.png){kind=icon}
.png){kind=icon}
Return
Data-Driven Control of Large-Scale Networks With Formal Guarantees: A Small-Gain-Free Approach
.png){kind=icon}
PRE
AI
B
A
A
DOI：10.1109/tac.2026.3676316.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article offers a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">data-driven divide-and-conquer</i> strategy to analyze large-scale interconnected networks, characterized by both unknown mathematical models and interconnection topologies. Our data-driven scheme treats an unknown network as an interconnection of individual agents (a.k.a. subsystems) and aims at constructing their <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">symbolic models</i>, referred to as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">discrete-domain</i> representations of unknown agents, by collecting data from their trajectories. The primary objective is to synthesize a control strategy that guarantees desired behaviors over an unknown network by employing local controllers, derived from symbolic models of individual agents. To achieve this, we leverage the concept of alternating sub-bisimulation function (ASBF) to establish a relation between the state trajectories of each unknown agent and its data-driven symbolic model. Under a newly developed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">data-driven compositional</i> condition, we then establish an alternating bisimulation function between an unknown network and its symbolic model based on ASBFs of individual agents while providing correctness guarantees. Despite the sample complexity in monolithic studies being exponential with respect to the network size, we demonstrate that our divide-and-conquer strategy reduces it to the subsystem level. We also showcase that our data-driven compositional condition does not necessitate the traditional small-gain condition, which demands precise knowledge of the interconnection topology for its fulfillment. We apply our data-driven findings to three benchmarks comprising unknown networks with an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">arbitrary</i>, a priori <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">undefined</i> number of agents and unknown interconnection topologies.
Keywords:
Compositional techniques
data-driven control
formal guarantees
large-scale networks
unknown interconnection topology
Journal
IF:
7
Papers:
1.3W
Citations:
6.7W
Organization
Cited Papers