Energy ManagEment and RechArging for efficient eLectric car Driving

EMERALD focuses on energy use optimization and on the seamless integration of the FEV into the transport and energy infrastructure, by delivering clear advances over the state-of-the-art. The goal is to assist the FEV in becoming a successful commercial product. To this end, EMERALD will innovate a range of novel ICT solutions, each one seamlessly integrated with the others, providing a multifaceted and comprehensive approach on these issues. EMERALD will introduce Integrated in-vehicle energy management, comprising:

  • Dynamic energy-driven management of FEV auxiliaries, tightly integrated with consumption prediction functionality, enabling pre-emptive energy conservation measures.
  • Energy-efficient long-range route planning and optimization, enabling extension of FEV’s driving range and automatic scheduling of recharging stops en route.
  • Performance-centric machine learning for consumption prediction, introducing optimization and cooperative training of machine learning functions targeted for energy consumption and traffic prediction based on experience.
  • Driver profiling functionalities, through monitoring of acceleration/braking patterns, for the enhancement of route consumption prediction functionality.
  • Data synchronization using power-line communication (V2IoG, Vehicle to Infrastructure over the Grid), as a new cooperative information-sharing scheme.
  • User-centric charge and discharge management, enabling automatically-generated, optimal for the user, charge and discharge schedules, accessible both on-board and on his mobile phone.

EMERALD will also introduce: Enhanced FEV-related power demand prediction and power flow management support, taking advantage of consumption patterns as shared in a cooperative manner by the FEVs themselves, as well as from FEVs’ recharging bookings; Cooperative FEV fleet management, though holistic and dynamic, multi-parameter, fleet control optimization, taking into account energy and recharging limitations; and FEV-specific driver training for energy efficiency.