Scalable analysis of linear networked systems via chordal decomposition

This paper introduces a chordal decomposition approach for scalable analysis of linear networked systems, including stability, $\mathcal{H_{2}}$ and $\mathcal{H_{\infty}}$ performance. Our main strategy is to exploit any sparsity within these analysis problems and use chordal decomposition. We first show that Grone’s and Agler’s theorems can be generalized to block matrices with any partition. This facilitates networked systems analysis, allowing one to solely focus on the physical connections of networked systems to exploit scalability. Then, by choosing Lyapunov functions with appropriate sparsity patterns, we decompose large positive semidefinite constraints in all of the analysis problems into multiple smaller ones depending on the maximal cliques of the system graph. This makes the solutions more computationally efficient via a recent first-order algorithm. Nu- merical experiments demonstrate the efficiency and scalability of the proposed method.