arXiv subjects

Zhaoyu Wang

Publications and source records attributed to Zhaoyu Wang.

120 records · Page 7Linked to original sources

arXiv2019

Deep Generative Graph Distribution Learning for Synthetic Power Grids

Power system studies require the topological structures of real-world power networks; however, such data is confidential due to important security concerns. Thus, power grid synthesis (PGS), i.e., creating realistic power grids that imitate actual power networks, has gained significant attention. In this letter, we cast PGS into a graph distribution learning (GDL) problem where the probability distribution functions (PDFs) of the nodes (buses) and edges (lines) are captured. A novel deep GDL (DeepGDL) model is proposed to learn the topological patterns of buses/lines with their physical features (e.g., power injection and line impedance). Having a deep nonlinear recurrent structure, DeepGDL understands complex nonlinear topological properties and captures the graph PDF. Sampling from the obtained PDF, we are able to create a large set of realistic networks that all resemble the original power grid. Simulation results show the significant accuracy of our created synthetic power grids in terms of various topological metrics and power flow measurements.

cs.SI↗

arXiv2019

Markov Decision Process-based Resilience Enhancement for Distribution Systems: An Approximate Dynamic Programming Approach

Because failures in distribution systems caused by extreme weather events directly result in consumers' outages, this paper proposes a state-based decision-making model with the objective of mitigating loss of load to improve the distribution system resilience throughout the unfolding events. The sequentially uncertain system states, e.g., feeder line on/off states, driven by the unfolding events are modeled as Markov states, and the probabilities from one Markov state to another Markov state throughout the unfolding events are determined by the component failure caused by the unfolding events. A recursive optimization model based on Markov decision processes (MDP) is developed to make state-based actions, i.e., system reconfiguration, at each decision time. To overcome the curse of dimensionality caused by enormous states and actions, an approximate dynamic programming (ADP) approach based on post-decision states and iteration is used to solve the proposed MDP-based model. IEEE 33-bus system and IEEE 123-bus system are used to validate the proposed model.

math.OC↗

arXiv2018

A Survey on State Estimation Techniques and Challenges in Smart Distribution Systems

This paper presents a review of the literature on State Estimation (SE) in power systems. While covering some works related to SE in transmission systems, the main focus of this paper is Distribution System State Estimation (DSSE). The paper discusses a few critical topics of DSSE, including mathematical problem formulation, application of pseudo-measurements, metering instrument placement, network topology issues, impacts of renewable penetration, and cyber-security. Both conventional and modern data-driven and probabilistic techniques have been reviewed. This paper can provide researchers and utility engineers with insights into the technical achievements, barriers, and future research directions of DSSE.

eess.SY↗

arXiv2018

Counterexample to Equivalent Nodal Analysis for Voltage Stability Assessment

Existing literature claims that the L-index for voltage instability detection is inaccurate and proposes an improved index quantifying voltage stability through system equivalencing. The proposed stability condition is claimed to be exact in determining voltage instability.We show the condition is incorrect through simple arguments accompanied by demonstration on a two-bus system counterexample.

math.OC↗

arXiv2018

Energy Disaggregation via Deep Temporal Dictionary Learning

This paper addresses the energy disaggregation problem, i.e. decomposing the electricity signal of a whole home to its operating devices. First, we cast the problem as a dictionary learning (DL) problem where the key electricity patterns representing consumption behaviors are extracted for each device and stored in a dictionary matrix. The electricity signal of each device is then modeled by a linear combination of such patterns with sparse coefficients that determine the contribution of each device in the total electricity. Although popular, the classic DL approach is prone to high error in real-world applications including energy disaggregation, as it merely finds linear dictionaries. Moreover, this method lacks a recurrent structure; thus, it is unable to leverage the temporal structure of energy signals. Motivated by such shortcomings, we propose a novel optimization program where the dictionary and its sparse coefficients are optimized simultaneously with a deep neural model extracting powerful nonlinear features from the energy signals. A long short-term memory auto-encoder (LSTM-AE) is proposed with tunable time dependent states to capture the temporal behavior of energy signals for each device. We learn the dictionary in the space of temporal features captured by the LSTM-AE rather than the original space of the energy signals; hence, in contrast to the traditional DL, here, a nonlinear dictionary is learned using powerful temporal features extracted from our deep model. Real experiments on the publicly available Reference Energy Disaggregation Dataset (REDD) show significant improvement compared to the state-of-the-art methodologies in terms of the disaggregation accuracy and F-score metrics.

cs.LG↗

arXiv2018

A Multi-Timescale Data-Driven Approach to Enhance Distribution System Observability

This paper presents a novel data-driven method that determines the daily consumption patterns of customers without smart meters (SMs) to enhance the observability of distribution systems. Using the proposed method, the daily consumption of unobserved customers is extracted from their monthly billing data based on three machine learning models: first, a spectral clustering (SC) algorithm is used to infer the typical daily load profiles of customers with SMs. Each typical daily load behavior represents a distinct class of customer behavior. In the second module, a multi-timescale learning (MTSL) model is trained to estimate the hourly consumption using monthly energy data for the customers of each class. The third stage leverages a recursive Bayesian learning (RBL) method and branch current state estimation (BCSE) residuals to estimate the daily load profiles of unobserved customers without SMs. The proposed data-driven method has been tested and verified using real utility data.

eess.SY↗

arXiv2018

A Game-Theoretic Data-Driven Approach for Pseudo-Measurement Generation in Distribution System State Estimation

In this paper, we present an efficient computational framework with the purpose of generating weighted pseudo-measurements to improve the quality of Distribution System State Estimation (DSSE) and provide observability with Advanced Metering Infrastructure (AMI) against unobservable customers and missing data. The proposed technique is based on a game-theoretic expansion of Relevance Vector Machines (RVM). This platform is able to estimate the customer power consumption data and quantify its uncertainty while reducing the prohibitive computational burden of model training for large AMI datasets. To achieve this objective, the large training set is decomposed and distributed among multiple parallel learning entities. The resulting estimations from the parallel RVMs are then combined using a game-theoretic model based on the idea of repeated games with vector payoff. It is observed that through this approach and by exploiting the seasonal changes in customers' behavior the accuracy of pseudo-measurements can be considerably improved, while introducing robustness against bad training data samples. The proposed pseudo-measurement generation model is integrated into a DSSE using a closed-loop information system, which takes advantage of a Branch Current State Estimator (BCSE) data to further improve the performance of the designed machine learning framework. This method has been tested on a practical distribution feeder model with smart meter data for verification.

eess.SY↗

arXiv2018

Optimizing Service Restoration in Distribution Systems with Uncertain Repair Time and Demand

This paper proposes a novel method to co-optimize distribution system operation and repair crew routing for outage restoration after extreme weather events. A two-stage stochastic mixed integer linear program is developed. The first stage is to dispatch the repair crews to the damaged components. The second stage is distribution system restoration using distributed generators, and reconfiguration. We consider demand uncertainty in terms of a truncated normal forecast error distribution, and model the uncertainty of the repair time using a lognormal distribution. A new decomposition approach, combined with the Progressive Hedging algorithm, is developed for solving large-scale outage management problems in an effective and timely manner. The proposed method is validated on modified IEEE 34- and 8500-bus distribution test systems.

math.OC↗

arXiv2018

Dynamic Game-based Maintenance Scheduling of Integrated Electric and Natural Gas Grids with a Bilevel Approach

This paper proposes a dynamic game-based maintenance scheduling mechanism for the asset owners of the natural gas grid and the power grid by using a bilevel approach. In the upper level, the asset owners of the natural gas grid and the power grid schedule maintenance to maximize their own revenues. This level is modeled as a dynamic game problem, which is solved by the backward induction algorithm. In the lower level, the independent system operator (ISO) dispatches the system to minimize the loss of power load and natural gas load in consideration of the system operating conditions under maintenance plans from the asset owners in the upper level. This is modeled as a mixed integer linear programming problem. For the model of the natural gas grid, a piecewise linear approximation associated with the big-M approach is used to transform the original nonlinear model into the mixed integer linear model. Numerical tests on a 6-bus system with a 4-node gas grid show the effectiveness of the proposed model.

math.OC↗

arXiv2018

A Linear Solution Method of Generalized Robust Chance Constrained Real-time Dispatch

In this letter, a novel solution method of generalized robust chance constrained real-time dispatch (GRCC-RTD) considering wind power uncertainty is proposed. GRCC models are advantageous in dealing with distributional uncertainty, however, they are difficult to solve because of the complex ambiguity set. By constructing traceable counterparts of the robust chance constraints and using the reformulation linearization technique, the model is equivalently transformed into a deterministic linear programming problem, which can be solved efficiently by off-the-shelf solvers. Numerical results verify the effectiveness and efficiency of the approach.

eess.SP↗

arXiv2017

Exploring cascading outages and weather via processing historic data

We describe some bulk statistics of historical initial line outages and the implications for forming contingency lists and understanding which initial outages are likely to lead to further cascading. We use historical outage data to estimate the effect of weather on cascading via cause codes and via NOAA storm data. Bad weather significantly increases outage rates and interacts with cascading effects, and should be accounted for in cascading models and simulations. We suggest how weather effects can be incorporated into the OPA cascading simulation and validated. There are very good prospects for improving data processing and models for the bulk statistics of historical outage data so that cascading can be better understood and quantified.

physics.soc-ph↗

arXiv2017

A Necessary Condition for Power Flow Insolvability in Power Distribution Systems with Distributed Generators

This paper proposes a necessary condition for power flow insolvability in power distribution systems with distributed generators (DGs). We show that the proposed necessary condition indicates the impending singularity of the Jacobian matrix and the onset of voltage instability. We consider different operation modes of DG inverters, e.g., constant-power and constant-current operations, in the proposed method. A new index based on the presented necessary condition is developed to indicate the distance between the current operating point and the power flow solvability boundary. Compared to existing methods, the operating condition-dependent critical loading factor provided by the proposed condition is less conservative and is closer to the actual power flow solution space boundary. The proposed method only requires the present snapshots of voltage phasors to monitor the power flow insolvability and voltage stability. Hence, it is computationally efficient and suitable to be applied to a power distribution system with volatile DG outputs. The accuracy of the proposed necessary condition and the index is validated by simulations on a distribution test system with different DG penetration levels.

math.OC↗