Search scope:
排序: Display mode:
A distributed stochastic optimization algorithm with gradient-tracking and distributed heavy-ball acceleration Research Articles
Bihao Sun, Jinhui Hu, Dawen Xia, Huaqing Li,huaqingli@swu.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 11, Pages 1463-1476 doi: 10.1631/FITEE.2000615
Keywords: 分布式优化;高性能算法;多智能体系统;机器学习问题;随机梯度
The Application of Multi-agent Based Distributed Intelligent Control in VAV Air Conditioning System
Zhang Hongwei,Wu Aiguo,Sheng Tao
Strategic Study of CAE 2006, Volume 8, Issue 7, Pages 58-62
A VAV system can be treated as a multi-agent system. In this paper, a multi-agent-based distributed intelligent control method is presented to solve the problem of concordance and decoupling in the VAV system. A simulation program of VAV system is set up for control analysis. Through a simulation, this control method has been proved to be satisfactory.
Keywords: VAV agent multi-agent system distributed intelligent control
Decentralized multi-agent reinforcement learning with networked agents: recent advances Review Article
Kaiqing Zhang, Zhuoran Yang, Tamer Başar,kzhang66@illinois.edu,zy6@princeton.edu,basar1@illinois.edu
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 6, Pages 802-814 doi: 10.1631/FITEE.1900661
Keywords: 强化学习;多智能体系统;网络系统;一致性优化;分布式优化;博弈论
Containment control for heterogeneous nonlinear multi-agent systems under distributed event-triggered schemes Research Articles
Ya-ni Sun, Wen-cheng Zou, Jian Guo, Zheng-rong Xiang,xiangzr@njust.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 1, Pages 1-140 doi: 10.1631/FITEE.2000034
Keywords: Multi-agent systems Distributed event-triggered control Containment control Heterogeneous nonlinear systems Zeno behavior
Recent progress on the study of distributed economic dispatch in smart grid: an overview Review Articles
Guanghui Wen, Xinghuo Yu, Zhiwei Liu,wenguanghui@gmail.com,x.yu@rmit.edu.au,zwliu@hust.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 1, Pages 1-140 doi: 10.1631/FITEE.2000205
Keywords: Distributed economic dispatch Distributed optimization Smart grid Continuous-time optimization algorithm Discrete-time optimization algorithm
Strategies and Principles of Distributed Machine Learning on Big Data Review
Eric P. Xing,Qirong Ho,Pengtao Xie,Dai Wei
Engineering 2016, Volume 2, Issue 2, Pages 179-195 doi: 10.1016/J.ENG.2016.02.008
The rise of big data has led to new demands for machine learning (ML) systems to learn complex models, with millions to billions of parameters, that promise adequate capacity to digest massive datasets and offer powerful predictive analytics (such as high-dimensional latent features, intermediate representations, and decision functions) thereupon. In order to run ML algorithms at such scales, on a distributed cluster with tens to thousands of machines, it is often the case that significant engineering efforts are required—and one might fairly ask whether such engineering truly falls within the domain of ML research. Taking the view that “big” ML systems can benefit greatly from ML-rooted statistical and algorithmic insights—and that ML researchers should therefore not shy away from such systems design—we discuss a series of principles and strategies distilled from our recent efforts on industrial-scale ML solutions. These principles and strategies span a continuum from application, to engineering, and to theoretical research and development of big ML systems and architectures, with the goal of understanding how to make them efficient, generally applicable, and supported with convergence and scaling guarantees. They concern four key questions that traditionally receive little attention in ML research: How can an ML program be distributed over a cluster? How can ML computation be bridged with inter-machine communication? How can such communication be performed? What should be communicated between machines? By exposing underlying statistical and algorithmic characteristics unique to ML programs but not typically seen in traditional computer programs, and by dissecting successful cases to reveal how we have harnessed these principles to design and develop both high-performance distributed ML software as well as general-purpose ML frameworks, we present opportunities for ML researchers and practitioners to further shape and enlarge the area that lies between ML and systems.
Keywords: Machine learning Artificial intelligence big data Big model Distributed systems Principles Theory Data-parallelism Model-parallelism
Matrix-valued distributed stochastic optimization with constraints
夏子聪,刘洋,卢文联,桂卫华
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 9, Pages 1239-1252 doi: 10.1631/FITEE.2200381
Keywords: Distributed optimization Matrix-valued optimization Stochastic optimization Penalty method Gossip model
Robust distributed model predictive consensus of discrete-time multi-agent systems: a self-triggered approach Research Articles
Jiaqi Li, Qingling Wang, Yanxu Su, Changyin Sun,jiaqil2018@seu.edu.cn,qlwang@seu.edu.cn,yanxu.su@seu.edu.cn,cysun@seu.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 8, Pages 1068-1079 doi: 10.1631/FITEE.2000182
Keywords: 一致性;自触发控制;分布式模型预测控制
Leader-following consensus of second-order nonlinear multi-agent systems subject to disturbances None
Mao-bin LU, Lu LIU
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 1, Pages 88-94 doi: 10.1631/FITEE.1800611
In this study, we investigate the leader-following consensus problem of a class of heterogeneous secondorder nonlinear multi-agent systems subject to disturbances. In particular, the nonlinear systems contain uncertainties that can be linearly parameterized. We propose a class of novel distributed control laws, which depends on the relative state of the system and thus can be implemented even when no communication among agents exists. By Barbalat’s lemma, we demonstrate that consensus of the second-order nonlinear multi-agent system can be achieved by the proposed distributed control law. The effectiveness of the main result is verified by its application to consensus control of a group of Van der Pol oscillators.
Keywords: Multi-agent systems Leader-following consensus Distributed control
Remarks on Distributed Energy System
Song Zhiping
Strategic Study of CAE 2004, Volume 6, Issue 12, Pages 78-84
The emergence of distributed energy system is a matter of great significance relating to implementation of sustainable strategy. As proposed by the author, distributed energy system(DES)is defined as an electric power total system compatible with environment, sited in or in the vicinity of the consumer center area without bulk and/or remote power transmission. The DES concept allows people to build and operate energy system on total energy basis and thus facilitates demand side management as well as a more intelligent use of energy. It is considered essential for fossil fueled DES that energy is utilized in a cascade way matching the energy quality supplied and needed. DES also opens the most effective way of implementation of Combined Heat & Power as well as multi-generation. While the preferable choice of primary energy might be the clean fuel such as natural gas, but from the long-term point of view, the clean coal technology should not be excluded from the DES category. Although there is a great deal of interest in micro-turbines at the moment, combustion engines still have their tremendous potential for DES application.
Keywords: distributed energy system sustainable strategy Combined Heat & Power multi-generation
ONFS: a hierarchical hybrid file system based on memory, SSD, andHDDfor high performance computers Article
Xin LIU, Yu-tong LU, Jie YU, Peng-fei WANG, Jie-ting WU, Ying LU
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 12, Pages 1940-1971 doi: 10.1631/FITEE.1700626
Keywords: High performance computing Hierarchical hybrid storage system Distributed metadata management Data migration
徐谦,俞楚天,袁翔,韦梦立,刘洪喆
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 9, Pages 1253-1260 doi: 10.1631/FITEE.2200596
Keywords: Distributed optimization Nonidentical constraints Improved push-sum framework
Theory of Collective Intelligence Evolution and Its Applications in Intelligent Robots
Qi Xiaoya, Liu Chuang, Fu Chen, Gan Zhongxue
Strategic Study of CAE 2018, Volume 20, Issue 4, Pages 101-111 doi: 10.15302/J-SSCAE-2018.04.017
Collective intelligence (CI) is widely studied in the past few decades. The most well-known CI algorithm is the ant colony optimization (ACO). ACO is used to solve complex path searching problems through CI emergence. Recently, DeepMind announced the AlphaZero program which has achieved superhuman performance in the game of Go, Chess, and Shogi, by tabula rasa reinforcement learning from games of self-play. By experimenting and implementing the AlphaZero series program in the game of Gomoku, along with analyzing and comparing the Monte-Carlo tree search (MCTS) and ACO algorithms, it is realized that the success of AlphaZero is not only due to the deep neural network and reinforcement learning, but also due to the MCTS algorithm, which is discovered to be a CI emergence algorithm. Thus we propose a CI evolution theory, as a general framework towards artificial general intelligence (AGI). Combining the strengths of deep learning, reinforcement learning, and CI algorithm, CI evolution theory enables individual intelligence to evolve with high efficiency and low cost through CI emergence. This CI evolution theory has natural applications in intelligent robots. A cloud-terminal platform is developed to help intelligent robots evolve their intelligent models. As a proof of this idea, a welding robot's welding parameter optimization intelligent model is implemented on the platform.
Keywords: collective intelligence emergence evolution positive feedback ant colony optimization Monte-Carlo tree search distributed AI cloud-terminal platform intelligent robot
Intelligent Ironmaking Optimization Service on a Cloud Computing Platform by Digital Twin Article
Heng Zhou, Chunjie Yang, Youxian Sun
Engineering 2021, Volume 7, Issue 9, Pages 1274-1281 doi: 10.1016/j.eng.2021.04.022
The shortage of computation methods and storage devices has largely limited the development of multiobjective optimization in industrial processes. To improve the operational levels of the process industries, we propose a multi-objective optimization framework based on cloud services and a cloud distribution system. Real-time data from manufacturing procedures are first temporarily stored in a local database, and then transferred to the relational database in the cloud. Next, a distribution system with elastic compute power is set up for the optimization framework. Finally, a multi-objective optimization model based on deep learning and an evolutionary algorithm is proposed to optimize several conflicting goals of the blast furnace ironmaking process. With the application of this optimization service in a cloud factory, iron production was found to increase by 83.91 t∙d-1, the coke ratio decreased 13.50 kg∙t-1, and the silicon content decreased by an average of 0.047%.
Keywords: Cloud factory Blast furnace Multi-objective optimization Distributed computation
Cyber-Physical Production Systems for Data-Driven, Decentralized, and Secure Manufacturing—A Perspective Perspective
Manu Suvarna, Ken Shaun Yap, Wentao Yang, Jun Li, Yen Ting Ng, Xiaonan Wang
Engineering 2021, Volume 7, Issue 9, Pages 1212-1223 doi: 10.1016/j.eng.2021.04.021
With the concepts of Industry 4.0 and smart manufacturing gaining popularity, there is a growing notion that conventional manufacturing will witness a transition toward a new paradigm, targeting innovation, automation, better response to customer needs, and intelligent systems. Within this context, this review focuses on the concept of cyber-physical production system (CPPS) and presents a holistic perspective on the role of the CPPS in three key and essential drivers of this transformation: data-driven manufacturing, decentralized manufacturing, and integrated blockchains for data security. The paper aims to connect these three aspects of smart manufacturing and proposes that through the application of data-driven modeling, CPPS will aid in transforming manufacturing to become more intuitive and automated. In turn, automated manufacturing will pave the way for the decentralization of manufacturing. Layering blockchain technologies on top of CPPS will ensure the reliability and security of data sharing and integration across decentralized systems. Each of these claims is supported by relevant case studies recently published in the literature and from the industry; a brief on existing challenges and the way forward is also
provided.
Keywords: Smart manufacturing Cyber-physical production systems Industrial Internet of Things Data analytics Decentralized system Blockchain
Title Author Date Type Operation
A distributed stochastic optimization algorithm with gradient-tracking and distributed heavy-ball acceleration
Bihao Sun, Jinhui Hu, Dawen Xia, Huaqing Li,huaqingli@swu.edu.cn
Journal Article
The Application of Multi-agent Based Distributed Intelligent Control in VAV Air Conditioning System
Zhang Hongwei,Wu Aiguo,Sheng Tao
Journal Article
Decentralized multi-agent reinforcement learning with networked agents: recent advances
Kaiqing Zhang, Zhuoran Yang, Tamer Başar,kzhang66@illinois.edu,zy6@princeton.edu,basar1@illinois.edu
Journal Article
Containment control for heterogeneous nonlinear multi-agent systems under distributed event-triggered schemes
Ya-ni Sun, Wen-cheng Zou, Jian Guo, Zheng-rong Xiang,xiangzr@njust.edu.cn
Journal Article
Recent progress on the study of distributed economic dispatch in smart grid: an overview
Guanghui Wen, Xinghuo Yu, Zhiwei Liu,wenguanghui@gmail.com,x.yu@rmit.edu.au,zwliu@hust.edu.cn
Journal Article
Strategies and Principles of Distributed Machine Learning on Big Data
Eric P. Xing,Qirong Ho,Pengtao Xie,Dai Wei
Journal Article
Robust distributed model predictive consensus of discrete-time multi-agent systems: a self-triggered approach
Jiaqi Li, Qingling Wang, Yanxu Su, Changyin Sun,jiaqil2018@seu.edu.cn,qlwang@seu.edu.cn,yanxu.su@seu.edu.cn,cysun@seu.edu.cn
Journal Article
Leader-following consensus of second-order nonlinear multi-agent systems subject to disturbances
Mao-bin LU, Lu LIU
Journal Article
ONFS: a hierarchical hybrid file system based on memory, SSD, andHDDfor high performance computers
Xin LIU, Yu-tong LU, Jie YU, Peng-fei WANG, Jie-ting WU, Ying LU
Journal Article
Distributed optimization based on improved push-sum framework for optimization problem with multiple local constraints and its application in smart grid
徐谦,俞楚天,袁翔,韦梦立,刘洪喆
Journal Article
Theory of Collective Intelligence Evolution and Its Applications in Intelligent Robots
Qi Xiaoya, Liu Chuang, Fu Chen, Gan Zhongxue
Journal Article
Intelligent Ironmaking Optimization Service on a Cloud Computing Platform by Digital Twin
Heng Zhou, Chunjie Yang, Youxian Sun
Journal Article