Limits...
Energy-efficient scheduling for hybrid tasks in control devices for the Internet of Things.

Gao Z, Wu Y, Dai G, Xia H - Sensors (Basel) (2012)

Bottom Line: Dynamic voltage scaling (DVS) has been proved to be an effective method for reducing the energy consumption of processors.HoW describes the structure of HRCTs and SRTs, and their properties, e.g., deadlines, execution time, preemption properties, and energy-saving goals, etc.HTDVS first sets the slowdown factors of subtasks while meeting the different real-time requirements of HRCTs and SRTs, and then dynamically reclaims, reserves, and reuses the slack time of the subtasks to meet their ideal energy-saving goals.

View Article: PubMed Central - PubMed

Affiliation: College of Computer Science, Hangzhou Dianzi University, Hangzhou 310018, China. gaozhigang@zju.edu.cn

ABSTRACT
In control devices for the Internet of Things (IoT), energy is one of the critical restriction factors. Dynamic voltage scaling (DVS) has been proved to be an effective method for reducing the energy consumption of processors. This paper proposes an energy-efficient scheduling algorithm for IoT control devices with hard real-time control tasks (HRCTs) and soft real-time tasks (SRTs). The main contribution of this paper includes two parts. First, it builds the Hybrid tasks with multi-subtasks of different function Weight (HoW) task model for IoT control devices. HoW describes the structure of HRCTs and SRTs, and their properties, e.g., deadlines, execution time, preemption properties, and energy-saving goals, etc. Second, it presents the Hybrid Tasks' Dynamic Voltage Scaling (HTDVS) algorithm. HTDVS first sets the slowdown factors of subtasks while meeting the different real-time requirements of HRCTs and SRTs, and then dynamically reclaims, reserves, and reuses the slack time of the subtasks to meet their ideal energy-saving goals. Experimental results show HTDVS can reduce energy consumption about 10%-80% while meeting the real-time requirements of HRCTs, HRCTs help to reduce the deadline miss ratio (DMR) of systems, and HTDVS has comparable performance with the greedy algorithm and is more favorable to keep the subtasks' ideal speeds.

No MeSH data available.


Related in: MedlinePlus

Normalized unweighted energy consumption when using different energy-saving algorithms.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3472887&req=5

f6-sensors-12-11334: Normalized unweighted energy consumption when using different energy-saving algorithms.

Mentions: The greedy algorithm is a widely used dynamic energy reclamation and reuse algorithm [8,20,36], and has proved its good energy-saving effects. In this experiment, we compared the energy-saving effect of the HTDVS algorithm to that of the greedy algorithm. We use a randomly generated task set with 50% HRCTs and 50% SRTs. Because the subtasks in HoW have different function weight, we compare their energy-saving effect in two cases, i.e., without weight and with weight respectively. When not considering weight, we believe the energy-saving benefit is the same among all subtasks, and compared energy consumption ratio between the HTDVS algorithm and the greedy algorithm. When considering weight, we compared the weighted energy consumption between the HTDVS algorithm and the greedy algorithm. The weighted energy consumption of a task is the sum of the multiplication of energy-saving energy of each subtask and the function weight of each subtask. In Figure 6, T1 denotes the energy consumption when the HTDVS algorithm is used, and T2 denotes the energy consumption when the greedy algorithm is used. The experiment results are shown in Figures 6 and 7, respectively.


Energy-efficient scheduling for hybrid tasks in control devices for the Internet of Things.

Gao Z, Wu Y, Dai G, Xia H - Sensors (Basel) (2012)

Normalized unweighted energy consumption when using different energy-saving algorithms.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3472887&req=5

f6-sensors-12-11334: Normalized unweighted energy consumption when using different energy-saving algorithms.
Mentions: The greedy algorithm is a widely used dynamic energy reclamation and reuse algorithm [8,20,36], and has proved its good energy-saving effects. In this experiment, we compared the energy-saving effect of the HTDVS algorithm to that of the greedy algorithm. We use a randomly generated task set with 50% HRCTs and 50% SRTs. Because the subtasks in HoW have different function weight, we compare their energy-saving effect in two cases, i.e., without weight and with weight respectively. When not considering weight, we believe the energy-saving benefit is the same among all subtasks, and compared energy consumption ratio between the HTDVS algorithm and the greedy algorithm. When considering weight, we compared the weighted energy consumption between the HTDVS algorithm and the greedy algorithm. The weighted energy consumption of a task is the sum of the multiplication of energy-saving energy of each subtask and the function weight of each subtask. In Figure 6, T1 denotes the energy consumption when the HTDVS algorithm is used, and T2 denotes the energy consumption when the greedy algorithm is used. The experiment results are shown in Figures 6 and 7, respectively.

Bottom Line: Dynamic voltage scaling (DVS) has been proved to be an effective method for reducing the energy consumption of processors.HoW describes the structure of HRCTs and SRTs, and their properties, e.g., deadlines, execution time, preemption properties, and energy-saving goals, etc.HTDVS first sets the slowdown factors of subtasks while meeting the different real-time requirements of HRCTs and SRTs, and then dynamically reclaims, reserves, and reuses the slack time of the subtasks to meet their ideal energy-saving goals.

View Article: PubMed Central - PubMed

Affiliation: College of Computer Science, Hangzhou Dianzi University, Hangzhou 310018, China. gaozhigang@zju.edu.cn

ABSTRACT
In control devices for the Internet of Things (IoT), energy is one of the critical restriction factors. Dynamic voltage scaling (DVS) has been proved to be an effective method for reducing the energy consumption of processors. This paper proposes an energy-efficient scheduling algorithm for IoT control devices with hard real-time control tasks (HRCTs) and soft real-time tasks (SRTs). The main contribution of this paper includes two parts. First, it builds the Hybrid tasks with multi-subtasks of different function Weight (HoW) task model for IoT control devices. HoW describes the structure of HRCTs and SRTs, and their properties, e.g., deadlines, execution time, preemption properties, and energy-saving goals, etc. Second, it presents the Hybrid Tasks' Dynamic Voltage Scaling (HTDVS) algorithm. HTDVS first sets the slowdown factors of subtasks while meeting the different real-time requirements of HRCTs and SRTs, and then dynamically reclaims, reserves, and reuses the slack time of the subtasks to meet their ideal energy-saving goals. Experimental results show HTDVS can reduce energy consumption about 10%-80% while meeting the real-time requirements of HRCTs, HRCTs help to reduce the deadline miss ratio (DMR) of systems, and HTDVS has comparable performance with the greedy algorithm and is more favorable to keep the subtasks' ideal speeds.

No MeSH data available.


Related in: MedlinePlus