Learning Parametric Time-Vertex Graph Processes from Incomplete Realizations

Güneyi, Eylem Tuğçe; Canbolat, Abdullah; Vural, Elif

doi:10.1109/mlsp52302.2021.9596563

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Активна потужність і-ї гармонійної складової, що споживається первинною обмоткою тягового трансформатора, розрахована за формулою Фазовий зсув між першими гармонійними складовими напруги і струму первинної обмотки тягового трансформатора визначався за формулою В роботах [107][108][109] зазначалось, що існують три способи реалізації АРметоду:…”

Section: модель системи тягового електропостачанняunclassified

The theory of adaptive reactive power compensation of electric railways rolling stock

Hulak¹,

Tkachenko

2022

View full text Add to dashboard Cite

The monograph is dedicated to the creation of scientific foundations for the selection of optimal parameters and operating modes of the reactive power compensation system on AC electric locomotives. The factors that have the greatest impact on the quality of the traction power supply on the side of the alternating current electric rolling stock are analyzed. It is shown that the nature of operation of electric rolling stock leads to non-determinism and non- ergodicity of the voltage change process in the catenary. Mathematical and software-oriented models of operation of an AC traction electric locomotive have been created, the distinctive features of which are the possibility of taking into account the modes of operation of the electric locomotive. A control system for the active part of the hybrid reactive power compensator has been developed, which is based on an algorithm for determining the spectral components of the traction current based on the Levinson-Darbin linear prediction method. This makes it possible to take into account the random nature of the voltage change on the current receivers of the electric locomotive and to adapt the work of the compensator to the voltage parameters of the catenary network.

show abstract

Section: модель системи тягового електропостачанняunclassified

The theory of adaptive reactive power compensation of electric railways rolling stock

Hulak¹,

Tkachenko

2022

View full text Add to dashboard Cite

show abstract

“…Graph-based spatiotemporal models can be divided into three categories: ARMA models: These methods model the signal evolution as a combination of filtered past temporal signals [2]. They consider the graph topology at each time instant for a variety of applications [3][4][5][6][7][8][9][10]; State space models. These methods use a state transition and an obervation step to model spatiotemporal signals [11,12].…”

Section: Introductionmentioning

confidence: 99%

Online Vector Autoregressive Models Over Expanding Graphs

Das

Isufi

2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Current spatiotemporal learning methods for complex data exploit the graph structure as an inductive bias to restrict the function space and improve data and computation efficiency. However, these methods work principally on graphs with a fixed size, whereas in several applications there are expanding graphs where new nodes join the network; e.g., new sensors joining a sensor network or new users joining a recommender system. This paper focuses on the non-trivial extension of spatiotemporal methods to this setting, where now it is key to jointly capture both the topological and signal dynamics. Specifically, it considers a graph vector autoregressive (GVAR) model for multivariate time series. The GVAR is a multivariate linear model that leverages a bank of graph filters allowing scalability and data efficiency. To account for the dynamic nature of the graphs, the filters's parameters are learned on-the-fly via adaptive gradient descent with provable sub-linear regret. Numerical results on both synthetic and real data corroborate the proposed method.

show abstract