PhD in AI-driven Fair Energy Curtailment Policies
Core
Design AI-driven control algorithms and probabilistic curtailment policies to manage congestion in electricity distribution networks while ensuring fairness and stability for distributed energy resources.
Role type
PhD candidate in AI and distributed optimization for energy systems
Builds
Scalable multi-agent decision-making methods and fairness-aware control rules for grid operators
Domain
Electrical engineering, distributed energy resources, machine learning, and control theory
Deliverable
production ML models
Required skills
Distributed optimization algorithms, probabilistic modeling, multi-agent systems, fairness theory, stochastic modeling, algorithm simulation
Preferred skills
Interdisciplinary collaboration, teaching, research mentorship
Technologies
ADMM, multi-agent MPC, consensus-based algorithms, open datasets
Responsibilities
Review literature on congestion management, analyze distributed optimization methods, develop probabilistic curtailment policies, design fairness-aware distributed controllers, model uncertainty in renewable generation, evaluate robustness of control policies, implement multi-agent coordination mechanisms, simulate large-scale distribution networks, collaborate with energy system experts, validate methods on real-world data
Seniority
PhD candidate, research-focused