Sustainable Mobile Networks


Mobile network capacity is continuously demanded to increase to provide a higher and higher volume of data traffic. Such growth has a hidden cost: the increase of the network energy consumption (with its related expenses) and therefore, the generation of greenhouse gases at a high level.
Digital Power Group and GSMA have estimated that all the ICT industry is already responsible of about 4% of the carbon footprint generated by the human activity, the same as the airplane emissions. The trend is a further increase due to the estimated 70% annual growth rate of mobile data traffic. Therefore it is impossible nowadays to design next generation mobile networks without addressing energy saving.

Sustainable design principles must be applied to mobile networks:

  • Lower energy consumption through the entire life-cycle (from manufacture to daily use).
  • Minimize environmental footprint by reducing greenhouse gas (GHG) emissions.
  • Limit resource consumption through waste-free/no-toxic manufacturing, a preference for renewable resources, and an emphasis on recycled materials.


Proposed scenario: HetNets powered by renewable energy

Our proposal: HetNets powered by renewable energy


In this research line the application of sustainable design principles to mobile networks is studied.
Three technological objectives have been targeting to achieve this goal:

  1. Network energy efficiency: the design of network architecture and management schemes that reduce the consumption of the energy resource without damaging system performance. The key issue is to achieve proportionality between energy consumption and traffic load, while maintaining an adequate quality of service for the users.
  2. Mobile demand-response: the design of network architecture and control schemes that balance energy inflow and spending in presence of equipment powered by harvested ambient energy. The main issue  is to satisfy the traffic demands and to meet the quality of service requirements using the available energy budget coming from intermittent and erratic sources (e.g., renewable energy).
  3. Mobile energy-sharing: the design of control schemes and architecture enabling the exchange of energy (e.g., from the renewables) among the network nodes to increase the level of self-sustainability of the mobile system.


We state energy saving in mobile networks as a decision making process. It is formulated as a single or multiple agent problem. Dynamic Programming, Reinforcement Learning, Grey Relational Analysis, Genetic Algorithms, Fuzzy Logic are tools used for solving our problems. System modeling is for us a key part of our proposals. For this, we take particular attention on it by using data analytics from real or synthetic traces. Statistical inference and machine learning are tools utilized for this analysis.


Thesis and Internships

  • P. Lastella, Implementation of prediction algorithms using Python, internship for Master Thesis at Politecnico di Bari, July-September 2019.
  • A. El Amine, Reinforcement Learning for Multi-Sleeping Control of Delay-Constrained and Energy-Optimal Small Base Stations, PhD Internship IMT-Atlantique – CTTC, May 2019.
  • A. Fernandez Gambín, Mobile traffic load classification through deep learning, director: P. Dini, advisor: M. Rossi, EU-MSCA Secondment, University of Padova-CTTC, April 2018-February 2019.
  • E. Cuoccio, Reinforcement learning for energy harvesting 5G mobile networks, director: P. Dini, advisors: A. Pascual and G. Boggia, joint Master Thesis by Universitat Politecnica de Catalunya and Politecnico di Bari, July 2016.
  • A. Dudnikova, Multi-criteria decision analysis for sleep mode in 5G networks, advisors: L. Giupponi, P. Dini, PhD internship, Università degli studi di Catania, February-September 2015.

If you are interested in working with us (as a trainee, PhD student or post-doc) please send an email with your CV and a tentative research proposal.


The activities of this research line are inserted within the following projects:


Relation with past research lines

This research line is the clear evolution of the activities carried out in the past “Green Wireless Networks” research line.
Moreover, the group working in this line has also contributed to the past research lines on “Smart IP Flow and Mobility Management Techniques” and “Cognitive Network Optimization Techniques”.