Perspectives on Future Power System Control Centers for Energy Transition

Abstract

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.

Data-Driven Anomaly Detection and Event Log Profiling of SCADA Alarms

“…Topics for future work include: a) integrate network topology information; b) create separate models according to the SS equipment generation or vendors (departing from the PCA and clustering process discussed in section V); c) generate synthetic data for SS or specific lines with few historical events. This work represents a first step towards AI-assisted operation of electrical grids [37].…”

“…This particular cluster, manually designated by the domain expert as protection trip with failed autoreclosing, includes outages events where a circuit breaker opens due to a distance protection trip, followed by an unsuccessful automatic reclosing cycle and a subsequent action by the human operator. It is important to emphasize that human domain knowledge remains fundamental to extract in-terpretable information from the clustering results, and it will not be fully replaced by autonomous AI functions (see [37] for an interesting discussion about human-AI interaction in power systems).…”

Towards an AI Assistant for Power Grid Operators

“…An assistant could hence help augment the operator's decision-making capability [1] to address : (a) More rapidly evolving and changing system environment; (b) More numerous, complex, and coordinated decisions to make; (c) More uncertainty to consider and more anticipation needed; (d) Information overload and fragmented work environment; (e) Human operator cognitive load saturation. It would eventually help limit the grid operational cost to a few percent increase rather than a 2-fold one.…”

“…Operators are facing aging grids, with slower grid asset developments due to decreasing social acceptability. Operators hence need to operate a system closer to its limits while dealing with greater uncertainty and increasing grid automation [1] inducing complex cyber-physical dynamics [2]. While there could be a temptation to develop a fully autonomous grid to cope with that complexity, it falls short for such large critical system operations.…”

“…Historically, control rooms have tackled grid evolution dynamics by gradually adding more applications and screens. While incrementally growing a monitoring alarmdriven management system has worked until now, we are today struggling to maintain effective decision-making at a new scale of complexity, essentially in terms of manageable cognitive load for human operators, who should remain at the center of decisions [1]. In that regard, Human-Machine Interfaces (HMI) have been identified as a risk factor for human error [4], and should now be considered more closely.…”