Yan Xu

Nanyang Technological University | ntu · School of Electrical and Electronic Engineering

Enhanced by machine learning (ML) techniques, data-driven dynamic security assessment (DSA) in smart cyber-physical grids has attracted significant research interest in recent years. However, the current centralized ML architectures have limited scalability, are vulnerable to privacy exposure, and are costly to manage. To resolve these limitations,...

Comprehensive treatment of an aspect of stability constrained operations and planning, including the latest research and engineering practices Stability-Constrained Optimization for Modern Power System Operation and Planning focuses on the subject of power system stability. Unlike other books in this field, which focus mainly on the dynamic modeli...

Photovoltaic (PV) power generation has highly penetrated in distribution networks, providing clean and sustainable energy. However, its uncertain and intermittent power outputs significantly impair network operation, leading to unexpected power loss and voltage fluctuation. To address the uncertainties, this paper proposes a multi-timescale affinel...

Distributed secondary control of a microgrid highly relies on information exchange via communication networks, which may be vulnerable to cyber-attacks. This paper aims to enhance the cyber-attack tolerance against various types of cyber-attacks, including false data injection (FDI) attack, denial of service (DoS) attack, latency attack. To this en...

This paper proposes a hybrid data-driven method for fast solutions of preventive security-constrained optimal power flow (SCOPF) of power systems. The proposed method formulates the SCOPF problem as constraints-satisfying training of a deep reinforcement learning (DRL) agent, where the action-value function of DRL is augmented by contingency securi...

In recent years, energy storage systems (ESS) are becoming an integral part of modern all-electric ships (AES). The topic of optimal ESS sizing is important as it determines the cost and effectiveness of the vessel operation. Conventional ESS sizing only considers the investment stage and ignores the operation stage and uncertainties. This research...

With the advancement of machine learning techniques, data-driven power system dynamic security assessment (DSA) has received great research interests. Traditional methods usually apply one DSA model for one specific fault and cannot simultaneously address different multiple faults by one model. To solve this issue and further improve the DSA accura...

Voltage stability assessment is essential for maintaining reliable power grid operations. Stability assessment approaches using deep learning address the shortfalls of the traditional time-domain simulation-based approaches caused by increased system complexity. However, deep learning models are shown to be vulnerable to adversarial examples in the...

With the growing adoption of Electrical Vehicles (EVs), it is expected that a large number of on-board Li-ion batteries will be retired from EVs in the future. Retired batteries will typically retain 80% of their initial capacities and can be recycled as second life batteries (SLBs). Although the capital costs of SLBs are much cheaper, their operat...

Multiple microgrids can be interconnected to form a networked-microgrid (NMG) system. In this paper, a data-driven decentralized economic frequency control method is proposed for isolated NMG systems. Based on multi-agent deep reinforcement learning (MA-DRL) framework, each DRL agent controls the generator and energy storage system (ESS) in each mi...

This chapter introduces the integration of battery energy storage systems (BESS) into the Micro-grid to improve the grid’s economic efficiency and sustainability. Firstly, basic concepts for Micro-grids and the recent developing trend of key energy storage technologies are introduced in detail. Then, along with two different time frames, this chapt...

Under the reliability consideration of the multi-energy system, more and more regional networks are in meshed topology. This paper presents a novel method for the regional meshed power–gas system based on the reformulated and tightened cone relaxations. The proposed model defines two energy flows, which are relaxed as convex constraints in the opti...

This paper proposes a data-driven approach for multi-energy management of a smart home with different types of appliances, including battery energy storage system (BESS), thermal energy storage system (TES), micro combined heat and power system (mCHP), electrical heat pump (EHP), rooftop photovoltaics (PV) and electrical vehicle (EV). Firstly, home...

Aiming at timely and adaptive remedial control for the fault-induced voltage recovery (FIDVR) events in power systems, this paper develops a probabilistic data-driven method for response-based load shedding (RLS). In the proposed method, a scalable Gaussian process (SGP) model is developed to estimate the required load shedding (LS) amount and the...

Based on machine learning (ML) technique, the data-driven power system stability assessment (SA) has received significant research interests in recent years. However, even with a high SA accuracy performance, the data-driven SA models may be vulnerable to adversarial examples (caused by some physical noises or adversarial attacks), which are very c...

With increasing installation of behind-the-meter distributed energy resources (DERs) at the household level, the power load profile has been significantly masked. As a result, original load forecasting models are becoming not suitable for the continuously masked-load. Besides, present masked-load may not have sufficient samples to train an accurate...

The decarbonization of energy systems has posed unprecedented challenges in system complexity and operational uncertainty that render it imperative to exploit cutting-edge artificial intelligence (AI) technologies to realize real-time, autonomous power system operation and control. In particular, deep reinforcement learning (DRL)-based approaches i...

In modern power systems, power system dynamic security assessment is a critical task against the risk of blackout. This paper aims to develop reliable recognition models for system real-time dynamic security assessment, where ensemble learning models consisting of extreme learning machine, stochastic configuration networks and random vector functio...

This is the Guest Editorial of the Special Issue on Data-Analytics for Stability Analysis, Control, and Situational Awareness of Power System with High-Penetration of Renewable Energy.

The integration of information and communication technologies has introduced cybersecurity challenges to microgrid (MG) apart from bringing more flexibility, reliability, and resilience. Especially in the upcoming quantum era, the existing cryptographic systems are vulnerable to attacks from quantum computers. Motivated by these challenges, this ar...

Solar power forecasting is a key task in modern power grid operation, which can be achieved by machine learning-based methods. Due to multiple practical issues, the data may be incomplete, making the existing machine learning models inaccurate or even ineffective. To counteract the missing data problem, this paper proposes a hybrid learning method....

Networked microgrid (NMG) system is an effective solution to enhance the power system's reliability and resilience. The distributed control is promising for NMG system due to its high reliability and scalability and low computational burden. The distributed control relies on the information exchange among distributed generators and sub-microgrids (...

Addressing the rapidly growing penetration of renewable energy sources and the increasing variations in loads has been a significant challenge in the planning and operation of modern power systems. As effective tools for describing uncertainty issues, scenario analysis methods have been used in the uncertainty evaluation of power systems for years....

Energy storage system (ESS) integrated all-electric ship (AES) is gaining popularity as it renders higher efficiency and emission reduction. Being an isolated system, generation and storage capabilities are limited, and hence network losses, mechanical and electrical load estimation must be modeled accurately to establish a reliable operation strat...

Increasing global greenhouse gas (GHG) emissions call for new operation strategies towards low-carbon marine transportation. This paper proposes a coordinated operation strategy for a ship micorgird with hybrid propulsion systems (HPSs) to minimize the whole-voyage operation cost within GHG emission limitations. Hydrogen fuel cells are integrated t...

Since extreme weather events usually severely damage the power grid and lead to widespread power outages, coordinating repair and dispatch resources, such as repair crews (RCs), mobile power sources (MPSs), renewable energy sources (RESs) and energy storage systems (ESSs), is an efficient method to restore the power supply for outage loads. However...

Based on machine learning (ML) technique, the data-driven power system dynamic security assessment (DSA) has received significant research interests. Yet, the well-trained ML-based models with high training and testing accuracy may be vulnerable to the adversarial example, which is a modified version of the original sample that is intentionally per...

The existing analyses of integrated natural gas and power systems generally ignore gas temperature variations, which may misjudge gas pressure and jeopardize natural gas transmission. Furthermore, the conventional Newton-Raphson based natural gas flow analysis methods may cause non-convergence or unnecessary computational burden. Based on topology...

This paper proposes a data-driven method for distributed frequency control of islanded microgrids based on multi-agent quantum deep reinforcement learning (MA-QDRL). The proposed method combines the conventional DRL framework with quantum machine learning, and can adaptively obtain the optimal cooperative control strategy. The microgrid secondary f...

Mobile energy storage systems (MESSs), wind power and repair crews (RCs) are usually coordinated to restore distribution systems damaged by hurricanes. However, the forced cut-off of wind power occurs as wind speed exceeds the cut-off value, which can lead to sudden power shortage. To address this challenge, this paper proposes a restoration approa...

With the rapid development of microgrid, its tie-line switching from grid-connected to islanded mode is a topic worth discussing for considering both main grid resilience and microgrid security. In this paper, a stochastic security-constrained optimal power flow (OPF) method is proposed to deal with these conditions under high uncertainties. Firstl...

To analyze the small signal stability of large-scale time-delay power systems (TDPSs), critical oscillation modes are required to be reliably computed. The solution operator discretization with pseudo-spectral collocation (SOD-PS)-based method has been proposed to indirectly calculate critical eigenvalues from the solution operator’s discretization...

Renewable energy based distributed generators are key components in islanded microgrids. However, their power intermittency and uncertainty may impair power quality and cause system operating constraint violations. It is imperative to evaluate and maximize the hosting capacity of an islanded mi-crogrid for renewable generation. Besides, conventiona...

This article proposes a speed sensor fault diagnosis methodology based on a learning-based data-driven principle in induction motor drive systems. The proposed method is derived from signal estimation and residual evaluation. First, a speed estimator is designed with a nonlinear autoregressive exogenous (NARX) learning model and a randomized learni...

Accurate solar photovoltaic (PV) generation forecast is critical to the reliable and economic operation of a modern power system. In practice, due to various faulty issues in the sensor, communication, or database system, the historical and online measurement data may not be always complete, and the missing data could dramatically degrade the forec...

The increasing prevalence of electric vehicles (EVs) has intensified the coupling between power distribution networks (PDNs) and transportation networks (TNs) in both temporal and spatial dimensions. In order to accurately model the coupled network, this paper studies the dynamic network equilibrium to capture the temporally-dynamic interactions be...

High penetration of renewable energy resources into distribution networks induces frequency and voltage fluctuations to the power grids. Unlike high-voltage transmission lines, the x/r ratio of distribution lines is relatively low, thereby frequency support and voltage regulation are closely coupled. Considering their coupling relationship, a rule-...

Intermittent photovoltaic (PV) power generation brings voltage fluctuation and stability issues to distribution networks. Mean-while, PV inverters can support voltage/Var control (VVC) to address these issues. Utilizing PV inverters, this paper proposes a three-stage hierarchically-coordinated (TSHC-) VVC method considering network voltage stabilit...

Due to increasing installation of photovoltaic (PV) units, reactive power compensation from PV inverters contributes significantly to Volt/Var control (VVC) for active distribution net-works. While PV inverters support VVC functions, lack of system-atic coordination and heavily varying PV power generation lead to low control efficiency. To maximize...

This paper discusses a bilayer coordinated operation scheme for the multi-energy building microgrid (MEBM) with comprehensive uncertainty sources. First, a building model considering the battery degradation, practical/detailed thermal loads, and various operating tasks of residential appliances is presented. Second, to alleviate the adverse effects...

A multi-unit battery energy storage system (BESS) which aggregates individual battery units can be used to provide auxiliary services in power grid. Existing state-of-charge (SOC)-based power sharing strategies for multi-unit BESSs rarely consider the unit-level battery aging characteristics and may lead to high aging rates. This paper proposes a r...

This paper proposes a comprehensive analysis method for levelized costs of energy (LCOE) in tidal current power generation farms (TCPGFs). The detailed investment and operation costs in the life cycles of TCPGF projects are all quantified and incorporated in the calculation of LCOE, including the emission reduction benefits brought by TCPGFs. An an...

Emergency load shedding is an effective and frequently used emergency control action for power system transient stability. Solving the full optimization models for load shedding is computational burdensome and thus slow react to the intense system variations from the increasing renewable energy sources and the more active demand-side behavior. Othe...

Based on machine learning (ML) technique, the data-driven power system stability assessment has received significant research interests in recent years. Yet, the ML-based models may be vulnerable to the adversarial examples, which are very close to the original input but can lead to a different (wrong) assessment result. Taking short-term voltage s...

Deep learning (DL) techniques have shown promising performance for designing data-driven power system transient stability assessment (TSA) models. However, due to the deep structure of the DL, the resulting model is always a black-box and hard to explain, which hinders its practical adoption by the industry. This paper proposes an interpretable DL-...

This paper studies the multi-stage real-time stochastic operation of grid-tied multi-energy microgrids (MEMGs) via the hybrid model predictive control (MPC) and approximate dynamic programming (ADP) approach. In the MEMG, practical power and thermal network constraints, heterogeneous energy storage devices, and distributed generations are involved....

Accurate state-of-charge (SOC) estimation and lifetime prognosis of lithium-ion batteries are of great significance for reliable operations of energy storage systems. This paper proposes a novel two-layer hierarchical approach for online SOC estimation and remaining-useful-life (RUL) prediction based on a robust observer and Gaussian-process-regres...

To fully consider the impacts of complex submarine terrains and ensure the profitability of tidal current power generation farms (TCPGFs), a 3-dimensional (3D) planning method for TCPGFs is proposed to simultaneously determine the tidal current turbine (TCT) layout and electrical collector system (ECS) planning schemes. Based on the limited observe...

This paper proposes a multi-data driven hybrid learning method for weekly photovoltaic (PV) power scenario forecast that is coordinately driven by weather forecasts and historical PV power output data. Patterns of historical data and weather forecast information are simultaneously captured to ensure the quality of the generated scenarios. By combin...

Transient stability of a power system can be significantly affected by wind power generators due to their stochastic power output and complex dynamic characteristics. This paper proposes a robust optimization approach for coordinating generation dispatch and emergency load shedding against transient instability under uncertain wind power output. Th...

During frequency controller design, the system frequency dynamic behavior is normally assessed by a system frequency response (SFR) model, which is a linearized low-order model that can be efficiently handled. Existing SFR models for a system with wind turbines cannot precisely characterize the nonlinear dynamic of fast frequency controllers in the...

The complex voltage variation is an emerging issue caused by the large-scale distributed energy resources (DERs) integration and the forming prosumers. The prosumers with uncertain photovoltaic (PV) generation will serve as autonomous entities for distributed voltage regulation, which have interaction during the voltage regulation process and have...

This paper studies the vulnerability of deep reinforcement learning (DRL) models for power systems topology optimization under data perturbations and cyber-attack. DRL has recently solved many complex power system optimization problems. However, it has been practically proven that small perturbations of input data can lead to drastically different...

This paper studies the communication time-delay issues in islanded microgrids (MGs) with the distributed secondary control architecture. Firstly, a time-delayed MG small-signal model is developed. Then, a new weight-average-prediction (WAP) controller is proposed to compensate the delayed system state. By introducing a time-delayed differential ter...

Machine learning (ML) based data-driven methods have shown promising performance in power converter fault diagnosis. However, the existing ML model trained by one fault database can only work for the corresponding converter system, but cannot work accurately for a different system with the same topology but different parameters. In this paper, a no...

Medium-voltage DC power systems have been recognized as a promising electrical architecture for marine vessels. Such shipboard power systems (SPS) require advanced control architectures to ensure reliability and flexibility as well as achieve fuel-efficient operation. With this regard, this paper presents a multi-agent distributed power management...

This letter proposes an integrated transfer learning (TL) method for pre-fault dynamic security assessment (DSA) of power systems, which aims to simultaneously achieve fault transfer and address missing data issue for unlearned faults. Moreover, this letter provides the tight mathematic proof for the guaranteed DSA performance of the proposed integ...

With an increasing penetration level of intermittent renewable energy sources and heterogeneous energy demands, the secure and economic operation of multi-energy microgrids (MEMGs) becomes more and more critical. Under this circumstance, this paper proposes an adaptive (two-layer) stochastic approach to obtain optimal MEMG operation decisions by ta...

Abstract The interdependency of power systems and natural gas systems is being reinforced by the emerging power‐to‐gas facilities (PtGs), and the existing gas‐fired generators. To jointly improve the efficiency and security under diverse uncertainties from renewable energy resources and load demands, it is essential to co‐optimise these two energy...

In high renewable penetrated microgrids, energy storage systems (ESSs) play key roles for various functionalities. In this chapter, the control and application of energy storage systems in the microgrids system are reviewed and introduced. First, the categories of energy storage systems utilized in microgrids and the power electronic interface betw...

The increasing penetration of photovoltaic (PV) systems promotes utilization of PV inverters for volt/var control (VVC) in distribution networks. However, PV inverters are vulnerable and their reliability is one of the most critical concerns for sustainable PV energy utilization. To enhance PV inverter reliability, this paper proposes a PV inverter...

Thermostatically controlled loads (TCLs) are regarded as one of the promising resources for suppressing power fluctuations of renewable energy (RENs). However, due to great burdens of fully considering each users characteristics, it is difficult to achieve unity of the individual optimal consumption and global optimal scheme in demand-side manageme...

Due to the stochastic and non-stationary characteristics of wind speed, the wind power generation is highly uncertain and fluctuating, which significantly challenges the operation of the power system and the associated electricity market. In this paper, a new spatial-temporal method is proposed for short-term wind power prediction based on image in...

This paper proposes a radial-grouping-based planning method for the electrical collector systems (ECSs) to design the topology and select the cross-sections of ECS submarine cables in tidal current generation farms (TCGFs) while minimizing investment and operation costs. First, an angle-based radial-grouping method is proposed to group the tidal cu...

This paper develops a fully data-driven, missing-data tolerant method for post-fault short-term voltage stability (STVS) assessment of power system against the incomplete PMU measurements. The super-resolution perception (SRP), based on deep residual learning convolutional neural network, is employed to cope with the missing PMU measurements. The i...

The number of electric vehicles (EVs) is expected to grow significantly, which calls for effective planning of charging infrastructures. While the planning of the charging infrastructure relies on an accurate charging demands, the behaviours of EVs charging are not always predictable and can be sensitive to many uncertain future environmental facto...

In this study, a hybrid model‐based and data‐driven method is proposed for the current sensor fault diagnosis used in single‐phase pulse width modulation (PWM) rectifier. According to the principle of model‐based methods, the proposed diagnostic method is based on signal prediction and residual generation. Differently, instead of a mathematical mod...

Networked-microgrid (NMG) system has a much more complex structure with larger control difficulties and complicated dynamic behaviors. This paper firstly proposes a layered distributed control framework for NMG system, which is comprised of two layers: individual MG control layer and NMG control layer. The NMG control layer generates the voltage/fr...

The critical clearing time (CCT) is one of the most important indexes for large-disturbance rotor angle stability margin evaluation. In practice, model-driven methods are usually realized based on simplified models to ease the computational burden, but the accuracy is sacrificed. To solve this problem, a data-driven method is adopted in this paper...

This study proposes an operation task-aware energy management strategy for ship power systems that consist of main engines, diesel–electric engines, and energy storage systems. The proposed strategy aims to meet the fuel consumption and task-dependent objectives of the vessel by optimally dispatching the generation and storage units. Firstly, rule-...

A prior knowledge of residential load demand is critical for power system operations at the distribution level, such as economic dispatch, demand response and energy storage schedule. However, as residential customers perform more casual and active consumption behaviors, prediction of such highly volatile loads can be much harder. Owing to the deve...

The increasing penetration of wind power deteriorates the frequency stability of power systems. To address this issue, a fast frequency response (FFR) from wind farms is required to provide frequency support. However, the power point tracking controllers in wind turbines may counteract the effect of droop-based fast frequency controllers during the...

A consensus-based distributed voltage control architecture of isolated DC microgrids (MGs) with deception attack awareness is investigated in this paper. Firstly, a fully distributed voltage control algorithm with only adjacent information sharing is proposed by expanding the consensus-based distributed algorithm in AC MGs. To further enhance the a...

Time delays are inevitable in the power systems with wide-area control signals, which may compromise the control performance and thus jeopardize the stability of the power systems. To analyze the impacts of system parameters on critical oscillation modes of a time-delayed power system (TDPS), a new method for eigenvalue trajectory tracking of TDPS...

Key topics covered: (1) Intelligent system design and algorithms for on-line stability assessment (2) Intelligent system design and algorithms for preventive stability control (3) Intelligent system design and algorithms for real-time stability prediction (4) Intelligent system design and algorithms for emergency stability control (5) Methodologies...

During power system restoration, the planning of the generator start-up sequence (GSUS) can significantly affect the restoration efficiency. However, a GSUS optimization model based on mixed integer linear programming (MILP) cannot satisfy the need for flexible re-energizing times of transmission lines and the serial restoration of generators. To s...

This paper proposes an operational reliability assessment approach of photovoltaic (PV) inverters considering a voltage/VAR control (VVC) function. The approach aims to quantify the reliability degradation and estimate the lifetime of PV inverters when they are utilized for the VVC function. Firstly, an inverter based VVC model considering uncertai...

A battery energy storage system (BESS) is an effective solution to mitigate real‐time power imbalance by participating in power system frequency control. However, battery aging resulted from intensive charge–discharge cycles will inevitably lead to lifetime degradation, which eventually incurs high‐operating costs. This study proposes a deep reinfo...

As a critical step of VAR planning, candidate bus selection can significantly reduce the scale of the planning problem without impairing the optimality of the planning decisions. A novel candidate bus selection method is proposed considering not only the capacity sensitivity of candidate buses, but also the correlation among uncertainties of wind p...