Abstract
Artificial intelligence-generated image content (AIGIC) is produced through the extraction of features and patterns from a vast image dataset, requiring substantial computational resources for training. Due to the limited computational resources of terminal devices, efficiently processing and responding to AIGIC has emerged as a critical concern in current research. To address this challenge, the present paper proposed the utilization of edge computing technology. Edge computing enables the offloading of certain training tasks to edge nodes, facilitating expedited task offloading strategies that empower terminal devices to generate image content efficiently. Building upon the edge serverless architecture, this paper introduces an edge serverless computing framework based on Web Assembly (WASM). Notably, this framework effectively resolves the latency issue associated with container cold start in serverless computing. Additionally, to enhance the collaborative capabilities of edge nodes, entropy-based Proximal Policy Optimization (E-PPO2) is proposed. This algorithm enables each edge node to share global rewards, continually update parameters, and ultimately derive the optimal response strategy, thereby harnessing edge device resources to their fullest potential. Finally, the efficacy of the proposed serverless computing architecture based on WASM is demonstrated through the evaluation of 13 benchmark functions. Comparative analyses with four task offloading algorithms highlight that the E-PPO2 algorithm, proposed in this article, significantly reduces task execution latency, facilitating rapid processing and response in AIGIC scenarios.
Similar content being viewed by others
Data availability
The data that support the findings of this study are available in “Serverless-faas-workbench” at https://github.com/ddps-lab/serverless-faas-workbench, reference number [35].
References
Shi, W., Zhang, X., Yifan, W., Zhang, Q.: Edge computing: state-of-the-art and future directions. J. Comput. Res. Dev. 56, 69–89 (2019)
Aslanpour, M.S., Toosi, A.N., Cicconetti, C., Javadi, B., Sbarski, P.: Serverless edge computing: vision and challenges. In: Proc. 2021 Australasian Computer Science Week Multiconference (2021)
Hellerstein, J.M., Faleiro, J., Gonzalez, J.E., Schleier-Smith, J., Sreekanti, V., Tumanov, A., Wu, C.: Serverless Computing: One Step Forward, Two Steps Back. arXiv preprint (2018)
Kjorveziroski, V., Canto, C.B., Roig, P.J., Gilly, K., Mishev, A., Trajkovikj, V., Filiposka, S.: IoT serverless computing at the edge: open issues and research direction. Trans. Netw. Commun. 9, 1–33 (2021)
Mendki, P.: Evaluating web assembly enabled serverless approach for edge computing. In: Proc. 2020 IEEE cloud summit. IEEE (2020)
Webassembly. In: Book Webassembly, vol 2023, Series Webassembly (2020). https://developer.mozilla.org/en-US/docs/WebAssembly
Wu, J., Gan, W., Chen, Z., Wan, S., Lin, H.: AI-Generated Content (AIGC): A Survey. arXiv preprint arXiv:2304.06632 (2023)
Liu, G., Du, H., Niyato, D., Kang, J., Xiong, Z., Kim, D.I.: Semantic Communications for Artificial Intelligence Generated Content (AIGC) Toward Effective Content Creation. arXiv preprint arXiv:2308.04942 (2023)
Wen, J., Kang, J., Xu, M., Du, H., Xiong, Z., Zhang, Y., Niyato, D.: Freshness-aware incentive mechanism for mobile AI-generated content (AIGC) networks. In: 2023 IEEE/CIC International Conference on Communications in China (ICCC), pp. 1–6. IEEE (2023)
Wen, J., Liu, Y., Chen, Z., Chen, J., Ma, Y.: Characterizing commodity serverless computing platforms. J. Softw. Evol. Process (2021). https://doi.org/10.1002/smr.2394
AWS IOT Greengrass—Amazon Web Services. In: Book AWS Iot Greengrass—Amazon Web Services, vol. 2023. Series AWS IOT Greengrass—Amazon Web Services (2020). https://aws.amazon.com/greengrass
IOT edge. Microsoft azure. In: Book IOT edge. Microsoft azure, vol. 2023. Series IOT edge. Microsoft azure (2020). https://azure.microsoft.com/en-us/services/iot-edge
Kjorveziroski, V., Filiposka, S.: Kubernetes distributions for the edge: serverless performance evaluation. J. Supercomput. 78(11), 13728–13755 (2022)
Baresi, L., Mendonça, D.F.: Towards a serverless platform for edge computing. In: Proc. 2019 IEEE International Conference on Fog Computing (ICFC) (2019)
Mendki, P.: Blockchain enabled IoT edge computing. In: Proceedings of the 2019 International Conference on Blockchain Technology (2019)
Nastic, S., Rausch, T., Scekic, O., Dustdar, S., Gusev, M., Koteska, B.: A serverless real-time data analytics platform for edge computing. IEEE Internet Comput 21(4), 64–71 (2017)
Mohanty, S.K., Premsankar, G., di Francesco, M.: An evaluation of open source serverless computing frameworks. In: 2018 IEEE International Conference on Cloud Computing Technology and Science (CloudCom) (2018)
Mendki, P.: Docker container-based analytics at IoT edge video analytics use case. In: Proc. 2018 3rd International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU) (2018)
Raith, P., Nastic, S., Dustdar, S.: Serverless edge computing—where we are and what lies ahead. IEEE Internet Comput. 27(3), 50–64 (2023)
Haas, A., Rossberg, A., Schuff, D.L., Titzer, B.L., Holman, M., Dan Gohman, E.A.: Bringing the web up to speed with WebAssembly. In: Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation (2017)
Long, J., Tai, H., Hsieh, S., Yuan, M.J.: A lightweight design for serverless function as a service. IEEE Softw. 38(1), 75–80 (2020)
Kjorveziroski, V., Filiposka, S.: WebAssembly as an enabler for next generation serverless computing. J Grid Comput (2023). https://doi.org/10.1007/s10723-023-09669-8
Hall, A., Ramachandran, U.: An execution model for serverless functions at the edge. In: Proceedings of the International Conference on Internet of Things Design and Implementation, pp. 225–236 (2019)
Hockley, D., Williamson, C.: Benchmarking runtime scripting performance in Wasmer. In: Proc. Companion of the 2022 ACM/SPEC International Conference on Performance Engineering (2022)
Jangda, A., Powers, B., Berger, E.D., Guha, A.: Not so fast: analyzing the performance of {WebAssembly} vs. native code. In: Proc. 2019 USENIX Annual Technical Conference (USENIX ATC 19), pp. 107–120 (2019)
Kjorveziroski, V., Filiposka, S.: WebAssembly orchestration in the context of serverless computing. J. Netw. Syst. Manage. (2023). https://doi.org/10.1007/s10922-023-09753-0
Ménétrey, J., Pasin, M., Felber, P., Schiavoni, V.: WebAssembly as a common layer for the cloud-edge continuum. In: Proceedings of the 2nd Workshop on Flexible Resource and Application Management on the Edge (2022)
Wang, X., Zhao, K., Bin, Q.: Overview of WebAssembly application research for edge serverless computing. Comput. Eng. Appl. 59(11), 28–36 (2023)
Gackstatter, P., Frangoudis, P.A., Dustdar, S.: Pushing serverless to the edge with webassembly runtimes. In: Proc. 2022 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid) (2022)
Ma, Z., Liu, B., Lin, W., Li, J.: Overview of resource scheduling on server free platforms. Comput. Sci 48(4), 261–267 (2021). https://doi.org/10.11896/jsjkx.200800023
Yang, B., Zhao, S., Liu, F.: Overview of serverless computing technology research. Comput. Eng. Sci. 44(4), 611–619 (2022)
Shahrad, M., Goiri, R.F.I., Chaudhry, G., Batum, P., Cooke, J., Laureano, E., Tresness, C., Russinovich, M., Bianchini, R.: Serverless in the wild: characterizing and optimizing the serverless workload at a large cloud provider. In: Proc. 2020 USENIX Annual Technical Conference (USENIX ATC 20), pp. 205–218 (2020)
Wen, J., Chen, Z., Jin, X., Liu, X.: Rise of the planet of serverless computing: a systematic review. ACM Trans. Softw. Eng. Methodol. 32(5), 1–61 (2023)
Mampage, A., Karunasekera, S., Buyya, R.: Deep reinforcement learning for application scheduling in resource-constrained, multi-tenant serverless computing environments. Future Gener. Comput. Syst. 143, 277–292 (2023)
Kim, J., Lee, K.: Functionbench: a suite of workloads for serverless cloud function service. In: Proc. 2019 IEEE 12th International Conference on Cloud Computing (CLOUD) (2019)
Ciuperca, G., Girardin, V., Lhote, L.: Computation and estimation of generalized entropy rates for denumerable Markov chains. IEEE Trans. Inf. Theory 57(7), 4026–4034 (2011)
Ren, Y., Yu, X., Chen, X., Guo, S., Xue-Song, Q.: Vehicular network edge intelligent management: a deep deterministic policy gradient approach for service offloading decision. In: Proc. 2020 International Wireless Communications and Mobile Computing (IWCMC) (2020)
Chen, X., Zhang, H., Wu, C., Mao, S., Ji, Y., Bennis, M.: Optimized computation offloading performance in virtual edge computing systems via deep reinforcement learning. IEEE Internet Things 6(3), 4005–4018 (2018)
Funding
Natural Science Foundation of Hebei Province, Grant/Award Number: F2021207005.
Author information
Authors and Affiliations
Contributions
Suzhen Wang proposed the idea of the paper. Suzhen Wang and Yongchen Deng conducted mathematical modeling. Suzhen Wang, Yongchen Deng and Lisha Hu conducted experiments. Lisha Hu and Ning Cao analyzed the results. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, S., Deng, Y., Hu, L. et al. Edge-computing-assisted intelligent processing of AI-generated image content. J Real-Time Image Proc 21, 39 (2024). https://doi.org/10.1007/s11554-023-01400-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11554-023-01400-w