Skip to search formSkip to main contentSkip to account menu

Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods

A deep learning approach to the Optimal Power Flow problem that exploits the information available in the prior states of the system, as well as a dual Lagrangian method to satisfy the physical and engineering constraints present in the OPF.
View PDF on arXiv (opens in a new tab)

Lagrangian Duality for Constrained Deep Learning

Lagrangian duality can be used to enforce fairness constraints on a predictor and obtain state-of-the-art results when minimizing disparate treatments and can complement deep learning to impose monotonicity constraints on the predictor without sacrificing accuracy.
View PDF on arXiv (opens in a new tab)

Efficient dynamic compressor optimization in natural gas transmission systems

An efficient scheme to minimize compression costs under dynamic conditions where deliveries to customers are described by time-dependent mass flow and the proposed optimization scheme is validated against an integration of dynamic equations with adaptive time-stepping, as well as a recently proposed state-of-the-art optimal control method.
View on IEEE (opens in a new tab)

Spatial Network Decomposition for Fast and Scalable AC-OPF Learning

A novel machine-learning approach for predicting AC-OPF solutions that features a fast and scalable training that exploits a spatial decomposition of the power network that is viewed as a set of regions.
View on IEEE (opens in a new tab)

Differential Privacy for Power Grid Obfuscation

Experimental results show that the obfuscation significantly reduces the potential damage of an attack carried by exploiting the released dataset, and largely preserves the fidelity of the obfuscated power network.
View on IEEE (opens in a new tab)

Power system restoration planning with standing phase angle and voltage difference constraints

The paper examines transient effects in power restoration and generalizes the ROP formulation with standing phase angle and voltage difference constraints in order to minimize rotor swings and reduces rotor swings of synchronous generators by over 50%.
View on IEEE (opens in a new tab)

High-Fidelity Machine Learning Approximations of Large-Scale Optimal Power Flow

This paper proposes an integration of deep neural networks and Lagrangian duality to capture the physical and operational constraints of the AC Optimal Power Flow and produces highly accurate approximations whose costs are within 0.01% of optimality.
View PDF on arXiv (opens in a new tab)

Power System Restoration With Transient Stability

This paper shows how to integrate transient stability in the optimization procedure by capturing the rotor dynamics of power generators by minimizing the difference with respect to steady states solutions.
View via Publisher (opens in a new tab)

Privacy-Preserving Obfuscation for Distributed Power Systems

A distributed algorithm is proposed that complies with the notion of Differential Privacy, a strong privacy framework used to bound the risk of re-identification, and guarantees that the released privacy-preserving data retains high fidelity and satisfies the AC power flow constraints.
View PDF on arXiv (opens in a new tab)

Dynamic Compressor Optimization in Natural Gas Pipeline Systems

A computationally efficient method for minimizing gas compression costs under dynamic conditions where deliveries to customers are described by time-dependent mass flows and the resulting large-scale NLPs are solved using an interior point method.
View via Publisher (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)