Machine learning for protection of distribution networks and power electronics-interfaced systems

Aminifar, Farrokh; Teimourzadeh, Saeed; Shahsavari, Alireza; Savaghebi, Mehdi; Golsorkhi, Mohammad S.

doi:10.1016/j.tej.2020.106886

Cited by 23 publications

(10 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many applications in smart power grids based on IoT technologies, which including, but not limited to real-time monitoring and control system [33], medium-voltage protection of smart grid [34], protection of distribution networks [35], and protection and control of microgrids [36]. The power grid's operation and protection require faster sensing, communication, and switching systems.…”

Section: A Related Workmentioning

confidence: 99%

IoT Technology-Based Protection Scheme for MT-HVDC Transmission Grids With Restoration Algorithm Using Support Vector Machine

et al. 2021

View full text Add to dashboard Cite

This paper proposes a protection scheme for multi-terminal high voltage direct current (MT-HVDC) transmission grids. The proposed scheme is based on three protection levels; di/dt overcurrent protection as the main protection, dv/dt undervoltage protection as a backup one protection. If the main and backup one fails to detect and clear the fault current, then the fault tripping and clearing is accomplished using the overcurrent protection by AC circuit breakers (ACCBs) in the AC grid side after a coordinated time. The tripping in the main and backup one protection levels are based on using fault isolation devices (FIDs) tripping. Support vector machine (SVM) is proposed for the fault detection and discrimination in the MT-HVDC using the backup two protection system. The Internet of things (IoT) has been used for monitoring and coordination between the AC grid and MT-HVDC grid. The proposed protection scheme is applied and verified on the MT-HVDC network under different transmission system faults using the MATLAB/Simulink ® environment. The results show that the proposed scheme's effectiveness as a fast and reliable scheme in fault detection and discrimination for the MT-HVDC grids.

show abstract

Section: A Related Workmentioning

confidence: 99%

IoT Technology-Based Protection Scheme for MT-HVDC Transmission Grids With Restoration Algorithm Using Support Vector Machine

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Big data analytics is key to effective microgrid energy management as it can provide load and system stability prediction based on analysis. Analytical data can be fed into AI-based control algorithms for optimized performance of the MG. Learning based on this analysed data has also been mentioned to provide support for power system protection [42].…”

Section: ) Ai-based Performancementioning

confidence: 99%

Software-Defined Power Grids: A Survey on Opportunities and Taxonomy for Microgrids

et al. 2021

View full text Add to dashboard Cite

Future generation power grids will require the introduction and deployment of distributed energy resources to meet modern day load requirements. Consequently, we expect to see a rise in microgrids (MGs) existing as part of the main grid (grid-connected) or independent (islanded). Contained in these microgrids are a combination of energy resources such as solar, wind and fossil-fuels coupled with storage devices, electric vehicles and smart devices supporting prosumer operation. However, the addition of renewable energy resources would mean fluctuations in energy supply which would cause power system instability if not managed effectively. Hence, to maximize the management flexibility of MGs, the concept of microgrid software-definition is introduced. A concept that can be looked at as giving the microgrid an operating system to improve operation response and event detection by maintaining a global view of the network. This paper therefore critically analyses what this entails by presenting an architecture for Software-Defined Microgrids and discussing the management opportunities that softwarization of the MG introduces. We also highlight the design requirements and associated challenges in implementing and deploying SDMGs.INDEX TERMS Energy balancing, grid resiliency, microgrids, power grid management, software-defined networking, smart grids.

show abstract

“…To address the destabilization effect of constant power loads under voltage variations, neural networks have been used in [19], and the authors in [20] developed a model for voltage stability prediction using an active learning solution as well. Similarly, machine learning has been used in protection of power electronic based systems and determining the possible outage of grid components in [21] and [22]. Further, some data-driven control has been presented to improve frequency regulation and lowvoltage ride through (LVRT) performance of converters in [23] and [24], and the data-driven control of DC power converters has been developed in [25].…”

Section: Introductionmentioning

confidence: 99%

Employing Machine Learning for Enhancing Transient Stability of Power Synchronization Control During Fault Conditions in Weak Grids

Sepehr

Gomis‐Bellmunt

Pouresmaeil

2022

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

Machine learning for protection of distribution networks and power electronics-interfaced systems

Cited by 23 publications

References 65 publications

IoT Technology-Based Protection Scheme for MT-HVDC Transmission Grids With Restoration Algorithm Using Support Vector Machine

IoT Technology-Based Protection Scheme for MT-HVDC Transmission Grids With Restoration Algorithm Using Support Vector Machine

Software-Defined Power Grids: A Survey on Opportunities and Taxonomy for Microgrids

Employing Machine Learning for Enhancing Transient Stability of Power Synchronization Control During Fault Conditions in Weak Grids

Contact Info

Product

Resources

About