S YSTEM -W IDE E NERGY M ANAGEMENT FOR R EAL -T IME T ASKS : L OWER B OUND AND A PPROXIMATION Xiliang Zhong and Cheng-Zhong Xu ICCAD 2006, ACM Trans. on.

Slides:



Advertisements
Similar presentations
Multiprocessor Scheduling
Advertisements

Greening Backbone Networks Shutting Off Cables in Bundled Links Will Fisher, Martin Suchara, and Jennifer Rexford Princeton University.
Answering Approximate Queries over Autonomous Web Databases Xiangfu Meng, Z. M. Ma, and Li Yan College of Information Science and Engineering, Northeastern.
Fakultät für informatik informatik 12 technische universität dortmund Classical scheduling algorithms for periodic systems Peter Marwedel TU Dortmund,
On the Complexity of Scheduling
QoS-based Management of Multiple Shared Resources in Dynamic Real-Time Systems Klaus Ecker, Frank Drews School of EECS, Ohio University, Athens, OH {ecker,
Real-Time Competitive Environments: Truthful Mechanisms for Allocating a Single Processor to Sporadic Tasks Anwar Mohammadi, Nathan Fisher, and Daniel.
THERMAL-AWARE BUS-DRIVEN FLOORPLANNING PO-HSUN WU & TSUNG-YI HO Department of Computer Science and Information Engineering, National Cheng Kung University.
1 Column Generation. 2 Outline trim loss problem different formulations column generation the trim loss problem master problem and subproblem in column.
IGLS/1 © P. Pongcharoen Using Genetic Algorithms for Scheduling the Production of Capital Goods P. Pongcharoen, C. Hicks, P.M. Braiden, A.V. Metcalfe,
Energy-efficient Task Scheduling in Heterogeneous Environment 2013/10/25.
1 Optimal Online Algorithms for Minimax Resource Scheduling Imen BOURGUIBA CAS 744 McMaster University.
The simplex algorithm The simplex algorithm is the classical method for solving linear programs. Its running time is not polynomial in the worst case.
Problems and Their Classes
Minimum Clique Partition Problem with Constrained Weight for Interval Graphs Jianping Li Department of Mathematics Yunnan University Jointed by M.X. Chen.
Based on customer demand, estimate:  ω s : minimum required amount of material s For final products, ω s is the customer demand Calculated once µ i is.
Hadi Goudarzi and Massoud Pedram
Class-constrained Packing Problems with Application to Storage Management in Multimedia Systems Tami Tamir Department of Computer Science The Technion.
1 EE5900 Advanced Embedded System For Smart Infrastructure RMS and EDF Scheduling.
1 Finite Constraint Domains. 2 u Constraint satisfaction problems (CSP) u A backtracking solver u Node and arc consistency u Bounds consistency u Generalized.
CPE555A: Real-Time Embedded Systems
1 EE5900 Advanced Embedded System For Smart Infrastructure Static Scheduling.
Online Scheduling with Known Arrival Times Nicholas G Hall (Ohio State University) Marc E Posner (Ohio State University) Chris N Potts (University of Southampton)
RUN: Optimal Multiprocessor Real-Time Scheduling via Reduction to Uniprocessor Paul Regnier † George Lima † Ernesto Massa † Greg Levin ‡ Scott Brandt ‡
Power Management Algorithms An effort to minimize Processor Temperature and Energy Consumption.
THE SINGLE MACHINE EARLY/TARDY PROBLEM* PENG SI OW & THOMAS E. MORTON IE Paper Presentation A. İrfan Mahmutoğulları *Ow, P. S., & Morton, T. E. (1989).
Towards Feasibility Region Calculus: An End-to-end Schedulability Analysis of Real- Time Multistage Execution William Hawkins and Tarek Abdelzaher Presented.
Watermarking in WSNs Anuj Nagar CS 590. Introduction WSNs provide computational and Internet interfaces to the physical world. They also pose a number.
Investigating the Effect of Voltage- Switching on Low-Energy Task Scheduling in Hard Real-Time Systems Paper review Presented by Chung-Fu Kao.
CSE 421 Algorithms Richard Anderson Lecture 6 Greedy Algorithms.
System-Wide Energy Minimization for Real-Time Tasks: Lower Bound and Approximation Xiliang Zhong and Cheng-Zhong Xu Dept. of Electrical & Computer Engg.
Branch and Bound Algorithm for Solving Integer Linear Programming
Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment Presented by Pete Perlegos C.L. Liu and James W. Layland.
Distributed Combinatorial Optimization
By Group: Ghassan Abdo Rayyashi Anas to’meh Supervised by Dr. Lo’ai Tawalbeh.
Cmpt-225 Simulation. Application: Simulation Simulation  A technique for modeling the behavior of both natural and human-made systems  Goal Generate.
Energy, Energy, Energy  Worldwide efforts to reduce energy consumption  People can conserve. Large percentage savings possible, but each individual has.
Task Alloc. In Dist. Embed. Systems Murat Semerci A.Yasin Çitkaya CMPE 511 COMPUTER ARCHITECTURE.
Control and Optimization Meet the Smart Power Grid: Scheduling of Power Demands for Optimal Energy Management Authors: Iordanis Koutsopoulos Leandros Tassiulas.
Efficient and Scalable Computation of the Energy and Makespan Pareto Front for Heterogeneous Computing Systems Kyle M. Tarplee 1, Ryan Friese 1, Anthony.
A S CHEDULABILITY A NALYSIS FOR W EAKLY H ARD R EAL - T IME T ASKS IN P ARTITIONING S CHEDULING ON M ULTIPROCESSOR S YSTEMS Energy Reduction in Weakly.
Scheduling policies for real- time embedded systems.
DESIGNING VM SCHEDULERS FOR EMBEDDED REAL-TIME APPLICATIONS Alejandro Masrur, Thomas Pfeuffer, Martin Geier, Sebastian Drössler and Samarjit Chakraborty.
Real-Time Scheduling CS4730 Fall 2010 Dr. José M. Garrido Department of Computer Science and Information Systems Kennesaw State University.
A Faster Approximation Scheme for Timing Driven Minimum Cost Layer Assignment Shiyan Hu*, Zhuo Li**, and Charles J. Alpert** *Dept of ECE, Michigan Technological.
6. Application mapping 6.1 Problem definition
CSC 8420 Advanced Operating Systems Georgia State University Yi Pan.
O PTIMAL SERVICE TASK PARTITION AND DISTRIBUTION IN GRID SYSTEM WITH STAR TOPOLOGY G REGORY L EVITIN, Y UAN -S HUN D AI Adviser: Frank, Yeong-Sung Lin.
A Membrane Algorithm for the Min Storage problem Dipartimento di Informatica, Sistemistica e Comunicazione Università degli Studi di Milano – Bicocca WMC.
ECE555 Topic Presentation Energy-efficient real-time scheduling Xing Fu 20 September 2008 Acknowledge Dr. Jian-Jia Chen from ETH providing PPT Slides for.
CSCI1600: Embedded and Real Time Software Lecture 23: Real Time Scheduling I Steven Reiss, Fall 2015.
1 BECO 2004 When can one develop an FPTAS for a sequential decision problem? with apologies to Gerhard Woeginger James B. Orlin MIT working jointly with.
Introduction to Real-Time Systems
Common Intersection of Half-Planes in R 2 2 PROBLEM (Common Intersection of half- planes in R 2 ) Given n half-planes H 1, H 2,..., H n in R 2 compute.
Determining Optimal Processor Speeds for Periodic Real-Time Tasks with Different Power Characteristics H. Aydın, R. Melhem, D. Mossé, P.M. Alvarez University.
Introduction to Algorithms: Brute-Force Algorithms.
O PTIMAL R EPLACEMENT AND P ROTECTION S TRATEGY FOR P ARALLEL S YSTEMS R UI P ENG, G REGORY L EVITIN, M IN X IE AND S ZU H UI N G Adviser: Frank, Yeong-Sung.
Embedded System Scheduling
Memory Segmentation to Exploit Sleep Mode Operation
Priority Queues An abstract data type (ADT) Similar to a queue
Outline Introduction Network Model and Problem Formulation
Integer Programming (정수계획법)
Sanjoy Baruah The University of North Carolina at Chapel Hill
Elastic Task Model For Adaptive Rate Control
Dynamic Voltage Scaling
CSCI1600: Embedded and Real Time Software
Greedy Algorithms: Homework Scheduling and Optimal Caching
Priority Queues An abstract data type (ADT) Similar to a queue
Integer Programming (정수계획법)
Ch 4. Periodic Task Scheduling
Presentation transcript:

S YSTEM -W IDE E NERGY M ANAGEMENT FOR R EAL -T IME T ASKS : L OWER B OUND AND A PPROXIMATION Xiliang Zhong and Cheng-Zhong Xu ICCAD 2006, ACM Trans. on Embedded Computing Systems, Presenter: Mohammad A Haque

M OTIVATION Energy cost is becoming one of the greatest concern for Data Centers and large computer systems. The total energy and cooling cost for servers in the USA are expected to rise to $50 Billion per year by the end of this year. Generated heat is proportional to the energy consumption. Overheating affects device performance and lifetime. CS, GMU cluster HYDRA has more than 50 nodes. Only 18 nodes are kept active at the same time due to overheating problem. Introduction System Model Algorithm Simulation Results Conclusion

B ACKGROUND System-wide energy management means the power model considers energy consumed by different system components (memory, wireless interface, …) along with CPU. In Real-Time Systems, every task has an associated deadline. Deadline could be either Hard or Soft. This paper deals with system-wide energy management of Periodic and Sporadic (Aperiodic ) tasks in hard real-time system. Introduction System Model Algorithm Simulation Results Conclusion

P ROBLEM S ETTINGS We are given a set of periodic/sporadic tasks. The tasks need to be executed on a single processor machine with discrete speed levels. Our goal is to find speed assignments for the tasks, such that total system-level energy consumption is minimized while meeting the deadline constraints. Introduction System Model Algorithm Simulation Results Conclusion

T ASK M ODEL A set of n tasks are scheduled using Earliest Deadline First (EDF) policy. A task is characterized by a tuple {C i, T i, D i }, where C i is the execution time under maximum speed. T i and D i are task period and deadline respectively. Its common to assume T i = D i. A task utilization is defined by the ratio C i /T i. A well known result in real-time system is, a task set can be feasibly scheduled using EDF if and only if the following condition holds. Introduction System Model Algorithm Simulation Results Conclusion

E NERGY M ODEL CPU speed can be adjusted in discrete steps in range [ f min, f max ]. We define slowdown factor, S = f/f max. At S i, a task takes C i /S i time to complete and the new utilization is C i /(T i S i ). The system-level energy consumption for a task i at slowdown factor S i is, power consumed by j -th device in standby state. energy consumed by all the devices in active state. Introduction System Model Algorithm Simulation Results Conclusion

P ROBLEM F ORMULATION minimize subject to Introduction System Model Algorithm Simulation Results Conclusion

R EDUCTION TO 0-1 MCKP For each task, i and for each speed level, j we have a corresponding (utilization, energy) pair denoted by (u ij, e ij ). So the problem can be thought as choosing one pair from each set, {(u 11, e 11 ), (u 12, e 12 ), …, (u 1m, e 1m )}, {(u 21, e 21 ), (u 22, e 22 ), …, (u 2m, e 2m )}, …, {(u n1, e n1 ), (u n2, e n2 ), …, (u nm, e nm )}. to minimize the sum of e ij, while keeping the sum of u ij ’s below MCKP is NP hard. Therefore, so is our problem. Introduction System Model Algorithm Simulation Results Conclusion

We know pseudo-polynomial time algorithm for solving 0-1 MCKP problem. But the traditional algorithms do not work here, due to a limitation of the traditional 0-1 Knapsack problem solutions. What is the biggest limitation with those solutions?? The traditional solutions for 0-1 Knapsack problem works only with integer coefficients. Introduction System Model Algorithm Simulation Results Conclusion

O PTIMAL A LGORITHM Start with an empty list, L 0 =. For each task i and for each speed level j, perform component wise addition of the pair (u ij, e ij ) with the list L i-1. Merge the lists and keep it sorted in non-decreasing order of energy. Delete all infeasible solution from the list in each step. Prune the dominated states from the list. A state is dominated by another state, if it has a larger utilization and a larger energy consumption than the other. Introduction System Model Algorithm Simulation Results Conclusion

E XAMPLE Consider a task set with 2 tasks and 2 speed levels. The algorithm works as follows. Initialization: L 0 = 1 st step: L 1,1 = L 1,2 = L 1 = 2 nd step: L 2,1 = L 2,2 = L 2 = Introduction System Model Algorithm Simulation Results Conclusion

A NALYSIS The runtime of the algorithm is bounded by where U is the upper bound for the number of elements in the list and m i is the number speed levels for task i. Since the size of the list can grow very large, the runtime of the algorithm is not polynomially bounded. The space requirement for the algorithm is O(U). Introduction System Model Algorithm Simulation Results Conclusion

A PPROXIMATION A LGORITHM (FPTAS) Choose ε and replace e ij with The maximum error we can have is nε. For a given relative error r, we choose, where, E* is the energy consumption of the optimal algorithm. The number of undominated states in the list reduces to (E max /E min - 1)(n/r). Introduction System Model Algorithm Simulation Results Conclusion

S PORADIC T ASKS Sporadic tasks are released at random time instants and the task parameters are only known after release. Whenever a task arrives, we perform an admission control test to determine whether we can accept the task or not. The problem reduces to Multi-dimensional MCKP (MMKP), which is NP-hard in the strong sense. Similar optimal and approximation algorithm works for the sporadic task as well. A key assumption is the feasibility of a task does not depend on the task that finishes later. Introduction System Model Algorithm Simulation Results Conclusion

S IMULATION R ESULT (P ERIODIC ) Introduction System Model Algorithm Simulation Results Conclusion

S IMULATION R ESULT (S PORADIC ) Introduction System Model Algorithm Simulation Results Conclusion

C ONCLUSION The paper provides pseudo-polynomial optimal algorithm and FPTAS for both periodic and sporadic tasks. The algorithm is simple yet interesting. However some more simulation results, specially the effect of number of speed levels and ratio of E max /E min will be worth experimenting. Introduction System Model Algorithm Simulation Results Conclusion

T HANK Y OU