The introduction of the microprocessor-based numerical relay in the 1980s resulted in multifunctional, multidimensional, communications-enabled complex protection systems for zone and system protection. The increasing capabilities of this technology created new unintended challenges: 1) complexity has increased and selecting coordinated settings is a challenge leading to occasional miscoordination; 2) protection functions still rely on a small number of measurements (typically three voltages and three currents) limiting the ability of protection functions to dependably identify the type of fault conditions; and 3) present approaches are incapable of dealing with hidden failures in the protection system. Statistically, 10% of protection operations are misoperations. This paper presents a new approach to protection that promises to eliminate the majority of the problems that lead to misoperations. The approach is described, demonstrated in the laboratory, compared to traditional protection functions and its application to a substation coordinated protection system capable of detecting and dealing with hidden failures is described. This paper also discusses the planned field testing of the approach.

Dynamic State Estimation-Based Protection: Status and Promise

In this study, a new algorithm for discrimination between internal faults and inrush current conditions in power transformers is presented. First, the proposed algorithm removes the pre-fault conditions of the fault currents. Then, those currents are processed using the discrete wavelet transform to obtain the wavelet matrix. The correlation matrix is computed from wavelet matrix to know the eigenvalues associated with each frequency scale and to reduce the analysed information. This algorithm, which the authors are going to call wavelet correlation modes, is used to identify inrush and internal fault currents in power transformer. To validate the proposed algorithm, simulations are carried out in power systems computer-aided design software, and the obtained signals are analysed in order to evaluate its performance and sensitivity.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/iet-gtd.2015.1147

Algorithm for transformer differential protection based on wavelet correlation modes

Faults diagnosis in power transformers has been traditionally based on the insulation resistance measurement, polarisation index, analysis of dissolved gasses in oil, dissipation/power factor measurement, and partial discharges within many other alternatives. Originally, all these techniques presented an offline implementation, that is, with the transformer out of service. Currently, some of them, such as partial discharges measurement or gas analysis (gas chromatography), are carried out online in those cases in which the importance of a machine justifies it. These techniques have been recently complemented with new alternatives, such as frequency response analysis, an offline application technique. At the same time, in recent years, development of online diagnostic strategies has been carried out only based in monitoring of electrical variables. These techniques have the advantage of being economical in relation to traditional ones. Its development are incipient and with high growth potential. This study presents a review of the most important techniques and a critical comparison between them.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/iet-gtd.2017.2086

Power transformers monitoring based on electrical measurements: state of the art

Current transformer (CT) saturation can cause the maloperation of transformer differential protection under external faults. To avoid this problem, a method based on the histogram of the normalized rotated current (NRC) is proposed. NRC is obtained by a symmetric waveform transformation of a part differential current. An index based on the histogram is defined to evaluate the NRC frequency distribution. The external faults with different degrees of CT saturation, internal faults, and transferring faults can be clearly distinguished by the proposed method. Moreover, the detection time is invariably less than a half cycle after the obvious increase of the differential current. Simulation results validated the proposed method.

Histogram-Based Method to Avoid Maloperation of Transformer Differential Protection Due to Current-Transformer Saturation Under External Faults

Differential relays are the main protection for power transformers including transmission and industrial transformers. Protection against internal fault is generally relegated to these relays. The most probable internal fault of the industrial transformer is phase to ground type. To limit the fault current in this condition, a limiter resistor is utilised in the transformer. However, it has considerable impact on sensitivity of the differential and restricted earth fault (REF) protections. In this study, an effective approach is proposed to improve the differential and REF protections sensitivity of the industrial transformers. The proposed technique not only realises the fault current limitation function, but preserves sensitivity of the protections. In this method, a developed fault current limiter is utilised in the transformer neutral instead of the neutral grounding resistor. The performance of the proposed technique is evaluated by some simulations and experiments. The results confirm the high capability of the proposed technique in different conditions.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/iet-gtd.2015.1343

New approach to improve sensitivity of differential and restricted earth fault protections for industrial transformers

Setting the pickup current and slope of differential relays of power transformer protection is a well-known compromise. It has been the focus of study to improve both the security and sensitivity of transformer differential protection recently. However, it is difficult to achieve a high degree of security and sensitivity at the same time by conventional percentage restraint differential criteria based on a fixed predetermined characteristic curve. Therefore a novel adaptive protection criterion is proposed in this study, which can self-regulate the parameters of percentage differential characteristic (e.g. pickup current, restraint coefficient and restraint current at the knee point of the slope characteristic) on the basis of operating conditions of power transformers. The test results show that the proposed scheme provides a high operating sensitivity on internal faults, while retaining higher security on all external faults. Furthermore, because of self-regulation of the setting values of relays, it is more convenient for engineers in the field who only need to give the upper and lower limits but not the exact value of the settings of protective relay.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/iet-gtd.2011.0739

Self-adaptive transformer differential protection

Wind power prediction (WPP) is extremely important in promoting the power grid's consumption of wind power. To improve the accuracy of WPP, a three-stage multiensemble short-term WPP method based on ensemble learning and deep learning is proposed in this paper. In the first stage, variational mode decomposition and wavelet transform were applied to decompose the original data sequence into different frequency bands. In the second stage, based on the decomposition sequences, the stacked denoising autoencoder (SDAE), long short-term memory (LSTM), and bidirectional long short-term memory (BLSTM) were used to predict the sequences; and 42 submodels were obtained. In the third stage, a support vector machine (SVM) was applied to give weight to each submodel to obtain the final ensemble prediction results. Based on three-stage integration, a new multi-integration model is proposed that repeats the third-stage integration operation. A case study is presented to verify the effectiveness and superiority of the proposed three-stage multi-integration WPP method. The normalized root mean square error (NRMSE) decreased by 0.0343 compared with LSTM, decreased by 0.0336 compared with BLSTM, and decreased by 0.0323 compared with SDAE, which demonstrated the effectiveness of the proposed new multistage ensemble and deep learning WPP method. 

A short‐term wind power prediction method based on deep learning and multistage ensemble algorithm

This article proposes a combined prediction method based on the Markov chain to realize precise short-term wind power predictions. First, three chaotic models are proposed for the prediction of chaotic time series, which can master physical principles in wind power processes and guide long-term prediction. Then, considering a mechanism switching between different physical models via a Markov chain, a combined model is constructed. Finally, the industrial data from a Chinese wind farm were taken as a study case, and the results validated the feasibility and superiority of the proposed prediction method.

/pdf/hybrid-short-term-wind-power-prediction-based-on-markov-3ep0d1ir.pdf

Liangsong Zhou

Papers

Self-adaptive transformer differential protection

A short‐term wind power prediction method based on deep learning and multistage ensemble algorithm

Hybrid Short-Term Wind Power Prediction Based on Markov Chain