Application of Artificial Intelligence and Machine Learning Techniques in Island Detection in a Smart Grid

Dutta, Soham; Sadhu, Pradip Kumar; Cherikuri, Murthy; Mohanta, Dusmanta Kumar

doi:10.1002/9781119786306.ch3

Cited by 3 publications

(2 citation statements)

References 95 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first model, called the "Up Pyramid," increases the units of the neural network in the order of 32, 128, 512 and 2056 until a final output layer classifies the data. In an ANN, a unit is nothing but a mathematical equation associated with a weight which serves as the most basic building block in a neural network [41]. These increasing layers showed the best experimental results with "Rectified Linear Unit" or "ReLu" activation function whose equation is given as per (1) [42] where x is the input variable.…”

Section: Methodology To Develop the Cannmentioning

confidence: 99%

A customised artificial neural network for power distribution system fault detection

Bhagwat,

Dutta,

Jadoun

et al. 2024

IET Generation Trans & Dist

View full text Add to dashboard Cite

Machine learned fault detection approaches are being increasingly used for fault detection in distribution grid. However, the performance of the models can be improved by customizing the models. In this regard, a customised artificial neural network (CANN) for fault detection in a distribution grid is proposed in this paper. The proposed work develops a CANN that combines the “up‐pyramid” and “down‐pyramid” model of ANN into a “custom‐pyramid” model. As a result, the same model can be used both for determining the types of fault as well as its location. The data needed to train the model has been taken from a reconfigured IEEE‐33 bus distribution system developed in Typhoon HIL real‐time simulator. Spectral‐kurtosis is utilized for extraction of features of the faulted transient signals which are used as input data to develop the CANN. The result showcases that the reduction of input features reduces computational complexity without compromising its accuracy. The proposed model classifies fault location with an accuracy of 95.43%. The proposed method also identifies fault type with an accuracy of 96.08%. Several test cases have been developed to test the method. The method proved to be able to perform in most of the cases.

show abstract

Section: Methodology To Develop the Cannmentioning

confidence: 99%

A customised artificial neural network for power distribution system fault detection

Bhagwat,

Dutta,

Jadoun

et al. 2024

IET Generation Trans & Dist

View full text Add to dashboard Cite

show abstract

“…Source: The authors' own work based on: [88,92,99,104,[128][129][130]132,134,135,137,139,[142][143][144][145][148][149][150][151][152][153][154][155][156][157][158][159][160].…”

Section: Data Privacy Concernsunclassified

AI-Driven Urban Energy Solutions—From Individuals to Society: A Review

Stecuła,

Wolniak,

Grebski

2023

Energies

View full text Add to dashboard Cite

This paper provides a comprehensive review of solutions based on artificial intelligence (AI) in the urban energy sector, with a focus on their applications and impacts. The study employed a literature review methodology to analyze recent research on AI’s role in energy-related solutions, covering the years 2019 to 2023. The authors classified publications according to their main focus, resulting in two key areas of AI implementation: residential and individual user applications, and urban infrastructure integration for society. The objectives of this review of the literature are the following: O1: to identify trends, emerging technologies, and applications using AI in the energy field; O2: to provide up-to-date insights into the use of AI in energy-related applications; O3: to gain a comprehensive understanding of the current state of AI-driven urban energy solutions; O4: to explore future directions, emerging trends, and challenges in the field of AI-driven energy solutions. This paper contributes to a deeper understanding of the transformative potential of AI in urban energy management, providing valuable insights and directions for researchers and practitioners in the field. Based on the results, it can be claimed that AI connected to energy at homes is used in the following areas: heating and cooling, lighting, windows and blinds, home devices, and energy management systems. AI is integrating into urban infrastructure through the following solutions: enhancement of electric vehicle charging infrastructure, reduction in vehicle emissions, development of smart grids, and efficient energy storage. What is more, the latest challenges associated with the implementation of AI-driven energy solutions include the need to balance resident comfort with energy efficiency in smart homes, ensuring compatibility and cooperation among various devices, preventing unintended energy consumption increases due to constant connectivity, the management of renewable energy sources, and the coordination of energy consumption.

show abstract

An island detection methodology with protection against cyber attack

Shukla,

Dutta,

Sadhu

et al. 2024

Microsyst Technol

View full text Add to dashboard Cite

Unplanned islanding of micro-grids is a significant barrier to supplying continuous power to key customers. The identification of the islanding moments must be rapid to enable the distributed generators (DG) to perform control measures in the shortest possible period. Micro phasor measuring units (µ-PMU) are gaining popularity in distribution systems and micro grids as a result of their ability to produce high-quality data at a high speed. These µ-PMUs can be utilized to detect islands. However, the µ-PMU relies heavily on the communication system for transmission of data, which is vulnerable to cyberattacks. In consideration of the previous technique, this research provides a smart island detection application with µ-PMU having lowered cyberattack probabilities. This representation is equipped with a µ-PMU implemented on the relevant DG’s bus. The voltage data acquired from these µ-PMUs are processed using the sequence transformation in order to simulate the sequence component angle. The angular sum of the negative and positive sequence components is evaluated and the maximum value is deployed for detection of islanding. MATLAB/Simulink tests the proposed approach through an IEEE-34 node distribution network. Multiple simulations demonstrate the robustness of the technique.

show abstract

Application of Artificial Intelligence and Machine Learning Techniques in Island Detection in a Smart Grid

Cited by 3 publications

References 95 publications

A customised artificial neural network for power distribution system fault detection

A customised artificial neural network for power distribution system fault detection

AI-Driven Urban Energy Solutions—From Individuals to Society: A Review

An island detection methodology with protection against cyber attack

Contact Info

Product

Resources

About