arXiv subjects

Guannan Qu

Publications and source records attributed to Guannan Qu.

68 records · Page 4Linked to original sources

arXiv2020

Semi-Global Exponential Stability of Augmented Primal-Dual Gradient Dynamics for Constrained Convex Optimization

Primal-dual gradient dynamics that find saddle points of a Lagrangian have been widely employed for handling constrained optimization problems. Building on existing methods, we extend the augmented primal-dual gradient dynamics (Aug-PDGD) to incorporate general convex and nonlinear inequality constraints, and we establish its semi-global exponential stability when the objective function is strongly convex. We also provide an example of a strongly convex quadratic program of which the Aug-PDGD fails to achieve global exponential stability. Numerical simulation also suggests that the exponential convergence rate could depend on the initial distance to the KKT point.

math.OC↗

arXiv2020

Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networks

This paper introduces for the first time a framework to obtain provable worst-case guarantees for neural network performance, using learning for optimal power flow (OPF) problems as a guiding example. Neural networks have the potential to substantially reduce the computing time of OPF solutions. However, the lack of guarantees for their worst-case performance remains a major barrier for their adoption in practice. This work aims to remove this barrier. We formulate mixed-integer linear programs to obtain worst-case guarantees for neural network predictions related to (i) maximum constraint violations, (ii) maximum distances between predicted and optimal decision variables, and (iii) maximum sub-optimality. We demonstrate our methods on a range of PGLib-OPF networks up to 300 buses. We show that the worst-case guarantees can be up to one order of magnitude larger than the empirical lower bounds calculated with conventional methods. More importantly, we show that the worst-case predictions appear at the boundaries of the training input domain, and we demonstrate how we can systematically reduce the worst-case guarantees by training on a larger input domain than the domain they are evaluated on.

cs.AI↗

arXiv2020

Combining Model-Based and Model-Free Methods for Nonlinear Control: A Provably Convergent Policy Gradient Approach

Model-free learning-based control methods have seen great success recently. However, such methods typically suffer from poor sample complexity and limited convergence guarantees. This is in sharp contrast to classical model-based control, which has a rich theory but typically requires strong modeling assumptions. In this paper, we combine the two approaches to achieve the best of both worlds. We consider a dynamical system with both linear and non-linear components and develop a novel approach to use the linear model to define a warm start for a model-free, policy gradient method. We show this hybrid approach outperforms the model-based controller while avoiding the convergence issues associated with model-free approaches via both numerical experiments and theoretical analyses, in which we derive sufficient conditions on the non-linear component such that our approach is guaranteed to converge to the (nearly) global optimal controller.

math.OC↗

arXiv2020

Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward

It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exponentially large in the number of agents. In this paper, we identify a rich class of networked MARL problems where the model exhibits a local dependence structure that allows it to be solved in a scalable manner. Specifically, we propose a Scalable Actor-Critic (SAC) method that can learn a near optimal localized policy for optimizing the average reward with complexity scaling with the state-action space size of local neighborhoods, as opposed to the entire network. Our result centers around identifying and exploiting an exponential decay property that ensures the effect of agents on each other decays exponentially fast in their graph distance.

math.OC↗

arXiv2020

Online Optimization with Predictions and Switching Costs: Fast Algorithms and the Fundamental Limit

This paper studies an online optimization problem with a finite prediction window of cost functions and additional switching costs on decisions. We propose two gradient-based online algorithms: Receding Horizon Gradient Descent (RHGD), and Receding Horizon Accelerated Gradient (RHAG). Both algorithms only require a finite number of projected gradient evaluations at each stage. We provide upper bounds on the dynamic regrets of the proposed algorithms and show that the regret upper bounds decay exponentially with the length of the prediction window. Moreover, we study the fundamental lower bound on the dynamic regret for a broad class of deterministic online algorithms. The lower bound is close to RHAG's regret upper bound, indicating that our gradient-based RHAG is a near-optimal online algorithm. Finally, we conduct numerical experiments to complement our theoretical analysis.

math.OC↗

arXiv2020

Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning

We consider a general asynchronous Stochastic Approximation (SA) scheme featuring a weighted infinity-norm contractive operator, and prove a bound on its finite-time convergence rate on a single trajectory. Additionally, we specialize the result to asynchronous $Q$-learning. The resulting bound matches the sharpest available bound for synchronous $Q$-learning, and improves over previous known bounds for asynchronous $Q$-learning.

math.OC↗

arXiv2020

Distributed Optimal Voltage Control with Asynchronous and Delayed Communication

The increased penetration of volatile renewable energy into distribution networks necessities more efficient distributed voltage control. In this paper, we design distributed feedback control algorithms where each bus can inject \emph{both active and reactive} power into the grid to regulate the voltages. The control law on each bus is only based on local voltage measurements and communication to its physical neighbors. Moreover, the buses can perform their updates \emph{asynchronously} without receiving information from their neighbors for periods of time. The algorithm enforces \emph{hard upper and lower limits} on the active and reactive powers at every iteration. We prove that the algorithm converges to the optimal feasible voltage profile, assuming linear power flows. This provable convergence is maintained under bounded communication delays and asynchronous communications. We further numerically test the performance of the algorithm using the full \emph{nonlinear AC power flow} model. Our simulations show the effectiveness of our algorithm on realistic networks with both static and fluctuating loads, even in the presence of communication delays.

eess.SY↗

arXiv2019

Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structure

This paper considers a multi-agent Markov Decision Process (MDP), where there are $n$ agents and each agent $i$ is associated with a state $s_i$ and action $a_i$ taking values from a finite set. Though the global state space size and action space size are exponential in $n$, we impose local dependence structures and focus on local policies that only depend on local states, and we propose a method that finds nearly optimal local policies in polynomial time (in $n$) when the dependence structure is a one directional tree. The algorithm builds on approximated reward functions which are evaluated using locally truncated Markov process. Further, under some special conditions, we prove that the gap between the approximated reward function and the true reward function is decaying exponentially fast as the length of the truncated Markov process gets longer. The intuition behind this is that under some assumptions, the effect of agent interactions decays exponentially in the distance between agents, which we term "fast decaying property".

math.OC↗

arXiv2019

Optimal Distributed Feedback Voltage Control under Limited Reactive Power

In this paper, we propose a distributed voltage control in power distribution networks through reactive power compensation. The proposed control can (i) operate in a distributed fashion where each bus makes its decision based on local voltage measurements and communication with neighboring buses, (ii) always satisfy the reactive power capacity constraint, (iii) drive the voltage magnitude into an acceptable range, and (iv) minimize an operational cost. We also perform various numerical case studies to demonstrate the effectiveness and robustness of the controller using the nonlinear power flow model.

math.OC↗

arXiv2019

Accelerated Distributed Nesterov Gradient Descent

This paper considers the distributed optimization problem over a network, where the objective is to optimize a global function formed by a sum of local functions, using only local computation and communication. We develop an Accelerated Distributed Nesterov Gradient Descent (Acc-DNGD) method. When the objective function is convex and $L$-smooth, we show that it achieves a $O(\frac{1}{t^{1.4-ε}})$ convergence rate for all $ε\in(0,1.4)$. We also show the convergence rate can be improved to $O(\frac{1}{t^2})$ if the objective function is a composition of a linear map and a strongly-convex and smooth function. When the objective function is $μ$-strongly convex and $L$-smooth, we show that it achieves a linear convergence rate of $O([ 1 - C (\fracμ{L})^{5/7} ]^t)$, where $\frac{L}μ$ is the condition number of the objective, and $C>0$ is some constant that does not depend on $\frac{L}μ$.

math.OC↗

arXiv2019

Voltage Control Using Limited Communication

In electricity distribution networks, the increasing penetration of renewable energy generation necessitates faster and more sophisticated voltage controls. Unfortunately, recent research shows that local voltage control fails in achieving the desired regulation, unless there is communication between the controllers. However, the communication infrastructure for distribution systems is less reliable and less ubiquitous as compared to that for the bulk transmission system. In this paper, we design distributed voltage control that uses limited communication. That is, only neighboring buses need to communicate a few bits between each other for each control step. We investigate how these controllers can achieve the desired asymptotic behavior of the voltage regulation and we provide upper bounds on the number of bits that are needed to ensure a predefined accuracy of the regulation. Finally, we illustrate the results by numerical simulations.

math.OC↗

arXiv2018

On the Exponential Stability of Primal-Dual Gradient Dynamics

Continuous time primal-dual gradient dynamics that find a saddle point of a Lagrangian of an optimization problem have been widely used in systems and control. While the global asymptotic stability of such dynamics has been well-studied, it is less studied whether they are globally exponentially stable. In this paper, we study the primal-dual gradient dynamics for convex optimization with strongly-convex and smooth objectives and affine equality or inequality constraints, and prove global exponential stability for such dynamics. Bounds on decaying rates are provided.

math.OC↗

arXiv2017

Harnessing Smoothness to Accelerate Distributed Optimization

There has been a growing effort in studying the distributed optimization problem over a network. The objective is to optimize a global function formed by a sum of local functions, using only local computation and communication. Literature has developed consensus-based distributed (sub)gradient descent (DGD) methods and has shown that they have the same convergence rate $O(\frac{\log t}{\sqrt{t}})$ as the centralized (sub)gradient methods (CGD) when the function is convex but possibly nonsmooth. However, when the function is convex and smooth, under the framework of DGD, it is unclear how to harness the smoothness to obtain a faster convergence rate comparable to CGD's convergence rate. In this paper, we propose a distributed algorithm that, despite using the same amount of communication per iteration as DGD, can effectively harnesses the function smoothness and converge to the optimum with a rate of $O(\frac{1}{t})$. If the objective function is further strongly convex, our algorithm has a linear convergence rate. Both rates match the convergence rate of CGD. The key step in our algorithm is a novel gradient estimation scheme that uses history information to achieve fast and accurate estimation of the average gradient. To motivate the necessity of history information, we also show that it is impossible for a class of distributed algorithms like DGD to achieve a linear convergence rate without using history information even if the objective function is strongly convex and smooth.

math.OC↗

arXiv2016

Real-time Decentralized and Robust Voltage Control in Distribution Networks

Voltage control plays an important role in the operation of electricity distribution networks, especially when there is a large penetration of renewable energy resources. In this paper, we focus on voltage control through reactive power compensation and study how different information structures affect the control performance. In particular, we first show that using only voltage measurements to determine reactive power compensation is insufficient to maintain voltage in the acceptable range. Then we propose two fully decentralized and robust algorithms by adding additional information, which can stabilize the voltage in the acceptable range. The one with higher complexity can further minimize a cost of reactive power compensation in a particular form. Both of the two algorithms use only local measurements and local variables and require no communication. In addition, the two algorithms are robust against heterogeneous update rates and delays.

math.OC↗