SUSTAINABLE INTELLIGENCE AT THE EDGE: USING SUSTAINABILITY AS A METRIC

FOR AI CLOUD-EDGE DESIGN

DOWNLOAD DOI: 10.62897/COS2025.3-1.6

Author:

Mustafa Abdulkadhim*,a,b, Sandor R. Repasa
aSzéchenyi István University, Department of Telecommunications, Gyor, Hungary
bAl-Nahrain University, College of Information Engineering, Baghdad, Iraq
 abdulkadhim..mustafa@sze.hu

Abstract: The swift growth of Cloud-Edge infrastructure to support IoT and artificial intelligence workloads with low latency is exceeding the capacity of our management to control the environmental impact. Whereas there are energy-efficient hardware and software, the measures of sustainability, such as lifecycle assessment (LCA), carbon intensity, and circularity, are inconsistently defined and seldom reported. This piece of work brings sustainability to first-class design and operations measures of CloudEdge systems, inquiring how it can be directly incorporated into benchmarking and decision-making. The literature review and cross-venue trend analysis (2018-2025) have been conducted in a structured way
to map existing practices and gaps. Based on these results, we suggest the Sustainability-conscious Hybrid Edge Assessment Blueprint (SHEAB): a workflow that integrates automated lifecycle inventory, power/CO2 estimation at workload, and circular economy into what is today taken as performance benchmarking. The review is a revelation of ongoing LCA scope, boundary setting, and reporting gaps; in its turn, SHEAB unifies a small, similar metrics portfolio, e.g., Performance-per-Watt (PPW), CO2e per inference/transaction, and embodied carbon per device, and offers a sustainable evaluation pipeline. Using the blueprint to calculate representative edge workloads and device classes shows end-to-end feasibility and uncovers viable trade-offs between throughput and carbon intensity among deployment options. When sustainability is the key metric, the choices of the system change: hardware is selected, its location is different, and the timeframe is varied when CO2e and circularity can be placed next to latency and price. We end up with reporting guidelines and lessons learned to be put into action to fast-track the truly sustainable intelligent edge systems as the AI demand and its carbon footprint continue to increase.

 

REFERENCES

  • Abdulkadhim M., Hassan S., 2021, Boosting the Network Performance using Two Security Measure
    Scenarios for Service Provider Network, https://doi.org/10.24996/ijs.2021.SI.1.24.
  • Abdulkadhim M., Repas S.R., 2025, SHEAB: A Novel Automated Benchmarking Framework for Edge AI.
    Technologies, 13(11), 515, https://doi.org/10.3390/technologies13110515.
  • Abdulkadhim M., Repas S.R., 2026, Introducing LEAF: LLM Edge Assessment Framework for Generative AI
    on the Edge. Machine Learning and Knowledge Extraction, 8(2), 48, https://doi.org/10.3390/make8020048.
  • Al-Kadhimi A., Abdulkadhim M., 2021, Queueing model analysis of shopping malls in COVID-19 pandemic
    era: a case study. International Journal of Advanced Technology and Engineering Exploration, 8(85),1545-
    1556, https://doi.org/10.19101/IJATEE.2021.874672.
  • Heckmann O., Ravindran A., 2023, Evaluating Kubernetes at the Edge for Fault Tolerant Multi-Camera
    Computer Vision Applications. 2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and
    Internet Computing Workshops (CCGridW), 269–271, https://doi.org/10.1109/CCGridW59191.2023.00054.
  • Jhingran S., Bansal N., Chaturvedi R., Singh A., Arora Y., 2024, Decentralized Generative AI Model
    Deployment Using Microservices. 2024 International Conference on Artificial Intelligence and Quantum
    Computation-Based Sensor Application (ICAIQSA),https://doi.org/10.1109/ICAIQSA64000.2024.10882424.
  • Karam Z.A., Abdulkadhim M., 2022, Design, Implementation, Interfacing and Control of Internet of Robot
    Things for Assisting Robot. International Journal of Computing and Digital Systems, 11, 388–401, https://
    doi.org/10.12785/ijcds/110132
  • Kim C., Kim G.-Y., Kim S., 2023, A Microservice-based MLOps Platform for Efficient Development of AI
    Services in an Edge-Cloud Environment. 2023 14th International Conference on Information and
    Communication Technology Convergence (ICTC), 1507–1509, https://doi.org/10.1109/
    ICTC58733.2023.10392296.
  • Kum S., Oh S., Moon J., 2024. Edge AI Framework for Large Scale Smart Agriculture, in: 2024 27th
    Conference on Innovation in Clouds, Internet and Networks (ICIN). Presented at the 2024 27th Conference
    on Innovation in Clouds, Internet and Networks (ICIN), IEEE, Paris, France, 143–147, https://doi.
    org/10.1109/ICIN60470.2024.10494451
  • Nezami Z., Hafeez M., Djemame K., Zaidi S.A.R., Xu J., 2025, Descriptor: Benchmark Dataset for Generative
    AI on Edge Devices (BeDGED). IEEE Data Descriptions, 2, 50–55, https://doi.org/10.1109/
    IEEEDATA.2025.3552083.
  • Nkenyereye L., Baeg K.-J., Chung W.-Y., 2023, Deep Reinforcement Learning for Containerized Edge
    Intelligence Inference Request Processing in IoT Edge Computing. IEEE Transac5rt 2aqrde3tions on
    Services Computing, 16(6), 4328–4344, https://doi/org/10.1109/TSC.2023.3320752.
  • Seisa A.S., Satpute S.G., Nikolakopoulos G., 2022, Comparison between Docker and Kubernetes-based
    Edge Architectures for Enabling Remote Model Predictive Control for Aerial Robots. IECON 2022 – 48th
    Annual Conference of the IEEE Industrial Electronics Society, 1–6, https://doi.org/10.1109/
    IECON49645.2022.9968933.
  • Szántó P., Kiss T., Sipos K.J., 2022, Energy-efficient AI at the Edge. 2022 11th Mediterranean Conference
    on Embedded Computing (MECO), 650–655, https://doi.org/10.1109/MECO55406.2022.9797178.
  • Welagedara L., Harischandra J., Jayawardene N., 2021, Edge Intelligence Based Collaborative Learning
    System for IoT Edge. 2021 IEEE 12th Annual Information Technology, Electronics and Mobile
    Communication Conference (IEMCON), 667–672, https://doi.org/10.1109/IEMCON53756.2021.9623215.
  • Zhang Y., Pasch F., Mirus F., Scholl K.-U., Wurll C., Hein B., 2024, Conquering the Robotic Software
    Development Cycle at Scale: Using KubeROS from Simulation to Real-world Deployment. 2024 IEEE 20th
    International Conference on Automation Science and Engineering (CASE), 1503–1509, https://doi.
    org/10.1109/CASE59546.2024.10711591.

Connection

E-mail address: cos@sze.hu