Resource Type

Journal Article 2543

Conference Videos 298

Conference Information 92

Conference Topics 3

Year

2024 7

2023 261

2022 300

2021 345

2020 282

2019 222

2018 176

2017 172

2016 99

2015 83

2014 64

2013 61

2012 60

2011 55

2010 59

2009 43

2008 59

2007 84

2006 87

2005 78

open ︾

Keywords

Machine learning 42

Artificial intelligence 35

Deep learning 34

artificial intelligence 18

intelligent manufacturing 18

optimization 14

sustainable development 13

Reinforcement learning 12

genetic algorithm 10

index system 10

Intelligent manufacturing 8

Multi-agent system 8

Additive manufacturing 7

Big data 7

Qian Xuesen 7

neural network 7

COVID-19 6

Multi-agent systems 6

Optimization 6

open ︾

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

Abstract: has been well developed in recent years due to its wide applications in machine learning and signal processing. In this paper, we focus on investigating to minimize a global objective. The objective is a sum of smooth and strongly convex local cost functions which are distributed over an undirected network of nodes. In contrast to existing works, we apply a distributed heavy-ball term to improve the convergence performance of the proposed algorithm. To accelerate the convergence of existing distributed stochastic first-order gradient methods, a momentum term is combined with a gradient-tracking technique. It is shown that the proposed algorithm has better acceleration ability than GT-SAGA without increasing the complexity. Extensive experiments on real-world datasets verify the effectiveness and correctness of the proposed algorithm.

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    

HTML PDF Collect

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

Abstract:

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    

HTML PDF Collect

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

Abstract: Multi-agent (MARL) has long been a significant research topic in both machine learning and control systems. Recent development of (single-agent) deep has created a resurgence of interest in developing new MARL algorithms, especially those founded on theoretical analysis. In this paper, we review recent advances on a sub-area of this topic: decentralized MARL with networked agents. In this scenario, multiple agents perform sequential decision-making in a common environment, and without the coordination of any central controller, while being allowed to exchange information with their neighbors over a communication network. Such a setting finds broad applications in the control and operation of robots, unmanned vehicles, mobile sensor networks, and the smart grid. This review covers several of our research endeavors in this direction, as well as progress made by other researchers along the line. We hope that this review promotes additional research efforts in this exciting yet challenging area.

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    

HTML PDF Collect

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

Abstract: We study the problem for high-order heterogeneous nonlinear under distributed event-triggered schemes. To achieve the objective and reduce communication consumption among agents, a scheme is proposed by applying the backstepping method, Lyapunov functional approach, and neural networks. Then, the results are extended to the self-triggered control case to avoid continuous monitoring of state errors. The developed protocols and triggered rules ensure that the output for each follower converges to the convex hull spanned by multi-leader signals within a bounded error. In addition, no agent exhibits . Two numerical simulations are finally presented to verify the correctness of the obtained results.

Keywords： Multi-agent systems     Distributed event-triggered control     Containment control     Heterogeneous nonlinear systems     Zeno behavior    

HTML PDF Collect

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

Abstract: Designing an efficient (DED) strategy for the (SG) in the presence of multiple generators plays a paramount role in obtaining various benefits of a new generation power system, such as easy implementation, low maintenance cost, high energy efficiency, and strong robustness against uncertainties. It has drawn a lot of interest from a wide variety of scientific disciplines, including power engineering, control theory, and applied mathematics. We present a state-of-the-art review of some theoretical advances toward DED in the SG, with a focus on the literature published since 2015. We systematically review the recent results on this topic and subsequently categorize them into distributed discrete- and continuous-time economic dispatches of the SG in the presence of multiple generators. After reviewing the literature, we briefly present some future research directions in DED for the SG, including the distributed security economic dispatch of the SG, distributed fast economic dispatch in the SG with practical constraints, efficient initialization-free DED in the SG, DED in the SG in the presence of smart energy storage batteries and flexible loads, and DED in the SG with artificial intelligence technologies.

Keywords： Distributed economic dispatch     Distributed optimization     Smart grid     Continuous-time optimization algorithm     Discrete-time optimization algorithm    

HTML PDF Collect

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

Abstract:

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    

HTML PDF Collect

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

Abstract: In this paper, we address matrix-valued distributed stochastic optimization with inequality and equality constraints, where the objective function is a sum of multiple matrix-valued functions with stochastic variables and the considered problems are solved in a distributed manner. A penalty method is derived to deal with the constraints, and a selection principle is proposed for choosing feasible penalty functions and penalty gains. A distributed optimization algorithm based on the gossip model is developed for solving the stochastic optimization problem, and its convergence to the optimal solution is analyzed rigorously. Two numerical examples are given to demonstrate the viability of the main results.

Keywords： Distributed optimization     Matrix-valued optimization     Stochastic optimization     Penalty method     Gossip model    

HTML Collect

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

Abstract: This study investigates the problem of a nonlinear discrete-time multi-agent system (MAS) under bounded additive disturbances. We propose a self-triggered robust algorithm. A new cost function is constructed and MAS is coupled through this function. Based on the proposed cost function, a self-triggered mechanism is adopted to reduce the communication load. Furthermore, to overcome additive disturbances, a local minimum– maximum optimization problem under the worst-case scenario is solved iteratively by the model predictive controller of each agent. Sufficient conditions are provided to guarantee the iterative feasibility of the algorithm and the of the closed-loop MAS. For each agent, we provide a concrete form of compatibility constraint and a error terminal region. Numerical examples are provided to illustrate the effectiveness and correctness of the proposed algorithm.

Keywords： 一致性；自触发控制；分布式模型预测控制    

HTML PDF Collect

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

Abstract:

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    

HTML PDF Collect

Remarks on Distributed Energy System

Song Zhiping

Strategic Study of CAE 2004, Volume 6, Issue 12,   Pages 78-84

Abstract:

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    

HTML PDF Collect

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

Abstract: With supercomputers developing towards exascale, the number of compute cores increases dramatically, making more complex and larger-scale applications possible. The input/output (I/O) requirements of large-scale applications, workflow applications, and their checkpointing include substantial bandwidth and an extremely low latency, posing a serious challenge to high performance computing (HPC) storage systems. Current hard disk drive (HDD) based underlying storage systems are becoming more and more incompetent to meet the requirements of next-generation exascale supercomputers. To rise to the challenge, we propose a hierarchical hybrid storage system, on-line and near-line file system (ONFS). It leverages dynamic random access memory (DRAM) and solid state drive (SSD) in compute nodes, and HDD in storage servers to build a three-level storage system in a unified namespace. It supports portable operating system interface (POSIX) semantics, and provides high bandwidth, low latency, and huge storage capacity. In this paper, we present the technical details on distributed metadata management, the strategy of memory borrow and return, data consistency, parallel access control, and mechanisms guiding downward and upward migration in ONFS. We implement an ONFS prototype on the TH-1A supercomputer, and conduct experiments to test its I/O performance and scalability. The results show that the bandwidths of single-thread and multi-thread ‘read’/‘write’ are 6-fold and 5-fold better than HDD-based Lustre, respectively. The I/O bandwidth of data-intensive applications in ONFS can be 6.35 times that in Lustre.

Keywords： High performance computing     Hierarchical hybrid storage system     Distributed metadata management     Data migration    

HTML PDF Collect

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

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 9,   Pages 1253-1260 doi: 10.1631/FITEE.2200596

Abstract: In this paper, the optimization problem subject to ,N, nonidentical closed convex set constraints is studied. The aim is to design a corresponding distributed optimization algorithm over the fixed unbalanced graph to solve the considered problem. To this end, with the push-sum framework improved, the distributed optimization algorithm is newly designed, and its strict convergence analysis is given under the assumption that the involved graph is strongly connected. Finally, simulation results support the good performance of the proposed algorithm.

Keywords： Distributed optimization     Nonidentical constraints     Improved push-sum framework    

HTML Collect

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

Abstract:

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    

HTML PDF Collect

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

Abstract:

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    

HTML PDF Collect

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

Abstract:

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    

HTML PDF Collect

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

Matrix-valued distributed stochastic optimization with constraints

夏子聪,刘洋,卢文联,桂卫华

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

Remarks on Distributed Energy System

Song Zhiping

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

Cyber-Physical Production Systems for Data-Driven, Decentralized, and Secure Manufacturing—A Perspective

Manu Suvarna, Ken Shaun Yap, Wentao Yang, Jun Li, Yen Ting Ng, Xiaonan Wang

Journal Article