Real-time out-of-step prediction control to prevent emerging blackouts in power systems: A reinforcement learning approach

Hassani, Hossein; Razavi–Far, Roozbeh; Saif, Mehrdad

doi:10.1016/j.apenergy.2022.118861

Cited by 15 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Initial scheduling of outage plans: After summarizing the above information, the scheduling specialist analyzes and schedules all outage plan sets for the month in accordance with the relevant protocols [8]. This process involves a number of complex factors, including prior and posterior correlations between plans, prioritization, constraints, and outage metrics to be considered, and how to schedule in a way that maximizes or minimizes those metrics, among other things.…”

Section: Monthly Outage Plan Manual Scheduling Process Sorting and An...mentioning

confidence: 99%

Intelligent scheduling model of main grid outage plan based on multiple indicator constraints

Zhang,

Huang,

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

This paper proposes an intelligent scheduling method based on expert knowledge and preference filtering to address the key issues in the grid outage plan scheduling business. By combing, reconstructing, and function disassembling the manual scheduling process of the monthly outage plan, this paper proposes the initial scheduling, coordinated adjustment, rolling scheduling, and conflict retrospective process of the monthly outage plan. It conducts research on the difficult problems existing in the process. For the difficult problem of decoupling the plan adjustment and scheduling-solving process, this paper proposes an expert knowledge-based method, including knowledge graph-based plan association relationship discrimination and supervised learning-based plan prioritization. Finally, this paper carries out the system framework design, service design, database, and data structure design for the proposed intelligent scheduling method. It verifies the effectiveness of the proposed method through case tests in real power grids.

show abstract

Section: Monthly Outage Plan Manual Scheduling Process Sorting and An...mentioning

confidence: 99%

Intelligent scheduling model of main grid outage plan based on multiple indicator constraints

Zhang,

Huang,

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Their research facilitated time-series predictions of blackout incidents and associated loss loads [4]. These studies have tackled the issue of power outages in distribution networks from diverse angles and dimensions [5]. They have explored fault analysis and modeling using outage data, risk prediction based on new energy grid nodes, and data-driven analysis for distribution networks.…”

Section: Introductionmentioning

confidence: 99%

Technology for Power Outage Research and Judgment-dependent Data Feature Noise Analysis

2023

EAI Endorsed Trans Energy Web

View full text Add to dashboard Cite

INTRODUCTION: Power grid blackouts occur frequently, which significantly impacts social impact. Because these accidents are dynamic and random, predicting and evaluating them is challenging. OBJECTIVES: To explore the complexity of the power grid itself, analyzes the critical changes of the self-organizing model during power grid fault, extracts the data characteristics related to the steady-state maintenance of abnormal systems, and puts forward an effective outage prediction model. METHODS: Starting with cluster analysis, The authors can reduce data fluctuation and eliminate noise interference to optimize data. The evaluation indexes of initial fault occurrence possibility and fault propagation speed in the power grid are constructed. RESULTS: The validation of the outage forecasting model has produced promising results, achieving 96.4% forecasting accuracy and a meager error rate. In addition, the evaluation index developed in this study accurately reflects the possibility and spread speed of power outage accidents. CONCLUSION: The research proves the feasibility of establishing an outage prediction model based on the power grid system data characteristics. The model has high accuracy and reliability and is a valuable tool for power outage research and judgment.

show abstract

“…The hierarchical feature extraction within the DL models enables them to learn complex underlying patterns in the observed input space. This makes DL models suitable for processing various data types and facilitating different tasks such as prediction [47], detection [93], imputation [43], and data reduction [46]. Although the success of DL-based projects is contingent on several factors, one of the most important requirements is usually to have access to abundant training samples.…”

Section: Introductionmentioning

confidence: 99%

Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms

Hallaji,

Razavi-Far,

Saif

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The advent of federated learning has facilitated large-scale data exchange amongst machine learning models while maintaining privacy. Despite its brief history, federated learning is rapidly evolving to make wider use more practical. One of the most significant advancements in this domain is the incorporation of transfer learning into federated learning, which overcomes fundamental constraints of primary federated learning, particularly in terms of security. This chapter performs a comprehensive survey on the intersection of federated and transfer learning from a security point of view. The main goal of this study is to uncover potential vulnerabilities and defense mechanisms that might compromise the privacy and performance of systems that use federated and transfer learning.

show abstract

Real-time out-of-step prediction control to prevent emerging blackouts in power systems: A reinforcement learning approach

Cited by 15 publications

References 34 publications

Intelligent scheduling model of main grid outage plan based on multiple indicator constraints

Intelligent scheduling model of main grid outage plan based on multiple indicator constraints

Technology for Power Outage Research and Judgment-dependent Data Feature Noise Analysis

Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms

Contact Info

Product

Resources

About