Dingguo Chen

Neural-network-based load modeling and its use in voltage stability analysis

Voltage stability analysis is very important for predicting potential voltage instability. Load modeling plays a key role in voltage stability assessment. In the literature, most available approaches to the voltage stability problem are either static or quasistatic, which do not take load dynamics into account. First, this paper presents a survey of those approaches, makes a comparison between them, and points out the possible consequences of not considering load dynamics, which at worst can be a complete voltage collapse. Based on this observation, modeling of load dynamics is considered in this paper, and neural networks including recurrent neural networks are applied for load modeling. Furthermore, this paper presents the strategies for the first time to incorporate the neural-network-based load model into static and dynamic voltage stability analysis. The computation of the relevant sensitivity is carried out for the neural-network-based load model, and the results are used in the popular modal analysis. The proposed methods are tested on both the IEEE 14-bus system and real data.

Synthesis of neural controller applied to flexible AC transmission systems

This paper first addresses the power system stability issue involving the regular generator-angle transient stability and load-driven voltage instability. Transient stabilization of simplified power systems equipped with the flexible AC transmission system (FACTS) device, the thyristor-controlled series capacitor (TCSC), is studied with consideration of unknown loads. With some off-line time-optimal trajectories computed based on the switching-times-variation method (STVM), some techniques are developed to synthesize robust near-time-optimal neural controllers. The theoretical support for these techniques is presented. The simulations illustrate the performance of the synthesized neural controllers. Furthermore, the results developed can be readily generalized to more general nonlinear systems.

On near optimal neural control of multiple-input nonlinear systems

It has been a common consensus that general techniques for stabilization of nonlinear systems are available only for some special classes of nonlinear systems. Control design for nonlinear systems with uncertain components is usually carried out on a per system basis, especially when physical control constraints, and certain control performance measures such as optimum time control are imposed. Elegant adaptive control techniques are difficult to apply to this type of problems. A new neural network based control design is proposed and presented in this paper to deal with a special class of uncertain nonlinear systems with multiple inputs. The desired system dynamics are analyzed and utilized in the process of the proposed intelligent control design. The theoretical results are provided to justify the design procedures. The simulation study is conducted on a second-order bilinear system with two inputs and uncertainties on its parameters. The simulation results indicate that the proposed design approach is effective.

Hierarchical fuzzy neural networks toward a unified load dynamics modeling framework

Modeling of both static and dynamic load characteristics has been studied in the context of voltage stability analysis incorporating load models. With the consideration that load models, or more precisely, load prediction models, can be used to predict the load shapes for the future from a few hours up to several days, and motivated by the fact that the various load models for different application purposes can be accommodated in a general mathematical form, this paper is intended for providing a unified framework to accommodate various applications that make use of load models whether they are represented in a mathematical form suitable for load dynamics modeling used in regular power system stability analysis, or used in voltage stability analysis, or used for forecasting purposes. The study is conducted in conjunction with the application of hierarchical fuzzy neural networks. It is shown that modeling of load dynamics can be formulated in such a way that hierarchical fuzzy neural networks become naturally and logically applicable. A few theoretical results on hierarchical fuzzy neural networks for load modeling are presented. Furthermore, a study case is presented to illustrate how hierarchical fuzzy neural networks can be applied and how they perform, which demonstrates the effectiveness of the proposed unified framework for modeling of load dynamics

Neural Control Toward a Unified Intelligent Control Design Framework for Nonlinear Systems

There have been significant progresses reported in nonlinear adaptive control in the last two decades or so, partially because of the introduction of neural networks (Polycarpou, 1996; Chen & Liu, 1994; Lewis, Yesidirek & Liu, 1995; Sanner & Slotine, 1992; Levin & Narendra, 1993; Chen & Yang, 2005). The adaptive control schemes reported intend to design adaptive neural controllers so that the designed controllers can help achieve the stability of the resulting systems in case of uncertainties and/or unmodeled system dynamics. It is a typical assumption that no restriction is imposed on the magnitude of the control signal. Accompanied with the adaptive control design is usually a reference model which is assumed to exist, and a parameter estimator. The parameters can be estimated within a predesignated bound with appropriate parameter projection. It is noteworthy that these design approaches are not applicable for many practical systems where there is a restriction on the control magnitude, or a reference model is not available. On the other hand, the economics performance index is another important objective for controller design for many practical control systems. Typical performance indexes include, for instance, minimum time and minimum fuel. The optimal control theory developed a few decades ago is applicable to those systems when the system model in question along with a performance index is available and no uncertainties are involved. It is obvious that these optimal control design approaches are not applicable for many practical systems where these systems contain uncertain elements. Motivated by the fact that many practical systems are concerned with both system stability and system economics, and encouraged by the promising images presented by theoretical advances in neural networks (Haykin, 2001; Hopfield & Tank, 1985) and numerous application results (Nagata, Sekiguchi & Asakawa, 1990; Methaprayoon, Lee, Rasmiddatta, Liao & Ross, 2007; Pandit, Srivastava & Sharma, 2003; Zhou, Chellappa, Vaid & Jenkins, 1998; Chen & York, 2008; Irwin, Warwick & Hunt, 1995; Kawato, Uno & Suzuki, 1988; Liang 1999; Chen & Mohler, 1997; Chen & Mohler, 2003; Chen, Mohler & Chen, 1999), this chapter aims at developing an

NN-Based Near Real Time Load Prediction for Optimal Generation Control

In the environment of ongoing deregulated power industry, traditional automatic generation control (AGC) has become a set of ancillary services traded in separate markets which are different than the energy market. The performance of AGC is mandated to meet the NERC control performance standards (CPS). The new CPS criteria allow the over-compliant power utilities to loosen control of their generating units. The competition introduced by the deregulation process provides the opportunities for the over-compliant power utilities to sell their excess regulating capabilities. In addition, load following service is often priced lower than regulation service. All these lead generation companies to optimizing the portfolio of their generating assets to achieve better economy. The optimization process involves economic allocation of generation over a consecutive set of time intervals, which requires the load profile to be predicted for the dispatch period of minute level. This paper addresses the importance of very short term load prediction in this context, and proposes a new approach to make load predictions. Procedures involved in this approach are presented. Case studies are presented to demonstrate the effectiveness of the proposed approach.

Neural Control of Uncertain Nonlinear Systems with Minimum Control Effort

A special class of nonlinear systems are studied in this paper in the context of fuel optimal control, which feature parametric uncertainties and confined control inputs. The control objective is to minimize the integrated control cost over the applicable time horizon. The conventional adaptive control schemes are difficult to apply. An innovative design approach is proposed to handle the uncertain parameters, physical limitations of control variables and fuel optimal control performance simultaneously. The proposed control design methodology makes an analysis of the fuel control problem for nominal cases, employs a hierarchical neural network structure, constructs the lower level neural networks to identify the switching manifolds, and utilizes the upper level neural network to coordinate the outputs of the lower level neural networks to achieve the control robustness in an approximately fuel-optimal control manner. Theoretical results are presented to justify the proposed design procedures for synthesizing adaptive, intelligent hierarchical neural controllers for uncertain nonlinear systems.

Neural Control Applied to Time Varying Uncertain Nonlinear Systems

This paper presents a neural network based control design to handle the stabilization of a class of multiple input nonlinear systems with time varying uncertain parameters while assuming that the range of each individual uncertain parameter is known. The proposed design approach allows incorporation of complex control performance measures and physical control constraints whereas the traditional adaptive control techniques are generally not applicable. The desired system dynamics are analyzed, and a collection of system dynamics data, that represents the desired system behavior and approximately covers the region of stability interest, is generated and used in the construction of the neural controller based on the proposed neural control design. Furthermore, the theoretical aspects of the proposed neural controller are also studied, which provides insightful justification of the proposed neural control design. The simulation study is conducted on a single-machine infinity-bus (SMIB) system with time varying uncertainties on its parameters. The simulation results indicate that the proposed design approach is effective.

Synthesis of hierarchical neural controller for nonlinear systems

The theoretical study on synthesis of hierarchical neural controllers for nonlinear systems affine in control is presented. We first show that performance criteria based optimal neural controllers can be synthesized to approximately identify the switching manifold for control. We then show that the hierarchical neural controller can deal with system uncertainties in parameters which are fixed but unknown, and should perform reasonably well in theory. Further, the adaptive hierarchical neural controllers are developed to deal with systems uncertainties in parameters which are time varying, and it is shown that they are able to perform satisfactorily.