Machine-learned security assessment for changing system topologies

Bellizio, Federica; Cremer, Jochen; Štrbac, Goran

doi:10.1016/j.ijepes.2021.107380

Cited by 14 publications

(13 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Fig. 2 , ML methods usually have an off-line training phase used in design of prompt classifiers or regressors for an online security assessment [ 13 , 81 , 87 ]. The training helps to acquire knowledge of the complex relationship between the initial system state and post contingency security status [ 25 ].…”

Section: Methods Of Power System Security Assessmentmentioning

confidence: 99%

Techniques of power system static security assessment and improvement: A literature survey

Hailu¹,

Nyakoe²,

Muriithi³

2023

Heliyon

View full text Add to dashboard Cite

Section: Methods Of Power System Security Assessmentmentioning

confidence: 99%

Techniques of power system static security assessment and improvement: A literature survey

Hailu¹,

Nyakoe²,

Muriithi³

2023

Heliyon

View full text Add to dashboard Cite

“…1. The first step is the time-ahead prediction of the available flexibility based on forecasts of the charging station generation and load, as well as EV arrival and departure times and energy demand [22]. Subsequently, such forecasts are fed as input to a multisite optimizer that provides 15-hour ahead optimal charging/ discharging schedules for an onsite BESS and an EV fleet moving between different sites during the day, thus being able to provide flexibility services at different locations.…”

Section: A Proposed Approachmentioning

confidence: 99%

“…The test system representing the PVbattery charging station included 168 kWh battery and 110 kWp PV systems, and 4 CPs. A fleet of 4 EVs with V2G technology moving between the charging station and the service site was sampled from real charging data provided by TotalEnergies [22]. The flexibility market framework shown in Fig.…”

Section: A Proposed Approachmentioning

confidence: 99%

Optimal V2X operation of EV fleets with PV-battery charging station for demand-side flexibility provision

Bellizio,

Heer

2023

Preprint

View full text Add to dashboard Cite

<p>The increasing number of electric vehicles expected on the road in the coming years poses new threats to the reliability of the power system. However, it can also play a key role as a source of demand-side flexibility to support the system in managing uncertainty resulting from the integration of renewable and distributed energy resources. In this paper, a novel operational tool for vehicle-to-everything operation of electric vehicle fleets with photovoltaics-battery charging station for demandside flexibility provision is proposed. The tool provides electric vehicle aggregators with a risk-aware flexibility quantification, robust market bids and real-time control decisions. The approach was tested on real demonstrators in Switzerland, highlighting the cost-benefits of demand-side flexibility provision.</p>

show abstract

“…The approach is to train an ML model offline when the computational time for simulations is abundant, and use the trained model to predict security and control actions in real time immediately before a fault or in response to it. Such methods are promising for real-time operation [79], [80] as their prediction requires minimal computational time, but have challenges related to the generation of training data [81], the interpretability of the prediction [82], their risks and probabilities of success [83], and their usability to other operating conditions and topologies [84], etc. Recently promising methods use the known dynamical model, i.e., the ODEs, to inform directly the ML training which can reduce the demands for training data [85], [86].…”

Section: E Real-time Dsamentioning

confidence: 99%

Perspectives on Future Power System Control Centers for Energy Transition

Marot

Kelly²,

Naglič

et al. 2022

Journal of Modern Power Systems and Clean Energy

View full text Add to dashboard Cite

Today's power systems are seeing a paradigm shift under the energy transition, sparkled by the electrification of demand, digitalisation of systems, and an increasing share of decarbonated power generation. Most of these changes have a direct impact on their control centers, forcing them to handle weather-based energy resources, new interconnections with neighbouring transmission networks, more markets, active distribution networks, micro-grids, and greater amounts of available data. Unfortunately, these changes have translated during the past decade to small, incremental changes, mostly centered on hardware, software, and human factors. We assert that more transformative changes are needed, especially regarding humancentered design approaches, to enable control room operators to manage the future power system. This paper discusses the evolution of operators towards continuous operation planners, monitoring complex time horizons thanks to adequate real-time automation. Reviewing upcoming challenges as well as emerging technologies for power systems, we present our vision of a new evolutionary architecture for control centers, both at backend and frontend levels. We propose a unified hypervision scheme based on structured decision-making concepts, providing operators with proactive, collaborative, and effective decision support.

show abstract

Machine-learned security assessment for changing system topologies

Cited by 14 publications

References 31 publications

Techniques of power system static security assessment and improvement: A literature survey

Techniques of power system static security assessment and improvement: A literature survey

Optimal V2X operation of EV fleets with PV-battery charging station for demand-side flexibility provision

Perspectives on Future Power System Control Centers for Energy Transition

Contact Info

Product

Resources

About