Construction industry is known as the economic heart and the main indicator for social development. The demand for construction is increasing in urban areas and because of urbanization, there is more need to setup new construction sites. This industry generates 9% of Europe’s GDP and provides 18 million direct jobs. At the same time, construction industry is one of the major sources of environmental damage due to the pollution generated by emissions. The construction industry has historically been very slow in adapting to new technologies, however, recently there were considerable advancement in electrifying the construction sites by producing autonomous electrical construction machines, that are more energy efficient. On the other hand, introducing such machines without the support of a suitable infrastructure would be inefficient and costly, since their regular operation could be compromised, and their full potential cannot be exploited.
This project aims at reducing the energy consumption in an electric construction site by designing relevant components that incorporate with energy, optimize energy distribution, storage and management, and optimize fleet. We propose an intelligent system architecture that provides decisions based on data processing techniques, while data is generated and transmitted through a reliable communication infrastructure. This project will consider analytical, simulation, and real-world experiments in order to verify the results obtained from the modeling and development. The communication infrastructure will aim at designing connected and reliable wireless networks, while novel Artificial Intelligence (AI) and optimization techniques will be applied to process data in real-time. Optimization and machine learning techniques will be applied to reduce the energy consumption and increase system productivity, while considering customer demands.
A toolchain will be developed in order to model all the components in a construction site for evaluating energy consumption. It provides new machine models, site operations using machine models, energy supply and communication components. It also defines the grid architecture for energy distribution, models the components of an energy management system, and optimizes the energy infrastructure distribution. Furthermore, it surveys the current wireless technologies for employing in such harsh and dynamic environment.
The project consortium consists of three partners, which are Mälardalen University (MDH), Volvo Construction Equipment (VCE) and the Swedish National Road and Transport Research Institute (VTI). MDH acts as the GREENER project coordinator. This project offers a complete value chain as VCE provides competence in construction site industry, electric machines and infrastructure for real tests, VTI provides competence in modeling a simulation tool for evaluation, and MDH provides optimization and communication expertise in order to design novel algorithms. The project is planned to start in September 2020, where it will run for 4 years. the estimated budget is about 17.6 million SEK, where 49.9% of the total budget is requested from public funds.
|Industrial Doctoral Student
|Associated Senior Lecturer
Selective Trimmed Average: A Resilient Federated Learning Algorithm With Deterministic Guarantees on the Optimality Approximation (Jan 2024) Mojtaba Kaheni, Martina Lippi , Andrea Gasparri , Mauro Franceschelli IEEE Transactions on Cybernetics (IEEE TCyb)
Demo Abstract: Towards Interoperability in a Hybrid TSN/6TiSCH Network (Dec 2023) Iliar Rabet, Ines Alvarez, Hossein Fotouhi, Mohammad Ashjaei ACM Embedded Networked Sensor Systems (SenSys 2023)
On the Deployment of Private Broadband Networks in Surface Mines (Sep 2023) Iliar Rabet, Hossein Fotouhi, Mário Alves , Maryam Vahabi, Mats Björkman 28th International Conference on Emerging Technologies and Factory Automation (ETFA 2023)
Resilient and Privacy-Preserving Multi-Agent Optimization and Control of a Network of Battery Energy Storage Systems Under Attack (Sep 2023) Mojtaba Kaheni, Elio Usai , Mauro Franceschelli IEEE Transactions on Automation Science and Engineering (TASE)
SDMob: SDN-Based Mobility Management for IoT Networks (Jan 2022) Iliar Rabet, Shunmuga Priyan Selvaraju, Hossein Fotouhi, Maryam Vahabi, Mats Björkman, Mário Alves Journal of Sensor and Actuator Networks (MDPI JSAN)
Pushing IoT Mobility Management to the Edge: Granting RPL Accurate Localization and Routing (Jun 2021) Iliar Rabet, Shunmuga Priyan Selvaraju, Hossein Fotouhi, Mohammad Hassan Adeli, Maryam Vahabi, Ali Balador, Mats Björkman, Mário Alves World Forum on the Internet of Things (WF-IoT)
|The Swedish National Road and Transport Research Institute
|Volvo Construction Equipment AB