Abstract
Driven by recent advances in networking and computing technologies, distributed application scenarios are increasingly deployed on resource-constrained processing platforms. This includes networked embedded and cyber-physical systems as well as edge computing in mobile applications and the Internet of Things (IoT). In such resource-constrained Networks-of-Systems (NoS), computation and communication workloads need to be carefully co-optimized yet are tightly coupled. How to optimally partition and schedule application tasks among an appropriately designed NoS architecture requires a simultaneous consideration of design parameters from applications and processing platforms all the way to network configurations. Traditionally, however, systems and networks are designed in isolation and combined in an ad hoc manner, which ignores joint effects and optimization opportunities. To systematically explore and optimize NoS design spaces, a higher level of design abstraction on top of traditional system and network design is required.
In this article, we propose a novel network-level design methodology for resource-constrained NoS optimization and design space exploration. A key component in such a design flow is fast yet accurate network/system co-simulation to rapidly evaluate NoS parameters with high fidelity. We first introduce a novel NoS simulator (NoSSim) that integrates source-level simulation models of applications with a host-compiled system simulation platform and a reconfigurable network simulation backplane to accurately capture system and network interactions. The co-simulation platform is further combined with model generation tools and a multi-objective genetic search algorithm to provide a comprehensive and fully automated NoS design space exploration framework. Finally, we apply our network-level design flow on several state-of-art IoT/mobile design case studies. Results show that NoSSim can achieve more than 86% simulation accuracy on average as compared to a real-world edge device cluster, where sensitivities to various design parameters are faithfully captured with high fidelity. When applying our network-level design space exploration methodology, design decisions are automatically optimized, where non-obvious NoS configurations are discovered outperforming manually designed solutions by more than 45%.
- Lan S. Bai, Robert P. Dick, Pai H. Chou, and Peter A. Dinda. 2011. Automated construction of fast and accurate system-level models for wireless sensor networks. In Proceedings of the Design, Automation and Test in Europe (DATE’11).Google Scholar
- A. Bakshi and V. K. Prasanna. 2004. Algorithm design and synthesis for wireless sensor networks. In Proceedings of the International Conference on Parallel Processing (ICPP’04).Google Scholar
- Amal Banerjee and Andreas Gerstlauer. 2009. Transaction level modeling of best-effort channels for networked embedded devices. In Proceedings of the International Embedded Systems Symposium (IESS’09).Google Scholar
Cross Ref
- Nicola Bombieri, Franco Fummi, and Davide Quaglia. 2010. System/network design-space exploration based on TLM for networked embedded systems. ACM Trans. Embed. Comput. Syst. 9, 4 (Apr. 2010), 37:1--37:32.Google Scholar
Digital Library
- A. Bonivento, L. P. Carloni, and A. Sangiovanni-Vincentelli. 2006. Platform-based design of wireless sensor networks for industrial applications. In Proceedings of the Design, Automation and Test in Europe (DATE’06).Google Scholar
- Oliver Bringmann, Wolfgang Ecker, Andreas Gerstlauer, Ajay Goyal, Daniel Mueller-Gritschneder, Prasanth Sasidharan, and Simranjit Singh. 2015. The next generation of virtual prototyping: Ultra-fast yet accurate simulation of HW/SW systems. In Proceedings of the Design, Automation and Test in Europe (DATE’15).Google Scholar
Cross Ref
- Luca Catarinucci, Danilo De Donno, Luca Mainetti, Luca Palano, Luigi Patrono, Maria Laura Stefanizzi, and Luciano Tarricone. 2015. An IoT-aware architecture for smart healthcare systems. IEEE Internet Things J. 2, 6 (2015), 515--526.Google Scholar
Cross Ref
- Zhaolin Cheng, Dhanya Devarajan, and Richard J. Radke. 2007. Determining vision graphs for distributed camera networks using feature digests. EURASIP J. Appl. Signal Process. 1 (2007), 220--220.Google Scholar
- Markus Damm, Javier Moreno, Jan Haase, and Christoph Grimm. 2010. Using transaction level modeling techniques for wireless sensor network simulation. In Proceedings of the Design, Automation and Test in Europe (DATE’10).Google Scholar
Cross Ref
- K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan. 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evolution. Comput. 6, 2 (Apr. 2002), 182--197.Google Scholar
Digital Library
- Dhanya Devarajan, Richard J. Radke, and Haeyong Chung. 2006. Distributed metric calibration of ad hoc camera networks. ACM Trans. Sensor Netw.2, 3 (2006), 380--403.Google Scholar
Digital Library
- Charalampos Doukas and Ilias Maglogiannis. 2012. Bringing IoT and cloud computing towards pervasive healthcare. In Proceedings of the Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS’12).Google Scholar
Digital Library
- Wan Du, Fabien Mieyeville, David Navarro, and Ian O’Connor. 2011. IDEA1: A validated SystemC-based system-level design and simulation environment for wireless sensor network. EURASIP J. Wireless Commun. Netw. 1 (2011), 143.Google Scholar
Cross Ref
- C. Erbas, S. Cerav-Erbas, and A. D. Pimentel. 2006. Multiobjective optimization and evolutionary algorithms for the application mapping problem in multiprocessor system-on-chip design. IEEE Trans. Evolution. Comput. 10, 3 (June 2006), 358--374.Google Scholar
Digital Library
- Konstantinos P. Ferentinos and Theodore A. Tsiligiridis. 2007. Adaptive design optimization of wireless sensor networks using genetic algorithms. Comput. Netw. 51, 4 (Mar. 2007), 1031--1051.Google Scholar
Digital Library
- Félix-Antoine Fortin, François-Michel De Rainville, Marc-André Gardner, Marc Parizeau, and Christian Gagné. 2012. DEAP: Evolutionary algorithms made easy. J. Mach. Learn. Res. 13 (July 2012), 2171--2175.Google Scholar
- Franco Fummi, Davide Quaglia, and Francesco Stefanni. 2008. A systemc-based framework for modeling and simulation of networked embedded systems. In Proceedings of the Forum on Specification, Verification and Design Languages (FDL’08).Google Scholar
Cross Ref
- Andreas Gerstlauer, Suhas Chakravarty, Manan Kathuria, and Parisa Razaghi. 2012. Abstract system-level models for early performance and power exploration. In Proceedings of the Asia and South Pacific Design Automation Conference (ASP-DAC’12).Google Scholar
Cross Ref
- A. Gerstlauer, C. Haubelt, A. D. Pimentel, T. P. Stefanov, D. D. Gajski, and J. Teich. 2009. Electronic system-level synthesis methodologies. IEEE Trans. Comput.-Aided Design Integr. Circ. Syst. 28, 10 (Oct 2009), 1517--1530.Google Scholar
- Yiping Kang, Johann Hauswald, Cao Gao, Austin Rovinski, Trevor Mudge, Jason Mars, and Lingjia Tang. 2017. Neurosurgeon: Collaborative intelligence between the cloud and mobile edge. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS’17).Google Scholar
Digital Library
- Jing Lin, Andreas Gerstlauer, and Brian L. Evans. 2012. Communication-aware heterogeneous multiprocessor mapping for real-time streaming systems. J. Signal Process. Syst. 69, 3 (Dec. 2012), 279--291.Google Scholar
- lwip 2018. lwIP—A Lightweight TCP/IP stack. Retrieved from http://savannah.nongnu.org/projects/lwip.Google Scholar
- Jiachen Mao, Xiang Chen, Kent W. Nixon, Christopher Krieger, and Yiran Chen. 2017. MoDNN: Local distributed mobile computing system for deep neural network. In Proceedings of the Design, Automation and Test in Europe (DATE’17).Google Scholar
Cross Ref
- Ivan Minakov and Roberto Passerone. 2013. PASES: An energy-aware design space exploration framework for wireless sensor networks. J. Syst. Architect. 59, 8 (2013), 626--642.Google Scholar
Digital Library
- George B. Moody and Roger G. Mark. 2001. The impact of the MIT-BIH arrhythmia database. IEEE Eng. Med. Biol. Mag. 20, 3 (2001), 45--50.Google Scholar
Cross Ref
- Daniel Mueller-Gritschneder and Andreas Gerstlauer. 2017. Host-Compiled Simulation. Springer Netherlands, Dordrecht, 1--27.Google Scholar
- Majid Nabi, Milos Blagojevic, Twan Basten, Marc Geilen, and Teun Hendriks. 2009. Configuring multi-objective evolutionary algorithms for design-space exploration of wireless sensor networks. In Proceedings of the ACM Workshop on Performance Monitoring and Measurement of Heterogeneous Wireless and Wired Networks.Google Scholar
Digital Library
- ns3 2019. NS-3 Discrete-Event Network Simulator. Retrieved from http://www.nsnam.org.Google Scholar
- Peter Ochs, Jitendra Malik, and Thomas Brox. 2014. Segmentation of moving objects by long term video analysis. IEEE Trans. Pattern Anal. Mach. Intell. 36, 6 (2014), 1187--1200.Google Scholar
Digital Library
- A. D. Pimentel. 2017. Exploring exploration: A tutorial introduction to embedded systems design space exploration. IEEE Design Test 34, 1 (Feb. 2017), 77--90.Google Scholar
Cross Ref
- A. Pinto, M. D’Angelo, C. Fischione, E. Scholte, and A. Sangiovanni-Vincentelli. 2008. Synthesis of embedded networks for building automation and control. In Proceedings of the American Control Conference.Google Scholar
- Markus Quaritsch, Markus Kreuzthaler, Bernhard Rinner, Horst Bischof, and Bernhard Strobl. 2007. Autonomous multicamera tracking on embedded smart cameras. EURASIP J. Embed. Syst. 1 (2007), 1--10.Google Scholar
Digital Library
- Parisa Razaghi and Andreas Gerstlauer. 2014. Host-compiled multicore system simulation for early real-time performance evaluation. ACM Trans. Embed. Comput. Syst. 13, 5s (Dec. 2014), 166:1--166:26.Google Scholar
Digital Library
- Joseph Redmon and Ali Farhadi. 2017. YOLO9000: Better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17).Google Scholar
Cross Ref
- K. Romer and F. Mattern. 2004. The design space of wireless sensor networks. IEEE Wireless Commun. 11, 6 (Dec. 2004), 54--61.Google Scholar
Digital Library
- Farzad Samie, Vasileios Tsoutsouras, Sotirios Xydis, Lars Bauer, Dimitrios Soudris, and Jörg Henkel. 2016. Distributed QoS management for internet of things under resource constraints. In Proceedings of the International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS’16).Google Scholar
Digital Library
- Parinaz Sayyah, Mihai T. Lazarescu, Davide Quaglia, Emad Ebeid, Sara Bocchio, and Alberto Rosti. 2012. Network-aware design-space exploration of a power-efficient embedded application. In Proceedings of the International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS’12).Google Scholar
Digital Library
- Jürgen Sommer, Simon Lüders, Suguna Subramanian, Stephen Schmitt, and Wolfgang Rosenstiel. 2009. SySifoS: SystemC simulator for sensor and communication systems. In Proceedings of the International Conference on Mobile Technology, Application 8 Systems.Google Scholar
Digital Library
- Thilo Streichert, Michael Glaß, Christian Haubelt, and Jürgen Teich. 2007. Design space exploration of reliable networked embedded systems. J. Syst. Architect. 53, 10 (2007), 751--763.Google Scholar
Digital Library
- Surat Teerapittayanon, Bradley McDanel, and Hsiang-Tsung Kung. 2017. Distributed deep neural networks over the cloud, the edge and end devices. In Proceedings of the International Conference on Distributed Computing Systems (ICDCS’17).Google Scholar
Cross Ref
- András Varga and Rudolf Hornig. 2008. An overview of the OMNeT++ simulation environment. In Proceedings of the International Conference on Simulation Tools and Techniques (SIMUtools’08).Google Scholar
Cross Ref
- Guohui Wang. 2018. ezSIFT: An easy-to-use standalone SIFT library. Retrieved from https://github.com/robertwgh/ezSIFT/.Google Scholar
- Zhuoran Zhao. 2018. DeepThings. Retrieved from https://github.com/SLAM-Lab/DeepThings.Google Scholar
- Zhuoran Zhao. 2019. NoSDSE. Retrieved from https://github.com/SLAM-Lab/NoSDSE.Google Scholar
- Zhuoran Zhao. 2019. NoSSim. Retrieved from https://github.com/SLAM-Lab/NoSSim.Google Scholar
- Zhuoran Zhao, Andreas Gerstlauer, and Lizy K. John. 2017. Source-level performance, energy, reliability, power and thermal (PERPT) simulation. IEEE Trans. Comput.-Aided Design Integr. Circ. Syst. 36, 2 (Feb. 2017), 299--312.Google Scholar
- Zhuoran Zhao, Kamyar Mirzazad, and Andreas Gerstlauer. 2018. DeepThings: Distributed adaptive deep learning inference on resource-constrained IoT edge clusters. IEEE Trans. Comput.-Aided Design Integr. Circ. Syst. 37, 11 (Nov. 2018), 2348--2359.Google Scholar
Cross Ref
- Zhuoran Zhao, Vasileios Tsoutsouras, Dimitrios Soudris, and Andreas Gerstlauer. 2017. Network/system co-simulation for design space exploration of IoT applications. In Proceedings of the International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS’17).Google Scholar
Cross Ref
- Eckart Zitzler, Marco Laumanns, and Lothar Thiele. 2001. SPEA2: Improving the strength pareto evolutionary algorithm. In Proceedings of the EUROGEN Conference: Evolutionary Methods for Design, Optimization and Control with Applications to Industrial Problems (2001).Google Scholar
Index Terms
Network-level Design Space Exploration of Resource-constrained Networks-of-Systems
Recommendations
Interdigitation for effective design space exploration using iSIGHT
Optimization studies for nonlinear constrained problems (i.e. most complex engineering design problems) have repeatedly shown that (i) no single optimization technique performs best for all design problems, and (ii) in most cases, a mix of techniques ...
Visualization of Computer Architecture Simulation Data for System-Level Design Space Exploration
SAMOS '09: Proceedings of the 9th International Workshop on Embedded Computer Systems: Architectures, Modeling, and SimulationSystem-level computer architecture simulations create large volumes of simulation data to explore alternative architectural solutions. Interpreting and drawing conclusions from this amount of simulation results can be extremely cumbersome. In other ...
Design space abstraction and metamodeling for embedded systems design space exploration
MOMPES '10: Proceedings of the 7th International Workshop on Model-Based Methodologies for Pervasive and Embedded SoftwareIn this paper, we present a design space exploration (DSE) method for embedded systems, which represents the design space as a categorical graph product, in order to overcome the challenge of performing multiple DSE activities, such as task mapping, ...






Comments