Publications
138 results found
Xu W, Wang J, Teng F, 2024, E2E-AT: A Unified Framework for Tackling Uncertainty in Task-Aware End-to-End Learning, Pages: 16220-16227, ISSN: 2159-5399
Successful machine learning involves a complete pipeline of data, model, and downstream applications. Instead of treating them separately, there has been a prominent increase of attention within the constrained optimization (CO) and machine learning (ML) communities towards combining prediction and optimization models. The so-called end-to-end (E2E) learning captures the task-based objective for which they will be used for decision making. Although a large variety of E2E algorithms have been presented, it has not been fully investigated how to systematically address uncertainties involved in such models. Most of the existing work considers the uncertainties of ML in the input space and improves robustness through adversarial training. We extend this idea to E2E learning and prove that there is a robustness certification procedure by solving augmented integer programming. Furthermore, we show that neglecting the uncertainty of COs during training causes a new trigger for generalization errors. To include all these components, we propose a unified framework that covers the uncertainties emerging in both the input feature space of the ML models and the COs. The framework is described as a robust optimization problem and is practically solved via end-to-end adversarial training (E2E-AT). Finally, the performance of E2E-AT is evaluated by a real-world end-to-end power system operation problem, including load forecasting and sequential scheduling tasks.
Zhang H, Li R, Chen Y, et al., 2024, Risk-Aware Objective-Based Forecasting in Inertia Management, IEEE Transactions on Power Systems, Vol: 39, Pages: 4612-4623, ISSN: 0885-8950
The objective-based forecasting considers the asymmetric and non-linear impacts of forecasting errors on decision objectives, thus improving the effectiveness of its downstream decision-making process. However, existing objective-based forecasting methods are risk-neutral and not suitable for tasks like power system inertia management and unit commitment, of which decision-makers are usually biased toward risk aversion in practice. To tackle this problem, this article proposes a generic risk-aware objective-based forecasting method. It enables decision-makers to customize their forecasting with different risk preferences. The equivalence between the proposed method and optimization under uncertainty (stochastic/robust optimization) is established for the first time. Case studies are carried out on a Great Britain 2030 power system with system operational data from National Grid. The results show that the proposed model with deterministic optimization can approximate the performance of stochastic programming or robust optimization at only a fraction of their computational cost.
He H, Zhang N, Kang C, et al., 2024, Communication Resources Allocation for Time Delay Reduction of Frequency Regulation Service in High Renewable Penetrated Power System, CSEE Journal of Power and Energy Systems, Vol: 10, Pages: 468-480, ISSN: 2096-0042
The high renewable penetrated power system has severe frequency regulation problems. Distributed resources can provide frequency regulation services but are limited by communication time delay. This paper proposes a communication resources allocation model to reduce communication time delay in frequency regulation service. Communication device resources and wireless spectrum resources are allocated to distributed resources when they participate in frequency regulation. We reveal impact of communication resources allocation on time delay reduction and frequency regulation performance. Besides, we study communication resources allocation solution in high renewable energy penetrated power systems. We provide a case study based on the HRP-38 system. Results show communication time delay decreases distributed resources’ ability to provide frequency regulation service. On the other hand, allocating more communication resources to distributed resources’ communication services improves their frequency regulation performance. For power systems with renewable energy penetration above 70%, required communications resources are about five times as many as 30% renewable energy penetrated power systems to keep frequency performance the same.
Xu W, Teng F, 2024, Task-Aware Machine Unlearning and Its Application in Load Forecasting, IEEE Transactions on Power Systems, ISSN: 0885-8950
Data privacy and security have become a non-negligible factor in load forecasting. Previous researches mainly focus on training stage enhancement. However, once the model is trained and deployed, it may need to ‘forget’ (i.e., remove the impact of) part of training data if the these data are found to be malicious or as requested by the data owner. This paper introduces the concept of machine unlearning which is specifically designed to remove the influence of part of the dataset on an already trained forecaster. However, direct unlearning inevitably degrades the model generalization ability. To balance between unlearning completeness and model performance, a performance-aware algorithm is proposed by evaluating the sensitivity of local model parameter change using influence function and sample re-weighting. Furthermore, we observe that the statistical criterion such as mean squared error, cannot fully reflect the operation cost of the downstream tasks in power system. Therefore, a task-aware machine unlearning is proposed whose objective is a trilevel optimization with dispatch and redispatch problems considered. We theoretically prove the existence of the gradient of such an objective, which is key to re-weighting the remaining samples. We tested the unlearning algorithms on linear, CNN, and MLP-Mixer based load forecasters with a realistic load dataset. The simulation demonstrates the balance between unlearning completeness and operational cost. All codes can be found at <uri>https://github.com/xuwkk/task_aware_machine_unlearning</uri>.
Liu M, Teng F, Zhang Z, et al., 2024, Enhancing Cyber-Resiliency of DER-Based Smart Grid: A Survey, IEEE Transactions on Smart Grid, ISSN: 1949-3053
The rapid development of information and communications technology has enabled the use of digital-controlled and software-driven distributed energy resources (DERs) to improve the flexibility and efficiency of power supply, and support grid operations. However, this evolution also exposes geographically-dispersed DERs to cyber threats, including hardware and software vulnerabilities, communication issues, and personnel errors, etc. Therefore, enhancing the cyber-resiliency of DER-based smart grid -the ability to survive successful cyber intrusions -is becoming increasingly vital and has garnered significant attention from both industry and academia. In this survey, we aim to provide a comprehensive review regarding the cyber-resiliency enhancement (CRE) developments of the DER-based smart grid, present a holistic CRE framework, and thoroughly discuss the research directions of the next-generation CRE methods. Firstly, an integrated threat modeling method is tailored for the hierarchical DER-based smart grid with special emphasises on vulnerability identification and impact analysis. Then, the defense-in-depth strategies encompassing prevention, detection, mitigation, and recovery are comprehensively surveyed, systematically classified, and rigorously summarized. A holistic CRE framework is subsequently proposed to incorporate the five key resiliency enablers. Finally, challenges and future directions are discussed in details. The overall aim of this survey is to illustrates the recent development of CRE methods and motivate further efforts to improve the cyber-resiliency of DER-based smart grid.
Chu Z, Cui G, Teng F, 2024, Scheduling of Software-Defined Microgrids for Optimal Frequency Regulation, IEEE Transactions on Sustainable Energy, ISSN: 1949-3029
Integrated with a high share of Inverter-Based Resources (IBRs), microgrids face increasing complexity of frequency dynamics, especially after unintentional islanding from the maingrid. These IBRs, on the other hand, provide more control flexibility to shape the frequency dynamics of microgrid and together with advanced communication infrastructure offer new opportunities in the future software-defined microgrids. To enhance the frequency stability of microgrids with high IBR penetration, this paper proposes an optimal scheduling framework for software-defined microgrids which aims at combining the control design of the IBR dynamic frequency response and the steady-state economic optimization. This is achieved by utilizing the non-essential load shedding and dynamical optimization of the virtual inertia and virtual damping from IBRs. Moreover, side effects of these services, namely, the time delay associated with non-essential load shedding and potential IBR control parameter update failure are explicitly modeled to avoid underestimations of frequency deviation and over-optimistic results. The effectiveness and significant economic value of the proposed simultaneous and dynamic virtual inertia and damping provision strategy are demonstrated based on case studies in the modified IEEE 33-bus system.
Wang Y, Qiu D, Teng F, et al., 2024, Towards microgrid resilience enhancement via mobile power sources and repair crews: a multi-agent reinforcement learning approach, IEEE Transactions on Power Systems, Vol: 39, Pages: 1329-1345, ISSN: 0885-8950
Mobile power sources (MPSs) have been gradually deployed in microgrids as critical resources to coordinate with repair crews (RCs) towards resilience enhancement owing to their flexibility and mobility in handling the complex coupled power-transport systems. However, previous work solves the coordinated dispatch problem of MPSs and RCs in a centralized manner with the assumption that the communication network is still fully functioning after the event. However, there is growing evidence that certain extreme events will damage or degrade communication infrastructure, which makes centralized decision making impractical. To fill this gap, this paper formulates the resilience-driven dispatch problem of MPSs and RCs in a decentralized framework. To solve this problem, a hierarchical multi-agent reinforcement learning method featuring a two-level framework is proposed, where the high-level action is used to switch decision-making between power and transport networks, and the low-level action constructed via a hybrid policy is used to compute continuous scheduling and discrete routing decisions in power and transport networks, respectively. The proposed method also uses an embedded function encapsulating system dynamics to enhance learning stability and scalability. Case studies based on IEEE 33-bus and 69-bus power networks are conducted to validate the effectiveness of the proposed method in load restoration.
Li K, Guo H, Fang X, et al., 2023, Market Mechanism Design of Inertia and Primary Frequency Response With Consideration of Energy Market, IEEE Transactions on Power Systems, Vol: 38, Pages: 5701-5713, ISSN: 0885-8950
The shortage of inertia and primary frequency response (IPFR) will be more severe in future power systems since conventional fossil-based synchronous generators are gradually being replaced by variable renewable energy (VRE) generators. To relieve the shortage of IPFR, corresponding market mechanisms should be designed and incorporated to motivate appropriate provision from various sources. The mechanism of IPFR provision from different types of generators and its tight relation with energy production should receive particular attention. This paper proposes a novel IPFR market mechanism in which the energy market is taken into joint consideration. The virtual inertia and droop factor provided by VRE generators are defined and introduced, considering its dominant share in future power systems. A differentiated pricing scheme is designed towards incentive compatibility, considering provision from different types of generators with different quality levels and opportunity costs. Then, the proposed IPFR market mechanism is formulated, and a modified piecewise linearization method is utilized to simplify the non-linear nadir constraints. Finally, the model is tested on a modified IEEE 30-bus system according to historical data in CAISO. The results indicate the proposed mechanism could increase the utilization of VREs, decrease system operation costs, and guarantee reasonable payback for various types of generators.
Feng X, Badesa L, Wang X, et al., 2023, Editorial for the Special Issue on Emerging Technology and Advanced Application of Energy Storage in Low-Carbon Power Systems, Chinese Journal of Electrical Engineering, Vol: 9, Pages: 1-2, ISSN: 2096-1529
- Cite
- Citations: 1
Wang C, Yan M, Pang K, et al., 2023, Cyber-Physical Interdependent Restoration Scheduling for Active Distribution Network via Ad Hoc Wireless Communication, IEEE Transactions on Smart Grid, Vol: 14, Pages: 3413-3426, ISSN: 1949-3053
This paper proposes a post-disaster cyber-physical interdependent restoration scheduling (CPIRS) framework for active distribution networks (ADN) where the simultaneous damages on cyber and physical networks are considered. The ad hoc wireless device-to-device (D2D) communication is leveraged, for the first time, to establish cyber networks instantly after the disaster to support ADN restoration. The repair and operation crew dispatching, the remote-controlled network reconfiguration and the system operation with DERs can be effectively coordinated under the cyber-physical interactions. The uncertain outputs of renewable energy resources (RESs) are represented by budget-constrained polyhedral uncertainty sets. Through implementing linearization techniques on disjunctive expressions, a monolithic mixed-integer linear programming (MILP) based two-stage robust optimization model is formulated and subsequently solved by a customized column-and-constraint generation (C&CG) algorithm. Numerical results on the IEEE 123-node distribution system demonstrate the effectiveness and superiorities of the proposed CPIRS method for ADN.
Zhang Z, Zuo K, Deng R, et al., 2023, Cybersecurity Analysis of Data-Driven Power System Stability Assessment, IEEE Internet of Things Journal, Vol: 10, Pages: 15723-15735
Machine learning-based intelligent systems enhanced with Internet of Things (IoT) technologies have been widely developed and exploited to enable the real-time stability assessment of a large-scale electricity grid. However, it has been extensively recognized that the IoT-enabled communication network of power systems is vulnerable to cyberattacks. In particular, system operating states, critical attributes that act as input to the data-driven stability assessment, can be manipulated by malicious actors to mislead the system operator into making disastrous decisions and thus cause major blackouts and cascading events. In this article, we explore the vulnerability of the data-driven power system stability assessment, with a special emphasis on decision tree-based stability assessment (DTSA) approaches, and investigate the feasibility of constructing a physics-constrained adversarial attack (PCAA) to undermine the DTSA. The PCAA is formulated as a nonlinear programming problem considering the misclassification constraint, power limits, and bad data detection, computing potential adversarial perturbations that reverse the 'stable/unstable' prediction of the real-time input while remaining invisible/stealthy. Extensive experiments based on the IEEE 68-bus system are conducted to evaluate the impact of PCAAs on predictions of DTSA and their transferability.
Ge P, Li P, Chen B, et al., 2023, Fixed-Time Convergent Distributed Observer Design of Linear Systems: A Kernel-Based Approach, IEEE TRANSACTIONS ON AUTOMATIC CONTROL, Vol: 68, Pages: 4932-4939, ISSN: 0018-9286
O'Malley C, Badesa L, Teng F, et al., 2023, Frequency response from aggregated V2G chargers with uncertain EV connections, IEEE Transactions on Power Systems, Vol: 38, Pages: 3543-3556, ISSN: 0885-8950
Fast frequency response (FR) is highly effective at securing frequency dynamics after a generator outage in low inertia systems. Electric vehicles (EVs) equipped with vehicle to grid (V2G) chargers could offer an abundant source of FR in future. However, the uncertainty associated with V2G aggregation, driven by the uncertain number of connected EVs at the time of an outage, has not been fully understood and prevents its participation in the existing service provision framework. To tackle this limitation, this paper, for the first time, incorporates such uncertainty into system frequency dynamics, from which probabilistic nadir and steady state frequency requirements are enforced via a derived moment-based distributionally-robust chance constraint. Field data from over 25,000 chargers is analysed to provide realistic parameters and connection forecasts to examine the value of FR from V2G chargers in annual operation of the GB 2030 system. The case study demonstrates that uncertainty of EV connections can be effectively managed through the proposed scheduling framework, which results in annual savings of Misplaced &6,300 or 37.4 tCO2 per charger. The sensitivity of this value to renewable capacity and FR delays is explored, with V2G capacity shown to be a third as valuable as the same grid battery capacity.
Ge P, Chen B, Teng F, 2023, Cyber-Resilient Self-Triggered Distributed Control of Networked Microgrids Against Multi-Layer DoS Attacks, IEEE TRANSACTIONS ON SMART GRID, Vol: 14, Pages: 3114-3124, ISSN: 1949-3053
Chu Z, Lakshminarayana S, Chaudhuri B, et al., 2023, Mitigating load-altering attacks against power grids using cyber-resilient economic dispatch, IEEE Transactions on Smart Grid, Vol: 14, Pages: 3164-3175, ISSN: 1949-3053
Large-scale Load-Altering Attacks (LAAs) against Internet-of-Things (IoT) enabled high-wattage electrical appliances pose a serious threat to power system security and stability. This paper investigates, for the first time, the optimal mitigation strategy from a system perspective against such attacks. In particular, a Cyber-Resilient Economic Dispatch (CRED) concept is proposed and seamlessly integrated with attack detection and identification to form a cyber resiliency enhancement framework. Instead of only relying on local resources, CRED coordinates the frequency droop control gains of Inverter-Based Resources (IBRs) in the system to mitigate the destabilizing effect of LAAs while minimizing the overall operational cost. To achieve this, the LAA-inclusive system frequency dynamics is formulated and the corresponding system stability constraints are explicitly derived based on parametric sensitivities, which are further incorporated into the system scheduling model with minimum error through a novel recursive linearization method. In addition, a distributionally robust approach is proposed to account for the uncertainty associated with system dynamics driven by the LAA detection/parameter estimation errors. The overall performance of the proposed CRED model is demonstrated through extensive simulations in a modified IEEE reliability test system.
Xu W, Higgins M, Wang J, et al., 2023, Blending Data and Physics Against False Data Injection Attack: An Event-Triggered Moving Target Defence Approach, IEEE TRANSACTIONS ON SMART GRID, Vol: 14, Pages: 3176-3188, ISSN: 1949-3053
- Author Web Link
- Cite
- Citations: 2
Wan X, Sun M, Chen B, et al., 2023, AdapSafe: Adaptive and Safe-Certified Deep Reinforcement Learning-Based Frequency Control for Carbon-Neutral Power Systems, Pages: 5294-5302
With the increasing penetration of inverter-based renewable energy resources, deep reinforcement learning (DRL) has been proposed as one of the most promising solutions to realize real-time and autonomous control for future carbon-neutral power systems. In particular, DRL-based frequency control approaches have been extensively investigated to overcome the limitations of model-based approaches, such as the computational cost and scalability for large-scale systems. Nevertheless, the real-world implementation of DRL-based frequency control methods is facing the following fundamental challenges: 1) safety guarantee during the learning and decision-making processes; 2) adaptability against the dynamic system operating conditions. To this end, this is the first work that proposes an Adaptive and Safe-Certified DRL (AdapSafe) algorithm for frequency control to simultaneously address the aforementioned challenges. In particular, a novel self-tuning control barrier function is designed to actively compensate the unsafe frequency control strategies under variational safety constraints and thus achieve guaranteed safety. Furthermore, the concept of meta-reinforcement learning is integrated to significantly enhance its adaptiveness in non-stationary power system environments without sacrificing the safety cost. Experiments are conducted based on GB 2030 power system, and the results demonstrate that the proposed AdapSafe exhibits superior performance in terms of its guaranteed safety in both training and test phases, as well as its considerable adaptability against the dynamics changes of system parameters.
Chen Y, Sun M, Chu Z, et al., 2023, Vulnerability and Impact of Machine Learning-Based Inertia Forecasting Under Cost-Oriented Data Integrity Attack, IEEE TRANSACTIONS ON SMART GRID, Vol: 14, Pages: 2275-2287, ISSN: 1949-3053
- Author Web Link
- Cite
- Citations: 1
Yan M, Teng F, Gan W, et al., 2023, Blockchain for secure decentralized energy management of multi-energy system using state machine replication, Applied Energy, Vol: 337, Pages: 1-11, ISSN: 0306-2619
Decentralized energy management can preserve the privacy of individual energy systems while mitigating computational and communication burdens. However, most decentralized energy management methods are partially decentralized and cannot ensure information exchange security. Therefore, this paper provides a secure fully decentralized energy management by using blockchain. First, a fully decentralized energy management framework using the optimality condition decomposition (OCD) is provided, in which individual energy system operators only exchange the boundary information with their peers rather than submitting proprietary information to a centralized system operator. Then, an asynchronous mechanism is proposed for updating the information exchange in OCD, enabling the proposed decentralized management to work under potential communication latency or interruption. Furthermore, the blockchain-based framework with state machine replication (SMR) based consensus algorithm is provided to safeguard the information exchange among individual energy systems in a secure and tamper-proof manner. The proposed decentralized energy management is tested on a multi-energy system with seven subsystems and a real-world multi-energy system in North China. The numerical results demonstrate the effectiveness of the proposed method in privacy protection and data security enhancement. The proposed method can prevent the cost increase caused by cheating activities, which in some subsystems can reach 17.6%. Additionally, the proposed fully decentralized method outperforms the partially decentralized method by 37.7% in reducing computation time. Also demonstrated are the computational precision, scalability and adaptability of the proposed method.1
Caputo C, Cardin M-A, Ge P, et al., 2023, Design and planning of flexible mobile Micro-Grids using Deep Reinforcement Learning, Applied Energy, Vol: 335, ISSN: 0306-2619
Ongoing risks from climate change have significantly impacted the livelihood of global nomadic communities and are likely to lead to increased migratory movements in coming years. As a result, mobility considerations are becoming increasingly important in energy systems planning, particularly to achieve energy access in developing countries. Advanced “Plug and Play” control strategies have been recently developed with such a decentralized framework in mind, allowing easier interconnection of nomadic communities, both to each other and to the main grid. Considering the above, the design and planning strategy of a mobile multi-energy supply system for a nomadic community is investigated in this work. Motivated by the scale and dimensionality of the associated uncertainties, impacting all major design and decision variables over the 30-year planning horizon, Deep Reinforcement Learning (DRL) Flexibility Analysis is implemented for the design and planning problem. DRL based solutions are benchmarked against several rigid baseline design options to compare expected performance under uncertainty. The results on a case study for ger communities in Mongolia suggest that mobile nomadic energy systems can be both technically and economically feasible, particularly when considering flexibility, although the degree of spatial dispersion among households is an important limiting factor. Additionally, the DRL based policies lead to the development of dynamic evolution and adaptability strategies, which can be used by the targeted communities under a very wide range of potential scenarios. Key economic, sustainability and resilience indicators such as Cost, Equivalent Emissions and Total Unmet Load are measured, suggesting potential improvements compared to available baselines of up to 25%, 67% and 76%, respectively. Finally, the decomposition of values of flexibility and plug and play operation is presented using a variation of real options theory, with important impl
Deng R, Ten CW, Li C, et al., 2023, Guest Editorial: Introduction to Special Issue on 'Cloud-Edge-End Orchestrated Computing for Smart Grid', IEEE Transactions on Cloud Computing, Vol: 11, Pages: 1107-1110
Chu Z, Teng F, 2023, Voltage Stability Constrained Unit Commitment in Power Systems With High Penetration of Inverter-Based Generators, IEEE TRANSACTIONS ON POWER SYSTEMS, Vol: 38, Pages: 1572-1582, ISSN: 0885-8950
- Author Web Link
- Cite
- Citations: 2
Wang D, Zheng K, Teng F, et al., 2023, Quantum Annealing With Integer Slack Variables for Grid Partitioning, IEEE TRANSACTIONS ON POWER SYSTEMS, Vol: 38, Pages: 1747-1750, ISSN: 0885-8950
Yan M, Wang L, Teng F, et al., 2023, Review and Prospect of Transactive Energy Market for Distributed Energy Resources, Dianli Xitong Zidonghua/Automation of Electric Power Systems, Vol: 47, Pages: 33-48, ISSN: 1000-1026
The transactive energy market can encourage prosumers to trade energy, and guide them to balance the random fluctuations of renewable energy output by adjusting the real-time electricity price, which can improve the accommodation level of renewable energy and achieve the goal of carbon emission peak and carbon neutrality in China. Firstly, the concept, characteristics and framework of the transactive energy market for distributed energy are introduced. Then, the trading mechanisms of the existing transactive energy markets and its advantages and disadvantages are comprehensively analyzed, and the platforms and pilot projects of the existing transactive energy markets are introduced. Finally, from the point of view of actual market operation, the present challenges and future development direction of the transactive energy markets are described.
Graham J, Teng F, 2023, Vehicle-to-grid plug-in forecasting for participation in ancillary services markets
Electric vehicle (EV) charge points (CPs) can be used by aggregators to provide frequency response (FR) ser-vices. Aggregators must have day-ahead half-hourly forecasts of minimum aggregate vehicle-to-grid (V2G) plug-in to produce meaningful bids for the day-ahead ancillary services market. However, there is a lack of understanding on what features should be considered and how complex the forecasting model should be. This paper explores the dependency of aggregate V2G plug-in on historic plug-in levels, calendar variables, and weather conditions. These investigations are used to develop three day-ahead forecasts of minimum aggregate V2G plug-in during 30-minute window. A neural network that considers previous V2G plug-in values the day before, three days before, and seven days before, in addition to day of the week, month, and hour, is found to be the most accurate.
Li Z, Chu Z, Teng F, 2023, Optimal Design of Neural Network Structure for Power System Frequency Security Constraints, Pages: 230-236
Recently, frequency security is challenged by high uncertainty and low inertia in power system with high penetration of Renewable Energy Sources (RES). In the context of Unit Commitment (UC) problems, frequency security constraints represented by neural networks have been developed and embedded into the optimisation problem to represent complicated frequency dynamics. However, there are two major disadvantages related to this technique: the risk of overconfident prediction and poor computational efficiency. To handle these disadvantages, novel methodologies are proposed to optimally design the neural network structure, including the use of asymmetric loss function during the training stage and scientifically selecting neural network size and topology. The effectiveness of the proposed methodologies are validated by case study which reveals the improvement of conservativeness and mitigation of computation performance issues.
Luo J, Teng F, Bu S, et al., 2023, Converter-driven stability constrained unit commitment considering dynamic interactions of wind generation, International Journal of Electrical Power and Energy Systems, Vol: 144, ISSN: 0142-0615
With increasing penetration of renewable energy in power systems, conventional unit commitment (UC) focusing on static constraints may fail to meet dynamic constraints, such as converter-driven stability. This paper proposes a practical paradigm to perform UC considering the requirement of converter-driven stability in wind generation penetrated power systems. First, wind generation is regarded as a constant source, and a regular UC problem is solved without considering the dynamic impact of wind generation. Second, converter-driven stability analysis is employed to evaluate the stability margin of the UC solution. Different wind penetration levels and dynamic interaction conditions are investigated to account for the dynamic impact of wind generation. In several time horizons, especially heavy loading periods, the stability margin may be very limited or negative, and a modification to the UC solution should be carried out. Thus, a power sensitivity-based power dispatch method is elaborated to enhance the stability margin as well as update the UC solution. It is substantiated that in strong interaction cases, the system has more unstable operating regions (e.g., 1.33 times of those in weak interaction cases) and greatly affects the feasibility of the UC solution, but can be effectively tackled with the proposed power dispatch method.
Xu W, Teng F, 2023, Availability Adversarial Attack and Countermeasures for Deep Learning-based Load Forecasting
The forecast of electrical loads is essential for the planning and operation of the power system. Recently, advances in deep learning have enabled more accurate forecasts. However, deep neural networks are prone to adversarial attacks. Although most of the literature focusses on integrity-based attacks, this paper proposes availability-based adversarial attacks, which can be more easily implemented by attackers. For each forecast instance, the availability attack target, i.e., a subset of input features, is optimally solved by a mixed-integer reformulation of the artificial neural network. To tackle this attack, an adversarial training algorithm is proposed. In simulation, a realistic load forecasting dataset is considered and the attack performance is comparable to the integrity-based counterpart. Meanwhile, the adversarial training algorithm is shown to significantly improve robustness against availability attacks. All codes are available at https://github.com/xuwkk/AAA-Load-Forecast.
Hou J, Teng F, Yin W, et al., 2023, Preventive-Corrective Cyber-Defense: Attack-Induced Region Minimization and Cybersecurity Margin Maximization, IEEE Transactions on Power Systems, ISSN: 0885-8950
False data injection (FDI) cyber-attacks on power systems can be prevented by strategically selecting and protecting a sufficiently large measurement subset, which, however, requires adequate cyber-defense resources for measurement protection. With any given cyber-defense resource, this paper proposes a preventive-corrective cyber-defense strategy, which minimizes the FDI attack-induced region in a preventive manner, followed by maximizing the cybersecurity margin in a corrective manner. First, this paper proposes a preventive cyber-defense strategy that minimizes the volume of the FDI attack-induced region via preventive allocation of any given measurement protection resource. Particularly, a sufficient condition for constructing the FDI unattackable lines is proposed, indicating that the FDI cyber-attack could be locally rather than globally prevented. Then, given a non-empty FDI attack-induced region, this paper proposes a corrective cyber-defense strategy that maximizes the cybersecurity margin, leading to a trade-off between the safest-but-expensive operation point (i.e., Euclidean Chebyshev center) and the cheapest-but-dangerous operation point. Simulation results on a modified IEEE 14 bus system verify the effectiveness and cost-effectiveness of the proposed preventive-corrective cyber-defense strategy.
Toubeau J-F, Teng F, Morstyn T, et al., 2023, Privacy-Preserving Probabilistic Voltage Forecasting in Local Energy Communities, IEEE TRANSACTIONS ON SMART GRID, Vol: 14, Pages: 798-809, ISSN: 1949-3053
- Author Web Link
- Cite
- Citations: 3
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.