Improper placement of distributed generation (DG) units in power systems would not only lead to an increased power loss, but could also jeopardise the system operation. To avert these scenarios and tackle this optimisation problem, this study proposes an effective method to guide electric utility distribution companies (DISCOs) in determining the optimal size and best locations of DG sources on their power systems. The approach, taking into account the system constraints, maximises the system loading margin as well as the profit of the DISCO over the planning period. These objective functions are fuzzified into a single multi-objective function, and subsequently solved using genetic algorithm (GA). In the GA, a fuzzy controller is used to dynamically adjust the crossover and mutation rates to maintain the proper population diversity (PD) during GA's operation. This effectively overcomes the premature convergence problem of the simple genetic algorithm (SGA). The results obtained on IEEE 6-bus and 30-bus test systems with the proposed method are evaluated with the simulation results of the classical grid search algorithm, which confirm its robustness and accuracy. This study also demonstrates DG's economic viability relative to upgrading substation and feeder facilities, when the incremental cost of serving additional load is considered.

This paper presents the methodology to detect and identify the type of fault that occurs in the shunt compensated static synchronous compensator (STATCOM) transmission line using a combination of Discrete Wavelet Transform (DWT) and Naive Bayes (NB) classifiers. To study this, the network model is designed using Matlab/Simulink. Different types of faults, such as Line to Ground (LG), Line to Line (LL), Double Line to Ground (LLG) and the three-phase (LLLG) fault, are applied at disparate zones of the system, with and without STATCOM, considering the effect of varying fault resistance. The three-phase fault current waveforms obtained are decomposed into several levels using Daubechies (db) mother wavelet of db4 to extract the features, such as the standard deviation (SD) and energy values. Then, the extracted features are used to train the classifiers, such as Multi-Layer Perceptron Neural Network (MLP), Bayes and the Naive Bayes (NB) classifier to classify the type of fault that occurs in the system. The results obtained reveal that the proposed NB classifier outperforms in terms of accuracy rate, misclassification rate, kappa statistics, mean absolute error (MAE), root mean square error (RMSE), percentage relative absolute error (% RAE) and percentage root relative square error (% RRSE) than both MLP and the Bayes classifier.

One of the most crucial prerequisites for effective wind power planning and operation in power systems is precise wind speed forecasting. Highly random fluctuations of wind influenced by the conditions of the atmosphere, weather and terrain result in difficulties of forecasting regardless of whether it is short-term or long-term. The current study has developed a method to model wind speed data predictions with dependence on seasonal wind variations over a particular time frame, usually a year, in the form of a Weibull distribution model with an artificial neural network (ANN). As a result, the essential dependencies between the wind speed and seasonal weather variation are exploited. The proposed model utilizes the ANN to predict the wind speed data, which has similar chronological and seasonal characteristics to the actual wind data. This model was applied to wind speed databases from selected sites in Malaysia, namely Mersing, Kudat, and Kuala Terengganu, to validate the proposed model. The results indicate that the proposed hybrid artificial neural network (HANN) model is capable of depicting the fluctuating wind speed during different seasons of the year at different locations.