An official website of the United States government
This paper presents a deep learning based multi-label attack detection approach for the distributed control in AC microgrids. The secondary control of AC microgrids is formulated as a constrained optimization problem with voltage and frequency as control variables which is then solved using a distributed primal-dual gradient algorithm. The normally distributed false data injection (FDI) attacks against the proposed distributed control are then designed for the distributed gener-ator's output voltage and active/reactive power measurements. In order to detect the presence of false measurements, a deep learning based attack detection strategy is further developed. The proposed attack detection is formulated as a multi-label classification problem to capture the inconsistency and co-occurrence dependencies in the power flow measurements due to the presence of FDI attacks. With this multi-label classification scheme, a single model is able to identify the presence of different attacks and load change simultaneously. Two different deep learning techniques are compared to design the attack detector, and the performance of the proposed distributed control and the attack detector is demonstrated through simulations on the modified IEEE 34-bus distribution test system.
more »
« less
An unsupervised cyberattack detection scheme for AC microgrids using Gaussian process regression and one‐class support vector machine anomaly detection
Abstract This paper addresses the cybersecurity of hierarchical control of AC microgrids with distributed secondary control. The false data injection (FDI) cyberattack is assumed to alter the operating frequency of inverter‐based distributed generators (DGs) in an islanded microgrid. For the microgrids consisting of the grid‐forming inverters with the secondary control operating in a distributed manner, the attack on one DG deteriorates not only the corresponding DG but also the other DGs that receive the corrupted information via the distributed communication network. To this end, an FDI attack detection algorithm based on a combination of Gaussian process regression and one‐class support vector machine (OC‐SVM) anomaly detection is introduced. This algorithm is unsupervised in the sense that it does not require labelled abnormal data for training which is difficult to collect. The Gaussian process model predicts the response of the DG, and its prediction error and estimated variances provide input to an OC‐SVM anomaly detector. This algorithm returns enhanced detection performance than the standalone OC‐SVM. The proposed cyberattack detector is trained and tested with the data collected from a 4 DG microgrid test model and is validated in both simulation and hardware‐in‐the‐loop testbeds.
more »
« less
- PAR ID:
- 10420736
- Publisher / Repository:
- DOI PREFIX: 10.1049
- Date Published:
- Journal Name:
- IET Renewable Power Generation
- Volume:
- 17
- Issue:
- 8
- ISSN:
- 1752-1416
- Format(s):
- Medium: X Size: p. 2113-2123
- Size(s):
- p. 2113-2123
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)In this paper, we introduce a distributed secondary voltage and frequency control scheme for an islanded ac microgrid under event-triggered communication. An integral type event-triggered mechanism is proposed by which each distributed generator (DG) periodically checks its triggering condition and determines whether to update its control inputs and broadcast its states to neighboring DGs. In contrast to existing event-triggered strategies on secondary control of microgrids, the proposed event-triggered mechanism is able to handle the consensus problem in case of asynchronous communication. Under the proposed sampled-data based event-triggered mechanism, DGs do not need to be synchronized to a common clock and each individual DG checks its triggering condition periodically, relying on its own clock. Furthermore, the proposed method efficiently reduces communication rate. We provide sufficient conditions under which microgrid's frequency and a critical bus voltage asymptotically converge to the nominal frequency and voltage, respectively. Finally, effectiveness of our proposed method is verified by testing different scenarios on an islanded ac microgrid benchmark in the MATLAB/Simulink environment as well as a hardware-in-the-loop (HIL) platform, where the physical system is modeled in the Opal-RT and the cyber system is realized in Raspberry Pis.more » « less
-
This paper presents a droop-free distributed secondary control for DC microgrids with admissible voltage profile guarantees. The control objectives are achieved through an average voltage regulator, voltage variance regulator, and a relaxed current sharing regulator. Regulations of the global average voltage to the microgrid rated voltage is ensured by the average voltage regulator and regulations of the global voltage variance to a predetermined reference is enabled by the voltage variance regulator. In order to achieve the objectives of voltage regulation, the current sharing from one of the DGs which may be owned by the microgrid community is relaxed. The global dynamic model of the DC microgrid with the proposed control is derived. Besides, steady-state analysis is performed to show that all objectives can be achieved. Finally, simulations on a 4-DG DC microgrid test system are performed to validate the efficacy of the proposed control.more » « less
-
This paper proposes a novel method to locate faults in an AC‐meshed microgrid. To this end, a set of features is first extracted and selected from the measured signals and fed to a Support Vector Machine (SVM) to detect the occurrence of fault. Then, the Distributed Generator (DG) with the lowest amount of fundamental voltage, which is the closest one to the fault, injects an appropriate voltage/current harmonic. As the faulted section has the lowest impedance value from the Point of Common Coupling of the DG, the harmonic current of the corresponding line has the highest value. Based on this fact, the first candidate DG sends a notification signal to the second candidate DG, in which the fault occurs between them. Finally, the impedances in the injected frequency are measured from these two DGs and fed into a multi‐class SVM to locate the faulted line. The proposed method has the ability to locate faults for islanded and grid‐connected microgrids with variable configurations. Real‐time simulation results are taken by OPAL‐RT to show the effectiveness of the proposed method in the meshed microgrid.more » « less
-
Microgrid, which is one of the main foundations of the future grid, inherits many properties of the smart grid such as, self‐healing capability, real‐time monitoring, advanced two‐way communication systems, low voltage ride through capability of distributed generator (DG) units, and high penetration of DGs. These substantial changes in properties and capabilities of the future grid result in significant protection challenges such as bidirectional fault current, various levels of fault current under different operating conditions, necessity of standards for automation system, cyber security issues, as well as, designing an appropriate grounding system, fast fault detection/location method, the need for an efficient circuit breaker for DC microgrids. Due to these new challenges in microgrid protection, the conventional protection strategies have to be either modified or substituted with new ones. This study aims to provide a comprehensive review of the protection challenges in AC and DC microgrids and available solutions to deal with them. Future trends in microgrid protection are also briefly discussed.more » « less
