
TimeSmart: Timeliness of Information in Smart Grids Networks
Duration: Oct 2022 — Mar 2025
(GA: 101063721)
TimeSmart project will investigate the applicability of the novel Age of Information metric in smart grid networks. While the metric has become a valuable tool for measuring the system’s performance, its practical value and impact in the real-time system are left unanswered. This project seeks to remedy that by applying the metric to a system in which the timing of collected data, currently measured through jitter or latency, profoundly impacts management and control. The AoI offers a new perspective on how the system should collect and process information, as such decisions are also based on the context of processed information(their semantic nature). In turn, the new approach can offer an innovative way of improving the efficiency of renewable electrical energy supply and electrical loads by taking advantage of the available edge infrastructure. This project aims to adopt the AoI metric in smart grid networks to improve the energy transmission efficiency, achievable through more timely collected information, to save energy.
The proposed research will be conducted by dr. Jernej Hribar and supervised by prof. Mihael Mohorčič, and dr. Carolina Fortuna from Institut Jožef Stefan. The applicant will also undertake a non-academic placement at ComSensus under the supervision of dr. Andrej Čampa.
Age of Information
The Age of Information (AoI) concept has recently been proposed in Information sciences, and researchers have already demonstrated its value as a tool to measure system’s performance. The AoI measures the time passed since a source of information, e.g., sensor, has generated information, e.g., took an observation, in the form of a status update. Each status update contains a timestamp revealing when the update was generated. These status updates are then collected at the sink, e.g., a monitor, where the timeliness of information is measured. For illustration, Figure 1 shows the basic system model as considered in the AoI literature and Figure 2 depicts the sample path of the AoI process at the sink.

It was also shown that the AoI has a profound impact on the design and control of communication networks. For example, even when the system can be described with a simple queuing model the network architecture has to be altered to minimize the AoI of collected information. The AoI should not be confused with latency or jitter, the traditional metrics used in communication networks. The former measures only the time necessary to transfer information from the source to the sink, while the latter refers to small intermittent delays during data transfers. Both are thus only measures of the quality of connection and not telling anything about the transferred information. AoI on the other hand is also connected to the context of processed information (their semantic nature) and has already revolutionized how the information is collected and processed in a real-time system.

Smart grids are a prime example of real-time systems that can benefit from the application of the AoI metric. By applying AoI to smart grids andleveraging the available edge infrastructure, it will be possible to improve the control of renewable electric power supply and electric loads. Any improvement in the efficiency of energy transmission that can be achieved through timely collected information can save a huge amount of energy in the European Union. The proposed project will help the European Union achieve its energy efficiency target of at least 32.5% by 2030. In addition, the AoI metric can play a crucial role in other smart grid scenarios, such as demand side management optimization, self-healing, etc.
Objectives of the Project
The main objective of the TimeSmart is to develop a novel way of monitoring and controlling smart grid networks. New insights, provided by the AoI metric, will be utilised to develop sustainable and energy-efficient control of smart grid resources. Develop criteria that quantifies the timelines of information Evaluate and simulate the effects of timeliness Design of a novel architecture to improve the timeliness of information Implement a fully operational AI-powered management system to demonstrate the gains of employing the AoI metric in smart grid networks
Publications:
- The Role of Age of Information in Enhancing Short-Term Energy ForecastingEnergy, 2025
- Towards the Standardization of Energy Efficiency Metrics of the AI Lifecycle in 6G and Beyond2024 IEEE Conference on Standards for Communications and Networking (CSCN): 25-27 Nov. 2024, 2024
- Self-Supervised Visual Exploration of Age of Information Process in IoT2024 IEEE 10th World Forum on Internet of Things (WF-IoT): November 10-13, 2024 in Ottawa, Ontario, Canada, 2024
- Metrika Starosti Informacije in Njena Vloga v Vzdržnih Omrežjih PrihodnostiElektrotehniški Vestnik Online, 2024
- Balancing Energy Preservation and Performance in Energy-Harvesting Sensor NetworksIEEE Sensors Journal, 2024
- Trajnostni Razvoj Interneta Stvari: Analiza Ogljičnega Odtisa LoRaWAN Omrežij Na Področju SlovenijeŠTeKam: Študentska Tehniška Konferenca, 2024
- Smart Homes, Smarter Savings: Energy Trading With Deep Reinforcement Learning2024 IEEE 22nd Mediterranean Electrotechnical Conference (MELECON): 25-27 June 2024, Porto, 2024
- Visibility Graph-Based Wireless Anomaly Detection for Digital Twin Edge NetworksIEEE Open Journal of the Communications Society, 2024
- Building Zero-Touch Service Management Framework for Automotive Services Using the Smart Highway Testbed2024 7th International Balkan Conference on Communications and Networking (BalkanCom): 3-6 June 2024, Ljubljana, 2024
- Digital Transformation With a Lightweight On-Premise PaaSFuture Generation Computer Systems, 2024
- FedSBS: Federated-Learning Participant-Selection Method for Intrusion Detection SystemsComputer Networks: The International Journal of Computer and Telecommunications Networking, 2024
- The Energy Cost of Artificial Intelligence of Things Lifecycle2024
- Smart Home Energy Cost Minimisation Using Energy Trading With Deep Reinforcement LearningBuildSys'23: Proceedings of the 10th ACM Conference on International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 2023
- Electrical Energy Cost Minimization in a Smart Home Using Deep Reinforcement LearningZbornik Dvaintridesete Mednarodne Elektrotehniške in Računalniške Konference ERK 2023: Portorož, Slovenija, 28. - 29. September 2023, 2023
- A Survey on Securing Federated Learning: Analysis of Applications, Attacks, Challenges, and TrendsIEEE Access, 2023
- Machine Learning Operations Model Store: Optimizing Model Selection for AI as a ServiceBalkanCom 2023, 2023 International Balkan Conference on Communications and Networking (BalkanCom) Took Place 5-8 June 2023 in İstanbul, Turkey, 2023
- Deep W-Networks: Solving Multi-Objective Optimisation Problems With Deep Reinforcement LearningICAART 2023: Proceedings of the 15th International Conference on Agents and Artificial Intelligence, 2023
- Federated Spatial Reuse Optimization in Next-Generation Decentralized IEEE 802.11 WLANSITU Journal: Future and Evolving Technologies, 2022
- Timely and Sustainable: Utilising Correlation in Status Updates of Battery-Powered and Energy-Harvesting Sensors Using Deep Reinforcement LearningComputer Communications, 2022
- Enabling Deep Reinforcement Learning on Energy Constrained Devices at the Edge of the NetworkIEEE Conference on Wireless Communications and Networking, 10-13, Austin, Texas, Usa, 2022
- Energy Aware Deep Reinforcement Learning Scheduling for Sensors Correlated in Time and SpaceIEEE Internet of Things Journal, 2022
- Federated Spatial Reuse Optimization in Next-Generation Decentralized IEEE 802.11 WLANs2022
- Analyse or Transmit: Utilising Correlation at the Edge With Deep Reinforcement Learning2021 IEEE Global Communications Conference (GLOBECOM), Madrid, Spain 7 - 11 December 2021: Proceedings, 2021
- SMART: Situationally-Aware Multi-Agent Reinforcement Learning-Based TransmissionsIEEE Transactions on Cognitive Communications and Networking, 2021
- Resource Reservation Within Sliced 5G Networks: A Cost-Reduction Strategy for Service Providers2020 IEEE International Conference on Communications Workshops (ICC): Proceedings, 2020
- Utilising Correlated Information to Improve the Sustainability of Internet of Things DevicesWF-IoT: 2019 IEEE 5th World Forum on Internet of Things, 2019
- Using Deep Q-Learning to Prolong the Lifetime of Correlated Internet of Things Devices2019 IEEE International Conference on Communications Workshops, (ICC Workshops): Proceedings, 2019
- Using Correlated Information to Extend Device LifetimeIEEE Internet of Things Journal, 2019
- Using Deep Q-Learning to Prolong the Lifetime of Correlated Internet of Things Devices2019
- Updating Strategies in the Internet of Things by Taking Advantage of Correlated SourcesIEEE Globecom: Global Hub: Connecting East and West, 2017