Latency-Aware Edge–Cloud Task Placement for Reliable Sensor Stream Analytics Under Variable Network Conditions
Keywords:
Computation offloading, Earliest-deadline-first scheduling, Fog computing, Internet of things, Markov-modulated Poisson processAbstract
Background: Sensor analytics increasingly spans devices, edge gateways, and the cloud. Sending every task to the cloud exposes it to wide-area delay and congestion, whereas running everything at the edge overloads limited processors, and both choices cause missed deadlines.
Objectives: This study proposes Latency-Aware Deadline-driven Placement (LADP), an interpretable policy for deciding where each sensor-analytics task should run, and quantifies its benefits and costs.
Methodology: For each arriving task, LADP predicts completion times at the edge and in the cloud from queue backlogs, exponentially weighted estimates of round-trip time and bandwidth, and profiled compute demand; it restricts the choice to targets predicted to meet the deadline, selects among them by a latency-plus-bandwidth cost, and serves both the edge processor and the uplink in earliest-deadline-first order. An event-driven simulator with four task classes, bursty arrivals, a four-core edge server, a shared uplink, and a wide-area network with congestion episodes was used for 1,130 paired runs.
Results: LADP had the lowest deadline-miss ratio at every load, round-trip time, and bandwidth tested. At 10 tasks per second, it missed 11.0% of deadlines, versus 16.3% for size-threshold offloading and 65.1% for cloud-only execution, and reduced 95th-percentile latency by 44% and halved uplink traffic relative to threshold offloading.
Conclusions: Placement and deadline-aware scheduling should be designed together; better network estimation is the main avenue for improvement.
References
W. Z. Khan, E. Ahmed, S. Hakak, I. Yaqoob, and A. Ahmed, “Edge Computing: A Survey,” Future Generation Computer Systems, vol. 97, pp. 219–235, Aug. 2019.
M. Satyanarayanan, “How We Created Edge Computing,” Nature Electronics, vol. 2, no. 1, pp. 42–42, Jan. 2019.
B. Varghese and R. Buyya, “Next Generation Cloud Computing: New Trends and Research Directions,” Future Generation Computer Systems, vol. 79, no. 3, pp. 849–861, Feb. 2018.
N. Abbas, Y. Zhang, A. Taherkordi, and T. Skeie, “Mobile Edge Computing: A Survey,” IEEE Internet of Things Journal, vol. 5, no. 1, pp. 450–465, Feb. 2018.
C.-H. Hong and B. Varghese, “Resource Management in Fog/Edge Computing,” ACM Computing Surveys, vol. 52, no. 5, pp. 1–37, Sept. 2019.
H. Lin, S. Zeadally, Z. Chen, L. Houda, and L. Wang, “A Survey on Computation Offloading Modeling for Edge Computing,” Journal of Network and Computer Applications, vol. 169, p. 102781, Nov. 2020.
L. Huang, S. Bi, and Y.-J. A. Zhang, “Deep Reinforcement Learning for Online Computation Offloading in Wireless Powered Mobile-Edge Computing Networks,” IEEE Transactions on Mobile Computing, vol. 19, no. 11, pp. 2581–2593, Nov. 2020.
A. Shakarami, M. Ghobaei-Arani, and A. Shahidinejad, “A Survey on the Computation Offloading Approaches in Mobile Edge Computing: A Machine Learning-Based Perspective,” Computer Networks, vol. 182, p. 107496, Dec. 2020.
J. Wang, J. Hu, G. Min, A. Y. Zomaya, and N. Georgalas, “Fast Adaptive Task Offloading in Edge Computing Based on Meta Reinforcement Learning,” IEEE Transactions on Parallel and Distributed Systems, vol. 32, no. 1, pp. 242–253, Jan. 2021.
S. Deng, H. Zhao, W. Fang, J. Yin, S. Dustdar, and A. Y. Zomaya, “Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence,” IEEE Internet of Things Journal, vol. 7, no. 8, pp. 7457–7469, Aug. 2020.
Z. Zhou, X. Chen, E. Li, L. Zeng, K. Luo, and J. Zhang, “Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing,” Proceedings of the IEEE, vol. 107, no. 8, pp. 1738–1762, Aug. 2019.
K. Kaffes, T. Chong, J. T. Humphries, A. Belay, D. Mazières, and C. Kozyrakis, “Shinjuku: Preemptive scheduling for {μsecond-scale} tail latency,” In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19), 2019, pp. 345-360.
R. Mahmud, K. Ramamohanarao, and R. Buyya, “Application Management in Fog Computing Environments,” ACM Computing Surveys, vol. 53, no. 4, pp. 1–43, July 2020.
J. Meng, H. Tan, C. Xu, W. Cao, L. Liu, and B. Li, “Dedas: Online Task Dispatching and Scheduling With Bandwidth Constraint in Edge Computing,” in IEEE INFOCOM 2019 - IEEE Conference on Computer Communications, IEEE, Apr. 2019, pp. 2287–2295.
R. Mahmud, K. Ramamohanarao, and R. Buyya, “Application Management in Fog Computing Environments,” ACM Computing Surveys, vol. 53, no. 4, pp. 1–43, July 2020.
C. R. Harris et al., “Array Programming With NumPy,” Nature, vol. 585, no. 7825, pp. 357–362, Sept. 2020.
P. Virtanen et al., “SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python,” Nature Methods, vol. 17, no. 3, pp. 261–272, Feb. 2020.
