelidir. Literatürde birçok ada çalışma tespit yöntemi önerilmiştir. Bu çalışmada, literatürde sunulan akıllı ada çalışma tespit yöntemleri detaylı olarak incelenmiş ve önerilen yöntemler algılama dışı bölge, tespit süresi, işletme maliyeti, doğruluk ve güç kalitesi bakımından analiz edilmiştir. Diğer çalışmalardan farklı olarak bu çalışmada, gerçek zamanlı deneysel çalışmalar, önerilen yöntemlerin uygulanabilirliğini göstermek amacıyla detaylı olarak incelenmiştir. Böylelikle ortaya konulan yöntemlerin pratikte uygulanabilirliği konusunda araştırmacılara önemli bir kaynak oluşturulmuştur.

show abstract

Islanding event detection technique based on change in apparent power in microgrid environment

Cited by 8 publications

References 41 publications

Enhancing Solar Forecasting Accuracy with Sequential Deep Artificial Neural Network and Hybrid Random Forest and Gradient Boosting Models across Varied Terrains

Enhancing Solar Forecasting Accuracy with Sequential Deep Artificial Neural Network and Hybrid Random Forest and Gradient Boosting Models across Varied Terrains

Economic Analysis of Isolator Placement in the Radial Network for Enhancement of Reliability Indicators

A Comprehensive Review of Intelligent Islanding Detection Methods for Grid Integrated Distributed Generation Systems

Contact Info

Product

Resources

About