Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Learning Fast Approximations For Nonconvex Optimization Problems Via Deep Learning With Applications To Power Systems

Basulaiman, Kamal Aboud (2024) Learning Fast Approximations For Nonconvex Optimization Problems Via Deep Learning With Applications To Power Systems. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

[img] PDF
Restricted to University of Pittsburgh users only until 11 January 2026.

Download (8MB) | Request a Copy


Nonlinear convex optimization has provided a great modeling language and a powerful solution tool for the control and analysis of power systems over the last decade. A main challenge today is solving non-convex problems in real-time. However, if an oracle can guess, ahead of time, a high quality initial solution, then most non-convex optimization problems can be solved in a limited number of iterations using off-the-shelf solvers. In this proposal, we study how deep learning can provide good approximations for real-time power system applications. These approximations can act as good initial solutions to any exact algorithm. Alternatively, such approximations could be satisfactory to carry out real-time operations in power systems.

First, we address the problem of joint power system state estimation and bad data identification. We propose a deep learning model that provides high quality approximations in milliseconds.
Second, we address the problem multi-step ahead power system state forecasting and advocate sequence-to-sequence models for better representation.

Lastly, we study the problem of learning fast approximations of the optimal basis of a linear program produced by the simplex algorithm. We cast the problem as a simple classification task and propose a deep learning model.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Basulaiman, Kamal Aboudkab391@pitt.edukab3910000-0002-2703-8872
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairBarati,
Committee MemberRajgopal,
Committee MemberMao,
Committee MemberHinder,
Date: 11 January 2024
Date Type: Publication
Defense Date: 13 November 2023
Approval Date: 11 January 2024
Submission Date: 10 November 2023
Access Restriction: 2 year -- Restrict access to University of Pittsburgh for a period of 2 years.
Number of Pages: 96
Institution: University of Pittsburgh
Schools and Programs: Swanson School of Engineering > Industrial Engineering
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Graph Convolution Neural Network, Power State Estimation, Warm-start, Non-convex Optimization, Mixed Integer Programming.
Date Deposited: 11 Jan 2024 19:25
Last Modified: 11 Jan 2024 19:25


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item