AISOP combines data access and ingestion, decision-support, dynamic tariffs, and digital platform integration for improved distribution grid situational awareness., focusing on grid state analysis, fault prediction, identification of anomalies and unexpected consumption patterns.
AISOP creates an AI-assisted decision support system for the DSO to drive decarbonisation that is underpinned by
advanced digital technology. Data is made available through deployed conventional and new grid measurements (e.g., dPMUs, IEDs), measurements from distributed energy resources (DERs), as well as enhanced metering infrastructure, combining advanced tools and protocols for acquisition and exploitation of data from distributed sensors.
The project demonstrates the potential of data-driven methods to increase the observability of distribution grids by developing innovative solutions to extract knowledge from large amounts of temporally and spatially heterogenous data, collected from intelligent distributed sensors.
Data are used for forecasting the grid state (nodal voltages, branch loading); predicting asset failure; forecasting intermittent grid faults and detecting anomalies in demand. ML techniques will be exploited to assess benefits. Decision-support tools will be developed and scenarios will be generated to test and increase the performance of the proposed tools.
When enhanced data sources are combined with advanced data analysis, the system applies risk analysis using machine learnining approaches, AISOP is then able to support DSO operational planning through ML-based dynamic tariff setting.. In this way, AISOP will advance the green energy transition in all sectors by leveraging artificial intelligence and machine learning in the DSO, and by integrating and linking data platforms and driving interoperability between them, including those relating to electricity, heat, transport and storage.
Platform providers provide the link to exploitation of the digital process twin and a route to implementation via tariff setting. The project also includes focus on people training within the test sites, exploring how decision support can be integrated into exploitable business processes.
The decision support system will be connected with innovation in LEMs through the HIVE platform, allowing insights from data to be translated into data-driven temporal and spatial identification of dynamic prices signals (e.g., time-variant feed-in-tariffs and retail prices) to steer customer/prosumer behaviour. In this way, the impacts and integration of local trading can be explored in relation to operational planning. The technology-agnostic nature of the HIVE platform allows for interdependencies and synergies between sectors.
Logarithmo provides their resilient data flow platform for digital process twin to link data silos and IT security classifications, enabling a flexible access to the data for use cases.
The system is enabled by a digital process twin. The AISOP concept of the Digital Process Twin is an innovative approach to connect the individual data silos along the different processes within the operational planning for a DSO and exploit them. In other domains, there are already comparable approaches in the combination of data silos, but not relating to integrated approaches to data exploitation for the DSO in the context of operational planning. This acts as the digitised representation of (i) the tasks performed by grid operators, (ii) tasks engineered by grid operators but performed by software, and (iii) the secure acquisition and representation of network and consumer data, building upon and expanding the definition of “digital twin” to address the needs of the DSO. This framework includes the collection and processing of heterogenous data (filtering, clustering, edge analysis, federation etc).
AISOP brings together an international consortium of highly qualified partners comprising need owners, scientific partners, technology providers and demo sites.