On-line monitoring and diagnosis of transformers have been investigated and discussed significantly in last decade. This study has concentrated on issues arising while on-line transformer winding deformation diagnosis is going to be applied on transformers with various kinds of techniques. From technical perspective, before replacing off-line methods by on-line methods and eventually by intelligent approaches, practical challenges must be addressed and overcome. Hence, available off-line transformer winding deformation diagnosis methods are discussed precisely. Mathematical calculation in on-line short circuit impedance measurement is investigated. On-line transformer transfer function measurement setup is presented. A profound insight to the problems pertaining on-line transformer winding deformation recognition methods, characterizes existing online methods, explains the concepts behind online measurements and striving to open the discussion doors towards challenges are discussed. In the end a 400 MVA step up transformer has been taken as a case in order to clarify the capability of Frequency Response Analysis (FRA) method in fault detection while short circuit impedance could only demonstrate some rough understanding about transformer condition.

Power transformers are in service under different environmental, electrical, and mechanical conditions [1] and may be subject to enormous hazards during the course of operation [2], [3]. They are commonly considered to be the heart of the transmission and distribution sectors of electric power systems; monitoring their condition and diagnosing faults are important parts of the maintenance function [4]. Utility engineers strive to keep power transformers in service and to prevent even shortterm outages. Failure of a transformer can cause extensive damage to equipment owned by consumers or the utility [5].

To mitigate the power quality issue in microgrids, a new online reference control strategy for distribution static compensator using the reinforcement learning algorithm is presented. The new controller is supposed to compensate the reactive power, harmonics, and unbalanced load current in a microgrid utilizing voltage and current parameters. Voltage controller is used to adjust the set point of the reactive power reference, whereas the current based controller tries to compensate the unbalanced load current in distributed resource network through the quadrature axis (q-axis) and zero axis (0-axis). The proposed control strategy is applied to an autonomous microgrid with a weak ac-supply (non-stiff source) distribution system under different loads as well as three-phase fault conditions. Different scenarios are studied and simulation results for various conditions are discussed. The performance of the proposed online secondary control strategy is also discussed in detail.

Wind power generation is considerably dependent on the weather condition and it is correlated closely with the air density, wind speed, and its direction through considering the transformer tap change cost. Therefore, an accurate prediction model is required to forecast and adopt with the complicated signals. In this article, an accurate prediction method trained with improved wavelet transform (IWT) to decompose the original signal to subsignals, new feature selection based on the maximum dependence, maximum relevancy, and minimum redundancy to filter the signal and select the best candidate inputs and a synthetic forecasting engine with minimum forecasting error is proposed. The proposed method of forecasting engine composed two-dimensional convolution neural network (TDCNN) and trained by improved optimization algorithm based on particle swarm optimization. The proposed improved optimization algorithm will fine-tune the weights of TDCNN to increase the prediction accuracy of the forecast engine. The training optimization processes and effectual fast classification are the main duty of the proposed intelligent algorithm. The efficiency of the suggested prediction approach is widely evaluated and compared to other prediction approaches using the practical power market data. A simulation study is conducted over the trained model and the results are discussed in detail. Obtained numerical results and also analysis in short-term and long-term forecasting horizons validate the high performance and advantages of the introduced approach.

Partial discharges are well known as a source for insulation degradation in power transformers. A hybrid transformer model is introduced to simulate the transformer winding transient response. Transformer structural data is used to determine the hybrid model parameters. Calculations of the hybrid transient model parameters are based on the parameters of the lumped parameter equivalent transformer model and electromagnetic rules. Modern computation techniques and optimizations are employed beside this model for PD location using the multi conductor transmission line model and also to analyze its propagation aimed at achieving (i) more reliable simulation results (ii) less computational time (iii) accurate results for a wide range of frequency. The simulation results on a 66 kV, 25 MVA fully interleaved winding are presented. The measurement results on this winding are employed to validate this model