B1: Carbon-aware Multi-site Workflow Scheduling Under Uncertainty

@inproceedings{10.1007/978-3-032-35251-4_19,

title = {Carbon-Aware Mapping and Scheduling for Deadline-Constrained Workflows},

author = {Dominik Schweisgut and Anne Benoit and Yves Robert and Henning Meyerhenke},

editor = {Massimo Torquati and Gabriele Mencagli and Valeria Cardellini and Alessia Antelmi and Doriana Medić},

url = {https://link.springer.com/chapter/10.1007/978-3-032-35251-4_19},

isbn = {978-3-032-35251-4},

year  = {2026},

date = {2026-08-15},

urldate = {2027-01-01},

booktitle = {Euro-Par 2026: Parallel Processing},

pages = {270–284},

publisher = {Springer Nature Switzerland},

abstract = {As datacenters continue to grow in scale, their energy consumption and resulting carbon footprint have become pressing concerns. With the increasing share of renewable energy in a datacenter's mixed energy supply, shifting task execution to periods of high green-power availability is a promising strategy to reduce carbon emissions. However, in heterogeneous computing environments, the power consumption of compute nodes in a datacenter can also vary. In practice, workloads submitted to datacenters are often not isolated tasks, but entire workflows consisting of interdependent tasks with precedence constraints. A further challenge arises from the fact that carbon emission reductions must typically be achieved under strict workflow deadlines. In this work, we show that the problem posed by these challenges for the scheduler is NP-hard and admits no constant-factor approximation even for the uni-processor case. Motivated by this hardness, we present a novel algorithm CWM that combines carbon-aware mapping and scheduling to construct feasible solutions. Our approach integrates dynamic programming with efficient heuristics to exploit renewable energy availability and infrastructure heterogeneity. To assess the quality of the new algorithm, we evaluate it against the state-of-the-art approach $$backslashtexttt CaWoSched$$CaWoSchedand show that CWM achieves significant reductions in terms of carbon emissions in experiments. In particular, we are able to achieve a median carbon cost reduction of $$42backslash%$$42%over the best version of $$backslashtexttt CaWoSched$$CaWoSchedwhen the deadline is two times the makespan of a carbon-agnostic baseline. Note that CaWoSched itself already reduces the carbon-agnostic baseline by $$36backslash%$$36%.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{iseni2026accuracy,

title = {Accuracy versus Efficiency in Model Selection for Remote Sensing Scientific Workflows},

author = {Diellza Sherifi Iseni and Jonathan Bader and Francisco Mena and Odej Kao},

url = {https://www.computer.org/csdl/proceedings-article/wacvw/2026/914900b455/2iG0siLKTwA},

year  = {2026},

date = {2026-01-01},

urldate = {2026-01-01},

booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},

pages = {1455–1464},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{irion_optimizing_2025,

title = {Optimizing Microgrid Composition for Sustainable Data Centers},

author = {Julius Irion and Philipp Wiesner and Jonathan Bader and Odej Kao},

url = {http://arxiv.org/abs/2508.04284},

doi = {10.48550/arXiv.2508.04284},

year  = {2025},

date = {2025-11-17},

urldate = {2025-11-17},

publisher = {Sustainable Supercomputing @ International Conference for High Performance Computing, Networking, Storage, and Analysis },

abstract = {As computing energy demand continues to grow and electrical grid infrastructure struggles to keep pace, an increasing number of data centers are being planned with colocated microgrids that integrate on-site renewable generation and energy storage. However, while existing research has examined the tradeoffs between operational and embodied carbon emissions in the context of renewable energy certificates, there is a lack of tools to assess how the sizing and composition of microgrid components affects long-term sustainability and power reliability. In this paper, we present a novel optimization framework that extends the computing and energy system co-simulator Vessim with detailed renewable energy generation models from the National Renewable Energy Laboratory’s (NREL) System Advisor Model (SAM). Our framework simulates the interaction between computing workloads, on-site renewable production, and energy storage, capturing both operational and embodied emissions. We use a multi-horizon black-box optimization to explore efficient microgrid compositions and enable operators to make more informed decisions when planning energy systems for data centers.},

note = {arXiv:2508.04284 [cs]},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{will2025flora,

title = {Flora: Efficient Cloud Resource Selection for Big Data Processing via Job Classification},

author = { Jonathan Will and Lauritz Thamsen and Jonathan Bader and Odej Kao},

url = {https://arxiv.org/pdf/2502.21046},

year  = {2025},

date = {2025-05-01},

urldate = {2025-05-01},

booktitle = {IEEE International Symposium on Cluster, Cloud, and Internet Computing (CCGRID)},

publisher = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kulaginaAdaptive2025,

title = {Memory-aware Adaptive Scheduling of Scientific Workflows On Heterogeneous Architectures},

author = {Svetlana Kulagina and Anne Benoit and Henning Meyerhenke},

url = {https://ieeexplore.ieee.org/document/11044792},

year  = {2025},

date = {2025-05-01},

urldate = {2025-05-01},

booktitle = {2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)},

address = {Tromsø, Norway},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lehmannWOW2025,

title = {WOW: Workflow-Aware Data Movement and Task Scheduling for Dynamic Scientific Workflows},

author = { Fabian Lehmann and Jonathan Bader and Friedrich Tschirpke and Ninon De Mecquenem and Ansgar Lößer and Sören Becker and Katarzyna Ewa Lewińska and Lauritz Thamsen and Ulf Leser},

url = {https://ieeexplore.ieee.org/document/11044799},

year  = {2025},

date = {2025-05-01},

urldate = {2025-05-01},

booktitle = {2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)},

address = {Tromsø, Norway},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{11402160b,

title = {Optimizing Memory Allocation in Distributed Clusters with Predictive Modeling},

author = {Jonathan Bader and Edgar Blumenthal and Marten Eckardt and Justus Krebs and Joel Witzke and Xemena Wysokinska and Haci Ismail Aslan and Odej Kao},

doi = {10.1109/BigData66926.2025.11402160},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

booktitle = {2025 IEEE International Conference on Big Data (BigData)},

pages = {8219-8221},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bader2024Sizey,

title = {Sizey: Memory-Efficient Execution of Scientific Workflow Tasks},

author = {Jonathan Bader and Fabian Skalski and Fabian Lehmann and Dominik Scheinert and Jonathan Will and Lauritz Thamsen and Odej Kao},

url = {https://ieeexplore.ieee.org/document/10740856},

year  = {2024},

date = {2024-09-21},

urldate = {2024-09-21},

booktitle = {2024 IEEE International Conference on Cluster Computing (CLUSTER)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{baderloesser2024ks,

title = {KS+: Predicting Workflow Task Memory Usage Over Time},

author = {Jonathan Bader and Ansgar Lößer and Lauritz Thamsen and Björn Scheuermann and Odej Kao},

url = {https://ieeexplore.ieee.org/document/10678686},

year  = {2024},

date = {2024-09-15},

urldate = {2024-09-15},

booktitle = {2024 IEEE 20th International Conference on e-Science (e-Science)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{baderPredictDynamicMemoryRequ2023,

title = {Predicting Dynamic Memory Requirements for Scientific Workflow Tasks},

author = {Jonathan Bader and Nils Diedrich and Lauritz Thamsen and Odej Kao},

url = {https://arxiv.org/pdf/2311.08185.pdf},

year  = {2023},

date = {2023-12-20},

urldate = {2023-12-20},

booktitle = {2023 IEEE International Conference on Big Data (Big Data)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}