Aalto

Towards Optimal Performance-Energy Trade-off in Server Farms (TOP-Energy)

Summary

Principal investigator Dr. Samuli Aalto
Title of research projectTowards Optimal Performance-Energy Trade-off in Server Farms
Acronym TOP-Energy
Site of research Aalto University School of Electrical Engineering, Department of Communications and Networking
Duration of project 48 months (1.9.2013-31.8.2017)
Funded by Academy of Finland
Queueing model for Server farm.
Fig. 1: The basic queueing model for a server farm.

1. Our approach

In this project, we develop advanced multi-server queueing models for server farms that include features essential for characterizing scheduling performance as well as energy efficiency. Our final target is to find optimal (or at least near optimal and robust) solutions both for the performance optimization and for the performance-energy tradeoff optimization of server farms.

2. Research tasks

Task 1: Central queue with parallel servers: performance optimization
Task 2: Parallel queues with their own servers: performance optimization
Task 3: Optimal performance-energy trade-off for server farms
Task 4: Optimal performance and performance-energy trade-off for layered server farms

3. People

4. Publications

  1. X. Lu, S. Aalto and P. Lassila,
    Performance-energy trade-off in data centers: Impact of switching delay, in SSEEGN 2013 (22nd ITC Specialist Seminar on Energy Efficient and Green Networking, Christchurch, New Zealand, November 2013), pp. 50-55, 2013
  2. E. Hyytiä and S. Aalto,
    Round-Robin routing policy: Value functions and mean performance with job- and server-specific costs, in ValueTools 2013 (7th International Conference on Performance Evaluation Methodologies and Tools, Torino, Italy, December 2013), pp. 68-79, 2013
  3. E. Hyytiä,
    Optimal routing of fixed size jobs to two parallel servers, INFOR: Information Systems and Operational Research 51, 215–224, 2013
  4. E. Hyytiä, R. Righter and S. Aalto,
    Energy-aware job assignment in server farms with setup delays under LCFS and PS, in ITC 26 (26th International Teletraffic Congress, Karlskrona, Sweden, September 2014)
    BEST PAPER AWARD
  5. E. Hyytiä, R. Righter and S. Aalto,
    Task assignment in a heterogeneous server farm with switching delays and general energy-aware cost structure, Performance Evaluation 75–76, 17–35, 2014
  6. S. Doroudi, E. Hyytiä and M. Harchol-Balter,
    Value driven load balancing, Performance Evaluation 79, 306-327, 2014
  7. M. Gebrehiwot, S. Aalto and P. Lassila,
    Optimal sleep-state control of energy-aware M/G/1 queues, in ValueTools 2014 (8th International Conference on Performance Evaluation Methodologies and Tools, Bratislava, Slovakia, December 2014), pp. 82-89, 2014
  8. S. Aalto, P. Lassila and P. Osti,
    Whittle index approach to size-aware scheduling with time-varying channels, in ACM SIGMETRICS 2015 (International Conference on Measurement and Modeling of Computer Systems, Portland, OR, June 2015), pp. 57-69, 2015
  9. K. Gardner, S. Zbarsky, S. Doroudi, M. Harchol-Balter, E. Hyytiä and A. Scheller-Wolf,
    Reducing latency via redundant requests: Exact analysis, in ACM SIGMETRICS 2015 (International Conference on Measurement and Modeling of Computer Systems, Portland, OR, June 2015), pp. 347-360, 2015
  10. E. Hyytiä and R. Righter,
    Fairness through linearly increasing holding costs in systems of parallel servers with setup delays, in ITC 27 (27th International Teletraffic Congress, Ghent, Belgium, September 2015), pp. 143-151, 2015
  11. E. Hyytia and S. Aalto,
    On round-robin routing with FCFS and LCFS scheduling, Performance Evaluation 97, 83-103, 2016
  12. M. Gebrehiwot, S. Aalto and P. Lassila,
    Energy-performance trade-off for processor sharing queues with setup delay, Operations Research Letters 44, 101–106, 2016
  13. E. Hyytia and R. Righter,
    Routing jobs with deadlines to heterogeneous parallel servers, Operations Research Letters 44, 507–513, 2016
  14. S. Aalto, P. Lassila and P. Osti,
    Whittle index approach to size-aware scheduling for time-varying channels with multiple states, Queueing Systems 83, 195–225, 2016
  15. K. Gardner, S. Zbarsky, S. Doroudi, M. Harchol-Balter, E. Hyytiä and A. Scheller-Wolf,
    Queueing with redundant requests: exact analysis, Queueing Systems 83, 227-259, 2016
  16. M. Gebrehiwot, S. Aalto and P. Lassila,
    Energy-aware control of server farms, in MIPRO 2016 (39th International Convention on Information and Communication Technology, Electronics and Microelectronics, Opatija, Croatia, May/June 2016), pp. 748-753, 2016
  17. M. Gebrehiwot, S. Aalto and P. Lassila,
    Energy-aware server with SRPT scheduling: analysis and optimization, in QEST 2016 (13th International Conference on Quantitative Evaluation of Systems, Quebec, Canada, August 2016), pp. 107-122, 2016
  18. M. Gebrehiwot, S. Aalto and P. Lassila,
    Optimal energy-aware control policies for FIFO servers, Performance Evaluation, 103, 41–59, 2016
  19. E. Hyytiä, R. Righter and J. Virtamo,
    Meeting soft deadlines in single- and multi-server systems, in ITC 28 (28th International Teletraffic Congress, Wurzburg, Germany, September 2016), pp. 166-174, 2016
  20. X. Lu, S. Aalto and P. Lassila,
    Performance-energy trade-off in controllable servers with setup delays, Australian Journal of Electrical and Electronics Engineering, 13, 109-121, 2016
  21. M. Gebrehiwot, S. Aalto and P. Lassila,
    Near-optimal policies for energy-aware task assignment in server farms, in TAPEMS 2017 (2nd International Workshop on Theoretical Approaches to Performance Evaluation, Modeling and Simulation, Madrid, Spain, May 2017), pp. 1017-1026, 2017
  22. S. Aalto, P. Lassila and P. Osti,
    Opportunistic scheduling with flow size information for Markovian time-varying channels, Performance Evaluation 112, 27-52, 2017
  23. M. Gebrehiwot, S. Aalto and P. Lassila,
    Energy-aware SRPT server with batch arrivals: analysis and optimization, Performance Evaluation 115, 92–107, 2017
  24. I. Taboada, S. Aalto, P. Lassila and F. Liberal,
    Delay- and energy-aware load balancing in ultra-dense heterogeneous 5G networks, Transactions on Emerging Telecommunications Technologies 28, 9, e3170, 2017
  25. E. Hyytiä, R. Righter, J. Virtamo and L. Viitasaari,
    Value (generating) functions for the MX/G/1 queue, ITC 29 (29th International Teletraffic Congress, Genoa, Italy, September 2017), pp. 232-240, 2017
  26. M. Gebrehiwot, S. Aalto and P. Lassila,
    Energy efficient load balancing in web server clusters, ITC 29 PhD Workshop “Modelling Communication Networks” (29th International Teletraffic Congress, Genoa, Italy, September 2017) , pp. 13-18, 2017
  27. E. Hyytiä, D. Down, P. Lassila and S. Aalto,
    Dynamic control of running servers, in MMB 2018 (19th International GI/ITG Conference on Measurement, Modelling and Evaluation of Computing Systems, Erlangen, Germany, February 2018), LNCS 10740, Springer, pp. 127-141, 2018

5. Theses

  1. P. Osti,
    Resource Allocation in the Wireless Access Network: A Queueing Theoretic Approach, Doctoral thesis, Aalto University School of Electrical Engineering, Finland, 2016
Related projects: