COMPUTATIONAL INTELLIGENCE IN ELECTRICAL ENGINEERING (INTELLIGENT SYSTEMS IN ELECTRICAL ENGINEERING)
Year:2019 | Volume:10 | Issue:2 |Papers Count:6

In this paper, a risk-constrained two-stage stochastic model is proposed for optimal scheduling of autonomous microgrids considering the participation of end-use customers in demand response programs. The goal of the proposed scheme is to maximize the profit of the microgrid operator in different conditions of the user's risk taking, so that customers pay the lowest cost for their energy consumption. Based on the proposed model, customers are able to provide part of the system's reserve capacity to deal with uncertainties by using smart and response loads capability. The uncertainties of the problem are due to the predicted error of renewable resources, energy prices and demand loads, modeled on scenario-based methods. In the proposed model, in order to deal with the effects of undesirable scenarios, an index for assessing the value of risk is employed to estimate the level of undesirable profits. In addition, in order to more accurately analyze the frequency and voltage limitations, an AC load flow is used in the problem-solving process that achieves more realistic result to the microgrid operation. Finally, the proposed model is implemented in a typical microgrid and the results are investigated in different cases.

Flight control system is a unit of the air defense and missile system that takes commands prescribed by the guideline law and operates due to the operators embedded in the system. Missile physical system includes nonlinear aerodynamic coefficients and other physical dependent variables, so accurate identification of them is difficult. This issue makes deference between real and mathematic model of missile equations of motion and causes designed linear controller performance degradation. In this paper, inverse dynamic approach is used for uncertainty identifying and mathematic modeling of missile defense system. Then, this model is used for optimizing and controlling the flight of a missile with nonlinear 6 DOF (Degrees of freedom) equations of motion. Thus, the designed controller is a nonlinear fuzzy-adaptive controller which has high adaption and robustness against the parametric changes during missile’ s flight. Using the invers dynamic method for modeling motion equations of missile defense is the innovation of this research.

The main purpose of this paper is to present an adaptive-neural controller for strict-feedback nonlinear systems with unknown time delays and in the presence of external disturbances and actuator failure. The proposed adaptive-neural controller is constructed based on DSC design technique. Radial Basis Functions (RBF) networks are utilized to approximate unknown nonlinear functions. Adaptive rules are obtained based on Lyapunov design for updating the parameters of neural networks. Disturbances are unknown functions which their bounds are partially known. Therefore, continuous robust terms are applied in order to minimize their effects. Furthermore, due to the existence of unknown time delays in the system, Lyapunov– Krasovskii functionals are utilized in the process of designing the controller and proofing the stability of the system. In addition, the controller is designed so that it can compensate its effect if the considered actuator failure happens. For the designed controller, the boundedness of all the closed-loop signals is guaranteed and the tracking error is proved to converge to a small neighborhood of the origin.

With the Penetration of renewable energies into power system, the influence of uncertainties in solving various problems in the field of power system operation has increased. One of the most important concepts in this field is optimal power flow, which, with the presence of uncertainties, cannot be modeled by definite methods, and should be revised based on applying the probabilistic approaches. In this paper, numerical methods including the Monte Carlo Simulation method and analytical methods including point estimation methods, internal point method and unscented transformation method are used to solve the POPF in an IEEE-118 bus system. The obtained results indicate that the methods based on point estimation are able to find the optimal points in less computational time than other techniques. This is mainly due to the limited points, which these methods need as the starting points. From another perspective, the magnitude changes in the voltage profile of the generation units are also more stable in the internal point method. Furthermore, in terms of the convergence rate, the internal point method is much faster than the Monte Carlo Simulation method.

Given that the price signal in the electricity market is highly volatile or otherwise uncertain, short-term forecasting is significantly affected. Since time-series methods cannot estimate such nonlinear models appropriately with high accuracy, we need to provide an efficient model. For this reason, in this paper, a new hybrid algorithm for day-ahead electricity price forecasting is proposed. In order to achieve this model, we first divide the forecasting problem into three main layers: preprocessor, training, and regulator. In the first layer, we use the curvelet transform to reduce possible noise in the price signal. Then, using the extended data selection model based on increasing correlation and decreasing redundancy, we eliminate the unnecessary data and reduce the volume of computation significantly. Then the regularized data is entered into the learning layer which is a developed Extreme Learning Machine (ELM) to obtain and extract the best pattern from the input data. Since adjusting the control parameters of the proposed ELM can maximize its ability to derive a nonlinear pattern from the price signal, a new developed Virus Colony Search (VCS) method based on the time-varying coefficients theory is proposed in the last layer. The proposed algorithm is a novel optimization method based on the function of viruses to destroy host cells and penetrate the best ones into a cell for replication. The proposed method is applied to existing real electricity markets and the results are compared based on prediction error rates and error-based criteria. The obtained results show the appropriate and acceptable performance of the proposed forecasting method.

In this paper, in order to fault locate in the transmission network, a discrete wavelet transform is used to extract the fault characteristics from the zero sequence current, in order to train the artificial neural network. Initially, Fortescue transform, the zero-sequence current seen from both terminals is calculated. By the wavelet transform of the high-frequency information stored in the horizontal component of zero-sequence current from both terminals, and finally by calculating the stored energy in the horizontal components, as well as extracting the maximum scale of horizontal component, we can identify certain features of fault that are suitable for training the neural network. The simulation results show that the horizontal components maximum scale as well as the energy stored in these components strongly depend on the fault resistance, type of fault and fault location. Therefore, educational data should be selected to make these changes well so that the neural network does not suffer from its diagnosis. Finally, the proposed method is implemented on the test grid whose results show the performance of the method with overall accuracy of 98. 6% and maximum estimation error of 0. 1666%.