Deep Learning-based Reliability and Resilience Enhancement of Future Navy Ships and Their Integration into Power Networks under Extreme Events
Abstract
The overarching objective of this project is to (i) study the energy management and fault detection of the Navy power ship systems, by utilizing deep learning-based techniques to track the demand changes with real-time interactions, and (ii) study the future potential Navy power ship systems and their interactions with typical coastal city electric network, to enhance the reliability and resilience of both the Navy ships and the coastline power grids in the presence ofnatural hazards, cyber/physical attacks, or any possible contingency. To this end, the proposed research intends to answer the following three research questions ultimately: Q1: How to improve the reliability and resilience of the Navy power ships in the presence of contingency (e.g., mechanical/electrical faults, cyber/physical attacks, or internal catastrophic failures) within the ship network? Q2: How to improve the reliability and resilience for coastline power network with the occurrences of interruptions under extreme events like natural disasters and cyber/physical attacks? Q3: What are the costs/benefits and risks from the perspectives of both the Navy power ships or the coastline power network operators?To address the challenges and answer the research questions, the following three research thrusts are planned to provide necessary results for such integrated future systems, as: Research Thrust 1: Develop deep learning-based algorithms to monitor and track demands changes of Navy power ships in real time. More specifically, a reinforcement learning baseddynamic model selection methodology will be developed for modeling and forecasting the electricity load of Navy ships, and a new distributed consensus-based algorithm will be developed to find the optimal solution for dispatching the power generation units on Navy ships, by matching the demand at any time. Research Thrust 2: Develop deep learning-based algorithms to automatically detect and isolate cyber-attacks and faults, and perform restoration within the Navy ships network. More specifically, a new artificial intelligence-based algorithm, i.e., hybrid long short-term memory and gated recurrent unit deep-learning-based algorithm, will be developed to: (i) detect the location and also the type of faults within the Navy system, and (ii) learn the topological patterns of Navy ship systems for obtaining the optimal reconfiguration switchings of the reconfigurable Navy grids. Research Thrust 3: Investigate the joint operating flexibility, reliability, and resilience of the integrated future Navy power ships and coastline power grids, by considering the distributed and real-time multi-timescale optimization and control for integrated operations of the power distribution network and Navy power ships. More specifically, a coordination framework of mobile marine power plants (MMPPs) and security-constraint unit commitment in power system operations will be developed, by taking into account of the impacts on base station and the transportation cost of the MMPPs.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Aug 31, 2020
- Source ID
- N000142012795
Entities
People
- Jie Zhang
Organizations
- Office of Naval Research
- United States Navy
- University of Texas at Dallas