XWXinan Wang

Xinan Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xinan Wang has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Privacy-Preserving Baseline Load Reconstruction for Residential Demand Response Considering Distributed Energy Resources

    by Yang Chen, Chunyu Chen, Xiao Zhang, Mingjian Cui, Fangxing Li, Xinan Wang, Shengfei Yin

    Customer baseline load (CBL) reconstruction is a critical problem in residential demand response. The difficulty of residential CBL lies in the variability of both irregular consumption and on-site distributed energy resources. Targeting the CBL reconstruction of residential prosumers, a regression-based estimation scheme is proposed using stacked autoencoders (SAEs) under the federated learning (FL) framework. In the FL framework, each residential unit (RU) stores and trains data locally without sharing them with neighboring RUs or the independent third party (ITP) responsible for CBL reconstruction. Local updates containing no load information are exchanged with the ITP (server) for the training improvement. The FL framework can, thus, protect the privacy of customers. Experimental results show that the proposed FL-based cascaded SAE outperforms the baseline on all tests and achieves up to 62.5% improvement in reducing reconstruction error. Moreover, it has enhanced privacy-preserving knowledge-sharing ability, higher efficiency, and better stability.


  • Open Access

    A High Linearity Process Angle Interference Resistant Multi-phase Output Digital Control Oscillator with Negative Feedback

    by Changpei Qiu, Xin'AN Wang, Xing Zhang, Tianxia Zhao, Qiuping Li, Hu Wang

    In this paper, we have proposed a high linearity process angle interference resistant multi-phase output digital control oscillator with negative feedback. The proposed digital control oscillator uses negative feedback structure to improve the output frequency linearity and resist process angle interference, while this paper optimizes and designs the circuit for the digital control current source differential cross-coupling structure basic delay unit, negative feedback structure. The DCO mentioned has beenimplemented in standard 130nm CMOS. The DCO designed in this paper has 8-phase output with frequency tuning in the range of 0.2 GHz-2.5 GHz and gain in the range of 2.14 MHz/LSB-5.5 MHz/LSB, with good linearity. At 1.5 GHz, the process leads to a frequency jitter size of only 6.6%, which has the property of resistance to process corner interference. The cycle integration jitter is 2.79ps, and the power consumption is 1.65mW.

  • Open Access

    A high precision, high linearity 10 bit Digital-to-Time Converter circuit

    by Changpei Qiu, Xin'AN Wang, Xing Zhang, Bo Wang, Tianxia Zhao, Qiuping Li

    In this paper, a high precision, high linearity 10 bit Digital-to-Time Converter (DTC) circuit was designed and implemented using a conventional open loop amplifier comparator and voltage reference source. The proposed Digital-to-Time Converter circuit (DTC) uses a large capacitor as the load to implement the "fixed-slope method" and controls the capacitor array with a "segmented coding method" to improve the nonlinearity of the DTC. The DTC mentioned has been implemented in standard 130nm CMOS. The DTC designed in this paper has high precision and linearity. The accuracy of the DTC designed in this paper is 315fs. The integral nonlinearity is below 0.52LSB, and the power consumption is 26.4μW.

  • Top Cited Papers

    Deep Reinforcement Learning Based Volt-VAR Optimization in Smart Distribution Systems

    by Ying Zhang, Xinan Wang, Jianhui Wang, Yingchen Zhang

    This paper develops a model-free volt-VAR optimization (VVO) algorithm via multi-agent deep reinforcement learning (DRL) in unbalanced distribution systems. This method is novel since we cast the VVO problem in distribution networks to an intelligent deep Q-network (DQN) framework, which avoids solving a specific optimization model directly when facing time-varying operating conditions in the systems. We consider statuses/ratios of switchable capacitors, voltage regulators, and smart inverters installed at distributed generators as the action variables of the agents. A delicately designed reward function guides these agents to interact with the distribution system, in the direction of reinforcing voltage regulation and power loss reduction simultaneously. The forward-backward sweep method for radial three-phase distribution systems provides accurate power flow results within a few iterations to the DRL environment. The proposed method realizes the dual goals for VVO. We test this algorithm on the unbalanced IEEE 13-bus and 123-bus systems. Numerical simulations validate the excellent performance of this method in voltage regulation and power loss reduction.


  • Model-Free Emergency Frequency Control Based on Reinforcement Learning

    by Chunyu Chen, Mingjian Cui, Fangxing Fran Li, Shengfei Yin, Xinan Wang

    Unexpected large power surges will cause instantaneous grid shock, and thus emergency control plans must be implemented to prevent the system from collapsing. In this paper, by the aid of reinforcement learning (RL), novel model-free control (MFC)-based emergency control schemes are presented. Firstly, multi-Q-learning-based emergency plans are designed for limited emergency scenarios by using offline-training-online approximation methods. To solve the more general multi-scenario emergency control problem, a deep deterministic policy gradient (DDPG) algorithm is adopted to learn near-optimal solutions. With the aid of deep Q network, DDPG-based strategies have better generalization abilities for unknown and untrained emergency scenarios, and thus are suitable for multi-scenario learning. Through simulations using benchmark systems, the proposed schemes are proven to achieve satisfactory performances.


  • Vehicle to Grid Frequency Regulation Capacity Optimal Scheduling for Battery Swapping Station Using Deep Q-Network

    by Xinan Wang, Jianhui Wang, Jianzhe Liu

    Battery swapping stations (BSSs) are ideal candidates for fast frequency regulation services (FFRS) due to their large battery stock capacity. In addition, BSSs can precharge batteries for customers and the batteries that are not in charging can provide a stable regulation capacity to the market. However, uncertainties, such as ACE signals and the EV per-hour visit counts, introduce stochastic nonlinear dynamics into the operation of a BSS-based FFRS. Currently, there is no quantification method to ensure its optimal economical operation. To close this gap, in this article, we propose a novel deep Q-learning-based FFRS capacity dynamic scheduling strategy. This method can autonomously schedule the hourly regulation capacity in real time to maximize the BSS's revenue for providing FFRS. Case studies using real-world data verify the efficacy of the proposed work.


  • Open Access

    Deep Reinforcement Learning Based Volt-VAR Optimization in Smart Distribution Systems

    by Ying Zhang, Xinan Wang, Jianhui Wang, Yingchen Zhang

    This paper develops a model-free volt-VAR optimization (VVO) algorithm via multi-agent deep reinforcement learning (MADRL) in unbalanced distribution systems. This method is novel since we cast the VVO problem in unbalanced distribution networks to an intelligent deep Q-network (DQN) framework, which avoids solving a specific optimization model directly when facing time-varying operating conditions of the systems. We consider statuses/ratios of switchable capacitors, voltage regulators, and smart inverters installed at distributed generators as the action variables of the DQN agents. A delicately designed reward function guides these agents to interact with the distribution system, in the direction of reinforcing voltage regulation and power loss reduction simultaneously. The forward-backward sweep method for radial three-phase distribution systems provides accurate power flow results within a few iterations to the DQN environment. Finally, the proposed multi-objective MADRL method realizes the dual goals for VVO. We test this algorithm on the unbalanced IEEE 13-bus and 123-bus systems. Numerical simulations validate the excellent performance of this method in voltage regulation and power loss reduction.

  • Two-Stage WECC Composite Load Modeling: A Double Deep Q-Learning Networks Approach

    by Xinan Wang, Yishen Wang, Di Shi, Jianhui Wang, Zhiwei Wang

    With the increasing complexity of modern power system, conventional dynamic load modeling with ZIP and induction motors (ZIP + IM) is no longer adequate to address the current load characteristic transitions. In recent years, the Western Electricity Coordinating Council Composite Load Model (WECC CLM) has shown to effectively capture the dynamic load responses over traditional load models in various stability studies and contingency analyses. However, a detailed WECC CLM model typically has a high degree of complexity, with over one hundred parameters, and no systematic approach to identifying and calibrating these parameters. Enabled by the wide deployment of PMUs and advanced deep learning algorithms, proposed here is a double deep Q-learning network (DDQN)-based, two-stage load modeling framework for the WECC CLM. This two-stage method decomposes the complicated WECC CLM for more efficient identification and does not require explicit model details. In the stage one, the DDQN agent determines a proper load composition that can approximate the true transient dynamics. In the second stage, the remaining parameters of the WECC CLM are selected with Monte-Carlo simulations. The proposed method shows that the identified load model is capable of accurately simulating the given dynamics of the reference load model. In addition, the identified load model has strong robustness to represent the reference load model under a wide range of contingencies. The proposed framework is verified using an IEEE 39-bus test system on commercial simulation platforms.


  • Economic Assessment for Battery Swapping Station Based Frequency Regulation Service

    by Xinan Wang, Jianhui Wang

    Battery swapping stations (BSS) have great potential in providing fast frequency regulation service (FFRS) owing to their large battery storage capacity. However, compared to a regular BSS, a BSS providing FFRS faces the following financial risks: 1). higher infrastructure investment to support the vehicle-to-grid (V2G) services; 2). higher battery aging costs due to FFRS; 3). FFRS causes uncertainties to batteries’ charging costs. Under such a context, we propose an economic risk assessment model for the BSS-based FFRS by comparing its economics with a regular BSS. In this model, the value at risk (VaR) of daily revenue and the long-term return on investment (ROI) of a regular BSS and a BSS providing FFRS are compared. The assessment results are obtained in three steps: first, we develop the operation and economic models for the BSS-based FFRS. Next, the mathematical models of the VAR and ROI analyses are formulated. Finally, the VaR of daily revenue is compared through a statistical analysis of a large number of scenarios. The ROI comparison is conducted by a policy gradient (PG)-based reinforcement learning algorithm, which can handle the non-convexity and stochastic dynamics brought by the EV visits. The practicality of the proposed framework is demonstrated by using the real ancillary market data from utilities and the traffic count data from onsite traffic sensors.


  • Residential Customer Baseline Load Estimation Using Stacked Autoencoder With Pseudo-Load Selection

    by Xinan Wang, Yishen Wang, Jianhui Wang, Di Shi

    Accurate estimation of customer baseline load (CBL) is a key factor in the successful implementation of demand response (DR). CBL technologies implemented at utilities currently are primarily designed for large industrial and commercial customers. The U.S. Federal Energy Regulatory Commission (FERC) order 745 states that DR owners, including residential customers, can sell their load reduction in the wholesale market. However, since residential load is random and unschedulable, this tends to inherently degrade the effectiveness of existing CBL technologies. In this paper, a novel SAE based CBL method for residential customers that uses the data reconstruction capability of a stacked autoencoder (SAE) is described. In the model, two SAEs are synchronously trained—one SAE generates a pseudo-load pool and the second one is used to select a pseudoload to reconstruct a residential CBL. A support vector machine (SVM) classifier is self-trained to conduct the pseudo-load selection. The proposed strategy is validated using a real data set consisting of 328 residential customers’ smart meter readings. Benchmarks from other machine learning techniques and existing CBL methods are compared with the proposed method. Test results show that the accuracy of the residential CBL reconstruction significantly improves when compared with existing methods, such as HighXofY and exponential moving average.