Deng Cao
Central State University, OH·Engineering
Self-driving and electric vehicles are changing how roads and power grids work. Both create the same kind of problem: many independent machines compete for shared resources, such as roadside computers, wireless links or charging stations.
- Fields
Engineering
Computer Science
- Topics
connected and autonomous vehicles
self-driving cars
edge computing
- Grants
- 2 known grants, through Sep 2029
What they work on
- Design a coordinated strategy for connected self-driving vehicles to decide when to send perception tasks to roadside edge computers, keeping the decisions manageable as vehicle numbers grow and robust to uncertain edge behavior.
- Build low-cost data processing units, made from programmable network cards and fast storage, and place them only at bottlenecks in roadside edge infrastructure to add computing and data-transfer capacity.
- Develop a mobility-aware framework that routes tasks and data across varied edge hardware as vehicles move, tested through a pilot, a data-driven simulation and field trials on the Chattanooga connected-vehicle testbed.
- Create a multi-agent reinforcement learning controller that lets the power grid adjust electricity prices and charging rates, using a model of how people actually charge their electric vehicles.
- Apply mean-field game methods, which model very large groups of decision-makers, so that large numbers of EVs can choose charging stations on their own while accounting for charging rates.
- Design an incentive mechanism using graph-based multi-agent reinforcement learning and Shapley values, a fair way to split shared benefits, to steer the grid and EV operators toward socially optimal actions.
More about the research
These systems can overload or work against each other. The research asks how to coordinate large numbers of vehicles with the infrastructure around them so the whole system stays reliable, cheap and sustainable. It combines computing hardware design, decision-making algorithms and machine learning.
Why it matters
This work could lower the cost of deploying self-driving vehicles and make roads safer as automated vehicles become common. It aims to do this by adding small amounts of computing hardware only where networks are strained, instead of upgrading roadside infrastructure everywhere. Coordinating EV charging with grid pricing could cut costs and charging times for drivers and improve grid stability for operators. The methods may also carry over to other connected-device settings, such as smart healthcare and connected homes.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Excellence in Research: Advancing Scalability of Connected and Autonomous Vehicles via Bottom-up Hardware-Software Co-design
NSF · Oct 2026 – Sep 2029
Collaborative Research: CISE MSI: RDP: CPS: Enhancing Efficiency and Sustainability in Electric Transportation and Power Systems through Interaction-Aware Management
NSF · Jan 2025 – Dec 2027
Closest labs
Zhaomiao Guo
University of Texas at Austin, TX·Engineering·Early-career
Develop network models of how decentralized transportation and power system stakeholders with incomplete information interact across space and time as electric vehicles and clean energy expand.
Sidi Lu
William & Mary, VA·Computer Science
Develop a vehicle-edge-cloud framework in which software-defined vehicles and roadside units work together to deliver verified over-the-air software updates on time.
Jiangfeng Zhang
Clemson University, SC·Engineering
Model electric vehicle fast-charging station management as a multi-objective optimization over charging protocols, power allocation, pricing and grid interaction, constrained by battery degradation, market prices, solar output, vehicle-to-grid service and demand response.
The school
Central State University: 1 labs on PI Pages, $11M a year on research.
Reach out
A start for your email. Fill in the brackets.