Real-Time and Embedded

Systems Research

Albert M. K. Cheng
Real-Time Systems Laboratory
Department of Computer Science
University of Houston, TX 77204, USA
An Embedded System or Real-
time System
 Real-time system
 Produces correct results in a timely manner.
 Embedded system
 computer hardware and software embedded as part of
complete device to perform one or a few dedicated
functions; often with real-time requirements.
 Examples:
 MMDs, PDAs, Cell phones, GPS, etc.
Motivations and Applications: Automotive
Control, Avionics, Medical Systems, and Many
Embedded Systems
More Applications: Oil Exploration and
Production
Control Systems: Old and
New
 Old: Entire control  New: Advances in
process is done by electronics and
mechanical hardware, computer systems
governed by the lead to energetically
isolate components of
mathematics of a controlled
feedback control. mechanical system.
 Examples: Mastered  Masterless cam
cam grinder, Watt grinder, Digital oil
governor, Pneumatic production control of
process controller. pump systems, Fly-
by-wire airplane,
Drive-by-wire
automobile.
Components of a Modern
Control and Monitoring System
M
Monitor/Instruments:
User(s)/Operator(s) Signal processing,
Energy conversion
UI
D T
User Interface Decision and Target System
Control System: Under Control:
Computer Chemical/Fluid,
Hardware, Electrical,
N Software,
Electronics
Mechanical,
Thermal
Networking and
Communication

A
Actuation:
Energy conversion,
Other Components
Power modulation
Cyber-Physical System
(CPS)
 Tight conjoining of and coordination between
computational and physical resources.
 Significantly enhance the adaptability, autonomy,
efficiency, functionality, reliability, safety, and usability
of current control systems.
 Example: An aerospace CPS will respond more quickly
(e.g., automatic aircraft collision avoidance), are more
precise (e.g., multiple landings in small airports), work
in inaccessible environments (e.g., autonomous space
exploration), provide large-scale, distributed
coordination (e.g., automated air traffic control), are
highly efficient (e.g., long-duration space travel), and
augment human capabilities (e.g., tele-robotics).
Correctness of Real-Time Control and
Monitoring Systems

 Satisfaction of logical correctness

constraints
 Satisfaction of timing constraints
Design and Implementation
Issues
 Control and monitoring systems: old and
new
 Model of an embedded/real-time system
 Scheduling real-time tasks
 Rate-monotonic scheduler, EDF, LLF
 Scheduling constraints
 Multiprocessor scheduling
 Identical, uniform, heterogeneous
multiprocessors
 Specification, verification, and debugging
Low Power Design for Real-
Time Systems
 Low power (energy) consumption is a key design for
embedded systems
 Battery’s life during operation.
 Reliability.
 Size of the system.
 Power-aware real-time scheduling
 Minimize the energy consumption
• Problem I: Power-aware scheduling for multiple
feasible interval jobs.
 Achieving some goal while satisfying the real-time
and/or energy constraints.
• Problem II: Real-time Task Assignment on
Rechargeable Multiprocessor System.
Dynamic Voltage Scaling (DVS)
Technique for Real-Time Task
 CPU’s energy/power consumption is a convex function of
the CPU’s speed, e.g. P = CV2f -> P = s3.
 Slowing down CPU’s speed reduces the energy usage for
CPU.
 Saving energy consumption V.S. Meeting deadline.
 Reducing the CPU’s speed as much as possible while
meeting every task’s deadline.
 A minimum constant speed is always an optimal
solution (if possible).
 If more than one speed are needed, a “smooth”
selection is better.
 For regular single instance real-time jobs with only one
feasible interval, Yao designed an algorithm for computing
the optimal solution.
A Motivational Example (EDF)
Job Feasible Intervals Comp. Time
J1 (1, 9] 2

J2 (2, 7], (8, 13] 2

J3 (1, 4], (5, 8], (9, 13] 2

0.66
(a) 0.5
0.4

1 4 9 13
J3 J1 J2

(b) 0.5

1 2 6 9 13
J1 J2 J1 J3
An Example….
Job Feasible Intervals Comp. Time
J1 (1, 9] 2

J2 (2, 7], (8, 13] 2

J3 (1, 4], (5, 8], (9, 13] 2

0.5

(a)

1 2 6 9 13
J1 J2 J1 J3

0.5 0.3 0.5

(b)

1 2 4 5 9 13
J1 J2 J1 J3

0.5 0.3 0.66

(c)

1 2 4 5 8
J1 J2 J1 J3
An illustrative example for dynamic
fetching
Job Feasible Intervals Comp. Time
J1 (1, 9] 2

J2 (2, 7], (8, 13] 2

J3 (1, 4], (5, 8], (9, 13] 2

J4 (4.5, 8.5], (9, 14] 3

1.0
0.5
(a)

1 2 6 9 11 14

J1 J2 J1 J3 J4

1.0

0.5
0.3
(b)

1 2 5 9 11 14
J1 J2 J1 J3 J4

0.66
0.6
(c) 0.5 0.3

1 2 5 8 9 14
J1 J2 J1 J3 J4
Considering power consumption
for leakage current
 As VLSI technology marches towards deep
submicron and nanoscale circuits operating at
multi-GHz frequencies, the rapidly elevated
leakage power dissipation will soon become
comparable to, if not exceeding, the dynamic
power consumption:
 Pleak = I leak V
 P = Pdyn + Pleak
 A critical speed s* = s where P(s) = P’(s)s
 Shut down the CPU when it is idle.
• Shut-down overhead.
Real-time Task Assignment in
Rechargeable Multiprocessor Systems
 Scheduling of frame-based real-time
tasks in partitioning schemes for
multiprocessor systems powered by
rechargeable batteries.
 In frame-based real-time systems, a
set of tasks must execute in a frame,
and the whole frame is repeated.
This system model is widely used in
real-time communication, real-time
imaging and a lot of other real-
time/embedded systems, including
medical systems.
 The problem for uniprocessor
system has been studied in
[Allavena and Mosse 2001], in which
an algorithm of complexity O(N) was
proposed for determining the Figure: Algorithm for rechargeable
feasibility of a task set. single processor [Allavena and Mosse 2001]
 However, doing so in a rechargeable
multiprocessor system is NP-Hard
[Lin and Cheng 2008].
 We propose heuristic and
approximation algorithms.
Simulation results have shown that
our algorithms exhibit very good
behavior.
Real-time Task Assignment in
Heterogeneous Distributed Systems
with Rechargeable Batteries
 Our techniques to solve the problem are based on
four heuristics, namely Minimum Schedule Length
(MSL), Min-min Schedule Length (MmSL), Genetic
Algorithm (GA), and Ant Colony Optimization
(ACO).
 While the modifications of the MSL, MmSL and GA
approaches from their original implementation are
somewhat straight-forward, we design a novel
structure using ACO.
 Performance comparisons of these four
techniques are performed and the results are
discussed in [Lin and Cheng 2009].
RealEnergy: a New Framework and Tool to
Evaluate Power-Aware Real-Time Scheduling
Algorithms

Linux
Applications
Benchmarks

RTAI
Low Power
Scheduling
Alg.
Intel XScale/PXA255 Module

Change CPU Sleep

Frequency & Wake-up

Target System
Measure Energy
Data Analysis
Example of the Measured Current
using RealEnergy
Actual Energy Consumption Using DVS as
meaured by RealEnergy
Concluding Remarks

 Achieve higher QoS in real-

time/embedded systems
 Formal verification
 New framework for CPS
 Reduce power consumption
 Ensure stable power supply
 Evaluate systems with actual
implementations and measurements
 Deliver actual benefit to society
 References
 J. Lin and A. M. K. Cheng, “Maximizing Guaranteed QoS in (m,k)-firm Real-time Systems,” Proc. 12th
IEEE International Conference on Embedded and Real-Time Computing Systems and Applications
(RTCSA), Sydney, Australia, Aug. 2006.
 J. Lin, Y. H. Chen, and A. M. K. Cheng, "On-Line Burst Header Scheduling in Optical Burst Switching
Networks,'' Proc. 22nd IEEE International Conference on Advanced Information Networking and
Applications (AINA), Okinawa, Japan, 2008.
 J. Lin and A. M. K. Cheng, “Real-time Task Assignment in Recharegable Multiprocessor Systems,” Proc.
14th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications
(RTCSA), Kaohsiung, Taiwan, Aug. 2006.
 J. Lin and A. M. K. Cheng, ``Real-time Task Assignment in Heterogeneous Distributed Systems with
Rechargeable Batteries,'' IEEE International Conference on Advanced Information Networking and
Applications (AINA), Bradford, UK, May 26-29, 2009.
 J. Lin and A. M. K. Cheng, “Real-time Task Assignment with Replication on Multiprocessor Platforms,"
Proc. 15th IEEE International Conference on Parallel and Distributed Systems (ICPADS), Shenzhen,
China, Dec. 8-11, 2009.
 A. M. K. Cheng. Real-time systems: scheduling, analysis and verification. Wiley-Interscience, 2002. 2nd
printing with updates, 2005.
 A. M. K. Cheng, ``Applying (m, k)-firm Scheduling to Medical and Medication Systems,'' Workshop on
Software and Systems for Medical Devices and Services (SMDS), in conjunction with IEEE-CS Real-
Time Systems Symposium,Tucson, Arizona, Dec. 2007.
 A. M. K. Cheng, ``Cyber-Physical Medical and Medication Systems,'' First International Workshop on
Cyber-Physical Systems (WCPS2008), sponsored by the United States National Science Foundation,
Beijing, China, June 20, 2008 (in conjunction with IEEE ICDCS 2008).
 J. Ras and A. M. K. Cheng, ``Response Time Analysis for the Abort-and-Restart Event Handlers of the
Priority-Based Functional Reactive Programming (P-FRP) Paradigm,'' Proc. 15th IEEE-CS International
Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), Beijing,
China, Aug. 2009. Nominated for Best Paper Award.
 J. Lin and A. M. K. Cheng, ``Power-aware scheduling for Multiple Feasible Interval Jobs,'' Proc. 15th
IEEE-CS International Conference on Embedded and Real-Time Computing Systems and Applications
(RTCSA), Beijing, China, Aug. 2009. Nominated for Best Paper Award.
 J. Lin, W. Song, A. M. K. Cheng ``RealEnergy: a New Framework and a Case Study to Evaluate Power-
Aware Real-Time Scheduling Algorithms ,'' to appear in ACM International Symposium on Low Power
Electronics and Design (ISLPED), Austin, Texas, USA, August 18-20, 2010.