Periodic Reporting for period 1 - EXPEDITE (Enabling Positive Energy Districts through a Planning and Management Digital Twin)
Periodo di rendicontazione: 2024-01-01 al 2025-06-30
ExPEDite aims to create and deploy a novel Digital Twin (DT) for real-time monitoring, visualization, and management of district-level energy flows. The project will deliver a suite of replicable modeling tools, allowing stakeholders to analyze planning actions towards positive energy and climate neutrality in a cost-effective manner. The tools will be able to model the district’s energy production and demand, building stock performance, optimize for flexibility and simulate mobility and transport. The DT’s design-platform will analyze various what-if planning actions, aiding energy and urban planners’ evidence-based decision-making processes, while its run-time engine will optimize the districts energy utilization efficiency. The DT will follow a modular open architecture to support multi-sectoral and multi-organizational stakeholder requirements. By employing gamification and co-creation approaches, the project will enhance public awareness and engagement in energy efficiency. The ExPEDite DT will be applied to a district in Riga, Latvia, and will provide practical guidelines, reusable models, algorithms, and training materials to aid other cities in replicating the DT for their districts, fostering widespread adoption of sustainable energy practices.
WP2 – System Requirements and Architecture
WP2 defined the ExPEDite platform’s system requirements and technical architecture, ensuring alignment with Riga’s strategic goals while enabling scalability and replicability. Activities included co-design of requirements and KPIs (T2.1) adoption of Minimum Interoperability Mechanisms (T2.2) and development of a layered system architecture with clear integration and security mechanisms (T2.3). Riga’s planning pathways to inform climate-neutral strategies were reviewed (T2.4) and reusable guidelines for sensor network consolidation were reviewed (T2.5). WP2 delivered a robust blueprint of the system requirements and architecture guiding subsequent implementation.
WP3 – Data and Knowledge Management Framework
WP3 created the data backbone for simulation (WP4) and Digital Twin (WP5). Core Data Services (T3.1) were implemented with IoT telemetry via ThingsBoard, Kafka-based messaging, multiple storage solutions and Keycloak-based access management. The Pattern Repository (T3.2) provides reusable digital models; the Data Spaces Integration Suite (T3.3) defined its architecture and NGSI-LD-based energy data model. BMS Integration (T3.4) enabled collection of building and energy data, while the District Data Fusion Engine (T3.5) delivered aggregation and anomaly detection via rule-based logic and ML prototypes. Together, these form a secure, interoperable data framework.
WP4 – Modelling and Simulation Suite
WP4 delivered interoperable tools for Positive Energy District planning and operation. T4.1 produced a TRL6 energy forecasting and flexibility tool using AI-based demand and RES prediction with optimisation for demand response. T4.2 created a GIS-integrated building stock modelling methodology, validated in Riga. T4.3 developed a SUMO-based mobility testbed. T4.4 prepared geospatial and system simulation methodology for PV, batteries, heat pumps and hydrogen. T4.5 completed a system-dynamics district heating and storage model, deployed online for interactive scenario testing. T4.6 produced cost–benefit guidelines, business model concepts and risk analysis. WP4 advanced core modelling tools and provided a comprehensive simulation suite.
WP5 – District Digital Twin
WP5 developed a 3D Digital Twin environment in Unreal Engine with a Design View for planning and Runtime View for live data. A citizen engagement mobile app prototype was released, using gamification and community inputs. The District Optimisation and Decision Support tool was built with short-term (RDME) and long-term (MCDA) planning capabilities. Preparations for AI-driven analytics and visualisation components were completed, setting the basis for advanced real-time data processing in future phases.
WP6 – PED Twin Deployment and Evaluation
WP6 prepared for deployment and evaluation of the PED Twin. Task 6.1 initiated scenario planning and training. Under T6.2 an integration server and Kafka broker were configured, and an integration matrix prepared. T6.3 progressed with Living Lab preparations, including an on-site meeting in Ostrava. Demonstration (T6.4) and evaluation (T6.5) will follow in later stages.
WP2 defined the ExPEDite platform’s system requirements and technical architecture, ensuring alignment with Riga’s strategic goals while enabling scalability and replicability. Activities included co-design of requirements and KPIs (T2.1) adoption of Minimum Interoperability Mechanisms (T2.2) and development of a layered system architecture with clear integration and security mechanisms (T2.3). Riga’s planning pathways to inform climate-neutral strategies were reviewed (T2.4) and reusable guidelines for sensor network consolidation were reviewed (T2.5). WP2 delivered a robust blueprint of the system requirements and architecture guiding subsequent implementation.
WP3 – Data and Knowledge Management Framework
WP3 created the data backbone for simulation (WP4) and Digital Twin (WP5). Core Data Services (T3.1) were implemented with IoT telemetry via ThingsBoard, Kafka-based messaging, multiple storage solutions and Keycloak-based access management. The Pattern Repository (T3.2) provides reusable digital models; the Data Spaces Integration Suite (T3.3) defined its architecture and NGSI-LD-based energy data model. BMS Integration (T3.4) enabled collection of building and energy data, while the District Data Fusion Engine (T3.5) delivered aggregation and anomaly detection via rule-based logic and ML prototypes. Together, these form a secure, interoperable data framework.
WP4 – Modelling and Simulation Suite
WP4 delivered interoperable tools for Positive Energy District planning and operation. T4.1 produced a TRL6 energy forecasting and flexibility tool using AI-based demand and RES prediction with optimisation for demand response. T4.2 created a GIS-integrated building stock modelling methodology, validated in Riga. T4.3 developed a SUMO-based mobility testbed. T4.4 prepared geospatial and system simulation methodology for PV, batteries, heat pumps and hydrogen. T4.5 completed a system-dynamics district heating and storage model, deployed online for interactive scenario testing. T4.6 produced cost–benefit guidelines, business model concepts and risk analysis. WP4 advanced core modelling tools and provided a comprehensive simulation suite.
WP5 – District Digital Twin
WP5 developed a 3D Digital Twin environment in Unreal Engine with a Design View for planning and Runtime View for live data. A citizen engagement mobile app prototype was released, using gamification and community inputs. The District Optimisation and Decision Support tool was built with short-term (RDME) and long-term (MCDA) planning capabilities. Preparations for AI-driven analytics and visualisation components were completed, setting the basis for advanced real-time data processing in future phases.
WP6 – PED Twin Deployment and Evaluation
WP6 prepared for deployment and evaluation of the PED Twin. Task 6.1 initiated scenario planning and training. Under T6.2 an integration server and Kafka broker were configured, and an integration matrix prepared. T6.3 progressed with Living Lab preparations, including an on-site meeting in Ostrava. Demonstration (T6.4) and evaluation (T6.5) will follow in later stages.
ExPEDite advances beyond the state of the art by leveraging Artificial Intelligence/Machine Learning (AI/ML) tools to enhance Digital Twin visualization, offering predictive analytics and automated decision-making capabilities. The project will develop novel methodologies for integrated urban energy modeling, including advanced building stock analysis, renewable energy source optimization, load forecasting with explainable AI, and intelligent strategies for mobility and transport. Furthermore, ExPEDite aims to create comprehensive frameworks for smart heating network design and optimization, ensuring the scalability and transferability of solutions to other urban districts, thereby promoting sustainable energy practices.