Abstract
Artificial Intelligence (AI) and edge computing have recently emerged as major trends in the ICT industry. Enterprise applications increasingly make intensive use of AI technologies and are often based on multiple components running across a computing continuum. However, the heterogeneity of the technologies and software development solutions in use are evolving quickly and are still a challenge for researchers and practitioners. Indeed, lack of solutions tailored for AI applications is observed in the areas of applications placement and design space exploration with performance guarantees, both under-developed. The aim of the AI-SPRINT “Artificial Intelligence in Secure PRIvacy-preserving computing coNTinuum” project is to develop a framework composed of design and runtime management tools to seamlessly design, partition and operate Artificial Intelligence (AI) applications among the current plethora of cloud-based solutions and AI-based sensor devices (i.e., devices with intelligence and data processing capabilities), providing resource efficiency, performance, data privacy, and security guarantees. AI-SPRINT is intended to accelerate the development of AI applications, whose components are spread across the edge-cloud computing continuum, while allowing trading-off application performance and AI models accuracy. This is accomplished by the thorough suite of design tools provided by the AI-SPRINT framework, which exposes a set of programming abstractions with the goal of hiding as much as possible the computing continuum complexity, while further providing a simple interface to define desired constraints upon which the application design is guided.
Notes
- 1.
This work is funded by EU Grant no. 101016577. The AI-SPRINT website is accessible at https://ai-sprint-project.eu.
- 2.
Source code available at https://github.com/grycap/im.
- 3.
Source code available at https://github.com/ai-sprint-eu-project/OSCAR-P.
- 4.
Source code available at https://github.com/ai-sprint-eu-project/space4ai-d.
- 5.
Source code is available at https://github.com/ai-sprint-eu-project/AI-SPRINT-STUDIO.
- 6.
Examples applications are provided at https://gitlab.polimi.it/ai-sprint/ai-sprint-examples.
- 7.
OSCAR is available at http://github.com/grycap/oscar.
- 8.
SCAR is available at http://github.com/grycap/scar.
- 9.
Source code available at https://github.com/ai-sprint-eu-project/monitoring-subsystem.
- 10.
Source code is available at https://github.com/grycap/im.
- 11.
Source code is available at https://gitlab.polimi.it/ai-sprint/a-mllibrary.
- 12.
- 13.
- 14.
References
Galimberti, E., et al.: OSCAR-P and amllibrary: performance profiling and prediction of computing continua applications. In: Companion of the 2023 ACM/SPEC International Conference on Performance Engineering (ICPE 2023 Companion) (2023)
Sedghani, H., Filippini, F., Ardagna, D.: A random greedy based design time tool for AI applications component placement and resource selection in computing continua. In: IEEE Edge 2021 Proceedings (2021 IEEE International Conference On Edge Computing), pp. 32–40. Guangzhou, China (online) (2021)
Falanti, A., Lomurno, E., Samele, S., Ardagna, D., Matteucci, M.: POPNASv2: an efficient multi-objective neural architecture search technique. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2022)
Yadwadkar, N., Romero, F., Li, Q., Kozyrakis, C.: A case for managed and model-less inference serving. In: HotOS 2019 (2019)
Teerapittayanon, S., McDanel, B., Kung, H.: Distributed deep neural networks over the cloud, the edge and end devices. In: IEEE 37th ICDCS (2017)
Kang, Y., Hauswald, J., Gao, C., Rovinski, A., Mudge, T., et al.: Neurosurgeon: collaborative intelligence between the cloud and mobile edge. In: ACM ASPLOS 2017 (2017)
Li, E., Zeng, L., Zhou, Z., Chen, X.: Edge AI: on-demand accelerating deep neural network inference via edge computing. IEEE Trans. Wirel. Commun.Wirel. Commun. 19(1), 447–457 (2019)
Shiand, W., Hou, Y., Zhou, S., Niu, Z., et al.: Improving device-edge cooperative inference of deep learning via 2-step pruning. In: IEEE INFOCOM 2019 Proceedings (2019)
Huang, Y., Qiao, X., Ren, P., Liu, L., et al.: A lightweight collaborative deep neural network for the mobile web in edge cloud. IEEE Trans. Mob. Comput. (2020)
Eshratifar, A.E., Abrishami, M.S., Pedram, M.: JointDNN: an efficient training and inference engine for intelligent mobile cloud computing services. IEEE Trans. Mob. Comput.Comput. 20(2), 565–576 (2019)
Liu, D., Chen, X., Zhou, Z., Ling, Q.: HierTrain: fast hierarchical edge AI learning with hybrid parallelism in mobile-edge-cloud computing. IEEE Open J. Commun. Soc. 1, 634–645 (2020)
Disabato, S., Roveri, M., Alippi, C.: Distributed deep convolutional neural networks for the internet-of-things. IEEE Trans. Comput.Comput. 14(8), 1–14 (2015)
Madougou, S., Varbanescu, A., de Laat, C., et al.: The landscape of GPGPU performance modeling tools. J. Parallel Comput. 56, 18–33 (2016)
Lu, Z., Rallapalli, S., Chan, K., La Porta, T.: Modeling the resource requirements of convolutional neural networks on mobile devices. In: Proc. Conf. Multimedia (2017)
Gianniti, E., Zhang, L., Ardagna, D.: Performance prediction of GPU-based deep learning applications. In: 30th Int’l Symp. Computer Architecture and High Performance Computing (SBAC-PAD 2018) (2018)
Mahmoudi, N., Khazaei, H.: Temporal performance modelling of serverless computing platforms. In: Sixth International Workshop on Serverless Computing (WoSC 2020) (2020)
Mahmoudi, N., Khazaei, H.: Performance modeling of serverless computing platforms. In: IEEE Transactions on Network and Service Management (2020)
Bellendorf, J., Mann, Z.Á.: Classification of optimization problems in fog computing. Future Gener. Comput. Syst. 107, 158–176 (2020)
Balevi, E., Gitlin, R.D.: Optimizing the number of fog nodes for cloud-fog-thing networks. IEEE Access 6, 11173–11183 (2018)
Bahreini, T., Grosu, D.: Efficient placement of multi-component applications in edge computing systems. In: The Second ACM/IEEE Symposium (SEC 2017) (2017)
Wang, S., Zafer, M., Leung, K.K.: Online placement of multi-component applications in edge computing environments. IEEE Access 5, 2514–2533 (2017)
Lin, C., Khazaei, H.: Modeling and optimization of performance and cost of serverless applications. IEEE Trans. Parallel Distrib. Syst.Distrib. Syst. 32(3), 615–632 (2021)
Elgamal, T., Sandur, A., Nahrstedt, K., Agha, G.: Costless: optimizing cost of serverless computing through function fusion and placement. In: IEEE/ACM Symposium on Edge Computing (SEC) (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lattari, F., Matteucci, M., Ardagna, D. (2024). AI-SPRINT: Design and Runtime Framework for Accelerating the Development of AI Applications in the Computing Continuum. In: Barolli, L. (eds) Advanced Information Networking and Applications. AINA 2024. Lecture Notes on Data Engineering and Communications Technologies, vol 203. Springer, Cham. https://doi.org/10.1007/978-3-031-57931-8_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-57931-8_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-57930-1
Online ISBN: 978-3-031-57931-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)