arXiv subjects

Baosen Zhang

Publications and source records attributed to Baosen Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2019

A tractable ellipsoidal approximation for voltage regulation problems

We present a machine learning approach to the solution of chance constrained optimizations in the context of voltage regulation problems in power system operation. The novelty of our approach resides in approximating the feasible region of uncertainty with an ellipsoid. We formulate this problem using a learning model similar to Support Vector Machines (SVM) and propose a sampling algorithm that efficiently trains the model. We demonstrate our approach on a voltage regulation problem using standard IEEE distribution test feeders.

eess.SY↗

arXiv2019

Optimal Control Via Neural Networks: A Convex Approach

Control of complex systems involves both system identification and controller design. Deep neural networks have proven to be successful in many identification tasks, however, from model-based control perspective, these networks are difficult to work with because they are typically nonlinear and nonconvex. Therefore many systems are still identified and controlled based on simple linear models despite their poor representation capability. In this paper we bridge the gap between model accuracy and control tractability faced by neural networks, by explicitly constructing networks that are convex with respect to their inputs. We show that these input convex networks can be trained to obtain accurate models of complex physical systems. In particular, we design input convex recurrent neural networks to capture temporal behavior of dynamical systems. Then optimal controllers can be achieved via solving a convex model predictive control problem. Experiment results demonstrate the good potential of the proposed input convex neural network based approach in a variety of control applications. In particular we show that in the MuJoCo locomotion tasks, we could achieve over 10% higher performance using 5* less time compared with state-of-the-art model-based reinforcement learning method; and in the building HVAC control example, our method achieved up to 20% energy reduction compared with classic linear models.

math.OC↗

arXiv2018

Distribution System Voltage Control under Uncertainties using Tractable Chance Constraints

Voltage control plays an important role in the operation of electricity distribution networks, especially with high penetration of distributed energy resources. These resources introduce significant and fast varying uncertainties. In this paper, we focus on reactive power compensation to control voltage in the presence of uncertainties. We adopt a chance constraint approach that accounts for arbitrary correlations between renewable resources at each of the buses. We show how the problem can be solved efficiently using historical samples via a stochastic quasi gradient method. We also show that this optimization problem is convex for a wide variety of probabilistic distributions. Compared to conventional per-bus chance constraints, our formulation is more robust to uncertainty and more computationally tractable. We illustrate the results using standard IEEE distribution test feeders.

math.OC↗

arXiv2018

Optimal Battery Control Under Cycle Aging Mechanisms in Pay for Performance Settings

We study the optimal control of battery energy storage under a general "pay-for-performance" setup such as providing frequency regulation and renewable integration. In these settings, batteries need to carefully balance the trade-off between following the instruction signals and their degradation costs in real-time. Existing battery control strategies either do not consider the uncertainty of future signals, or cannot accurately account for battery cycle aging mechanism during operation. In this work, we take a different approach to the optimal battery control problem. Instead of attacking the complexity of battery degradation function or the lack of future information one at a time, we address these two challenges together in a joint fashion. In particular, we present an electrochemically accurate and trackable battery degradation model called the rainflow cycle-based model. We prove the degradation cost is convex. Then we propose an online control policy with a simple threshold structure and show it achieve near-optimal performance with respect to an offline controller that has complete future information. We explicitly characterize the optimality gap and show it is independent to the duration of operation. Simulation results with both synthetic and real regulation traces are conducted to illustrate the theoretical results.

math.OC↗

arXiv2018

Real-Time Prediction of the Duration of Distribution System Outages

This paper addresses the problem of predicting duration of unplanned power outages, using historical outage records to train a series of neural network predictors. The initial duration prediction is made based on environmental factors, and it is updated based on incoming field reports using natural language processing to automatically analyze the text. Experiments using 15 years of outage records show good initial results and improved performance leveraging text. Case studies show that the language processing identifies phrases that point to outage causes and repair steps.

eess.SY↗

arXiv2018

Optimal Design of Virtual Inertia and Damping Coefficients for Virtual Synchronous Machines

Increased penetration of inverter-connected renewable energy sources (RES) in the power system has resulted in a decrease in available rotational inertia which serves as an immediate response to frequency deviation due to disturbances. The concept of virtual inertia has been proposed to combat this decrease by enabling the inverters to produce active power in response to a frequency deviation like a synchronous generator. In this paper, we present an algorithm to optimally design the inertia and damping coefficient required for an inverter-based virtual synchronous machine (VSM) to participate efficiently in the inertia response portion of primary frequency control. We design the objective function to explicitly trade-off between competing objectives such as the damping rate the the frequency nadir. Specifically, we formulate the design problem as a constrained and regularized H2 norm minimization problem, and develop an efficient gradient algorithm for this non-convex problem. This proposed algorithm is applied to a test case to demonstrate its performance against existing methods.

eess.SY↗

arXiv2018

Optimal Battery Participation in Frequency Regulation Markets

Battery participants in performance-based frequency regulation markets must consider the cost of battery aging in their operating strategies to maximize market profits. In this paper we solve this problem by proposing an optimal control policy and an optimal bidding policy based on realistic market settings and an accurate battery aging model. The proposed control policy has a threshold structure and achieves near-optimal performance with respect to an offline controller that has complete future information. The proposed bidding policy considers the optimal control policy to maximize market profits while satisfying the market performance requirement through a chance-constraint. It factors the value of performance and supports a trade-off between higher profits and a lower risk of violating performance requirements. We demonstrate the optimality of both policies using simulations. A case study based on the PJM regulation market shows that our approach is effective at maximizing operating profits.

math.OC↗

arXiv2018

How Much Urban Traffic is Searching for Parking? Simulating Curbside Parking as a Network of Finite Capacity Queues

With the increasing availability of transaction data collected by digital parking meters, paid curbside parking can be advantageously modeled as a network of interdependent queues. In this article we introduce methods for analyzing a special class of networks of finite capacity queues, where tasks arrive from an exogenous source, join the queue if there is an available server or are rejected and move to another queue in search of service according to the network topology. Such networks can be useful for modeling curbside parking since queues in the network perform the same function and drivers searching for an available server are under combinatorial constraints and jockeying is not instantaneous. Further, we provide a motivating example for such networks of finite capacity queues in the context of drivers searching for parking in the neighborhood of Belltown in Seattle, Washington, USA. Lastly, since the stationary distribution of such networks used to model parking are difficult to satisfactorily characterize, we also introduce a simulation tool for the purpose of testing the assumptions made to estimate interesting performance metrics. Our results suggest that a Markovian relaxation of the problem when solving for the mean rate metrics is comparable to deterministic service times reflective of a driver's tendency to park for the maximum allowable time.

cs.CY↗

arXiv2018

Non-Wire Alternatives to Capacity Expansion

Distributed energy resources (DERs) can serve as non-wire alternatives to capacity expansion by managing peak load to avoid or defer traditional expansion projects. In this paper, we study a planning problem that co-optimizes DERs investment and operation (e.g., energy efficiency, energy storage, demand response, solar photovoltaic) and the timing of capacity expansion. We formulate the problem as a large scale (in the order of millions of variables because we model the operation of DERs over a period of decades) non-convex optimization problem. Despite its non-convexities, we find its optimal solution by decomposing it using the Dantzig-Wolfe Decomposition Algorithm and solving a series of small linear problems. Finally, we present a real planning problem at the University of Washington Seattle Campus.

math.OC↗

arXiv2018

An Unsupervised Deep Learning Approach for Scenario Forecasts

In this paper, we propose a novel scenario forecasts approach which can be applied to a broad range of power system operations (e.g., wind, solar, load) over various forecasts horizons and prediction intervals. This approach is model-free and data-driven, producing a set of scenarios that represent possible future behaviors based only on historical observations and point forecasts. It first applies a newly-developed unsupervised deep learning framework, the generative adversarial networks, to learn the intrinsic patterns in historical renewable generation data. Then by solving an optimization problem, we are able to quickly generate large number of realistic future scenarios. The proposed method has been applied to a wind power generation and forecasting dataset from national renewable energy laboratory. Simulation results indicate our method is able to generate scenarios that capture spatial and temporal correlations. Our code and simulation datasets are freely available online.

math.OC↗

arXiv2018

An Online Optimization Algorithm for Alleviating Contingencies in Transmission Networks

Power systems are increasingly operated in corrective rather than preventive security mode, which means that appropriate control actions must be taken immediately after a contingency has occurred. This paper proposes an online algorithm for automatically alleviating contingencies such as voltage limit violations and line overloads. Unlike previously proposed approaches, the network itself serves as a natural solver of the power flow equations. This makes it possible to start the implementation immediately and avoids problems caused by modeling errors. Every time the controller receives measurements from the grid, it evaluates the presence of contingencies and computes the optimal corrective actions that can be implemented before the next sampling period, subject to ramping constraints of the generators. These corrective actions are implemented through the standard Automatic Generation Control. Finding the optimal incremental corrective actions is fast because this problem is linearized. The effectiveness of this algorithm at correcting both line overloads and voltage violations is demonstrated using the IEEE-118 Bus test system.

math.OC↗

arXiv2018

Tractable and Robust Modeling of Building Flexibility Using Coarse Data

Controllable building loads have the potential to increase the flexibility of power systems. A key step in developing effective and attainable load control policies is modeling the set of feasible building load profiles. In this paper, we consider buildings whose source of flexibility is their HVAC loads. We propose a data-driven method to empirically estimate a robust feasible region of the load using coarse data, that is, using only total building load and average indoor temperatures. The proposed method uses easy-to-gather coarse data and can be adapted to buildings of any type. The resulting feasible region model is robust to temperature prediction errors and is described by linear constraints. The mathematical simplicity of these constraints makes the proposed model adaptable to many power system applications, for example, economic dispatch, and optimal power flow. We validate our model using data from EnergyPlus and demonstrate its usefulness through a case study in which flexible building loads are used to balance errors in wind power forecasts.

math.OC↗

arXiv2018

Model-Free Renewable Scenario Generation Using Generative Adversarial Networks

Scenario generation is an important step in the operation and planning of power systems with high renewable penetrations. In this work, we proposed a data-driven approach for scenario generation using generative adversarial networks, which is based on two interconnected deep neural networks. Compared with existing methods based on probabilistic models that are often hard to scale or sample from, our method is data-driven, and captures renewable energy production patterns in both temporal and spatial dimensions for a large number of correlated resources. For validation, we use wind and solar times-series data from NREL integration data sets. We demonstrate that the proposed method is able to generate realistic wind and photovoltaic power profiles with full diversity of behaviors. We also illustrate how to generate scenarios based on different conditions of interest by using labeled data during training. For example, scenarios can be conditioned on weather events~(e.g. high wind day) or time of the year~(e,g. solar generation for a day in July). Because of the feedforward nature of the neural networks, scenarios can be generated extremely efficiently without sophisticated sampling techniques.

cs.LG↗

arXiv2018

Bayesian Renewables Scenario Generation via Deep Generative Networks

We present a method to generate renewable scenarios using Bayesian probabilities by implementing the Bayesian generative adversarial network~(Bayesian GAN), which is a variant of generative adversarial networks based on two interconnected deep neural networks. By using a Bayesian formulation, generators can be constructed and trained to produce scenarios that capture different salient modes in the data, allowing for better diversity and more accurate representation of the underlying physical process. Compared to conventional statistical models that are often hard to scale or sample from, this method is model-free and can generate samples extremely efficiently. For validation, we use wind and solar times-series data from NREL integration data sets to train the Bayesian GAN. We demonstrate that proposed method is able to generate clusters of wind scenarios with different variance and mean value, and is able to distinguish and generate wind and solar scenarios simultaneously even if the historical data are intentionally mixed.

math.OC↗

arXiv2018

Uncertainty in Multi-Commodity Routing Networks: When does it help?

We study the equilibrium behavior in a multi-commodity selfish routing game with many types of uncertain users where each user over- or under-estimates their congestion costs by a multiplicative factor. Surprisingly, we find that uncertainties in different directions have qualitatively distinct impacts on equilibria. Namely, contrary to the usual notion that uncertainty increases inefficiencies, network congestion actually decreases when users over-estimate their costs. On the other hand, under-estimation of costs leads to increased congestion. We apply these results to urban transportation networks, where drivers have different estimates about the cost of congestion. In light of the dynamic pricing policies aimed at tackling congestion, our results indicate that users' perception of these prices can significantly impact the policy's efficacy, and "caution in the face of uncertainty" leads to favorable network conditions.

cs.GT↗

arXiv2017

Accurate Semidefinite Programming Models for Optimal Power Flow in Distribution Systems

In this paper, we develop semidefinite programming (SDP) models aimed at solving optimal power flow (OPF) problems in distribution systems. We propose two models: the symmetrical SDP model which modifies the existing BFM-SDP model. Then based on the symmetrical SDP model, we develop a voltage regulation model that solves OPF problems with binding voltage constraints. To evaluate the accuracy of our proposed OPF models, we rely on OpenDSS, a power flow solver, to generate power flow solutions as the benchmarks. Comprehensive case studies are conducted showing our SDP models have better numerical stability and yield more accurate results than existing approaches

math.OC↗

arXiv2017

Modeling and Optimization of Complex Building Energy Systems with Deep Neural Networks

Modern buildings encompass complex dynamics of multiple electrical, mechanical, and control systems. One of the biggest hurdles in applying conventional model-based optimization and control methods to building energy management is the huge cost and effort of capturing diverse and temporally correlated dynamics. Here we propose an alternative approach which is model-free and data-driven. By utilizing high volume of data coming from advanced sensors, we train a deep Recurrent Neural Networks (RNN) which could accurately represent the operation's temporal dynamics of building complexes. The trained network is then directly fitted into a constrained optimization problem with finite horizons. By reformulating the constrained optimization as an unconstrained optimization problem, we use iterative gradient descents method with momentum to find optimal control inputs. Simulation results demonstrate proposed method's improved performances over model-based approach on both building system modeling and control.

math.OC↗

arXiv2017

Using Battery Storage for Peak Shaving and Frequency Regulation: Joint Optimization for Superlinear Gains

We consider using a battery storage system simultaneously for peak shaving and frequency regulation through a joint optimization framework which captures battery degradation, operational constraints and uncertainties in customer load and regulation signals. Under this framework, using real data we show the electricity bill of users can be reduced by up to 15\%. Furthermore, we demonstrate that the saving from joint optimization is often larger than the sum of the optimal savings when the battery is used for the two individual applications. A simple threshold real-time algorithm is proposed and achieves this super-linear gain. Compared to prior works that focused on using battery storage systems for single applications, our results suggest that batteries can achieve much larger economic benefits than previously thought if they jointly provide multiple services.

eess.SY↗