An official website of the United States government
Despite several calls from the community for improving the sustainability of computing, sufficient progress is yet to be made on one of the key prerequisites of sustainable computing---the ability to define and measure computing sustainability holistically. This position paper proposes metrics that aim to measure the end-to-end sustainability footprint in data centers. To enable useful sustainable computing efforts, these metrics can track the sustainability footprint at various granularities---from a single request to an entire data center. The proposed metrics can also broadly influence sustainable computing practices by incentivizing end-users and developers to participate in sustainable computing efforts in data centers.
more »
« less
Verifiable Sustainability in Data Centers
Sustainability is crucial for combating climate change and protecting our planet. While there are various systems that can pose a threat to sustainability, data centers are particularly significant due to their substantial energy consumption and environmental impact. Although data centers are becoming increasingly accountable to be sustainable, the current practice of reporting sustainability data is often mired with simple green-washing. To improve this status quo, users as well as regulators need to verify the data on the sustainability impact reported by data center operators. To do so, data centers must have appropriate infrastructures in place that provide the guarantee that the data on sustainability is collected, stored, aggregated, and converted to metrics in a secure, unforgeable, and privacy-preserving manner. Therefore, this paper first introduces the new security challenges related to such infrastructure, how it affects operators and users, and potential solutions and research directions for addressing the challenges for data centers and other industry segments.
more »
« less
- PAR ID:
- 10439011
- Date Published:
- Journal Name:
- arXivorg
- ISSN:
- 2331-8422
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Sustainability, including environmental and social sustainability, has been identified across all sectors, from government to industry to academia, as a critical area for action. Sustainability goals and actions, by necessity, require input from many fields, but engineers play a potentially outsized role due to the structures and products they build, and the associated choices they make. The Engineering for One Planet (EOP) initiative aims to address this challenge by ensuring all future engineers, no matter their discipline, are equipped with the skills, knowledge, understanding, and mindsets to design, build, and create in sustainable ways. Much has been achieved to date by the EOP initiative, through a process of multi-stakeholder engagement, in both understanding and piloting solutions to realize the EOP vision. However, in order to achieve the far reaching systemic changes desired, a roadmap for a Collective Impact-informed, cross-sector, collaborative initiative was developed. This roadmap leverages the approaches yielded from the recent National Science Foundation (NSF)-funded EOP Scaling for Impact Workshop, the lessons learned and results achieved from the initiative to date, and key considerations drawn from a Collective Impact approach that centers equity. This roadmap calls for stakeholders—including academia, industry, accrediting and professional organizations, community organizations, non-profits, funders, and those communities most impacted by the negative impacts of environmental and social sustainability challenges— to move beyond singular programmatic interventions, and instead work to collaboratively understand and construct coordinated solutions, to integrating sustainability into engineering education and the engineering profession. The roadmap’s call to action invites collaborators to join this initiative and engage with the roadmap as a starting point for their work together; the roadmap provides immediate action steps, and invites collaborators to further shape the roadmap into a collective, achievable plan for systems change, that they, their institutions/organizations, and other cross-sector collaborators can embrace. For systems change is never complete and the solutions not finite; it is only through ongoing, collective action that we can fully understand, and learn how to address the lack of sustainability in engineering as the complex, social problem it is.more » « less
-
Sustainability has become a critical focus area across the technology industry, most notably in cloud data centers. In such shared-use computing environments, there is a need to account for the power consumption of individual users. Prior work on power prediction of individual user jobs in shared environments has often focused on workloads that stress a single resource, such as CPU or DRAM. These works typically employ a specific machine learning (ML) model to train and test on the target workload for high accuracy. However, modern workloads in data centers can stress multiple resources simultaneously, and cannot be assumed to always be available for training. This paper empirically evaluates the performance of various ML models under different model settings and training data assumptions for the per-job power prediction problem using a range of workloads. Our evaluation results provide key insights into the efficacy of different ML models. For example, we find that linear ML models suffer from poor prediction accuracy (as much as 25% prediction error), especially for unseen workloads. Conversely, non-linear models, specifically XGBoost and xRandom Forest, provide reasonable accuracy (7–9% error). We also find that data-normalization and the power-prediction model formulation affect the accuracy of individual ML models in different ways.more » « less
-
IoT devices influence many different spheres of society and are predicted to have a huge impact on our future. Extracting real-time insights from diverse sensor data and dealing with the underlying uncertainty of sensor data are two main challenges of the IoT ecosystem In this paper, we propose a data processing architecture, M-DB, to effectively integrate and continuously monitor uncertain and diverse IoT data. M-DB constitutes of three components:(1) model-based operators (MBO) as data management abstractions for IoT application developers to integrate data from diverse sensors. Model-based operators can support event-detection and statistical aggregation operators,(2) M-Stream, a dataflow pipeline that combines model-based operators to perform computations reflecting the uncertainty of underlying data, and (3) M-Store, a storage layer separating the computation of application logic from physical sensor data management, to effectively deal with missing or delayed sensor data. M-DB is designed and implemented over Apache Storm and Apache Kafka, two open-source distributed event processing systems. Our illustrated application examples throughout the paper and evaluation results illustrate that M-DB provides a realtime data-processing architecture that can cater to the diverse needs of IoT applications.more » « less
-
null (Ed.)Edge data centers are an appealing place for telecommunication providers to offer in-network processing such as VPN services, security monitoring, and 5G. Placing these network services closer to users can reduce latency and core network bandwidth, but the deployment of network functions at the edge poses several important challenges. Edge data centers have limited resource capacity, yet network functions are re-source intensive with strict performance requirements. Replicating services at the edge is needed to meet demand, but balancing the load across multiple servers can be challenging due to diverse service costs, server and flow heterogeneity, and dynamic workload conditions. In this paper, we design and implement a model-based load balancer EdgeBalance for edge network data planes. EdgeBalance predicts the CPU demand of incoming traffic and adaptively distributes flows to servers to keep them evenly balanced. We overcome several challenges specific to network processing at the edge to improve throughput and latency over static load balancing and monitoring-based approaches.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
