research-article

Two-Stage Competitive Particle Swarm Optimization Based Timing-Driven X-Routing for IC Design Under Smart Manufacturing

Authors:
Genggeng Liu

Fuzhou University, Fuzhou, China

Fuzhou University, Fuzhou, China

0000-0002-3099-4371
View Profile

,
Ruping Zhou

Fuzhou University, Fuzhou, China

Fuzhou University, Fuzhou, China

0000-0003-0911-2327
View Profile

,
Saijuan Xu

Fujian Business University, Fuzhou, China

Fujian Business University, Fuzhou, China

0000-0002-1159-9253
View Profile

,
Yuhan Zhu

Fuzhou University, Fuzhou, China

Fuzhou University, Fuzhou, China

0000-0002-0246-3653
View Profile

,
Wenzhong Guo

Fuzhou University, Fuzhou, China

Fuzhou University, Fuzhou, China

0000-0001-6368-2414
View Profile

,
Yeh-Cheng Chen

University of California, Davis, CA, USA

University of California, Davis, CA, USA

0000-0001-7793-1098
View Profile

,
Guolong Chen

Fuzhou University, Fuzhou, China

Fuzhou University, Fuzhou, China

0000-0003-4243-4782
View Profile

ACM Transactions on Management Information Systems Volume 13 Issue 4Article No.: 41pp 1–26https://doi.org/10.1145/3531328

Published:10 August 2022Publication History

ACM Transactions on Management Information Systems

Abstract

As timing delay becomes a critical issue in chip performance, there is a burning desire for IC design under smart manufacturing to optimize the delay. As the best connection model for multi-terminal nets, the wirelength and the maximum source-to-sink pathlength of the Steiner minimum tree are the decisive factors of timing delay for routing. In addition, considering that X-routing can get the utmost out of routing resources, this article proposes a Timing-Driven X-routing Steiner Minimum Tree (TD-XSMT) algorithm based on two-stage competitive particle swarm optimization. This work utilizes the multi-objective particle swarm optimization algorithm and redesigns its framework, thus improving its performance. First, a two-stage learning strategy is presented, which balances the exploration and exploitation capabilities of the particle by learning edge structures and pseudo-Steiner point choices. Especially in the second stage, a hybrid crossover strategy is designed to guarantee convergence quality. Second, the competition mechanism is adopted to select particle learning objects and enhance diversity. Finally, according to the characteristics of the discrete TD-XSMT problem, the mutation and crossover operators of the genetic algorithm are used to effectively discretize the proposed algorithm. Experimental results reveal that TSCPSO-TD-XSMT can obtain a smooth trade-off between wirelength and maximum source-to-sink pathlength, and achieve distinguished timing delay optimization.

REFERENCES

[1] Alpert Charles J., Chow Wing-Kai, Han Kwangsoo, Kahng Andrew B., Li Zhuo, Liu Derong, and Venkatesh Sriram. 2018. Prim-Dijkstra revisited: Achieving superior timing-driven routing trees. In Proceedings of the 2018 International Symposium on Physical Design. ACM, New York, NY, 10–17. Google ScholarDigital Library
[2] Caihong Zhou, Zengyuan Wu, and Chang Liu. 2019. A study on quality prediction for smart manufacturing based on the optimized BP-AdaBoost model. In Proceedings of the 2019 IEEE International Conference on Smart Manufacturing, Industrial, and Logistics Engineering. IEEE, Los Alamitos, CA, 1–3. Google ScholarCross Ref
[3] Chakraborty Saurav, Onuchowska Agnieszka, Samtani Sagar, Jank Wolfgang, and Wolfram Brandon. 2021. Machine learning for automated industrial IoT attack detection: An efficiency-complexity trade-off. ACM Transactions on Management Information System 12, 4 (2021), 1–28. Google ScholarDigital Library
[4] Chen Baotong, Wan Jiafu, Celesti Antonio, Li Di, Abbas Haider, and Zhang Qin. 2018. Edge computing in IoT-based manufacturing. IEEE Communications Magazine 56, 9 (2018), 103–109. Google ScholarCross Ref
[5] Chen Gengjie, Tu Peishan, and Young Evangeline F. Y.. 2017. SALT: Provably good routing topology by a novel Steiner shallow-light tree algorithm. In Proceedings of the 2017 IEEE/ACM International Conference on Computer-Aided Design. 569–576. Google ScholarDigital Library
[6] Chen Gengjie and Young Evangeline F. Y.. 2020. SALT: Provably good routing topology by a novel Steiner shallow-light tree algorithm. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 39, 6 (2020), 1217–1230. Google ScholarCross Ref
[7] Chen Xiaohua, Zhou Ruping, Liu Genggeng, Chen Zhen, and Guo Wenzhong. 2021. Timing-driven X-architecture Steiner minimum tree construction based on social learning multi-objective particle swarm optimization. In Companion Proceedings of the Web Conference 2021 (WWW’21). ACM, New York, NY, 77–84. Google ScholarDigital Library
[8] Coello C. A. Coello and Lechuga M. S.. 2002. MOPSO: A proposal for multiple objective particle swarm optimization. In Proceedings of the 2002 Congress on Evolutionary Computation, Vol. 2. 1051–1056. Google ScholarCross Ref
[9] Deb K., Pratap A., Agarwal S., and Meyarivan T.. 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation 6, 2 (2002), 182–197. Google ScholarDigital Library
[10] Denysiuk Roman, Costa Lino, and Santo Isabel Espirito. 2014. Clustering-based selection for evolutionary many-objective optimization. In Proceedings of the International Conference on Parallel Problem Solving from Nature, Vol. 8672. 538–547. Google ScholarCross Ref
[11] Frolova Pelageya I., Chochaev Rustam Zh., Ivanova Galina A., and Gavrilov Sergey V.. 2020. Delay matrix based timing-driven placement for reconfigurable systems-on-chip. In Proceedings of the 2020 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering. IEEE, Los Alamitos, CA, 1799–1803. Google ScholarCross Ref
[12] Guo Wenzhong and Huang Xing. 2020. PORA: A Physarum-inspired obstacle-avoiding routing algorithm for integrated circuit design. Applied Mathematical Modelling 78 (2020), 268–286. Google ScholarCross Ref
[13] Hua Yicun, Jin Yaochu, and Hao Kuangrong. 2019. A clustering-based adaptive evolutionary algorithm for multiobjective optimization with irregular Pareto fronts. IEEE Transactions on Cybernetics 49, 7 (2019), 2758–2770. Google ScholarCross Ref
[14] Huang Tao and Young Evangeline F. Y.. 2012. Construction of rectilinear Steiner minimum trees with slew constraints over obstacles. In Proceedings of the International Conference on Computer-Aided Design. ACM, New York, NY, 144–151. Google ScholarDigital Library
[15] Huang Xing, Guo Wenzhong, and Chen Guolong. 2015. Fast obstacle-avoiding octilinear Steiner minimal tree construction algorithm for VLSI design. In Proceedings of the 16th International Symposium on Quality Electronic Design. IEEE, Los Alamitos, CA, 46–50. Google ScholarCross Ref
[16] Huang Xing, Ho Tsung-Yi, Li Zepeng, Liu Genggeng, Wang Lu, Li Qingshan, Guo Wenzhong, Li Bing, and Schlichtmann Ulf. 2022. MiniControl 2.0: Co-synthesis of flow and control layers for microfluidic biochips with strictly constrained control ports. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. Early access, March 8, 2022. Google ScholarCross Ref
[17] Huang Xing, Liu Genggeng, Guo Wenzhong, and Chen Guolong. 2013. Obstacle-avoiding octagonal Steiner tree construction based on particle swarm optimization. In Proceedings of the 2013 9th International Conference on Natural Computation. IEEE, Los Alamitos, CA, 539–543. Google ScholarCross Ref
[18] Huang Xing, Liu Genggeng, Guo Wenzhong, Niu Yuzhen, and Chen Guolong. 2015. Obstacle-avoiding algorithm in X-architecture based on discrete particle swarm optimization for VLSI design. ACM Transactions on Design Automation of Electronic Systems 20, 2 (2015), 1–28. Google ScholarDigital Library
[19] Iqbal Arif and Singh Girish Kumar. 2021. PSO based controlled six-phase grid connected induction generator for wind energy generation. CES Transactions on Electrical Machines and Systems 5, 1 (2021), 41–49. Google ScholarCross Ref
[20] Ismail Y. I., Friedman E. G., and Neves J. L.. 2000. Equivalent Elmore delay for RLC trees. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 19, 1 (2000), 83–97. Google ScholarDigital Library
[21] Katiyar Shubhi and Dutta Ashish. 2021. PSO based path planning and dynamic obstacle avoidance in CG space of a 10 DOF Rover. In Advances in Robotics—5th International Conference of the Robotics Society (AIR’21). Article 5, 6 pages ACM, New York, NY, 1–6. Google ScholarDigital Library
[22] Kennedy J. and Eberhart R.. 1995. Particle swarm optimization. In Proceedings of the International Conference on Neural Networks (ICNN’95), Vol. 4. IEEE, Los Alamitos, CA, 1942–1948. Google ScholarCross Ref
[23] Kim Won-Jin, Ahn Byung-Gyu, Chung Ki-Seok, Chung Jong-Wha, and Oh Sung-Hwan. 2008. Timing driven force-directed floorplanning with incremental static timing analyzer. In Proceedings of the 2008 IEEE Asia Pacific Conference on Circuits and Systems. IEEE, Los Alamitos, CA, 1000–1003. Google ScholarCross Ref
[24] Lei Wang, Yong Wang, Haigen Yang, Hongyan Yu, Wenting Xu, Longbao Han, and Kejia Jia. 2018. Research on application of virtual-real fusion technology in smart manufacturing. In Proceedings of the 2018 IEEE 9th International Conference on Software Engineering and Service Science. IEEE, Los Alamitos, CA, 1066–1069. Google ScholarCross Ref
[25] Leng Jiewu, Ye Shide, Zhou Man, Zhao J. Leon, Liu Qiang, Guo Wei, Cao Wei, and Fu Leijie. 2021. Blockchain-secured smart manufacturing in industry 4.0: A survey. IEEE Transactions on Systems, Man, and Cybernetics: Systems 51, 1 (2021), 237–252. Google ScholarCross Ref
[26] Li Ke, Chen Renzhi, Fu Guangtao, and Yao Xin. 2019. Two-archive evolutionary algorithm for constrained multiobjective optimization. IEEE Transactions on Evolutionary Computation 23, 2 (2019), 303–315. Google ScholarCross Ref
[27] Li Liangzhi, Ota Kaoru, and Dong Mianxiong. 2018. Deep learning for smart industry: Efficient manufacture inspection system with fog computing. IEEE Transactions on Industrial Informatics 14, 10 (2018), 4665–4673. Google Scholar
[28] Liu Genggeng, Chen Xiaohua, Zhou Ruping, Xu Saijuan, Chen Yeh-Cheng, and Chen Guolong. 2021. Social learning discrete particle swarm optimization based two-stage X-routing for IC design under intelligent edge computing architecture. Applied Soft Computing 104 (2021), 107215. Google ScholarDigital Library
[29] Liu Genggeng, Chen Zhisheng, Zhuang Zhen, Guo Wenzhong, and Chen Guolong. 2020. A unified algorithm based on HTS and self-adapting PSO for the construction of octagonal and rectilinear SMT. Soft Computing 24, 6 (2020), 3943–3961. Google ScholarDigital Library
[30] Liu Genggeng, Guo Wenzhong, Niu Yuzhen, Chen Guolong, and Huang Xing. 2015. A PSO-based timing-driven octilinear Steiner tree algorithm for VLSI routing considering bend reduction. Soft Computing 19, 5 (2015), 1153–1169. Google ScholarDigital Library
[31] Liu Genggeng, Huang Xing, Guo Wenzhong, Niu Yuzhen, and Chen Guolong. 2015. Multilayer obstacle-avoiding X-architecture Steiner minimal tree construction based on particle swarm optimization. IEEE Transactions on Cybernetics 45, 5 (2015), 1003–1016. Google ScholarCross Ref
[32] Liu Genggeng, Yang Liliang, Xu Saijuan, Li Zuoyong, Chen Yeh-Cheng, and Chen Chi-Hua. 2021. X-architecture steiner minimal tree algorithm based on multi-strategy optimization discrete differential evolution. PeerJ Computer Science 7 (2021), e473. Google ScholarCross Ref
[33] Liu Genggeng, Zhang Xinghai, Guo Wenzhong, Huang Xing, Liu Wen-Hao, Chao Kai-Yuan, and Wang Ting-Chi. 2021. Timing-aware layer assignment for advanced process technologies considering via pillars. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. Early access, July 26, 2021. Google ScholarCross Ref
[34] Liu Genggeng, Zhu Weida, Xu Saijuan, Zhuang Zhen, Chen Yeh-Cheng, and Chen Guolong. 2020. Efficient VLSI routing algorithm employing novel discrete PSO and multi-stage transformation. Journal of Ambient Intelligence and Humanized Computing. Published November 13, 2020. Google ScholarCross Ref
[35] Liu Genggeng, Zhu Yuhan, Xu Saijuan, Chen Yeh-Cheng, and Tang Hao. 2022. PSO-based power-driven X-routing algorithm in semiconductor design for predictive intelligence of IoT applications. Applied Soft Computing 114 (2022), 108114. Google ScholarDigital Library
[36] Liu J. C., Mukhopadhyay S., Kundu Amit, Chen S. H., Wang H. C., Huang D. S., Lee J. H., et al. 2020. A reliability enhanced 5nm CMOS technology featuring 5th generation FinFET with fully-developed EUV and high mobility channel for mobile SoC and high performance computing application. In Proceedings of the 2020 IEEE International Electron Devices Meeting. IEEE, Los Alamitos, CA, 9.2.1–9.2.4. Google ScholarCross Ref
[37] Lv Zhihan, Lou Ranran, Feng Hailin, Chen Dongliang, and Lv Haibin. 2021. Novel machine learning for big data analytics in intelligent support information management systems. ACM Transactions on Management Information Systems 13, 1 (2021), 1–21. Google ScholarDigital Library
[38] Nebro A. J., Durillo J. J., Garcia-Nieto J., Coello C. A. Coello, Luna F., and Alba E.. 2009. SMPSO: A new PSO-based metaheuristic for multi-objective optimization. In Proceedings of the 2009 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making. 66–73. Google ScholarCross Ref
[39] Samtani Sagar, Kantarcioglu Murat, and Chen Hsinchun. 2020. Trailblazing the artificial intelligence for cybersecurity discipline: A multi-disciplinary research roadmap. ACM Transactions on Management Information System 11, 4 (2020), 1–19. Google ScholarDigital Library
[40] Shang Song Pu and Jing Tong. 2007. Steiner minimal trees in rectilinear and octilinear planes. Acta Mathematica Sinica, English Series 23, 9 (2007), 1577–1586. Google ScholarCross Ref
[41] Song Jiho, Jang Cheoljon, Cho Kyungin, Go Seungryeol, and Chong Jongwha. 2014. Timing driven global router with a pin partition method for 3D stacked integrated circuits. In Proceedings of the 18th IEEE International Symposium on Consumer Electronics. IEEE, Los Alamitos, CA, 1–2. Google ScholarCross Ref
[42] Tao Fei, Qi Qinglin, Liu Ang, and Kusiak Andrew. 2018. Data-driven smart manufacturing. Journal of Manufacturing Systems 48 (2018), 157–169. Google ScholarCross Ref
[43] Teig Steven L.. 2002. The X-architecture: Not your father’s diagonal wiring. In Proceedings of the 2002 International Workshop on System-Level Interconnect Prediction. ACM, New York, NY, 33–37. Google ScholarDigital Library
[44] Tian Ye, Zhang Yajie, Su Yansen, Zhang Xingyi, Tan Kay Chen, and Jin Yaochu. 2021. Balancing objective optimization and constraint satisfaction in constrained evolutionary multiobjective optimization. IEEE Transactions on Cybernetics. Early access, March 17, 2021. Google ScholarCross Ref
[45] Tian Ye, Zheng Xiutao, Zhang Xingyi, and Jin Yaochu. 2020. Efficient large-scale multiobjective optimization based on a competitive swarm optimizer. IEEE Transactions on Cybernetics 50, 8 (2020), 3696–3708. Google ScholarCross Ref
[46] Vachhani Vimal L., Dabhi Vipul K., and Prajapati Harshadkumar B.. 2016. Improving NSGA-II for solving multi objective function optimization problems. In Proceedings of the 2016 International Conference on Computer Communication and Informatics. IEEE, Los Alamitos, CA, 1–6. Google ScholarCross Ref
[47] Wang Yujia and Yang Yupu. 2009. Particle swarm optimization with preference order ranking for multi-objective optimization. Information Sciences 179, 12 (2009), 1944–1959. Google ScholarDigital Library
[48] Warme David, Winter Pawel, and Zachariasen Martin. 2003. GeoSteiner Software for Computing Steiner Trees. Retrieved April 30, 2022 from http://geosteiner.net.Google Scholar
[49] Wu Dazhong, Jennings Connor, Terpenny Janis, Gao Robert X., and Kumara Soundar. 2017. A comparative study on machine learning algorithms for smart manufacturing: Tool wear prediction using random forests. Journal of Manufacturing Science and Engineering 139, 7 (2017), Article 071018, 9 pages. 071018Google ScholarCross Ref
[50] Wu Hailin, Xu Saijuan, Zhuang Zhen, and Liu Genggeng. 2019. X-architecture Steiner minimal tree construction based on discrete differential evolution. In Proceedings of the International Conference on Natural Computation, Fuzzy Systems, and Knowledge Discovery. 433–442. Google ScholarCross Ref
[51] Xiong Hu, Wang Yi, Li Wenchao, and Chen Chien-Ming. 2019. Flexible, efficient, and secure access delegation in cloud computing. ACM Transactions on Management Information System 10, 1 (2019), 1–20. Google ScholarDigital Library
[52] Yan Jin-Tai. 2008. Timing-driven octilinear Steiner tree construction based on Steiner-point reassignment and path reconstruction. ACM Transactions on Design Automation of Electronic Systems 13, 2 (2008), 1–18. Google ScholarDigital Library
[53] Yan Jin-Tai, Chen Zhi-Wei, and Hu Dun-Hao. 2008. Timing-driven Steiner tree construction for three-dimensional ICs. In Proceedings of the 2008 Joint 6th International IEEE Northeast Workshop on Circuits and Systems and TAISA Conference. 335–338. Google ScholarCross Ref
[54] Yan Jin-Tai, Huang Shi-Qin, and Chen Zhi-Wei. 2007. Top-down-based timing-driven Steiner tree construction with wire sizing and buffer insertion. In Proceedings of the 2007 IEEE Region 10 Conference (TENCON’07). IEEE, Los Alamitos, CA, 1–4. Google ScholarCross Ref
[55] Yan Jin-Tai, Wang Tzu-Ya, and Lee Yu-Cheng. 2005. Timing-driven Steiner tree construction based on feasible assignment of hidden Steiner points. In Proceedings of the 2005 IEEE International Symposium on Circuits and Systems, Vol. 2. 1370–1373. Google ScholarCross Ref
[56] Zhang Xianyu and Ming Xinguo. 2021. An implementation for smart manufacturing information system (SMIS) from an industrial practice survey. Computers & Industrial Engineering 151 (2021), 106938. Google ScholarCross Ref
[57] Zhang Xingyi, Tian Ye, Cheng Ran, and Jin Yaochu. 2015. An efficient approach to nondominated sorting for evolutionary multiobjective optimization. IEEE Transactions on Evolutionary Computation 19, 2 (2015), 201–213. Google ScholarDigital Library
[58] Zhang Xingyi, Zheng Xiutao, Cheng Ran, Qiu Jianfeng, and Jin Yaochu. 2018. A competitive mechanism based multi-objective particle swarm optimizer with fast convergence. Information Sciences 427 (2018), 63–76. Google ScholarDigital Library
[59] Zhou Ruping, Liu Genggeng, Guo Wenzhong, and Wang Xin. 2021. An X-architecture SMT algorithm based on competitive swarm optimizer. In Proceedings of the International Conference on Web Information Systems and Applications. 393–404. Google ScholarDigital Library
[60] Zhu Qingling, Lin Qiuzhen, Chen Weineng, Wong Ka-Chun, Coello Carlos A. Coello, Li Jianqiang, Chen Jianyong, and Zhang Jun. 2017. An external archive-guided multiobjective particle swarm optimization algorithm. IEEE Transactions on Cybernetics 47, 9 (2017), 2794–2808. Google ScholarCross Ref

Index Terms

Two-Stage Competitive Particle Swarm Optimization Based Timing-Driven X-Routing for IC Design Under Smart Manufacturing
1. Hardware
  1. Electronic design automation
    1. Physical design (EDA)
      1. Wire routing
  2. Power and energy
    1. Power estimation and optimization

Recommendations

Performance-Driven X-Architecture Routing Algorithm for Artificial Intelligence Chip Design in Smart Manufacturing
The new 7-nm Artificial Intelligence (AI) chip is an important milestone recently announced by the IBM research team, with a very important optimization goal of performance. This chip technology can be extended to various business scenarios in the ...
Read More
Timing-Driven X-architecture Steiner Minimum Tree Construction Based on Social Learning Multi-Objective Particle Swarm Optimization
WWW '21: Companion Proceedings of the Web Conference 2021

The construction of timing-driven Steiner minimum tree is a critical issue in VLSI routing design. Meanwhile, since the interconnection model of X-architecture can make full use of routing resources compared to the traditional Manhattan architecture, ...
Read More
Social learning discrete Particle Swarm Optimization based two-stage X-routing for IC design under Intelligent Edge Computing architecture
Abstract
One of the core features of Intelligent Edge Computing (IEC) is real-time decision making, therefore low delay is more important for IC design under IEC architecture. And in very large scale integration routing, wirelength is one of ...
Graphical abstract

Display Omitted
Highlights
- Better satisfying the high-performance requirement for IC design under IEC.
- ...
Read More

Comments

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

Published in
ACM Transactions on Management Information Systems Volume 13, Issue 4
December 2022
255 pages
ISSN:2158-656X
EISSN:2158-6578
DOI:10.1145/3555789
Editor:
Daniel Zeng
Chinese Academy of Sciences, China
Issue’s Table of Contents
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
- Published: 10 August 2022
- Online AM: 22 April 2022
- Revised: 1 April 2022
- Accepted: 1 April 2022
- Received: 1 January 2022
Published in tmis Volume 13, Issue 4

Permissions
Request permissions about this article.
Request Permissions

Check for updates
Author Tags
Smart manufacturing
X-routing
Timing-Driven
multi-objective particle swarm optimization
competitive mechanism
IC design
Qualifiers
- research-article
- Refereed
Conference
Funding Sources
Other Metrics
View Article Metrics

Article Metrics
- 2
  Total Citations
  View Citations
- 275
  Total Downloads
- Downloads (Last 12 months)113
- Downloads (Last 6 weeks)6
Other Metrics
View Author Metrics
Cited By
View all

PDF Format

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Full Text

View this article in Full Text.

View Full Text

HTML Format

View this article in HTML Format .

View HTML Format

Two-Stage Competitive Particle Swarm Optimization Based Timing-Driven X-Routing for IC Design Under Smart Manufacturing

ACM Transactions on Management Information Systems

Abstract

REFERENCES

Cited By

Index Terms

Recommendations

Performance-Driven X-Architecture Routing Algorithm for Artificial Intelligence Chip Design in Smart Manufacturing

Timing-Driven X-architecture Steiner Minimum Tree Construction Based on Social Learning Multi-Objective Particle Swarm Optimization

Social learning discrete Particle Swarm Optimization based two-stage X-routing for IC design under Intelligent Edge Computing architecture