energy/reliability trade-offs in fault-tolerant event-triggered distributed embedded systems

15
Energy/Reliability Trade- offs in Fault-Tolerant Event- Triggered Distributed Embedded Systems Junhe Gan, Flavius Gruian, Paul Pop, Jan Madsen

Upload: keane-mcfadden

Post on 03-Jan-2016

22 views

Category:

Documents


0 download

DESCRIPTION

Energy/Reliability Trade-offs in Fault-Tolerant Event-Triggered Distributed Embedded Systems. Junhe Gan, Flavius Gruian, Paul Pop, Jan Madsen. Motivation. The impact of power supply scaling on fault-tolerance (MTTF) and power dissipation - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

Energy/Reliability Trade-offs in Fault-Tolerant Event-Triggered Distributed Embedded Systems

Junhe Gan, Flavius Gruian, Paul Pop, Jan Madsen

Page 2: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

2

MotivationThe impact of power supply scaling

on fault-tolerance (MTTF) and power dissipation

Maheshwari, A. et al., Trading off transient fault tolerance and power consumption in deep submicron (DSM) VLSI circuits , VLSI Systems, pp. 299-311, 12(3), 2004.

Page 3: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

3

Outline

Architecture, Application and Energy Models Reliability model Energy/reliability trade-off model Schedulability analysis

Problem Formulation Example

Optimization Strategy TABU search-based algorithm

Experiment ResultsConclusion and Contributions

Page 4: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

4

Architecture Model

A set of heterogeneous Processing Elementsinterconnected by a communication channel.

Each PE has a set of operating mode Each operating mode, we know ( , , )j j jN N N

i i if v p

Page 5: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

5

Reliability Model

t1 t1 t1

Re-execution:Transient faults

t1

t1

t1

Replication:Transient faults /Permanent faults

N1

N2

N3

K = 2

1

1

1 (1 )

1 1

i

ci

reex ki

krepi i

i

A iP A

R e

R R

R R

R R

Page 6: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

6

Energy and Application ModelApplication Model:

A set of periodic tasks for each task, we know

Unique priority Critical/non-critical task

Energy Model:

j

i j

N i imap on N

Energy Power Time

E p t O

( , , )jN

i i iC T D

Sum of mode-switching

overheads

Page 7: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

7

Energy/reliability Trade-off ModelThe average failure rate of a system increases exponentially

when the supply voltage and the operating frequency decreases

0( , ) 10 VF V F

Page 8: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

8

Schedulability AnalysisFixed-Priority

Preemptive Scheduling

Response Time Analysis

Degree of Schedulability

( )j i

ii i j

hp j

rr c c

T

1 1

2 1

max(0, ) 0

( ) 0

m

i i iiA m

i i ii

d r D if dS

d r D if d

1 2 3priority priority priority

Page 9: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

9

Problem FormulationGiven:

Application Architecture Reliability Goal Tolerate k-faults for each task

We are interested to determine: the mapping for allocating each task the operating mode for executing each task

Such that: all tasks meet their timing requirements the application reliability meets the given reliability goal the energy consumption of system is minimized

Page 10: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

10

Motivational Example

Page 11: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

11

Optimization Strategy

NP-hard problem: ways of allocating tasks to PEs. ways of executing tasks at operating modes of an PE.

Search the optimal solution by heuristic algorithm.

Minimize the cost function:( ) max(0, ) max(0, )S R g s r sCost S E W R R W r

mnmk m

m nk

Energy Consumption Reliability

Goal

TimingRequirement

Page 12: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

12

Searching Loop:

Tabu Search-based Algorithm

Save Best Solution (if it is)

Select New Solution

First attempt: An improved solution Otherwise: Randomly select

a non-improved & not-tabu solution

Operating Mode (L-moves)Change a task’s operating mode

Mapping (M-moves)

Move a task from an PE to another PE Or Swap two tasks between PEs

Design Transformations

Use and Maintenance of

Tabu-list

Page 13: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

13

Experimental Results

Page 14: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

14

Experimental Results

Page 15: Energy/Reliability Trade-offs  in Fault-Tolerant Event-Triggered Distributed Embedded Systems

15

Conclusion and ContributionsConclusion:

Contributions: Energy/reliability model Combine deciding mapping and operating mode assignment Optimization algorithms for this energy/reliability trade-offs problem

It is possible to eliminate the negative impact of energy minimization on reliability

by carefully considering the energy/reliability trade-offs during optimization.