On Stability of Distance Measures for Event Sequences Induced by Level-Crossing Sampling

Moser, Bernhard; Natschläger, Thomas

doi:10.1109/tsp.2014.2305642

Cited by 32 publications

(19 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the most common detection strategies is the so called send-on-delta (SOD) in which the event is triggered if a predefined signal deviates more than a threshold [27]. For this application (i.e., islanded microgrids with multiple DGs) the sampling should be performed over the local active power or the frequency.…”

Section: Event Detection Strategiesmentioning

confidence: 99%

“…Notice that once the event is detected, the timedependent protocol works independently. However, considering the possibility of multi-event scenarios it is key to design a suitable event detection strategy.One of the most common detection strategies is the so called send-on-delta (SOD) in which the event is triggered if a predefined signal deviates more than a threshold [27]. For this application (i.e., islanded microgrids with multiple DGs) the sampling should be performed over the local active power or the frequency.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Secondary Switched Control With no Communications for Islanded Microgrids

Rey

Martí

Velasco

et al. 2017

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

Abstract-Flexibility and reliability of AC microgrids are enhanced by reducing the dependence on communications in multi-layer hierarchical control. In this sense, this paper presents a secondary control with no communications for islanded microgrids. It is based on a control scheme that switches between two configurations according to a time-dependent protocol. With this proposal, an excellent performance in terms of transient response and frequency restoration in steady-state is achieved. The paper also presents design considerations for the control parameters. In addition, the theoretical predictions are validated by experimental results from a laboratory microgrid.Index Terms-Distributed generation, hierarchical control, islanded microgrids, secondary control, switched control, time-dependent protocol. I. INTRODUCTIONICROGRIDS have recently emerged as a potential solution for electrical supply due to their advantages as environmental impacts reduction, reliability, and flexible operability [1], [2]. Basically, a microgrid is a cluster of distributed generators (DGs), loads, and energy storage systems which can operate in two possible modes: gridconnected or islanded [3].In islanded mode, microgrids are disconnected from the main grid intentionally or by an electrical fault and the DGs provide active and reactive power to the local loads [4]. To control frequency, voltage amplitude or power sharing, a multi-layer hierarchical scheme can be implemented, normallyManuscript received Month xx, 2xxx; revised Month xx, xxxx; accepted Month x, xxxx. This work has been supported by ELAC2014/ESE0034 from the European Union and its linked Spanish national project PCIN-2015-001. We also appreciate the support from the Ministry of Economy and Competitiveness of Spain and the European Regional Development Fund (FEDER) under projects ENE2015-64087-C2-1-R and TEC2013-46938-R.Juan M. Rey is with Escuela de Ingenierías Eléctrica, Electrónica y de Telecomunicaciones (E3T), Universidad Industrial de Santander (UIS), 680002 Bucaramanga, Colombia and with the Electronic Engineering Department, Technical University of Catalonia, Av. Victor Balaguer s/n, 08800 Vilanova i Ia Geltrú, Spain (e-mail: juanmrey@uis.edu.co).Pau Marti and Manel Velasco are with the Automatic Control Department, Technical University of Catalonia, Pau Gargallo 5, 08028 Barcelona, Spain.Jaume Miret and Miguel Castilla are with the Electronic Engineering Department, Technical University of Catalonia, Av. Victor Balaguer s/n, 08800 Vilanova i la Geltrú, Spain. divided in three control layers: primary, secondary and tertiary layer [5].Primary layer rapidly controls power sharing and stabilizes frequency and output voltage amplitude in each DG. However, steady-state errors or deviations are introduced, which are corrected by the secondary layer. Tertiary layer manages and coordinates the operation of the power flows at optimal points considering economic concerns (i.e., energy prices and electricity markets) and grid requirements (i.e., reactive power flows contr...

show abstract

Section: Event Detection Strategiesmentioning

confidence: 99%

mentioning

confidence: 99%

Secondary Switched Control With no Communications for Islanded Microgrids

Rey

Martí

Velasco

et al. 2017

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

show abstract

“…When a data object exhibits a large distance with other objects, it is regarded as abnormal. For example, Chandola et al [4,20] propose a kNN-based ( k -nearest neighbor) technique in which the k -nearest neighbor distances of all objects are calculated and treated as the anomaly scores of objects. Two disadvantages of distance-based techniques are found, i.e., the choice of the distance measure directly determines their performance and the time complexity is up to O ( n 2 ) when computing the distance among n points [7,25] .…”

Section: Introductionmentioning

confidence: 99%

Anomaly detection based on a dynamic Markov model

Ren

2017

Information Sciences

View full text Add to dashboard Cite

a b s t r a c tAnomaly detection in sequence data is becoming more and more important in a wide variety of application domains such as credit card fraud detection, health care in medical field, and intrusion detection in cyber security. In the existing anomaly detection approaches, Markov chain techniques are widely accepted for their simple realization and few parameters. However, the short memory property of a classical Markov model ignores the interaction among data, and the long memory property of a higher order Markov model clouds the relationship between the previous data and current test data, and reduces the reliability of the model. Besides, both of these models cannot successfully describe the sequences changing with a tendency. In this paper, we propose an anomaly detection approach based on a dynamic Markov model. This approach segments sequence data by a sliding window. In the sliding window, we define the states of data according to the value of the data and establish a higher order Markov model with a proper order consequently, to balance the length of the memory property and keep up with the trend of sequences. In addition, an anomaly substitution strategy is proposed to prevent the detected anomalies from impacting the building of the models and keep anomaly detection continuously. The experimental results using simulated datasets and real-world datasets have demonstrated that the proposed approach improves the adaptability and stability of anomaly detection in sequence data.

show abstract

“…The birth-death type DTMC is frequently used in many applications [6,11,12,19,26] for various purposes such as the learning of the statistical behavior [6,19] and the background image [26] in video observations. Birth-death type chains are also used in [11,12] for level-crossing based sampling. Other popular examples are in the literature of counting processes and their queuing applications, cf.…”

Section: Introductionmentioning

confidence: 99%

Efficient NP Tests for Anomaly Detection Over Birth-Death Type DTMCs

Özkan

Delibalta

et al. 2016

J Sign Process Syst

View full text Add to dashboard Cite

We propose computationally highly efficient Neyman-Pearson (NP) tests for anomaly detection over birth-death type discrete time Markov chains. Instead of relying on extensive Monte Carlo simulations (as in the case of the baseline NP), we directly approximate the loglikelihood density to match the desired false alarm rate; and therefore obtain our efficient implementations. The proposed algorithms are appropriate for processing large scale data in online applications with real time false alarm rate controllability. Since we do not require parameter tuning, our algorithms are also adaptive to non-stationarity in the data source. In our experiments, the proposed tests demonstrate superior detection power compared to the baseline NP while nearly achieving the desired rates with negligible computational resources.

show abstract

On Stability of Distance Measures for Event Sequences Induced by Level-Crossing Sampling

Cited by 32 publications

References 43 publications

Secondary Switched Control With no Communications for Islanded Microgrids

Secondary Switched Control With no Communications for Islanded Microgrids

Anomaly detection based on a dynamic Markov model

Efficient NP Tests for Anomaly Detection Over Birth-Death Type DTMCs

Contact Info

Product

Resources

About