Task Scheduling to Constrain Peak Current Consumption in Wearable Healthcare Sensors

Small embedded systems, in our case wearable healthcare devices, have significant engineering challenges to reduce their power consumption for longer battery life, while at the same time supporting ever-increasing processing requirements for more intelligent applications. Research has primarily focu...

Full description

Saved in:
Bibliographic Details
Published inElectronics (Basel) Vol. 8; no. 7; p. 789
Main Authors Sherratt, Robert Simon, Janko, Balazs, Hui, Terence, Harwin, William S., Dey, Nilanjan, Díaz-Sánchez, Daniel, Wang, Jin, Shi, Fuqian
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.07.2019
Subjects
Algorithms
Batteries
Chronic obstructive pulmonary disease
Design
Electromagnetic interference
Electronic devices
Embedded systems
Energy consumption
Health care
Internet of Things
Operating systems
Power consumption
Power management
Schedules
Scheduling
Sensors
Software
Task scheduling
Voltage regulators
Wearable computers
Wearable technology
Online AccessGet full text

Cover

More Information
Summary:Small embedded systems, in our case wearable healthcare devices, have significant engineering challenges to reduce their power consumption for longer battery life, while at the same time supporting ever-increasing processing requirements for more intelligent applications. Research has primarily focused on achieving lower power operation through hardware designs and intelligent methods of scheduling software tasks, all with the objective of minimizing the overall consumed electrical power. However, such an approach inevitably creates points in time where software tasks and peripherals coincide to draw large peaks of electrical current, creating short-term electrical stress for the battery and power regulators, and adding to electromagnetic interference emissions. This position paper proposes that the power profile of an embedded device using a real-time operating system (RTOS) will significantly benefit if the task scheduler is modified to be informed of the electrical current profile required for each task. This enables the task scheduler to schedule tasks that require large amounts of current to be spread over time, thus constraining the peak current that the system will draw. We propose a solution to inform the task scheduler of a tasks’ power profile, and we discuss our application scenario, which clearly benefited from the proposal.
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics8070789