Voltage stability detection is currently still becoming the main issue in the modern integrated renewable energy power systems. To assess the voltage stability, the classical methods based on continuation power flow (CPF) technique were used to show nose curve. However, the classical methods require complete model of power system and long computation time. Data driven analysis and synchronized real time measurement technologies currently are developing in power systems monitoring, including the stability detection. The detection method is built based on the historical event model and uses the real time measurement as an input. For that reason, the algorithm to detect the voltage instability and critical bus is proposed using the artificial neural network (ANN) technique to represent the historical event model using the PMU measurement data. The ANN model architecture for this application is developed by creating seven hidden layers consisting of one normalization, four rectifier linear unit, one softmax and one sigmoid layer. To warrant the accuracy, the k-fold cross-validation is used. The algorithm is simulated on modified IEEE 14 test system which consider different loading scenario, line contingency, number of PMU and Photovoltaic (PV) integration. To mimic the actual historical data, the synthetic data is generated and labelled. The result shows that the proposed method can represent the complete power system model by giving high accuracy which for voltage stability detection is > 97% and critical buses detection is > 96% for all scenarios. Moreover, the required computation time is between 16 and 18 s per detection which makes the scalability to the real time detection is reasonable.

The development of electric power systems has become more complex. Consequently, electric power systems are operating closer to their limits and are more susceptible to instability when a disturbance occurs. Transient stability problems are especially prevalent. In addition, the identification of transient stability is difficult to achieve in real time using the current measurement data. This research focuses on developing a convolutional neural network—long short-term memory (CNN-LSTM) model using historical data events to detect transient stability considering time-series measurement data. The model was developed by considering noise, delay, and loss in measurement data, line outage and variable renewable energy (VRE) integration scenarios. The model requires PMU measurements to provide high sampling rate time-series information. In addition, the effects of different numbers of PMUs were also simulated. The CNN-LSTM method was trained using a synthetic dataset produced using the DigSILENT PowerFactory simulation to represent the PMU measurement data. The IEEE 39 bus test system was used to simulate the model under different loading conditions. On the basis of the research results, the proposed CNN-LSTM model is able to detect stable and unstable conditions of transient stability only from the magnitude and angle of the bus voltage, without considering system parameter information on the network. The accuracy of transient stability detection reached above 99% in all scenarios. The CNN-LSTM method also required less computation time compared to CNN and conventional LSTM with the average computation times of 190.4, 4001.8 and 229.8 s, respectively.

Distributed Generation (DG) installation in the distribution system aimed to reduce power losses, increase the voltage profile, and increase the amount of power supplied. One DG that can be implemented is based on photovoltaic (PV). The stochastic PV characteristics will cause ups and downs of the power produced. When the power generated is greater than the load downstream, it will potentially cause the power flow to be two-way. The method for determining the placement location and optimal DG capacity is needed so that the effect of PV penetration on changes in power flow and voltage profile is still within the permissible limits.This study proposed the FPA algorithm to determine the optimal location and DG capacity to reduce power losses in the distribution system with a case study of distribution network in Semanu Substation, Gunung Kidul Yogyakarta. The findings confirmed that the FPA method can be used to determine the placement location and optimal DG capacity of 9.501 MW, with active power losses after DG having decreased by 68.75%, and reactive power losses of 61.40%.

Short-term load forecasting (STLF) is a very important factor in the planning and operation of power systems. The purpose of load forecasting is to balance the demand and electricity supply. The electrical load is dynamic, changing over the time. The provision of electrical energy is also dynamic following the pattern of load changes. Load forecasting is required to ensure an accurate decision on power plant scheduling, unit commitment, and power delivery. This paper presents a recurrent neural network (RNN) model with Levenberg-Marquardt and Bayesian regularization training algorithms used for short-term electrical load forecasting. The accuracy criterion used is Mean Absolute Percentage of Error (MAPE). The results show that the RNN model can make good predictions. RNN model with the Bayesian regularization training algorithm has better accuracy. Its average MAPE in one week is 1,4792%. It implies that the RNN model is great tool for STLF.

Energy sustainability has become one of the main issues in power system planning in the Indonesian archipelago system, which has many small, isolated systems. For that purpose, green and sustainable generation expansion planning (GEP) procedures based on local energy resources is required. GEP is a necessary procedure for fulfilling electricity demand, which determines the generating units to be installed within a specified time horizon with minimal total costs as the objective function. This study uses GEP considering the interconnection option among the existing small scattered generation systems in Maluku: the isolated Ambon, Seram, Haruku, and Saparua systems. With interconnection, the utilization of local renewable energy sources would be increased, especially biomass, which has abundant potential in these areas. The GEP was simulated in the PLEXOS environment using mixed-integer linear programming (MILP). For comparison purposes, there were interconnection and isolated system scenarios. The results showed that the interconnection system would have a high share of a renewable energy source (RES) of up to 54% in 2050, most of which is biomass as the primary local energy source. The interconnection system scenario met the LOLP criteria and had a lower reserve margin and total costs than the isolated scenario, with USD 773.7 million.