The paper addresses distributed state estimation over a peer-to-peer sensor network with an eye to communica- tion/energy efficiency. In particular, consensus on exponential families of probability distributions is first introduced and shown to be equivalent to iteratively performing convex linear combinations on the natural parameters of such distributions. Then, an event-triggered consensus strategy is presented and exploited to derive a novel energy-efficient consensus Kalman filter algorithm for distributed state estimation. Simulation results are provided to demonstrate the effectiveness of the proposed algorithm.
Energy-efficient distributed state estimation via event-triggered consensus on exponential families / Battistelli, Giorgio; Chisci, Luigi; Selvi, Daniela. - STAMPA. - (2016), pp. 6387-6392. (Intervento presentato al convegno 2016 American Control Conference tenutosi a Boston, MA, USA nel July 6-8, 2016) [10.1109/ACC.2016.7526674].
Energy-efficient distributed state estimation via event-triggered consensus on exponential families
BATTISTELLI, GIORGIO;CHISCI, LUIGI;SELVI, DANIELA
2016
Abstract
The paper addresses distributed state estimation over a peer-to-peer sensor network with an eye to communica- tion/energy efficiency. In particular, consensus on exponential families of probability distributions is first introduced and shown to be equivalent to iteratively performing convex linear combinations on the natural parameters of such distributions. Then, an event-triggered consensus strategy is presented and exploited to derive a novel energy-efficient consensus Kalman filter algorithm for distributed state estimation. Simulation results are provided to demonstrate the effectiveness of the proposed algorithm.File | Dimensione | Formato | |
---|---|---|---|
ACC2016-a.pdf
Accesso chiuso
Descrizione: Articolo principale
Tipologia:
Pdf editoriale (Version of record)
Licenza:
Tutti i diritti riservati
Dimensione
231.62 kB
Formato
Adobe PDF
|
231.62 kB | Adobe PDF | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.