Implementation of adaptive critic-based neurocontrollers for turbogenerators in a multimachine power system

This paper presents the design and practical hardware implementation of optimal neurocontrollers that replace the conventional automatic voltage regulator (AVR) and the turbine governor of turbogenerators on multimachine power systems. The neurocontroller design uses a powerful technique of the adaptive critic design (ACD) family called dual heuristic programming (DHP). The DHP neurocontrollers' training and testing are implemented on the Innovative Integration M67 card consisting of the TMS320C6701 processor. The measured results show that the DHP neurocontrollers are robust and their performance does not degrade unlike the conventional controllers even when a power system stabilizer (PSS) is included, for changes in system operating conditions and configurations. This paper also shows that it is possible to design and implement optimal neurocontrollers for multiple turbogenerators in real time, without having to do continually online training of the neural networks, thus avoiding risks of instability.     

Real-Time Implementation of a STATCOM on a Wind Farm Equipped With Doubly Fed Induction Generators

Voltage stability is a key issue to achieve the uninterrupted operation of wind farms equipped with doubly fed induction generators (DFIGs) during grid faults. This paper investigates the application of a static synchronous compensator (STATCOM) to assist with the uninterrupted operation of a wind turbine driving a DFIG, which is connected to a power network, during grid faults. The control schemes of the DFIG rotor- and grid-side converters and the STATCOM are suitably designed and coordinated. The system is implemented in real-time on a real time digital simulator. Results show that the STATCOM improves the transient voltage stability and therefore helps the wind turbine generator system to remain in service during grid faults.     

MLP/RBF neural-networks-based online global model identification of synchronous generator

This paper compares the performances of a multilayer perceptron neural network (MLPN) and a radial basis function neural network (RBFN) for online identification of the nonlinear dynamics of a synchronous generator in a power system. The computational requirement to process the data during the online training, local convergence, and online global convergence properties are investigated by time-domain simulations. The performances of the identifiers as a global model, which are trained at different stable operating conditions, are compared using the actual signals as well as the deviation signals for the inputs of the identifiers. Such an online-trained identifier with fixed optimal weights after the global convergence test is needed to provide information about the plant to a neurocontroller. The use of the fixed weights is to provide against a sensor failure in which case the training of the identifiers would be automatically stopped, and their weights frozen, but the control action, which uses the identifier, would be able to continue.     

Indirect adaptive control for synchronous Generator: comparison of MLP/RBF neural networks approach with Lyapunov stability analysis

This paper compares two indirect adaptive neurocontrollers, namely a multilayer perceptron neurocontroller (MLPNC) and a radial basis function neurocontroller (RBFNC) to control a synchronous generator. The different damping and transient performances of two neurocontrollers are compared with those of conventional linear controllers, and analyzed based on the Lyapunov direct method.     

A continually online trained neurocontroller for excitation andturbine control of a turbogenerator

The increasing complexity of the modern power grid highlights the need for advanced modeling and control techniques for effective control of turbogenerators. This paper presents the design of a continually online trained (COT) artificial neural network (ANN) based controller for a turbogenerator connected to an infinite bus through a transmission line. Two COT ANNs are used for the implementation; one ANN, the neuroidentifier, to identify the complex nonlinear dynamics of the power system and the other ANN, the neurocontroller, to control the turbogenerator. The neurocontroller replaces the conventional automatic voltage regulator (AVR) and turbine governor. Simulation and practical implementation results are presented to show that COT neurocontrollers can control turbogenerators under steady state as well as transient conditions     

Particle swarm optimization with quantum infusion for system identification

System identification is a challenging and complex optimization problem due to nonlinearity of the systems and even more in a dynamic environment. Adaptive infinite impulse response (IIR) systems are preferably used in modeling real world systems because of their reduced number of coefficients and better performance over the finite impulse response filters. Particle swarm optimization (PSO) and its other variants has been a subject of research for the past few decades for solving complex optimization problems. In this paper, PSO with quantum infusion (PSO–QI) is used in identification of benchmark IIR systems and a real world problem in power systems. PSO–QI’s performance is compared with PSO and differential evolution PSO (DEPSO) algorithms. The results show that PSO–QI has better performance over these algorithms in identifying dynamical systems.     

Real-time implementation of a measurement-based adaptive wide-area control system considering communication delays

A wide-area control system (WACS) uses wide-area measurement signals to provide auxiliary stabilising controls to power system devices. An adaptive WACS has been designed to provide damping control signals to the excitations of generators. The delays in signal transmission and the reliability of the communication network is a major concern with wide-area measurement- based control. The adaptive WACS is designed to compensate for a wide range of communication delays and provide robust damping to mitigate system oscillations. A single simultaneous recurrent neural network is used in the realisation of the adaptive WACS for both identification and control of the power system. The WACS has been implemented on a digital signal processor and its performance is evaluated on a power system implemented on a real-time platform - the real-time digital simulator. The additional damping provided by the WACS is enumerated using Prony analysis.     

RNN based MIMO channel prediction

A new hybrid PSO-EA-DEPSO algorithm based on particle swarm optimization (PSO), evolutionary algorithm (EA), and differential evolution (DE) is presented for training a recurrent neural network (RNN) for multiple-input multiple-output (MIMO) channel prediction. This algorithm is shown to outperform RNN predictors trained off-line by PSO, EA, and DEPSO as well as a linear predictor trained by the Levinson–Durbin algorithm. To explore the effects of channel prediction error at the receiver, new expressions for the received SNR, array gain, and average probability of error are derived and analyzed. These expressions differ from previous results which assume the prediction error is Gaussian and/or independent of the true CSI. The array gain decays with increasing signal-to-noise ratio and is slightly larger for spatially correlated systems. As the prediction error increases in the non-saturation region, the coding gain decreases and the diversity gain remains unaffected.     

Energy dispatch controllers for a photovoltaic system

In this paper two energy dispatch controllers for use in a grid-independent photovoltaic (PV) system are presented. The first, an optimal energy dispatch controller, is based on a class of Adaptive Critic Designs (ACDs) called Action Dependent Heuristic Dynamic Programming (ADHDP). This class of ACDs uses two neural networks to evolve an optimal control strategy over time. The first neural network or “Action” network dispenses the actual control signals while the second network or “Critic” network uses these control signals along with the system states to provide feedback to the action network, measuring performance using a utility function. This feedback loop allows the action network to improve behavior over time. The optimal energy dispatcher places emphasis on always meeting the critical load, followed by keeping the charge of the battery as high as possible so as to be able to power the critical load in cases of extended low output from the PV array, and lastly to power the non-critical load in so far as to not interfere with the first two objectives. The second energy dispatch controller is a smart energy dispatch controller and is built using knowledge from an expert, codified into a series of static rules. This smart energy dispatch controller is called the “PV-priority 2” controller. These energy dispatchers are compared with a static scheme called the “PV-priority 1”. The PV-priority 1 controller represents the standard control strategy. Results show that the ADHDP-based optimal energy dispatcher (or controller) outperforms the standard PV-priority 1 energy dispatcher in meeting the stated objectives, but trails the PV-priority 2 energy dispatcher. However, the major advantage of the ADHDP controller is that no expert is required for designing the controller, whereas for a rule-based controller such as the PV-priority 2 controller, an expert is always required.     

Intelligent unit commitment with vehicle-to-grid —A cost-emission optimization

A gridable vehicle (GV) can be used as a small portable power plant (S3P) to enhance the security and reliability of utility grids. Vehicle-to-grid (V2G) technology has drawn great interest in the recent years and its success depends on intelligent scheduling of GVs or S3Ps in constrained parking lots. V2G can reduce dependencies on small expensive units in existing power systems, resulting in reduced operation cost and emissions. It can also increase reserve and reliability of existing power systems. Intelligent unit commitment (UC) with V2G for cost and emission optimization in power system is presented in this paper. As number of gridable vehicles in V2G is much higher than small units of existing systems, UC with V2G is more complex than basic UC for only thermal units. Particle swarm optimization (PSO) is proposed to balance between cost and emission reductions for UC with V2G. PSO can reliably and accurately solve this complex constrained optimization problem easily and quickly. In the proposed solution model, binary PSO optimizes on/off states of power generating units easily. Vehicles are presented by integer numbers instead of zeros and ones to reduce the dimension of the problem. Balanced hybrid PSO optimizes the number of gridable vehicles of V2G in the constrained parking lots. Balanced PSO provides a balance between local and global searching abilities, and finds a balance in reducing both operation cost and emission. Results show a considerable amount of cost and emission reduction with intelligent UC with V2G. Finally, the practicality of UC with V2G is discussed for real-world applications.