Alternating iterative method for congestion management of microgrid integrated distribution network

Tang, Chuheng; Zhang, Wei; Liu, Ruiye

doi:10.1109/icpre.2017.8390580

Cited by 1 publication

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Volume 48 Issue 1 (March 2024) https://powertechjournal.com 3.8 Cost and Resource Constraints: Traditional methods of power grid restoration require significant human and financial resources to deploy field crews, equipment, and materials for repairs. [21] Budgetary constraints may limit the ability of utilities to invest in advanced technologies or training programs to improve the efficiency of restoration processes. Cost and resource constraints may hinder the adoption of more automated and data-driven approaches to power grid restoration, limiting the ability of utilities to enhance the resilience and reliability of their infrastructure.…”

Section: Data Management Challengesmentioning

confidence: 99%

Self-Healing Grids: AI Techniques for Automatic Restoration after Outages

Purushottam Kumar Maurya

2024

pst

View full text Add to dashboard Cite

The reliability and resilience of power grids are paramount for sustaining modern society's energy demands. However, power outages resulting from natural disasters, equipment failures, or human errors remain persistent challenges. Traditional approaches to power grid restoration, relying heavily on manual intervention, often lead to delays and inefficiencies in restoring services. [1],[2] Recent advancements in artificial intelligence (AI) have spurred the development of self-healing grids capable of autonomously detecting, diagnosing, and restoring power after outages. This paper presents a comprehensive overview of AI techniques employed in self-healing grids and their applications in automatic restoration following outages. The traditional methods of power grid restoration, characterized by manual inspection and decision-making processes, are discussed, highlighting their limitations and challenges. Subsequently, the paper delves into various AI techniques employed in self-healing grids. Machine learning algorithms, such as supervised and unsupervised learning, are utilized for outage detection by analyzing historical data to identify patterns indicative of faults or anomalies. Fault diagnosis is facilitated through the application of Bayesian networks, neural networks, and fuzzy logic systems, enabling operators to accurately identify the root cause of outages and prioritize restoration efforts. Optimization algorithms, including evolutionary algorithms and reinforcement learning, play a crucial role in planning and coordinating restoration efforts to minimize downtime and maximize efficiency. The benefits of self-healing grids, including improved reliability, reduced downtime, and enhanced safety, are discussed alongside the challenges posed by data quality, scalability, and cybersecurity concerns. Finally, the paper outlines future directions, emphasizing advancements in AI techniques, integration with emerging technologies, and the importance of standardization and regulatory frameworks for the future of power grid management. DOI: https://doi.org/10.52783/pst.302

show abstract

Section: Data Management Challengesmentioning

confidence: 99%

Self-Healing Grids: AI Techniques for Automatic Restoration after Outages

Purushottam Kumar Maurya

2024

pst

View full text Add to dashboard Cite

show abstract

Alternating iterative method for congestion management of microgrid integrated distribution network

Cited by 1 publication

References 10 publications

Self-Healing Grids: AI Techniques for Automatic Restoration after Outages

Self-Healing Grids: AI Techniques for Automatic Restoration after Outages

Contact Info

Product

Resources

About