| Abstract: |
Energy management is a critical concern in the design of embedded systems to prolong the lifetime or to maximize the performance under energy constraints. In particular, the emerging embedded
systems with renewable energy sources rise new problems and trigger the revision of conventional energy management. If, e.g., the size of a solar cell limits the available power/energy of an
electronic device, decisions like when to provide which service have to be made in order to satisfy the needs of the user as well as possible. In this paper, we explore how to maximize the system
reward of diverse applications for an energy harvesting system. By utilizing the notion of rewards to express the different priorities of services, we answer the fundamental question of how to
optimize the use of energy provided by a scarce and time-varying environmental source. For this purpose, we provide algorithms to optimally adjust service parameters dynamically. Our work is
supported by simulation results which are based on long-term measurements of the power generated by real solar cells. Furthermore, we demonstrate how to dimension the embedded system, e.g., the
battery capacity and elaborate on implementation details which are of practical importance. |
