Detection and classification of micro‐grid faults based on HHT and machine learning techniques

Mishra, Manohar; Rout, Pravat Kumar

doi:10.1049/iet-gtd.2017.0502

Cited by 198 publications

(83 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results obtained showed satisfactory performance of the proposed FD system, presenting an accuracy greater than 95% for all cases evaluated. Although similar performances were reported in [22,23,[25][26][27][28][29][30], in this work, a strategy to select the ML technique, the representative features, and their combination in order to optimize the performance of proposed FD technique were formulated. Additionally, all the stages were presented with enough detail for their understanding and replication, which is not usually observed in the FD state-of-the-art techniques.…”

Section: • Parametrization and Training Of ML Techniquesmentioning

confidence: 76%

“…Additionally, if a lower number of attributes is employed, the dimensionality of the problem space is also reduced, which can improve the performance of ML techniques on a given dataset [39]. Several attributes for FD approaches have been proposed in [13,[21][22][23]26,40]. In this work, the 49 attributes listed in Table 3 were used.…”

Section: Stage Ii: Input Data Adjustmentmentioning

confidence: 99%

“…However, typical network characteristics such as imbalance, topology changes, and upstream impedance changes are not considered [24]. In [25,26], a combined Hilbert/S-transform and decision tree-based intelligent scheme for fault detection and classification in microgrids is presented. The proposed method preprocesses the faulted current signals by using the S-transform to extract differential statistical features at the ends of the respective feeder, which are then used to build a decision tree model for final relaying decision.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Intelligent Fault Detection System for Microgrids

et al. 2020

View full text Add to dashboard Cite

The dynamic features of microgrid operation, such as on-grid/off-grid operation mode, the intermittency of distributed generators, and its dynamic topology due to its ability to reconfigure itself, cause misfiring of conventional protection schemes. To solve this issue, adaptive protection schemes that use robust communication systems have been proposed for the protection of microgrids. However, the cost of this solution is significantly high. This paper presented an intelligent fault detection (FD) system for microgrids on the basis of local measurements and machine learning (ML) techniques. This proposed FD system provided a smart level to intelligent electronic devices (IED) installed on the microgrid through the integration of ML models. This allowed each IED to autonomously determine if a fault occurred on the microgrid, eliminating the requirement of robust communication infrastructure between IEDs for microgrid protection. Additionally, the proposed system presented a methodology composed of four stages, which allowed its implementation in any microgrid. In addition, each stage provided important recommendations for the proper use of ML techniques on the protection problem. The proposed FD system was validated on the modified IEEE 13-nodes test feeder. This took into consideration typical features of microgrids such as the load imbalance, reconfiguration, and off-grid/on-grid operation modes. The results demonstrated the flexibility and simplicity of the FD system in determining the best accuracy performance among several ML models. The ease of design's implementation, formulation of parameters, and promising test results indicated the potential for real-life applications.Energies 2020, 13, 1223 2 of 21 as improved reliability, integration of renewable energies, reduction of network losses, and better voltage profile [7]. Nevertheless, microgrids present new challenges such as bidirectional power flow, considerable variations on fault currents levels, as well as power intermittency and quality issues, and additionally possible network reconfiguration, due to the presence of renewable energy sources [8]. Protection systems inside the distribution grid are particularly affected because they are based on the principle of overcurrent and unidirectional power flow [9]. Thus, traditional overcurrent protection schemes do not adequately protect microgrids [10].Several approaches have been proposed in the literature to deal with microgrid protection [11]. These protection schemes can be classified into three classes: external protection, adaptive protection, and fault detection. The external protection (EP) approach uses additional equipment such as reactances, super-capacitors, or fault current limiters (FCL) for preventing misfiring of the protection devices [12][13][14]. However, these solutions lack flexibility and, therefore, are not suitable for microgrids, where topology changes and DER connection/disconnection is possible [15]. The adaptive protection (AP) approach works online to dynamically modify protec...

show abstract

Section: • Parametrization and Training Of ML Techniquesmentioning

confidence: 76%

Section: Stage Ii: Input Data Adjustmentmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Fault Detection System for Microgrids

et al. 2020

View full text Add to dashboard Cite

show abstract

“…For example, the cost of electricity supply interruptions and the outage cost of DG units are critical measures that should be considered in the economic evaluation of the protection scheme [44], [45]. The trend towards using communication means for protecting distribution systems is also reflected on the numerous research papers adopting this philosophy [3]- [11], [13]- [25], [27], [28], [31], [32]. In fact, in [7], [8], communication-based protection schemes are considered for real looped distribution networks.…”

Section: G Economic Evaluationmentioning

confidence: 99%

“…Finally, several research efforts examine alternative protection solutions for looped/meshed distribution networks, not based on commercial relay functions. Protection techniques applying data-mining [26], [27], machine learning [28] and deep neural networks [29] have been proposed among others, which, however, require a training process, based on scenarios of the specific network examined. Other techniques regard dynamic-state-estimation-based protection [30], interval type-2 fuzzy logic [31] and checking power direction of the positive-sequence fault component, as part of a blocking-signalbased pilot protection scheme [32].…”

Section: Introductionmentioning

confidence: 99%

Towards Plug-and-Play Protection for Meshed Distribution Systems With DG

Tsimtsios

Nikolaidis

2020

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

Future distribution systems are expected to display increased complexity, mainly due to looped/meshed operation, switch between grid-connected and islanded mode and considerable integration of distributed generation. This paper investigates a plug-and-play protection solution for overhead distribution systems with such variable operation conditions, employing existing numerical relay capabilities. This solution is applied by designing plug-and-play, communication-assisted, multifunctional relays with integrated protection element settings, which apply universally to all distribution system conditions, rendering the protection scheme independent of a specific system. Hence, the need for user-defined settings or future revisions due to system changes is eliminated. The scheme ensures coordination between main line relays and backup protection of laterals, without a coordination study. There is no need to replace or modify existing lateral protection means for this purpose; only their known timeovercurrent curves are uploaded to the relays by the user. The scheme is described and evaluated through simulations in two test systems. Meaningful conclusions are finally derived.

show abstract

Transient energy‐based combined fault detector and faulted phase selector for distribution networks with distributed generators

Anudeep

Nayak

2019

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary Selective phase tripping during unbalanced short‐circuit fault helps in improving the reliability of the smart distribution systems. Selective phase tripping demands correct identification of faulted phase(s). The existing practices fail to identify the faulted phase(s) correctly in smart grids that include inverter‐interfaced distributed generators (DGs), such as wind and solar photovoltaic (PV) DGs. This paper presents a fault‐detection and faulted‐phase(s)‐identification scheme for smart distribution systems installed with both synchronous and PV distributed generators. In this work, the transient energies derived from the superimposed components of the measured voltage and current signals at both ends of a feeder are utilized for accomplishing the fault‐detection and faulted‐phase(s)‐identification task. The performance of the proposed method is evaluated for numerous fault and nonfault cases generated on three different test systems through power system computer aided design/EMTDC at different system operating modes and topologies. Fast response time (less than one cycle), low computational burden, and relatively high accuracy compared to the existing methods justify the efficacy of the proposed approach.

show abstract

Detection and classification of micro‐grid faults based on HHT and machine learning techniques

Cited by 198 publications

References 23 publications

Intelligent Fault Detection System for Microgrids

Intelligent Fault Detection System for Microgrids

Towards Plug-and-Play Protection for Meshed Distribution Systems With DG

Transient energy‐based combined fault detector and faulted phase selector for distribution networks with distributed generators

Contact Info

Product

Resources

About