Zouhir Bellal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zouhir Bellal has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
Nadjia Kara
Cole de Technologie Suprieure (TS), Montreal, QC, Canada
4 shared publicationsTan Phat Nguyen
Ericsson Canada, Montreal, QC, Canada
3 shared publicationsArif Ahmed
Ericsson Research, Stockholm, Sweden
2 shared publicationsLaaziz Lahlou
Dept. of Software Engineering and IT, École de Technologie Supérieure
2 shared publications- Laaziz Lahlou
Department of Software and IT Engineering, École de Technologie Supérieure, Montreal, Canada
2 shared publications Timothy Murphy
Ericsson
2 shared publications
Latest Publications
- 3 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Green Communications and Networking
- Vol. 10, 2118-2135
Investigating the Potential of Kepler Toward Power Observability for Sustainable Cloud Computing
Power monitoring is a cornerstone of sustainability efforts, especially as the energy demands of Artificial Intelligence (AI) workloads continue to rise. However, accurately measuring power consumption in cloud-native environments remains challenging due to technical constraints such as fine-grained monitoring requirements and the high abstraction introduced by virtualization and containerization. Kepler (Kubernetes-based Efficient Power Level Exporter), an open-source tool for container-level power monitoring, has emerged as a promising solution for cloud power observability. This paper outlines the key requirements for accurate power tracking in containerized environments and assesses Kepler’s alignment with these criteria. However, its precision remains unvalidated, mainly due to the lack of a systematic evaluation methodology. To fill this gap, we introduce a novel accuracy validation framework tailored to assess container-level power monitoring tools under dynamic controlled multi-tenancy environments, including CPU frequency scaling, C-state transitions, and varying co-runner workloads (i.e., co-hosted containers executing concurrently on other cores of the same processor socket). Using this framework, we perform the first in-depth evaluation of Kepler’s accuracy in real-world cloud scenarios (e.g., dynamic power configuration settings, dynamic workloads). Our results show that Kepler’s container-level power estimation exhibits a root mean squared error (RMSE) of 11.9 Watts against the RAPL ground truth, corresponding to an overestimation of approximately 15×. Its accuracy is highly sensitive to runtime factors such as CPU configuration and C-state transitions, which reveals critical limitations in Kepler’s current power model and highlights the need for refinement. This work establishes the foundation for more precise and effective power observability in cloud computing and paves the way for sustainable cloud computing.
- 3 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Green Communications and Networking
- Vol. 10, 2118-2135
Investigating the Potential of Kepler Toward Power Observability for Sustainable Cloud Computing
Power monitoring is a cornerstone of sustainability efforts, especially as the energy demands of Artificial Intelligence (AI) workloads continue to rise. However, accurately measuring power consumption in cloud-native environments remains challenging due to technical constraints such as fine-grained monitoring requirements and the high abstraction introduced by virtualization and containerization. Kepler (Kubernetes-based Efficient Power Level Exporter), an open-source tool for container-level power monitoring, has emerged as a promising solution for cloud power observability. This paper outlines the key requirements for accurate power tracking in containerized environments and assesses Kepler’s alignment with these criteria. However, its precision remains unvalidated, mainly due to the lack of a systematic evaluation methodology. To fill this gap, we introduce a novel accuracy validation framework tailored to assess container-level power monitoring tools under dynamic controlled multi-tenancy environments, including CPU frequency scaling, C-state transitions, and varying co-runner workloads (i.e., co-hosted containers executing concurrently on other cores of the same processor socket). Using this framework, we perform the first in-depth evaluation of Kepler’s accuracy in real-world cloud scenarios (e.g., dynamic power configuration settings, dynamic workloads). Our results show that Kepler’s container-level power estimation exhibits a root mean squared error (RMSE) of 11.9 Watts against the RAPL ground truth, corresponding to an overestimation of approximately 15×. Its accuracy is highly sensitive to runtime factors such as CPU configuration and C-state transitions, which reveals critical limitations in Kepler’s current power model and highlights the need for refinement. This work establishes the foundation for more precise and effective power observability in cloud computing and paves the way for sustainable cloud computing.
- Open Access
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
EC6: Enhancing Energy Efficiency in Kubernetes Through Dynamic Extension of CPU Deep Idle States (C6)
Although the energy footprint of cloud infrastructures is becoming a critical concern, mainstream orchestration platforms such as Kubernetes (K8s) continue to prioritize performance over power efficiency. By default, K8s employs static CPU pinning for latency-sensitive services to ensure predictable performance and prevent resource contention. However, during service idle periods, residual background activities-such as runtime threads and maintenance tasks-occupy the assigned cores, preventing them from entering deep idle states (e.g., C6) and leading to unnecessary power consumption. This paper introduces EC6, a lightweight, idle-aware scheduling policy for K8s that consolidates idle services onto a reserved single CPU core, allowing other cores to transition into deep C-states during service inactivity. Upon resumption of service activity, EC6 transparently restores services to their original CPU cores with minimal latency, ensuring resource allocation constraints (i.e., , number of CPU cores) are maintained. Experimental evaluations show that EC6 increases per-core C6 residency by up to 30% and reduces idle power consumption by up to 13.6% compared to K8s' default container scheduling policy, without compromising performance. This demonstrates its effectiveness in improving energy proportionality in cloud-native environments while preserving service quality.
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessEC6: Enhancing Energy Efficiency in Kubernetes Through Dynamic Extension of CPU Deep Idle States (C6)
Although the energy footprint of cloud infrastructures is becoming a critical concern, mainstream orchestration platforms such as Kubernetes (K8s) continue to prioritize performance over power efficiency. By default, K8s employs static CPU pinning for latency-sensitive services to ensure predictable performance and prevent resource contention. However, during service idle periods, residual background activities-such as runtime threads and maintenance tasks-occupy the assigned cores, preventing them from entering deep idle states (e.g., C6) and leading to unnecessary power consumption. This paper introduces EC6, a lightweight, idle-aware scheduling policy for K8s that consolidates idle services onto a reserved single CPU core, allowing other cores to transition into deep C-states during service inactivity. Upon resumption of service activity, EC6 transparently restores services to their original CPU cores with minimal latency, ensuring resource allocation constraints (i.e., , number of CPU cores) are maintained. Experimental evaluations show that EC6 increases per-core C6 residency by up to 30% and reduces idle power consumption by up to 13.6% compared to K8s' default container scheduling policy, without compromising performance. This demonstrates its effectiveness in improving energy proportionality in cloud-native environments while preserving service quality.
- Open Access
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Investigating the Potential of Kepler Towards Power Observability for Sustainable Cloud Computing
Power monitoring is a cornerstone of sustainability efforts, especially as the energy demands of Artificial Intelligence (AI) workloads continue to rise. However, accurately measuring power consumption in cloud-native environments remains challenging due to technical constraints such as fine-grained monitoring requirements and the high abstraction introduced by virtualization and containerization. Kepler (Kubernetes-based Efficient Power Level Exporter), an open-source tool for container-level power monitoring, has emerged as a promising solution for cloud power observability. This paper outlines the key requirements for accurate power tracking in containerized environments and assesses Kepler's alignment with these criteria. However, its precision remains unvalidated, mainly due to the lack of a systematic evaluation methodology. To fill this gap, we introduce a novel accuracy validation framework tailored to assess container-level power monitoring tools under dynamic controlled multi-tenancy environments, including CPU frequency scaling, C-state transitions, and varying co-runner workloads (i.e., co-execution of multiple workloads). Using this framework, we perform the first in-depth evaluation of Kepler’s accuracy in real-world cloud scenarios (e.g., dynamic power configuration settings, dynamic workloads). Our results show that Kepler can overestimate power consumption by up to 15×, with its accuracy highly sensitive to runtime factors such as CPU configuration and C-state transitions. These findings reveal critical limitations in Kepler’s current power model and highlight the need for refinement. This work establishes the foundation for more precise and effective power observability in cloud computing and paves the way for sustainable cloud computing.
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessInvestigating the Potential of Kepler Towards Power Observability for Sustainable Cloud Computing
Power monitoring is a cornerstone of sustainability efforts, especially as the energy demands of Artificial Intelligence (AI) workloads continue to rise. However, accurately measuring power consumption in cloud-native environments remains challenging due to technical constraints such as fine-grained monitoring requirements and the high abstraction introduced by virtualization and containerization. Kepler (Kubernetes-based Efficient Power Level Exporter), an open-source tool for container-level power monitoring, has emerged as a promising solution for cloud power observability. This paper outlines the key requirements for accurate power tracking in containerized environments and assesses Kepler's alignment with these criteria. However, its precision remains unvalidated, mainly due to the lack of a systematic evaluation methodology. To fill this gap, we introduce a novel accuracy validation framework tailored to assess container-level power monitoring tools under dynamic controlled multi-tenancy environments, including CPU frequency scaling, C-state transitions, and varying co-runner workloads (i.e., co-execution of multiple workloads). Using this framework, we perform the first in-depth evaluation of Kepler’s accuracy in real-world cloud scenarios (e.g., dynamic power configuration settings, dynamic workloads). Our results show that Kepler can overestimate power consumption by up to 15×, with its accuracy highly sensitive to runtime factors such as CPU configuration and C-state transitions. These findings reveal critical limitations in Kepler’s current power model and highlight the need for refinement. This work establishes the foundation for more precise and effective power observability in cloud computing and paves the way for sustainable cloud computing.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Green Communications and Networking
- Vol. 9 (1) , 108-124
GAS : DVFS-Driven Energy Efficiency Approach for Latency-Guaranteed Edge Computing Microservices
Edge computing-based microservices (ECM) are pivotal infrastructure components for latency-critical applications such as Virtual Reality/Augmented Reality (VR/AR) and the Internet of Things (IoT). ECM involves strategically deploying microservices at the networks edge to fulfill the low latency needs of modern applications. However, achieving efficient resource and energy consumption while meeting the latency requirement in the ECM environment remains challenging. Dynamic Voltage and Frequency Scaling (DVFS) is a common technique to address this issue. It adjusts the CPU frequency and voltage to balance energy cost and performance. However, selecting the optimal CPU frequency depends on the nature of the microservice workload (e.g., CPU-bound, memory-bound, or mixed). Moreover, various microservices with different latency requirement can be deployed on the same edge node. This makes the DVFS application extremely challenging, particularly for a chip-wide DVFS implementation for which CPU cores operate at the same frequency and voltage. To this end, we propose GAS, enerGy Aware microServices edge computing framework, which enables CPU frequency scaling to meet diverse microservice latency requirement with the minimum energy cost. Our evaluation indicates that our CPU scaling policy decreases energy consumption by 5% to 23% compared to Linux governors while maintaining latency requirement and significantly contributing to sustainable edge computing.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Green Communications and Networking
- Vol. 9 (1) , 108-124
GAS : DVFS-Driven Energy Efficiency Approach for Latency-Guaranteed Edge Computing Microservices
Edge computing-based microservices (ECM) are pivotal infrastructure components for latency-critical applications such as Virtual Reality/Augmented Reality (VR/AR) and the Internet of Things (IoT). ECM involves strategically deploying microservices at the networks edge to fulfill the low latency needs of modern applications. However, achieving efficient resource and energy consumption while meeting the latency requirement in the ECM environment remains challenging. Dynamic Voltage and Frequency Scaling (DVFS) is a common technique to address this issue. It adjusts the CPU frequency and voltage to balance energy cost and performance. However, selecting the optimal CPU frequency depends on the nature of the microservice workload (e.g., CPU-bound, memory-bound, or mixed). Moreover, various microservices with different latency requirement can be deployed on the same edge node. This makes the DVFS application extremely challenging, particularly for a chip-wide DVFS implementation for which CPU cores operate at the same frequency and voltage. To this end, we propose GAS, enerGy Aware microServices edge computing framework, which enables CPU frequency scaling to meet diverse microservice latency requirement with the minimum energy cost. Our evaluation indicates that our CPU scaling policy decreases energy consumption by 5% to 23% compared to Linux governors while maintaining latency requirement and significantly contributing to sustainable edge computing.
- 7 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Green Communications and Networking
- Vol. 5 (2) , 765-777
CoxNet: A Computation Reuse Architecture at the Edge
In recent years, edge computing has emerged as an effective solution to extend cloud computing and satisfy the demand of applications for low latency. However, with today's explosion of innovative applications (e.g., augmented reality, natural language processing, virtual reality), processing services for mobile and smart devices have become computation-intensive, consisting of multiple interconnected computations. This coupled with the need for delay-sensitivity and high quality of service put massive pressure on edge servers. Meanwhile, tasks invoking these services may involve similar inputs that could lead to the same output. In this paper, we present CoxNet, an efficient computation reuse architecture for edge computing. CoxNet enables edge servers to reuse previous computations while scheduling dependent incoming computations. We provide an analytical model for computation reuse joined with dependent task offloading and design a novel computing offloading scheduling scheme. We also evaluate the efficiency and effectiveness of CoxNet via synthetic and real-world datasets. Our results show that CoxNet is able to reduce the task execution time up to 66% based on a synthetic dataset and up to 50% based on a real-world dataset.
- 7 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Green Communications and Networking
- Vol. 5 (2) , 765-777
CoxNet: A Computation Reuse Architecture at the Edge
In recent years, edge computing has emerged as an effective solution to extend cloud computing and satisfy the demand of applications for low latency. However, with today's explosion of innovative applications (e.g., augmented reality, natural language processing, virtual reality), processing services for mobile and smart devices have become computation-intensive, consisting of multiple interconnected computations. This coupled with the need for delay-sensitivity and high quality of service put massive pressure on edge servers. Meanwhile, tasks invoking these services may involve similar inputs that could lead to the same output. In this paper, we present CoxNet, an efficient computation reuse architecture for edge computing. CoxNet enables edge servers to reuse previous computations while scheduling dependent incoming computations. We provide an analytical model for computation reuse joined with dependent task offloading and design a novel computing offloading scheduling scheme. We also evaluate the efficiency and effectiveness of CoxNet via synthetic and real-world datasets. Our results show that CoxNet is able to reduce the task execution time up to 66% based on a synthetic dataset and up to 50% based on a real-world dataset.
- 30 October 2020
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 37 (5) , 418-433
Integrating Mobile Multimodal Interactions based on Programming By Demonstration
- 30 October 2020
- Published by Taylor & Francis in International Journal of Human–Computer Interaction
- Vol. 37 (5) , 418-433
Integrating Mobile Multimodal Interactions based on Programming By Demonstration