Search Results for author: Zhaoyu Wang

Found 32 papers, 1 papers with code

Resilience assessment and planning in power distribution systems:Past and future considerations

no code implementations15 Aug 2023 Shuva Paul, Abodh Poudyal, Shiva Poudel, Anamika Dubey, Zhaoyu Wang

Moreover, this work provides an in-depth analysis of existing research on planning solutions to enhance distribution system resilience and support power distribution system operators and planners in developing effective mitigation strategies.

Optimal Power Flow for Integrated Primary-Secondary Distribution Networks with Service Transformers

no code implementations23 Jun 2023 Rui Cheng, Naihao Shi, Zhaoyu Wang, Zixiao Ma

This proposed SDNet OPF model can be easily embedded into existing primary distribution network (PDNet) OPF models, resulting in a holistic power system decision-making solution for integrated primary-secondary distribution networks.

Decision Making

Towards Practical Federated Causal Structure Learning

1 code implementation15 Jun 2023 Zhaoyu Wang, Pingchuan Ma, Shuai Wang

Federated learning can solve this problem, but existing solutions for federated causal structure learning make unrealistic assumptions about data and lack convergence guarantees.

Federated Learning

Robust Model Predictive Techno-Economic Control of Active Distribution Networks

no code implementations5 May 2023 Salish Maharjan, Prashant Tiwari, Rui Cheng, Zhaoyu Wang

Stochastic controllers are perceived as a promising solution for techno-economic operation of distribution networks having higher generation uncertainties at large penetration of renewables.

Continuous Control

Generalized Analytical Estimation of Sensitivity Matrices in Unbalanced Distribution Networks

no code implementations19 Apr 2023 Salish Maharjan, Rui Cheng, Zhaoyu Wang

Hence, this paper enhances the scope of analytical estimation of sensitivity matrices for unbalanced networks with 1-phase, 2-phase, and 3-phase Delta/Wye-connected loads, DERs with smart inverter functionality, and substation/line step-voltage regulators (SVR).

Data-Driven Affinely Adjustable Robust Volt/VAr Control

no code implementations10 Sep 2022 Naihao Shi, Rui Cheng, LiMing Liu, Zhaoyu Wang, Qianzhi Zhang

Finally, a distributed consensus-based solution, based on the alternating direction method of multipliers (ADMM), for the AARVVC is applied to decide the inverter reactive power adjustment rule with respect to its active power.

Tractable Data Enriched Distributionally Robust Chance-Constrained CVR

no code implementations7 Jul 2022 Qianzhi Zhang, Fankun Bu, Yi Guo, Zhaoyu Wang

To better consider the impacts of load and PV generation uncertainties on CVR implementation in distribution systems and provide less conservative solutions, this paper develops a data-based DRCC-CVR model with tractable reformulation and data enrichment method.

GPR

Automatic Self-Adaptive Local Voltage Control Under Limited Reactive Power

no code implementations18 Jun 2022 Rui Cheng, Naihao Shi, Salish Maharjan, Zhaoyu Wang

To this end, this paper proposes an automatic self-adaptive local voltage control (ASALVC) by locally controlling VAr outputs of distributed energy resources.

Online Voltage Control for Unbalanced Distribution Networks Using Projected Newton Method

no code implementations11 Jan 2022 Rui Cheng, Zhaoyu Wang, Yifei Guo, Qianzhi Zhang

It utilizes a non-diagonal symmetric positive definite matrix, developed from the Hessian matrix of the objective, to scale the gradient, and thus a fast convergence performance can be expected in this Newton-like algorithm.

Data-Driven Outage Restoration Time Prediction via Transfer Learning with Cluster Ensembles

no code implementations21 Dec 2021 Dingwei Wang, Yuxuan Yuan, Rui Cheng, Zhaoyu Wang

This paper develops a data-driven approach to accurately predict the restoration time of outages under different scales and factors.

Computational Efficiency Transfer Learning

Analyzing Photovoltaic's Impact on Conservation Voltage Reduction in Distribution Networks

no code implementations27 Oct 2021 Rui Cheng, Zhaoyu Wang, Yifei Guo, Fankun Bu

The results show that the allocations of solar PV have the most significant effect on the CVR performance, where a dispersed allocation of solar PV will help flatten voltage profile and achieve deeper voltage reductions at the substation, less energy consumption and line losses.

A Two-layer Approach for Estimating Behind-the-Meter PV Generation Using Smart Meter Data

no code implementations14 Oct 2021 Fankun Bu, Rui Cheng, Zhaoyu Wang

In this paper, we have come up with a novel two-layer approach to disaggregate the unknown PV generation and native demand from the known hourly net demand data recorded by smart meters: 1) At the aggregate level, the proposed approach separates the total PV generation and native demand time series from the total net demand time series for customers with PVs.

Time Series Time Series Analysis

Synthetic Active Distribution System Generation via Unbalanced Graph Generative Adversarial Network

no code implementations2 Aug 2021 Rong Yan, Yuxuan Yuan, Zhaoyu Wang, Guangchao Geng, Quanyuan Jiang

The basic idea is to learn the distribution of random walks both over a real-world system and across each phase of line segments, capturing the underlying local properties of an individual real-world distribution network and generating specific synthetic networks accordingly.

Generative Adversarial Network Time Series +1

Mitigating Smart Meter Asynchrony Error Via Multi-Objective Low Rank Matrix Recovery

no code implementations11 May 2021 Yuxuan Yuan, Kaveh Dehghanpour, Zhaoyu Wang

Smart meters (SMs) are being widely deployed by distribution utilities across the U. S.

An Online Feedback-Based Linearized Power Flow Model for Unbalanced Distribution Networks

no code implementations27 Mar 2021 Rui Cheng, Zhaoyu Wang, Yifei Guo

The non-linearity and non-convexity of power flow models and the phase coupling challenge the analysis and optimization of unbalanced distribution networks.

Distribution Grid Modeling Using Smart Meter Data

no code implementations28 Feb 2021 Yifei Guo, Yuxuan Yuan, Zhaoyu Wang

The knowledge of distribution grid models, including topologies and line impedances, is essential to grid monitoring, control and protection.

A Two-Level Simulation-Assisted Sequential Distribution System Restoration Model With Frequency Dynamics Constraints

no code implementations16 Jan 2021 Qianzhi Zhang, Zixiao Ma, Yongli Zhu, Zhaoyu Wang

This paper proposes a service restoration model for unbalanced distribution systems and inverter-dominated microgrids (MGs), in which frequency dynamics constraints are developed to optimize the amount of load restoration and guarantee the dynamic performance of system frequency response during the restoration process.

Stochastic Pre-Event Preparation for Enhancing Resilience of Distribution Systems with High DER Penetration

no code implementations24 Dec 2020 Qianzhi Zhang, Zhaoyu Wang, Shanshan Ma, Anmar Arif

This paper proposes a stochastic optimal preparation and resource allocation method for upcoming extreme weather events in distribution systems, which can assist utilities to achieve faster and more efficient post-event restoration.

Scheduling

Multi-Source Data Fusion Outage Location in Distribution Systems via Probabilistic Graph Models

no code implementations4 Dec 2020 Yuxuan Yuan, Kaveh Dehghanpour, Zhaoyu Wang, Fankun Bu

A novel aspect of the proposed approach is that it takes multi-source evidence and the complex structure of distribution systems into account using a probabilistic graphical method.

Graph Learning

A Hierarchical Deep Actor-Critic Learning Method for Joint Distribution System State Estimation

no code implementations4 Dec 2020 Yuxuan Yuan, Kaveh Dehghanpour, Zhaoyu Wang, Fankun Bu

To maintain monitoring accuracy, the two levels exchange boundary information with each other at the secondary nodes, including transformer voltages (first layer to second layer) and active/reactive total power injection (second layer to first layer).

Computational Efficiency Hierarchical Reinforcement Learning

Enriching Load Data Using Micro-PMUs and Smart Meters

no code implementations29 Nov 2020 Fankun Bu, Kaveh Dehghanpour, Zhaoyu Wang

The key to our approach is to statistically recover the high-resolution load data, which is masked by the low-resolution data, using trained probabilistic models of service transformers that have both high and low-resolution data sources, i. e, micro-PMUs and smart meters.

Hybrid Imitation Learning for Real-Time Service Restoration in Resilient Distribution Systems

no code implementations29 Nov 2020 Yichen Zhang, Feng Qiu, Tianqi Hong, Zhaoyu Wang, Fangxing Li

Self-healing capability is one of the most critical factors for a resilient distribution system, which requires intelligent agents to automatically perform restorative actions online, including network reconfiguration and reactive power dispatch.

Imitation Learning Reinforcement Learning (RL)

Switching Device-Cognizant Sequential Distribution System Restoration

no code implementations16 Nov 2020 Anmar Arif, Bai Cui, Zhaoyu Wang

This paper presents an optimization framework for sequential reconfiguration using an assortment of switching devices and repair process in distribution system restoration.

Computational Efficiency

Distributed Optimal Conservation Voltage Reduction in Integrated Primary-Secondary Distribution Systems

no code implementations9 Nov 2020 Qianzhi Zhang, Yifei Guo, Zhaoyu Wang, Fankun Bu

This paper proposes an asychronous distributed leader-follower control method to achieve conservation voltage reduction (CVR) in three-phase unbalanced distribution systems by optimally scheduling smart inverters of distributed energy resources (DERs).

Scheduling

Extracting resilience metrics from distribution utility data using outage and restore process statistics

no code implementations2 Nov 2020 Nichelle'Le K. Carrington, Ian Dobson, Zhaoyu Wang

The formulas express the mean value of these metrics as a function of the number of outages in the event.

Learning-Based Real-Time Event Identification Using Rich Real PMU Data

no code implementations17 Jun 2020 Yuxuan Yuan, Yifei Guo, Kaveh Dehghanpour, Zhaoyu Wang, Yanchao Wang

A large-scale deployment of phasor measurement units (PMUs) that reveal the inherent physical laws of power systems from a data perspective enables an enhanced awareness of power system operation.

Time Series Time Series Analysis

Self-supervised Learning: Generative or Contrastive

no code implementations15 Jun 2020 Xiao Liu, Fanjin Zhang, Zhenyu Hou, Zhaoyu Wang, Li Mian, Jing Zhang, Jie Tang

As an alternative, self-supervised learning attracts many researchers for its soaring performance on representation learning in the last several years.

Graph Learning Representation Learning +1

Singular Perturbation-based Large-Signal Order Reduction of Microgrids for Stability and Accuracy Synthesis with Control

no code implementations8 Oct 2019 Zixiao Ma, Zhaoyu Wang, Yuxuan Yuan, Tianqi Hong

Higher-level controller design and stability analysis of such high-order systems are usually intractable and computation-costly.

Deep Generative Graph Distribution Learning for Synthetic Power Grids

no code implementations17 Jan 2019 Mahdi Khodayar, Jianhui Wang, Zhaoyu Wang

Power system studies require the topological structures of real-world power networks; however, such data is confidential due to important security concerns.

Energy Disaggregation via Deep Temporal Dictionary Learning

no code implementations10 Sep 2018 Mahdi Khodayar, Jianhui Wang, Zhaoyu Wang

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.

Dictionary Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.