The Impact of Prediction Models on Energy-Aware Resource Management in FaaS Platforms
Edge Function-as-a-Service is an emerging computing model that dynamically schedules function executions across distributed edge (close to users) locations to reduce latency and improve user experience. Accurate time-series prediction models, which forecast the future number of function invocations,...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11000298/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850129689885016064 |
|---|---|
| author | Shahrokh Vahabi Francesca Righetti Carlo Vallati Nicola Tonellotto |
| author_facet | Shahrokh Vahabi Francesca Righetti Carlo Vallati Nicola Tonellotto |
| author_sort | Shahrokh Vahabi |
| collection | DOAJ |
| description | Edge Function-as-a-Service is an emerging computing model that dynamically schedules function executions across distributed edge (close to users) locations to reduce latency and improve user experience. Accurate time-series prediction models, which forecast the future number of function invocations, are crucial for energy-efficient function scheduling, enabling proactive resource allocation. In this work, we evaluate the impact of different neural time-series predictors based on Gaussian processes, recurrent neural networks, and transformer architectures in forecasting the number of function invocations. Furthermore, we propose the Energy-Aware Resource Management (EA-RM) scheduling algorithm, based on a mixed-integer problem, designed to minimize overall energy consumption by reducing the number of edge nodes used. We analyze how prediction accuracy influences function scheduling with respect to energy consumption, using real-world data that include different functions and resources. Experimental results show that the transformer-based predictor outperforms the other considered predictors, leading to more precise function scheduling. Moreover, resource allocation performed through the EA-RM algorithm reduces the energy consumption by ~12-45% on average w.r.t. competitors, and is proven to be more robust w.r.t. the accuracy of the prediction model used. |
| format | Article |
| id | doaj-art-22214523af48461d82c1a2e384754aa4 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-22214523af48461d82c1a2e384754aa42025-08-20T02:32:53ZengIEEEIEEE Access2169-35362025-01-0113857118572710.1109/ACCESS.2025.356906811000298The Impact of Prediction Models on Energy-Aware Resource Management in FaaS PlatformsShahrokh Vahabi0https://orcid.org/0000-0002-5833-7672Francesca Righetti1https://orcid.org/0000-0003-3892-8368Carlo Vallati2https://orcid.org/0000-0002-7833-5471Nicola Tonellotto3https://orcid.org/0000-0002-7427-1001Department of Information Engineering, University of Pisa, Pisa, ItalyDepartment of Information Engineering, University of Pisa, Pisa, ItalyDepartment of Information Engineering, University of Pisa, Pisa, ItalyDepartment of Information Engineering, University of Pisa, Pisa, ItalyEdge Function-as-a-Service is an emerging computing model that dynamically schedules function executions across distributed edge (close to users) locations to reduce latency and improve user experience. Accurate time-series prediction models, which forecast the future number of function invocations, are crucial for energy-efficient function scheduling, enabling proactive resource allocation. In this work, we evaluate the impact of different neural time-series predictors based on Gaussian processes, recurrent neural networks, and transformer architectures in forecasting the number of function invocations. Furthermore, we propose the Energy-Aware Resource Management (EA-RM) scheduling algorithm, based on a mixed-integer problem, designed to minimize overall energy consumption by reducing the number of edge nodes used. We analyze how prediction accuracy influences function scheduling with respect to energy consumption, using real-world data that include different functions and resources. Experimental results show that the transformer-based predictor outperforms the other considered predictors, leading to more precise function scheduling. Moreover, resource allocation performed through the EA-RM algorithm reduces the energy consumption by ~12-45% on average w.r.t. competitors, and is proven to be more robust w.r.t. the accuracy of the prediction model used.https://ieeexplore.ieee.org/document/11000298/Edge computingenergy efficiencyfunction-as-a-serviceprediction models |
| spellingShingle | Shahrokh Vahabi Francesca Righetti Carlo Vallati Nicola Tonellotto The Impact of Prediction Models on Energy-Aware Resource Management in FaaS Platforms IEEE Access Edge computing energy efficiency function-as-a-service prediction models |
| title | The Impact of Prediction Models on Energy-Aware Resource Management in FaaS Platforms |
| title_full | The Impact of Prediction Models on Energy-Aware Resource Management in FaaS Platforms |
| title_fullStr | The Impact of Prediction Models on Energy-Aware Resource Management in FaaS Platforms |
| title_full_unstemmed | The Impact of Prediction Models on Energy-Aware Resource Management in FaaS Platforms |
| title_short | The Impact of Prediction Models on Energy-Aware Resource Management in FaaS Platforms |
| title_sort | impact of prediction models on energy aware resource management in faas platforms |
| topic | Edge computing energy efficiency function-as-a-service prediction models |
| url | https://ieeexplore.ieee.org/document/11000298/ |
| work_keys_str_mv | AT shahrokhvahabi theimpactofpredictionmodelsonenergyawareresourcemanagementinfaasplatforms AT francescarighetti theimpactofpredictionmodelsonenergyawareresourcemanagementinfaasplatforms AT carlovallati theimpactofpredictionmodelsonenergyawareresourcemanagementinfaasplatforms AT nicolatonellotto theimpactofpredictionmodelsonenergyawareresourcemanagementinfaasplatforms AT shahrokhvahabi impactofpredictionmodelsonenergyawareresourcemanagementinfaasplatforms AT francescarighetti impactofpredictionmodelsonenergyawareresourcemanagementinfaasplatforms AT carlovallati impactofpredictionmodelsonenergyawareresourcemanagementinfaasplatforms AT nicolatonellotto impactofpredictionmodelsonenergyawareresourcemanagementinfaasplatforms |