Newsletter‎ > ‎

Newsletter - Volume 6 Issue 2 - April 2018

Monthly bulletin of the IEEE Computer Society Special Technical Community on Sustainable Computing

Providing quick access to timely information on sustainable computing.

Sponsored by:





Share It!




Message from the editor

Cristina Rottondi, Dalle Molle Institute for Artificial Intelligence 

With the April 2018 issue of the IEEE STC-SC Newsletter it is time to announce some important changes in our community: our new Chair, Prof. Christopher Stewart, is currently in the process of reorganizing and renovating the whole management team. For this reason, the publication of future Newsletter issues will be momentarily suspended. While taking my leave after serving as Newsletter editor for more than three years, I take the chance to wholeheartedly thank our readership for the dedication and interest showed during all this time. In the future, I will keep on being involved in the STC-SC community, as I have been recently appointed as new Vice-Chair.

This issue opens with a message from our Chair, which details his plans and goals for the future of the STC-SC community. We then host two technical contributions: Prof. Stelios Krinidis and Prof. Dimitrios Tzovaras (Centre for Research and Technology Hellas/Information Technologies Institute, Thessaloníki, Greece) discuss the adoption of machine learning techniques for building occupancy inference, whereas Dr. Sabidur Rahman (University of California Davis) reports on his recent research about energy consumption in datacenters.
As usual, the newsletter closes with the list of upcoming conferences and workshops in the field of sustainable computing.


Message from the Chair

Christopher Stewart  Ohio State University, USA

Dear STC Members,

Our technical committee has been a driving force for research and engineering in sustainable computing. As the world shifted to cloud computing, our STC fostered research on data center efficiency, renewable powered services and geographic load balancing. As smart grids, smart cities and electric vehicles emerged as key technologies in our sustainable future, our STC sponsored conferences like IGSC and E-Energy, spotlighted researchers and exposed problems in these domain via our newsletter.
 

The world is changing again. Computer architecture faces the end of Denard Scaling, moving the burden of energy efficiency toward software developers. Smart cities and smart grids are real and increasingly common, but they struggle to efficiently corral and analyze data into actionable insights. Sustainability is bigger than solar or wind energy.  Moving forward, sustainable computing solutions must consider long-term effects on society.  Are our solutions ethical?  Are human, ecological and energy resources sustainable for long-term autonomous deployments?  Have we discovered the best, sustainable solutions?  We haven't addressed these problems yet. It is fair to wonder aloud. Is our STC ready to address these challenges?

It is time to restructure our STC to better support leaders at the forefront of the new challenges in sustainable computing.  We will recruit a new board, senior advisors, newsletter contributors and research pioneers.  We are looking for fresh faces and established members.  This STC must continue to lead by highlighting, promoting and fostering the best research and engineering in sustainable computing. 

Over the next few months, as we restructure, the newsletter will go dark. In 2019, our STC will reemerge ready to take on new challenges facing sustainable computing.  I will reach out to the full membership to plan workshops and request feedback on our restructuring plans. If you would like to be more involved, please email me. We need as many volunteers as possible. I am truly excited about the future for sustainable computing and the important role this STC will continue to play.

Thank you,


Dr. Christopher Stewart




Occupancy Inference based on Machine Learning Techniques

T. Vafeiadis, S. Zikos, D. Ioannidis, S. Krinidis, D. Tzovaras, Centre for Research and Technology Hellas/Information Technologies Institute (CERTH/ITI), Thessaloníki, Greece

 

The knowledge of occupancy in domestic environments is vital for many applications, such as energy management, building management, demand/response, security, etc. But, in the majority of the cases, it is very difficult or even impossible to install sensors for receiving occupancy information.

Thus, the occupancy (absence – presence or two-class classification scenario) should be detected and inferred utilizing machine learning techniques via electricity and water consumption data received from smart meters in a domestic environment.

To this end, the power consumption of crucial electrical appliances (i.e. TV, washing machine, refrigerator, and hair dryer) is monitored every minute. Also, four water consumption sensors have been installed for monitoring the water usage by the occupants in the kitchen as well as the water consumed by the dishwasher and the washing machine. Finally, an occupancy sensor has been installed at the main entrance of the building detecting entries and exits and measuring its occupancy. This information is utilized as ground truth.

After retrieving the raw data of the three systems, a processing step was performed in order to create the final dataset which includes events per 1-minute intervals of all the measured features. The initial aggregated dataset constructed after processing the raw data contains 9 features [Central Power (lights of the domestic environment), Refrigerator, TV, Washing Machine, Dryer, Cold Water - Kitchen, Hot Water - Kitchen, Dishwasher - Water, Washing Machine - Water] denoted hereafter as [CP, R, TV, WM, D, CWK, HWK, DW, WMW] and the target Occupancy, denoted hereafter as [OCCUP]. The dataset contains energy and water consumption data of 1-minute resolution for a time interval of 16 consecutive days during summer time. Thus, the shape of overall dataset is 23040x9 (without taking into account the target feature) and its sparsity is 74.44%.

In order to rank the influence of each feature to occupancy inference and extract the more useful information, we have used Mutual Information (MI) as the feature selection technique. MI measures how much one random variable provides information. It is a dimensionless quantity, and can be thought of as the reduction in uncertainty about one random variable given knowledge of another. Thus, we decide to use only the top-5 ranked features for occupancy inference, meaning Central Power, Cold Water – Kitchen, Washing Machine, Refrigerator and Washing Machine – Water. Under this condition, the shape of overall dataset is 23040x5 (again without taking into account the target feature) and its sparsity is reduced to 70.76% (from 74.44%).

In the sequence, machine learning techniques have been utilized in order to infer the occupancy in a building. The tested machine learning algorithms are:

  • Support Vector Machines (SVMs);
  • Decision Trees (DT);
  • Random Forest (RF);
  • Back-Propagation Network (BPN).

All these approaches were also combined with the AdaBoost algorithm for even more accurate performance.

Our main objective is to find the predictive model that is more efficient on occupancy inference based on energy and water consumption data. To that end, our simulation schema is based on the application of all tested classifiers and their boosting versions on both Initial-DS and MI-DS.

Precision, recall, accuracy and f-measure (estimated averages) for 100 monte-carlo iterations with the application of adaboost, on MI-DS.

Classifier

Precision (%)

Recall (%)

Accuracy (%)

F-measure (%)

SVM – POLY

74.79

89.34

79.83

81.42

SVM – RBF

74.35

89.07

80.06

81.04

DT

74.89

91.37

80.94

82.31

RF

73.91

95.17

80.23

83.20

BPN

74.01

92.83

80.21

82.36

     

Table I presents precision, recall, accuracy and F-measure (on average of 100 Monte-Carlo iterations) with the application of boosting on tested classifiers on the dataset. One can see that the DT with AdaBoost achieves the higher performance compared to the other tested classifiers (see highlighted values) with 80.94% accuracy (82.31% F-measure), while the RF follows closely in accuracy (80.23%), but achieves higher F-measure compared to DT (83.20%).

The overall framework has been thoroughly evaluated in [1].


References: 

  1. T. Vafeiadis, S. Zikos, G. Stavropoulos, D. Ioannidis, S. Krinidis, D. Tzovaras and K. Moustakas, “Machine Learning Based Occupancy Detection Via The Use of Smart Meters”, International Conference on Energy Science and Electrical Engineering (ICESEE 2017), Budapest, Hungary, 20-22 October, 2017

 
 

Exploiting temporal and spatial pattern of electricity cost data and dynamic workload migration minimizes data-center electricity cost

Dr. Sabidur Raman, Dr. Abishek Gupta, Prof. Biswanath Mukherjee, University of California Davis, USA

Prof. Massimo Tornatore, Politecnico di Milano, Italy


As more organizations adopt cloud services, energy consumption of data centers (DCs) keeps increasing. Today, Information and Communication Technology (ICT) has become a major consumer of energy worldwide. A large portion of ICT energy consumption is used to power servers running in DCs [1] [2] and the network they use to communicate. In our study [3], we have considered that energy cost at a particular DC is often related to the electricity price regulated by Independent System Operators / Regional Transmission Organizations (ISOs/RTOs). As these prices vary in time and depend on the geographical locations of the DCs, recent studies [4] [5] have shown that the spatio-temporal variations of electricity price can be exploited to reduce electricity cost. Often, electricity prices are known beforehand, depending on the type of market and contract the DC is getting electricity from. But energy production and pricing have become more volatile due to recent trend towards Smart Grid and dependence on renewable energy sources (see Fig. 1).



Fig. 1. 24-hour electricity price for Aug. 25, 2016, from ISOs/RTOs in USA. [3]

     In particular, as workloads tend to change, often unpredictably, adaptive workload placement and migration can help to serve the workloads in regions with lower electricity costs. Typically, a DC consists of multiple racks, each rack hosts multiple servers, and each server contains many virtual machines (VMs) to serve the client requests. VM migration [6] can be used to exploit the spatio-temporal variation of electricity costs and minimize electricity expenditures. DC workload has dynamic characteristics such as unpredictable workload arrival times and durations, hourly variation in number of incoming workloads, etc. In such cases, quasi-static and batch-processing approaches [4] [5] fail to capture practical aspects of the problem. Instead, a dynamic VM placement and migration approach can capture these practical aspects: electricity cost variation, time-varying workload, and varying duration of services. In addition, our study also considers electricity cost of the backbone network.



Fig. 2. Overview of the problem statement. [3]


We proposed a Dynamic Placement and Migration Algorithms (DPMAs) use an event-driven approach for optimized placement and migration of VMs. DPMAs consider both initial VM placement and future migrations to ensure that the approach is adaptive towards changes of electricity price and workload. To capture realistic scenario, we have incorporated electricity cost of VM migration over a backbone network, bandwidth constraints for VM migration, VM consolidation, constraints from Service Level Agreement (SLA), and administrative overhead of VM migration (see Fig. 2). Our study also considers practical values of configuration [7-11] and power consumption of servers, [12] racks, and the backbone network [13]. Simulative results show that placement and migration performed by DPMAs yield significant savings in operational cost of DCs compared to prior studies. We also discuss how the cost savings varies with varying workload and electricity price. The results show how the proposed method is flexible with respect to abnormal changes in DC workload due to an event or a disaster. Such an analysis is a major motivation behind the adaptive approach presented in this work. Cloud services hosted in DCs can be classified by many criteria such as CPU requirement, memory requirement, and so on [14]. Different classes of services are hosted at different types of VMs. To address such scenario, we propose Class-aware Dynamic Placement and Migration Algorithm (Class-aware DPMA). This article is adopted from [3], the complete version of the study is available at IEEE Transactions on Green Communications and Networking (http://ieeexplore.ieee.org/abstract/document/8166762/).


Our findings show promising results on the use of workload-aware VM placement and migration. A recent article on using DeepMind AI technology to reduce DC energy cost by 15% shows that a lot more can be done in the field of DC cost minimization and energy efficiency. Impact of machine learning and data mining techniques in cloud data center cost minimization and energy efficiency is yet to be explored in detail. New virtualization platforms such as ‘docker containers’ are on the rise. Future research can investigate such scenarios.


References:

  1.  “White paper, Emerson Network Power,” Emerson Network, [Online]. Available: http://www.emersonnetworkpower.com/ documentation/en-us/latest-thinking/edc/documents/white%20paper/energylogicreducing datacenterenergyconsumption.pdf. [Accessed: July 22, 2017].

  2. “America's Data Centers Consuming and Wasting Growing Amounts of Energy,” Natural Resources Defense Council, Feb. 2015, [Online]. Available:https://www.nrdc.org/resources/americas-data-centers-consu ming-and-wasting-growing-amounts-energy. [Accessed: July 22, 2017].

  3. S. Rahman, A. Gupta, M. Tornatore, B. Mukherjee, “Dynamic Workload Migration over Backbone Network to Minimize Data Center Electricity Cost”, IEEE Transactions on Green Communications and Networking, Issue: 99, Dec. 2017.

  4. A. Gupta, U. Mandal, P. Chowdhury, M. Tornatore, and B. Mukherjee, “Cost-efficient live VM migration based on varying electricity cost in optical cloud networks,” Photonic Network Communications, vol. 30, no. 3, pp. 376-386, Dec. 2015.

  5. A. Qureshi, R. Weber, H. Balakrishnan, J. Guttag, and B. Maggs, “Cutting the electric bill for internet-scale systems,” Proc., ACM SIGCOMM ’09, vol. 39, no. 4, pp. 123–134, Oct. 2009.

  6. “Virtual Machine Live Migration Overview,” Technet Microsoft, Aug. 2013, [Online]. Available: https://technet.microsoft.com/en-us/ library/ hh831435(v=ws.11).aspx. [Accessed: July 23, 2017].

  7. “VMWare VMotion,” VMware, [Online]. Available: https://www.vmw are.com/products/vsphere/features/vmotion. [Accessed: July 23, 2017].

  8.  “VMWare VSphare6 documentation,” VMware, [Online]. Available: https://www.vmware.com/pdf/vsphere6/r60/vsphere-60-configuration-maximums.pdf. [Accessed: July 23, 2017].

  9. A. K. Mishra, J. L. Hellerstein, W. Cirne, and C. R. Das, “Towards Characterizing Cloud Backend Workloads: Insights from Google Compute Clusters,” ACM SIGMETRICS Performance Evaluation Review, vol. 37, no. 4, pp. 34-41, Mar. 2010.

  10. T. Paul, D. Puscher, and T. Strufe, “The User Behavior in Facebook and its Development from 2009 until 2014,” arXiv preprint arXiv:1505.04943, May 2015.

  11. “Efficiency: How we do it,” Google, [Online]. Available:  https://www. google.com/about/datacenters/efficiency/internal/. [Accessed: Aug 12, 2017].

  12.  “HP rack servers,” HP, [Online]. Available: https://www.hpe.com /us/en/servers/rack.html. [Accessed: Aug 12, 2017].

  13. “NSFNet,” NSFNet, [Online]. Available: http://www.nsfnet-legacy.org/about.php. [Accessed: Aug 12, 2017]

  14. “EC2 instance types–Amazon Web Services (AWS),” [Online]. Avail able: https://aws.amazon.com/ec2/instance-types/. [Accessed: Aug 12, 2017].


 

Upcoming Events

The following venues are requesting submissions on subtopics related to sustainable computing or IT for sustainability.

 

Conference, Workshop & Symposium Call For Papers

Short Name

Main Topic

Location

Dates

Paper Due

Notification

GREEN 2018

The Third International Conference on Green Communications, Computing and Technologies

Venice, Italy

Sep 16- 20, 2018

Apr 30, 2018

May 30, 2018

EMSICC 2018

International Workshop on Energy Management for Sustainable Internet-of-Things and Cloud Computing

Barcelona, Spain

Aug 6- 8, 2018

April 30, 2018

May 30, 2018

SDEWES Conference 2018

Conference on sustainable development of energy, water and environment systems

Palermo, Italy

Sep 30 – Oct 04, 2018

      April 30, 2018          (abstract)

September 12, 2018 (full paper)

NA

SmartGridComm 2018

IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids

Aalborg, Denmark

29 Oct - 1 Nov 2018

May 1, 2018

July 18, 2018

 

Journal and Special Issue Call For Papers

Journal                                                                                                                             Papers Due

Elsevier Sustainable Computing                                                                                        (Open)

IEEE Transactions on Sustainable Computing                                                                  (Open)

IEEE Transactions on Green Communications and Networking                                       (Open)

IEEE Access, special issue on Social Computing Applications for Smart Cities                                                             (http://ieeeaccess.ieee.org/special-sections/social-computing-applications-smart-cities/)                       Apr. 30, 2018