Control-theoretic dynamic voltage scaling for embedded controllers

Abstract

For microprocessors used in real-time embedded systems, minimizing power consumption is difficult due to the timing constraints. Dynamic voltage scaling (DVS) has been incorporated into modern microprocessors as a promising technique for exploring the trade-off between energy consumption and system performance. However, it remains a challenge to realize the potential of DVS in unpredictable environments where the system workload cannot be accurately known. Addressing system-level power-aware design for DVS-enabled embedded controllers, this paper establishes an analytical model for the DVS system that encompasses multiple real-time control tasks. From this model, a feedback control based approach to power management is developed to reduce dynamic power consumption while achieving good application performance. With this approach, the unpredictability and variability of task execution times can be attacked. Thanks to the use of feedback control theory, predictable performance of the DVS system is achieved, which is favorable to real-time applications. Extensive simulations are conducted to evaluate the performance of the proposed approach.

Adaptive control for power management

“…This saturation characteristic is given in (12), where u min and u max correspond to the actuator limitations. Thus, for the controller design, the effects of the Actuator block must be considered by means of antiwindup compensation [10], as shown in (13). For a deadbeat observer, A aw is equal to 1, and (13) is rewritten as (14).…”

“…Let s max = max s ∈ S be the maximum frequency from the set of frequencies of the processor. If a processor with frequency s max completes a task within a time d, then, according to the reasoning of Tian et al [13], if the same processor operates on a frequency s < s max , with s ∈ S, then the time to complete the task will be ds max /s. Therefore, when the frequency is reduced from s max to s, the execution time is increased by a factor s max /s.…”

Enhanced Energy-Aware Feedback Scheduling of Embedded Control Systems

“…Marinoni and Buttazzo [16] presented a method that integrates elastic scheduling with DVS management to fully exploit the available computational resources in processors with limited voltage levels. In our previous work [17], a control theoretic approach to DVS for embedded control systems was explored. We have also developed a simple yet efficient DVS scheme that combines time-triggered and event-triggered mechanisms [18].…”

Performance-Aware Power Management in Embedded Controllers with Multiple-Voltage Processors

“…Jin et al (2007) presented a feedback fuzzy-DVS scheduling architecture integrating feedback control and fuzzy DVS for real-time control tasks. Recently, we have also developed several DVS algorithms for real-time control systems (Xia and Sun, 2006;Xia et al, 2008).…”