carbon-aware scheduling

To address the challenge of reducing Scope 2 emissions (indirect emissions from grid electricity consumption) in manufacturing’s net-zero transition, this paper proposes a carbon-aware flow shop scheduling method. The approach jointly models real-time grid carbon intensity dynamics and on-site distributed renewable energy generation within a mixed-integer linear programming (MILP) scheduling framework. A dedicated memetic algorithm—integrating evolutionary optimization with local search—is developed to efficiently solve the resulting complex optimization problem. Experimental results demonstrate that, while maintaining near-identical production efficiency, the proposed method reduces Scope 2 emissions by up to 27.4% compared to conventional energy- or makespan-oriented scheduling policies. This work constitutes the first effort to co-model grid carbon intensity and facility-level renewable generation and embed them directly into production scheduling. It provides a theoretically grounded, practically implementable methodology and technical pathway for low-carbon production planning in manufacturing.

Existing carbon-aware schedulers treat jobs as atomic units, ignoring their DAG structure and heterogeneous resource demands across subtasks, thereby limiting carbon efficiency. Method: We model batched DAG workloads from a job-shop scheduling perspective and propose a dependency-aware carbon-aware scheduling framework that maximizes execution of critical-path tasks during low-carbon time intervals—without extending the optimal makespan. Leveraging a flexible job-shop formulation and an offline solver, we quantify the theoretical carbon-reduction upper bound attainable through structured scheduling. Contribution/Results: Our approach achieves an average 25% reduction in carbon emissions; permitting twice the optimal makespan nearly doubles emission reductions. We explicitly characterize the Pareto trade-offs among carbon emissions, energy consumption, and makespan. Experiments demonstrate that explicit modeling of task structure and server scale are decisive factors for carbon efficiency—establishing, for the first time, the fundamental limits and design principles of carbon-aware DAG scheduling.

To address high carbon emissions from DAG-based workflow scheduling in hybrid-energy data centers, this paper formulates carbon-aware scheduling under fixed task-to-processor mapping and given task ordering as an optimization problem—polynomially solvable for single processors but NP-hard for multi-processor settings. We propose CaWoSched, a general framework integrating greedy initialization with local search, and supporting exact solution via integer linear programming (ILP). Our approach explicitly models the time-varying availability of green energy and enforces task precedence constraints, maximizing green energy consumption while meeting workflow deadlines. Extensive experiments across diverse scenarios demonstrate that CaWoSched, evaluated over 16 strategy combinations, reduces carbon emissions by 23.7% on average compared to baseline algorithms. These results validate the effectiveness and robustness of carbon-aware scheduling under realistic, time-varying green energy supply profiles.

Addressing carbon emissions from energy-intensive cloud services—particularly generative AI—this work tackles the challenge of reducing operational carbon footprints while maintaining service quality and regulatory compliance. Method: We propose a carbon-aware Quality-of-Experience (QoE) orchestration framework that treats LLM response quality (e.g., output length, accuracy) as an adjustable dimension for carbon optimization. The framework dynamically adapts to real-time grid carbon intensity under latency and data locality constraints, integrating multi-timescale carbon intensity forecasting, annual hard carbon-budget-constrained multi-objective integer programming, online feedback control, and hierarchical SLA modeling. Contribution/Results: Evaluated on large-scale LLM inference workloads, our approach achieves up to 10% reduction in service-related carbon emissions—amounting to tens of thousands of tons of CO₂ annually—while preserving user availability and ensuring adherence to environmental regulations.

To address the real-time low-carbon operational demands of data centers, this paper proposes DC-CFR, a multi-agent reinforcement learning (MARL) framework that jointly optimizes carbon emissions, energy consumption, and electricity cost under dynamic weather conditions and time-varying grid carbon intensity. The method integrates renewable-energy-aware IT workload scheduling, coordinated cooling system control, and dynamic uninterruptible power supply (UPS) battery storage management. Evaluated across multiple geographic regions using real-world traces, DC-CFR achieves average annual reductions of 14.5% in carbon emissions, 14.4% in energy consumption, and 13.7% in energy cost compared to the ASHRAE baseline controller. Its core contribution is the first real-time MARL control paradigm for holistic, stack-wide co-optimization of energy efficiency, carbon footprint, and economic cost—overcoming the limitations of conventional static-threshold control strategies—and providing a deployable intelligent decision-making foundation for green data centers.

This study addresses the problem of scheduling precedence-constrained workflows in heterogeneous data centers with the dual objectives of meeting strict deadlines and minimizing carbon emissions. The authors formally prove that this problem is NP-hard and does not admit a constant-factor approximation algorithm. To tackle it, they propose a novel algorithm, Carbon-aware Workflow Mapping (CWM), which integrates dynamic programming with heuristic strategies to jointly optimize task mapping and scheduling. CWM explicitly models node-level energy heterogeneity and temporal fluctuations in renewable energy availability. Experimental results demonstrate that under a deadline constraint set at twice the baseline makespan, CWM reduces median carbon cost by 42% compared to the state-of-the-art CaWoSched algorithm, substantially improving carbon efficiency.

This work addresses the challenge of balancing emission constraints, operational cost, and service quality in dynamic power grids where carbon intensity varies over time. Traditional fixed emission rate strategies prove inadequate under such conditions. To overcome this limitation, the authors propose a time-window-based emission budgeting mechanism that replaces static rates, enabling applications to accrue emission allowances during low-carbon periods and flexibly consume them during high-carbon intervals. Integrated within a MAPE-K adaptive control architecture, the approach leverages real-time monitoring of grid carbon intensity and system power consumption to dynamically schedule resources while adhering to long-term emission caps. Simulations using six weeks of real-world data from Germany, France, and Poland demonstrate that the method improves task completion rates by up to 36% in volatile grids while matching the performance of existing approaches in stable grids, achieving effective co-optimization of emissions, cost, and performance.

This study addresses the lack of reproducible evaluation frameworks for assessing the sustainability of carbon-aware scheduling strategies in heterogeneous edge-cloud environments. To bridge this gap, we propose the first reproducible evaluation architecture supporting heterogeneous federated edge-cloud topologies, integrating an event-driven deterministic simulator, a policy hook mechanism, and heterogeneity-aware reference policies, all compatible with the Kubernetes scheduler interface. The framework holistically accounts for grid carbon intensity, power usage effectiveness (PUE), and hardware heterogeneity. Through experiments with synthetic batch workloads, we demonstrate that our approach significantly outperforms the default Kubernetes scheduler as well as state-of-the-art strategies such as KEIDS and TOPSIS/KCSS in reducing carbon emissions.