Heating Homes with Servers: Workload Scheduling for Heat Reuse in Distributed Data Centers
Data centers consume lots of energy to execute their computational workload and generate heat that is mostly wasted. In this paper, we address this problem by considering heat reuse in the case of a distributed data center that features IT equipment (i.e., servers) installed in residential homes to...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/8/2879 |
| _version_ | 1797537078069690368 |
|---|---|
| author | Marcel Antal Andrei-Alexandru Cristea Victor-Alexandru Pădurean Tudor Cioara Ionut Anghel Claudia Antal (Pop) Ioan Salomie Nicolas Saintherant |
| author_facet | Marcel Antal Andrei-Alexandru Cristea Victor-Alexandru Pădurean Tudor Cioara Ionut Anghel Claudia Antal (Pop) Ioan Salomie Nicolas Saintherant |
| author_sort | Marcel Antal |
| collection | DOAJ |
| description | Data centers consume lots of energy to execute their computational workload and generate heat that is mostly wasted. In this paper, we address this problem by considering heat reuse in the case of a distributed data center that features IT equipment (i.e., servers) installed in residential homes to be used as a primary source of heat. We propose a workload scheduling solution for distributed data centers based on a constraint satisfaction model to optimally allocate workload on servers to reach and maintain the desired home temperature setpoint by reusing residual heat. We have defined two models to correlate the heat demand with the amount of workload to be executed by the servers: a mathematical model derived from thermodynamic laws calibrated with monitored data and a machine learning model able to predict the amount of workload to be executed by a server to reach a desired ambient temperature setpoint. The proposed solution was validated using the monitored data of an operational distributed data center. The server heat and power demand mathematical model achieve a correlation accuracy of 11.98% while in the case of machine learning models, the best correlation accuracy of 4.74% is obtained for a Gradient Boosting Regressor algorithm. Also, our solution manages to distribute the workload so that the temperature setpoint is met in a reasonable time, while the server power demand is accurately following the heat demand. |
| first_indexed | 2024-03-10T12:09:59Z |
| format | Article |
| id | doaj.art-cf5c9220b8704610aaef4da024530f77 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T12:09:59Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cf5c9220b8704610aaef4da024530f772023-11-21T16:18:13ZengMDPI AGSensors1424-82202021-04-01218287910.3390/s21082879Heating Homes with Servers: Workload Scheduling for Heat Reuse in Distributed Data CentersMarcel Antal0Andrei-Alexandru Cristea1Victor-Alexandru Pădurean2Tudor Cioara3Ionut Anghel4Claudia Antal (Pop)5Ioan Salomie6Nicolas Saintherant7Computer Science Department, Technical University of Cluj-Napoca, Memorandumului 28, 400114 Cluj-Napoca, RomaniaPhysics Department, Merton College, Merton St, Oxford OX1 4JD, UKComputer Science Department, Technical University of Cluj-Napoca, Memorandumului 28, 400114 Cluj-Napoca, RomaniaComputer Science Department, Technical University of Cluj-Napoca, Memorandumului 28, 400114 Cluj-Napoca, RomaniaComputer Science Department, Technical University of Cluj-Napoca, Memorandumului 28, 400114 Cluj-Napoca, RomaniaComputer Science Department, Technical University of Cluj-Napoca, Memorandumului 28, 400114 Cluj-Napoca, RomaniaComputer Science Department, Technical University of Cluj-Napoca, Memorandumului 28, 400114 Cluj-Napoca, RomaniaQarnot Computing, 40–42 Rue Barbès, 92120 Montrouge, FranceData centers consume lots of energy to execute their computational workload and generate heat that is mostly wasted. In this paper, we address this problem by considering heat reuse in the case of a distributed data center that features IT equipment (i.e., servers) installed in residential homes to be used as a primary source of heat. We propose a workload scheduling solution for distributed data centers based on a constraint satisfaction model to optimally allocate workload on servers to reach and maintain the desired home temperature setpoint by reusing residual heat. We have defined two models to correlate the heat demand with the amount of workload to be executed by the servers: a mathematical model derived from thermodynamic laws calibrated with monitored data and a machine learning model able to predict the amount of workload to be executed by a server to reach a desired ambient temperature setpoint. The proposed solution was validated using the monitored data of an operational distributed data center. The server heat and power demand mathematical model achieve a correlation accuracy of 11.98% while in the case of machine learning models, the best correlation accuracy of 4.74% is obtained for a Gradient Boosting Regressor algorithm. Also, our solution manages to distribute the workload so that the temperature setpoint is met in a reasonable time, while the server power demand is accurately following the heat demand.https://www.mdpi.com/1424-8220/21/8/2879heat reusedistributed data centersworkload schedulingmachine learningmathematical modeling |
| spellingShingle | Marcel Antal Andrei-Alexandru Cristea Victor-Alexandru Pădurean Tudor Cioara Ionut Anghel Claudia Antal (Pop) Ioan Salomie Nicolas Saintherant Heating Homes with Servers: Workload Scheduling for Heat Reuse in Distributed Data Centers Sensors heat reuse distributed data centers workload scheduling machine learning mathematical modeling |
| title | Heating Homes with Servers: Workload Scheduling for Heat Reuse in Distributed Data Centers |
| title_full | Heating Homes with Servers: Workload Scheduling for Heat Reuse in Distributed Data Centers |
| title_fullStr | Heating Homes with Servers: Workload Scheduling for Heat Reuse in Distributed Data Centers |
| title_full_unstemmed | Heating Homes with Servers: Workload Scheduling for Heat Reuse in Distributed Data Centers |
| title_short | Heating Homes with Servers: Workload Scheduling for Heat Reuse in Distributed Data Centers |
| title_sort | heating homes with servers workload scheduling for heat reuse in distributed data centers |
| topic | heat reuse distributed data centers workload scheduling machine learning mathematical modeling |
| url | https://www.mdpi.com/1424-8220/21/8/2879 |
| work_keys_str_mv | AT marcelantal heatinghomeswithserversworkloadschedulingforheatreuseindistributeddatacenters AT andreialexandrucristea heatinghomeswithserversworkloadschedulingforheatreuseindistributeddatacenters AT victoralexandrupadurean heatinghomeswithserversworkloadschedulingforheatreuseindistributeddatacenters AT tudorcioara heatinghomeswithserversworkloadschedulingforheatreuseindistributeddatacenters AT ionutanghel heatinghomeswithserversworkloadschedulingforheatreuseindistributeddatacenters AT claudiaantalpop heatinghomeswithserversworkloadschedulingforheatreuseindistributeddatacenters AT ioansalomie heatinghomeswithserversworkloadschedulingforheatreuseindistributeddatacenters AT nicolassaintherant heatinghomeswithserversworkloadschedulingforheatreuseindistributeddatacenters |