In recent years, due to extensive applications of robotics, sensors, power and wireless communication networks in the field of machine learning, signal processing and control, decentralized optimization has been widely studied [1–5]. Quite a few problems occurring in such fields can be transformed into distributed convex optimization problems on multi-agent networks, in which each single agent works together to minimize a shared cost function in the circumstance of various constraints. A salient feature of solving distributed convex optimization problems is that an agent only communicates with its in-neighbors. The communication architecture can be formulated as a network, often directed and/or unbalanced. These problems typically demand the design of optimization algorithms being completely distributed, that is, algorithms are implemented by agents without a central coordinator [6]. Moreover, these observations naturally need algorithms to solve problems that can work well merely based on local information exchange and are robust against changes of network topologies and potential link failures.
Asynchronous Broadcast-Based Distributed Optimization over Unbalanced Directed Networks
Distributed Optimization: Advances in Theories, Methods, and Applications ; Chapter : 4 ; 57-84
2020-08-05
28 pages
Article/Chapter (Book)
Electronic Resource
English
Quantized Communication-Based Distributed Optimization over Time-Varying Directed Networks
Springer Verlag | 2020
|Random Sleep Scheme-Based Distributed Optimization over Time-Varying Directed Networks
Springer Verlag | 2020
|Distributed Economic Dispatch in Smart Grids: General Unbalanced Directed Network
Springer Verlag | 2020
|