The introduction of electric vehicles impose large disturbance to the grid-level power signal due to the charging and discharging mechanism. Power signal monitoring in the electrical grid can provide several insights such as power quality disturbance detection, major power consumption area, peak power usage period, and their potential catastrophic failure conditions. As for preventive maintenance purpose, automatic classification of power quality disturbance using a hybrid method incorporating wavelet transform and deep LSTM network is proposed in this paper. Multi-level signal decomposition is applied to input signal to increase the resolution of input decomposing into multiple frequency bands. Subsequently, these multi-level frequency components are fed into deep LSTM layer to further extract useful higher order latent feature. Classification performance of the proposed wavelet-based LSTM (WTLSTM) network is bench-marked with deep LSTM method. Additive white Gaussian noise (AWGN) with signal-to-noise (SNR) levels between 20-50dB are inserted during the training process to increase the generalization of signal learning with the realistic scenarios. The classification performance of both WT-LSTM and Deep LSTM networks are tested with 20,30,40,50dB SNR AWGN and noiseless conditions. As a result, the WT-LSTM network obtains an overall classification performance of 89.77% on 20dB and 99.21% on noiseless condition as compared to Deep LSTM, with 88.48% and 98.54% respectively.

No abstract

In classical power systems, frequency measurements are transferred via a specialised communication channel, resulting in time delay. The time delay plays a major role in a power system, which can reduce the dynamic performance of the load–frequency control (LFC) system and can destabilise the system. The research to date has tended to focus on developing a new algorithm to determine the delay margin (DM) rather than looking into a hybrid algorithm which includes a nature-inspired metaheuristic optimisation technique. This paper introduces a novel method for computing the DM based on grey wolf optimisation (GWO), specifically for the constant time delay. In the proposed method, GWO is employed to optimise the minimum error of the spectral radius and to determine the best design variable of the crossing frequency. With the help of the proposed method, the sweeping range is no longer required, which improves the accuracy of the result. To evaluate the proposed method, a two-area network power system is considered as a case study. Furthermore, the effect of the PI controller gains on the DM is taken into account. The proposed method efficacy is demonstrated by comparing it with the most recently published methods. The results demonstrate that the proposed method is remarkably better than the existing methods found in the literature, where the smallest percentage inaccuracy using the simulation-based DM based on GWO is found to be 0.000%.

Efficient detection and classification of power quality disturbances is required with the increasing penetration of multi-energy systems such as microgrids and features from renewable energy resources. Machine learning approach is popular to generate useful and optimal features from data learning to improve the classification performance. This paper aims to analyse the classification performance using the hybrid model of multi-resolution analysis and long short-term memory network. The proposed model uses four-level decomposition wavelet transform to increase the resolution of input signals into multi-bands signal representation. Spatial and temporal feature representation of the wavelet coefficients are highlighted using attention mechanism before feeding into long short-term memory network for sequence feature extraction. The sequence feature output is then passed into multiple dense layer for the classification process. Synthetic disturbance signals are used as training samples. The performance test carried out includes the condition of 20–50 dB signal-to-noise ratio signals, where additive white Gaussian noise are added into the test samples.

No abstract

No abstract

No abstract

No abstract