Maraga Alex
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Maraga Alex has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Sunday Olusegun Ojo
Durban University of Technology
2 shared publications - Fredrick Mzee Awuor
Computing Sciences, School of Information Science & Technology, Kisii University, P.O. Box 408, Kisii 40200, Kenya
1 shared publication
Latest Publications
- Open Access
Model for Green AI and Sustainable Computing: Energy-Efficient Architectures and Carbon-Aware Deployment in Industrial Systems
The fast growth of AI and large-scale industrial compute infrastructures has led to unsustainable increases in energy consumption and greenhouse gas emissions on a global scale, creating serious sustainability issues in today’s modern cloud computing. The proposed hybrid framework called the Hierarchical Clustering Deep Q-Network Carbon-Aware Placement System (HC-DQNCAPS) was developed as a means to combine energy efficient design with carbon-aware deployment strategies to support intelligent, adaptive and environmentally sustainable workload scheduling and resource allocation for industrial computing systems. This framework uses real time metrics of resource utilization (server and network) and information about carbon intensity to improve the distribution of workloads across geographically distributed cloud and hybrid infrastructures through both Hierarchical Agglomerative Clustering (HAC)- and Deep Q-Network (DQN)-based reinforcement learning models. Multi-objective optimization is leveraged to optimize energy usage, carbon emissions and SLA violations while optimizing resource utilization. The HC-DQNCAPS architecture significantly outperformed such work practices as FCFS, Energy-Aware VM Allocation, Carbon-Unaware RL, PPO, DDQN and MADRL Scheduling, with SLA breaches always less than 5%, and with energy utilization consistently reduced by 30–35%, carbon emissions reduced by 25–30% and resource utilization increased by +20%. The model’s significance and stability were demonstrated using both ANOVA and Wilcoxon signed-rank statistical tests to be significant (p < 0.05) at 95% confidence intervals. Overall, the findings show that there is potential for implementing carbon-aware AI methods in order to maintain economic viability for all computing systems involved in the industrial cloud.
Open AccessModel for Green AI and Sustainable Computing: Energy-Efficient Architectures and Carbon-Aware Deployment in Industrial Systems
The fast growth of AI and large-scale industrial compute infrastructures has led to unsustainable increases in energy consumption and greenhouse gas emissions on a global scale, creating serious sustainability issues in today’s modern cloud computing. The proposed hybrid framework called the Hierarchical Clustering Deep Q-Network Carbon-Aware Placement System (HC-DQNCAPS) was developed as a means to combine energy efficient design with carbon-aware deployment strategies to support intelligent, adaptive and environmentally sustainable workload scheduling and resource allocation for industrial computing systems. This framework uses real time metrics of resource utilization (server and network) and information about carbon intensity to improve the distribution of workloads across geographically distributed cloud and hybrid infrastructures through both Hierarchical Agglomerative Clustering (HAC)- and Deep Q-Network (DQN)-based reinforcement learning models. Multi-objective optimization is leveraged to optimize energy usage, carbon emissions and SLA violations while optimizing resource utilization. The HC-DQNCAPS architecture significantly outperformed such work practices as FCFS, Energy-Aware VM Allocation, Carbon-Unaware RL, PPO, DDQN and MADRL Scheduling, with SLA breaches always less than 5%, and with energy utilization consistently reduced by 30–35%, carbon emissions reduced by 25–30% and resource utilization increased by +20%. The model’s significance and stability were demonstrated using both ANOVA and Wilcoxon signed-rank statistical tests to be significant (p < 0.05) at 95% confidence intervals. Overall, the findings show that there is potential for implementing carbon-aware AI methods in order to maintain economic viability for all computing systems involved in the industrial cloud.
- Top Cited PapersOpen Access
Carbon-Aware, Energy-Efficient, and SLA-Compliant Virtual Machine Placement in Cloud Data Centers Using Deep Q-Networks and Agglomerative Clustering
The fast expansion of cloud computing has raised carbon emissions and energy usage in cloud data centers, so creative solutions for sustainable resource management are more necessary. This work presents a new algorithm—Carbon-Aware, Energy-Efficient, and SLA-Compliant Virtual Machine Placement using Deep Q-Networks (DQNs) and Agglomerative Clustering (CARBON-DQN)—that intelligibly balances environmental sustainability, service level agreement (SLA), and energy efficiency. The method combines a deep reinforcement learning model that learns optimum placement methods over time, carbon-aware data center profiling, and the hierarchical clustering of virtual machines (VMs) depending on resource constraints. Extensive simulations show that CARBON-DQN beats conventional and state-of-the-art algorithms like GRVMP, NSGA-II, RLVMP, GMPR, and MORLVMP very dramatically. Among many virtual machine configurations—including micro, small, high-CPU, and extra-large instances—it delivers the lowest carbon emissions, lowered SLA violations, and lowest energy usage. Driven by real-time input, the adaptive decision-making capacity of the algorithm allows it to dynamically react to changing data center circumstances and workloads. These findings highlight how well CARBON-DQN is a sustainable and intelligent virtual machine deployment system for cloud systems. To improve scalability, environmental effect, and practical applicability even further, future work will investigate the integration of renewable energy forecasts, dynamic pricing models, and deployment across multi-cloud and edge computing environments.
Top Cited PapersOpen AccessCarbon-Aware, Energy-Efficient, and SLA-Compliant Virtual Machine Placement in Cloud Data Centers Using Deep Q-Networks and Agglomerative Clustering
The fast expansion of cloud computing has raised carbon emissions and energy usage in cloud data centers, so creative solutions for sustainable resource management are more necessary. This work presents a new algorithm—Carbon-Aware, Energy-Efficient, and SLA-Compliant Virtual Machine Placement using Deep Q-Networks (DQNs) and Agglomerative Clustering (CARBON-DQN)—that intelligibly balances environmental sustainability, service level agreement (SLA), and energy efficiency. The method combines a deep reinforcement learning model that learns optimum placement methods over time, carbon-aware data center profiling, and the hierarchical clustering of virtual machines (VMs) depending on resource constraints. Extensive simulations show that CARBON-DQN beats conventional and state-of-the-art algorithms like GRVMP, NSGA-II, RLVMP, GMPR, and MORLVMP very dramatically. Among many virtual machine configurations—including micro, small, high-CPU, and extra-large instances—it delivers the lowest carbon emissions, lowered SLA violations, and lowest energy usage. Driven by real-time input, the adaptive decision-making capacity of the algorithm allows it to dynamically react to changing data center circumstances and workloads. These findings highlight how well CARBON-DQN is a sustainable and intelligent virtual machine deployment system for cloud systems. To improve scalability, environmental effect, and practical applicability even further, future work will investigate the integration of renewable energy forecasts, dynamic pricing models, and deployment across multi-cloud and edge computing environments.