Direct adaptive power system stabilizer design using fuzzy wavelet neural network with self-recurrent consequent part
Graphical abstract
Introduction
The nonlinear dynamics and the complex characteristics of a power system trigger low frequency oscillations when the power system is exposed to the disturbances. The power system stabilizer, a very efficient controller installed in the automatic voltage regulator of the generator, is extensively utilized for enhancing the stability of power systems. The parameters of conventional fixed structure PSS (CPSS) are determined based on a linearized model of the power system considering a single operating point. Factors such as the nonlinearity of the power system, changes in operating conditions or system topology, and deviations in system parameters all cause a degradation in the performance of the CPSS.
To address the abovementioned issues there is a need for a method to design a PSS that could demonstrate better performance compared to the conventional ones. Some methods in this field are adaptive control [1], [2], [3], [4], smart control [5], artificial intelligence [6], [7], robust control [8], [9], [10] and sliding mode control [11]. Among these, the methods based on adaptive control and robust control can be considered a good approach for the effects of uncertainty in the power system. In adaptive control, the controller's parameters are updated based on the identification of the plant parameters, while in robust control, a worst-case design scenario for the plant families is considered, which corresponds to the different uncertainties in the system.
Wavelet functions have recently attracted much attention in various engineering areas [12], [13], [14], [15], [16], [17]. Based on wavelet theory, any signal or function can be closely approximated by a finite sum of the weighted wavelet functions. Wavelet neural networks (WNNs), which incorporate wavelet functions into a neural network, have been proposed by Zhang and Benveniste [18], and used for identifying and controlling nonlinear systems [19], [20], [21]. The activation functions such as sigmoid and Gaussian functions which have non-local properties in time are swapped with the wavelet functions in the hidden layers of neurons in the WNN. The output of a WNN is localized in both the time and frequency domains, thus providing the time-frequency localization properties of the input signal. This means that the WNN is a local network. Therefore, in on-line training and corresponding to any given point of the input space, a small subset of the network parameters is active and can thus be updated. This means that the generalization ability of the WNN can be maintained while its flexibility is high, and its training can be performed in speeds higher than that of a non-local network. Furthermore, local minima can be eliminated in the WNN. The WNN, however, has a shortcoming too [22]: it has a feed-forward structure. To solve this problem, the self-recurrent wavelet neural network (SRWNN) has been proposed [22]. Due to having a mother wavelet layer with self-feedback wavelets, the SRWNN is able to record the previous data of the network, adapting very fast to sudden changes in configuration or conditions of the controlled plant.
A fuzzy wavelet neural network (FWNN) combines wavelet neural networks (WNN) with a Takagi-Sugeno-Kang (TSK) fuzzy model in order to enhance the function approximation accuracy, as well as the generalization ability in very complex processes. Several previous works have discussed the synthesis of an FWNN to solve such problems as forecasting, function approximation, fault diagnosis, system identification, and control problems [23], [24], [25], [26]. In [23], fault diagnosis for power transformers is discussed using a rough set (RS) and fuzzy wavelet neural network, integrated with a least square weighted fusion algorithm. A gradient-based update rule is employed to update all parameters of the FWNN in on-line mode, while an ALRs algorithm is also proposed to guarantees the convergence of the adaptive process in [24]. The constructed network is used for identification and control of dynamic plants. In [25], using a combination of TSK fuzzy models with wavelet transform and ROLS learning algorithm, a fuzzy wavelet network is proposed with the aim of approximating arbitrary nonlinear functions. A fuzzy wavelet neural network (FWNN) approach is introduced for forecasting long-term electricity consumption in a high energy consuming city, while the rate of training is raised compared with the prediction model based on the artificial neural network in [26].
In this paper, a stable fuzzy wavelet neural-based adaptive power system stabilizer (SFWNAPSS) is proposed for stabilizing the inter-area oscillations in a multi-machine power system. Considering the advantages of SRWNN, in our proposed approach we employ it as several distinct sub-networks to construct a flexible self-recurrent wavelet- based consequent part. By applying an efficient genetic algorithm, the optimal values of the proposed SFWNAPSS parameters are obtained. A back-propagation algorithm with LALRs is proposed in order to update all parameters of the consequent part of each fuzzy rule in on-line operation. Kundur's four-machine two-area benchmark power system and six-machine three-area power system are used with an aim of assessing the effectiveness of the proposed stabilizer. Studies demonstrate promising results and show that the inter-area oscillations are successfully damped by the SFWNAPSS. In brief, the main contributions of the paper are summarized as follows:
- a.
The main disadvantage of FWNN is that the application domain is limited to static problems due to its feed-forward network structure. Therefore, we propose to use a self-recurrent wavelet neural network (SRWNN) in the consequent part of FWNN, solving the control problem for chaotic systems.
- b.
Our proposed structure requires fewer wavelet nodes than the networks with feed-forward structure, due to the dynamic behavior of the recurrent network.
- c.
Finding the optimal learning rates is a challenging task in the classic gradient-based learning algorithms. Hence, in our proposed framework, all of the learning rates are determined optimally based on Lyapunov stability theory.
- d.
We develop a controller based on the proposed network structure and use it for damping the oscillations in the multi-machine power system.
The brief outline of this paper is as follows: a brief background of SRWNN structure is presented in Section 2; Section 3 describes the architecture of the proposed FWNN with self-recurrent consequent part; the design procedure of a stable fuzzy wavelet neural-based adaptive PSS is discussed in Section 4; in Section 5, a comprehensive stability study is provided; the initialization of the proposed stabilizer by GA is presented in Section 6; design validation and simulation results are provided in Section 7; finally, the conclusions are presented in Section 8.
Section snippets
The SRWNN structure
A detailed structure of SRWNN with Nin inputs, one output and Nin × Nw mother wavelets is illustrated in Fig. 1. Network inputs are directly passed to the second layer, i.e., mother wavelet layer 3. Note that different choices of wavelet prototypes are possible for use as the elementary building blocks when constructing wavelet neural network models. Some choices can be effectively employed for some problems and other choices for others; there is no systematic approach. However, in practice,
FWNN with self-recurrent consequent part
The FWNN model is a feed-forward multi-layer network which integrates a traditional Takagi-Sugeno-Kang (TSK) fuzzy model with wavelet neural networks. The TSK-type systems [28], [29], [30], due to having a constant or a linear equation-based consequent part with a certain number of rules, cannot provide a complete mapping of high-order non-linear dynamical plants with an admissible accuracy level, because the TSK system cannot model the local properties of the plant with a limited number of
Stable fuzzy wavelet neural-based adaptive PSS (SFWNAPSS) design
In this section, the proposed FWNN with self-recurrent THEN-part is used to design a stable fuzzy wavelet neural-based adaptive PSS (SFWNAPSS) for power system stabilization, based on direct adaptive control theory. The parameters of the consequent part in the fuzzy rules are chosen to be adapted in real-time operation, while the antecedent part's parameters are constant throughout the process. The detailed structure of the proposed SFWNAPSS is illustrated in Fig. 3.
The main control object is
A comprehensive stability study
In a BP-based learning algorithm, when a small value is chosen for the learning rate, it leads to the lower speed of convergence. However, a large value of the learning rate leads to a non-stable learning procedure, too. In this section, we introduce a Lyapunov-based adaptive learning rate (LALR) algorithm which can effectively be used firstly to increase the learning speed of the control system, and secondly to guarantee the convergence of the proposed approach.
The control performance index
Initialization of the proposed stabilizer by GA
As we know, the convergence rate of BP depends on the choice of the initial values of the unknown parameters to be optimized; thus, a GA-based approach is proposed for stabilizer initialization in this section. Although the binary representation has been frequently applied to optimization problems, in the present paper, we use the real-valued representation scheme for the solution. The application of real-valued representation in the GA is claimed by [33] to offer some advantages in numerical
Design validation and Simulation results
In order to investigate the effectiveness of the proposed SFWNAPSS stabilizer, and tuning its parameters in the way presented in this paper, simulation studies based on two different models of multi-machine power system are performed. The first model is a four-machine two-area system, which is used as a benchmark problem in the literature [34]. The second model is a six-machine three-area system which is an expansion of a two-area benchmark system taken from [35].
Conclusions
In this paper, a new stable fuzzy wavelet neural-based adaptive power system stabilizer (SFWNAPSS) for damping low frequency oscillations in a multi-machine power system is proposed. Design of this controller is based on a TSK fuzzy model so that the consequent parts of fuzzy rules are constructed using a self-recurrent wavelet neural network (SRWNN). The usage of the SRWNN enables the controller to cope with the complex nonlinear system by capturing the dynamic response of the system. An
References (37)
- et al.
Adaptive robust PSS to enhance stabilization of interconnected power systems with high renewable energy penetration
Renew. Energy
(2014) - et al.
Simulation based neuro-fuzzy hybrid intelligent PI control approach in four-area load frequency control of interconnected power system
Appl. Soft Comput.
(2014) - et al.
Design of power system stabilizers using two level fuzzy and adaptive neuro-fuzzy inference systems
Int. J. Electr. Power Energy Syst.
(2012) - et al.
Smart control techniques for design of TCSC and PSS for stability enhancement of dynamical power system
Appl. Soft Comput.
(2014) - et al.
Optimal tunning of type-2 fuzzy logic power system stabilizer based on differential evolution algorithm
Int. J. Electr. Power Energy Syst.
(2014) - et al.
Robust fuzzy logic power system stabilizer based on evolution and learning
Int. J. Electr. Power Energy Syst.
(2013) - et al.
Robust control of electrical power systems using PSSs and Bilinear Matrix Inequalities
Int. J. Electr. Power Energy Syst.
(2014) - et al.
Robust decentralized multi-machine power system stabilizer design using quantitative feedback theory
Int. J. Electr. Power Energy Syst.
(2012) - et al.
Robust adaptive control for a single-machine infinite-bus power system with an SVC
Control Eng. Practice
(2014) - et al.
Enhanced design of an indirect adaptive fuzzy sliding mode power system stabilizer for multi-machine power systems
Int. J. Electr. Power Energy Syst.
(2014)
Evolving spiking wavelet-neuro-fuzzy self-learning system
Appl. Soft Comput.
Identification of synchronous generators using adaptive wavelet networks
Int. J. Electr. Power Energy Syst.
The multidimensional function approximation based on constructive wavelet RBF neural network
Appl. Soft Comput
Generalized neural network and wavelet transform based approach for fault location estimation of a transmission line
Appl. Soft Comput.
Wavelet based Neuro-Detector for low frequencies of vibration signals in electric motors
Appl. Soft Comput.
On the detection of card-sharing traffic through wavelet analysis and Support Vector Machines
Appl. Soft Comput.
A self-evolving functional-linked wavelet neural network for control applications
Appl. Soft Comput.
Rough set and fuzzy wavelet neural network integrated with least square weighted fusion algorithm based fault diagnosis research for power transformers
Electr. Power Syst. Res.
Cited by (38)
A minimal architecture neuro adaptive predictive control scheme for power system stabilizer
2022, International Journal of Electrical Power and Energy SystemsFuzzy Elman Wavelet Network: Applications to function approximation, system identification, and power system control
2022, Information SciencesCitation Excerpt :Since FWNNs combines the advantages of WNNs and TSK fuzzy models, they have become a popular tool for function approximation, dynamic system identification, and nonlinear system control. In [25,26], a new FWNN was developed. In the antecedent and THEN-parts of the proposed FWNN, a type-1 fuzzy system and several SRWNNs are used.
A robust power system stabilizer for enhancement of stability in power system using adaptive fuzzy sliding mode control
2018, Applied Soft Computing JournalNonlinear system modeling using a self-organizing recurrent radial basis function neural network
2018, Applied Soft Computing JournalCitation Excerpt :Recurrent neural networks (RNNs) are artificial neural networks with feedback connections and have the capability to model spatial as well as temporal dependencies between input and output sequences [1–3].