Hybrid online model based multi seasonal decompose for short-term electricity load forecasting using ARIMA and online RNN

Short-term electricity load forecasting (STLF) plays a key role in operating the power system of a nation. A challenging problem in STLF is to deal with real-time data. This paper aims to address the problem using a hybrid online model. Online learning methods are becoming essential in STLF because load data often show complex seasonality (daily, weekly, annual) and changing patterns. Online models such as Online AutoRegressive Integrated Moving Average (Online ARIMA) and Online Recurrent neural network (Online RNN) can modify their parameters on the fly to adapt to the changes of real-time data. However, Online RNN alone cannot handle seasonality directly and ARIMA can only handle a single seasonal pattern (Seasonal ARIMA). In this study, we propose a hybrid online model that combines Online ARIMA, Online RNN, and Multi-seasonal decomposition to forecast real-time time series with multiple seasonal patterns. First, we decompose the original time series into three components: trend, seasonality, and residual. The seasonal patterns are modeled using Fourier series. This approach is flexible, allowing us to incorporate multiple periods. For trend and residual components, we employ Online ARIMA and Online RNN respectively to obtain the predictions. We use hourly load data of Vietnam and daily load data of Australia as case studies to verify our proposed model. The experimental results show that our model has better performance than single online models. The proposed model is robust and can be applied in many other fields with real-time time series.

Marginally Stable Triangular Recurrent Neural Network Architecture for Time Series Prediction

This paper introduces a discrete-time recurrent neural network architecture using triangular feedback weight matrices that allows a simplified approach to ensuring network and training stability. The triangular structure of the weight matrices is exploited to readily ensure that the eigenvalues of the feedback weight matrix represented by the block diagonal elements lie on the unit circle in the complex z-plane by updating these weights based on the differential of the angular error variable. Such placement of the eigenvalues together with the extended close interaction between state variables facilitated by the nondiagonal triangular elements, enhances the learning ability of the proposed architecture. Simulation results show that the proposed architecture is highly effective in time-series prediction tasks associated with nonlinear and chaotic dynamic systems with underlying oscillatory modes. This modular architecture with dual upper and lower triangular feedback weight matrices mimics fully recurrent network architectures, while maintaining learning stability with a simplified training process. While training, the block-diagonal weights (hence the eigenvalues) of the dual triangular matrices are constrained to the same values during weight updates aimed at minimizing the possibility of overfitting. The dual triangular architecture also exploits the benefit of parsing the input and selectively applying the parsed inputs to the two subnetworks to facilitate enhanced learning performance.

Exponential stabilization of delayed recurrent neural networks: A state estimation based approach

This paper is concerned with the stabilization problem of delayed recurrent neural networks. As the states of neurons are usually difficult to be fully measured, a state estimation based approach is presented. First, a sufficient condition is derived such that the augmented system under consideration is globally exponentially stable. Then, by employing a decoupling technique, the gain matrices of the controller and state estimator are achieved by solving some linear matrix inequalities. Finally, a delayed neural network with chaotic behaviors is exploited to demonstrate the applicability of the developed result.

An adaptive recurrent-neural-network motion controller for X-Y table in CNC machine

In this paper, an adaptive recurrent-neural-network (ARNN) motion control system for a biaxial motion mechanism driven by two field-oriented control permanent magnet synchronous motors (PMSMs) in the computer numerical control (CNC) machine is proposed. In the proposed ARNN control system, a RNN with accurate approximation capability is employed to approximate an unknown dynamic function, and the adaptive learning algorithms that can learn the parameters of the RNN on line are derived using Lyapunov stability theorem. Moreover, a robust controller is proposed to confront the uncertainties including approximation error, optimal parameter vectors, higher-order terms in Taylor series, external disturbances, cross-coupled interference and friction torque of the system. To relax the requirement for the value of lumped uncertainty in the robust controller, an adaptive lumped uncertainty estimation law is investigated. Using the proposed control, the position tracking performance is substantially improved and the robustness to uncertainties including cross-coupled interference and friction torque can be obtained as well. Finally, some experimental results of the tracking of various reference contours demonstrate the validity of the proposed design for practical applications.

A stable learning algorithm for block-diagonal recurrent neural networks: application to the analysis of lung sounds

A novel learning algorithm, the Recurrent Neural Network Constrained Optimization Method (RENNCOM) is suggested in this paper, for training block-diagonal recurrent neural networks. The training task is formulated as a constrained optimization problem, whose objective is twofold: (1) minimization of an error measure, leading to successful approximation of the input/output mapping and (2) optimization of an additional functional, the payoff function, which aims at ensuring network stability throughout the learning process. Having assured the network and training stability conditions, the payoff function is switched to an alternative form with the scope to accelerate learning. Simulation results on a benchmark identification problem demonstrate that, compared to other learning schemes with stabilizing attributes, the RENNCOM algorithm has enhanced qualities, including, improved speed of convergence, accuracy and robustness. The proposed algorithm is also applied to the problem of the analysis of lung sounds. Particularly, a filter based on block-diagonal recurrent neural networks is developed, trained with the RENNCOM method. Extensive experimental results are given and performance comparisons with a series of other models are conducted, underlining the effectiveness of the proposed filter.

Recurrent fuzzy neural network control for piezoelectric ceramic linear ultrasonic motor drive

In this study, a recurrent fuzzy neural network (RFNN) controller is proposed to control a piezoelectric ceramic linear ultrasonic motor (LUSM) drive system to track periodic reference trajectories with robust control performance. First, the structure and operating principle of the LUSM are described in detail. Second, because the dynamic characteristics of the LUSM are nonlinear and the precise dynamic model is difficult to obtain, a RFNN is proposed to control the position of the moving table of the LUSM to achieve high precision position control with robustness. The back propagation algorithm is used to train the RFNN on-line. Moreover, to guarantee the convergence of tracking error for periodic commands tracking, analytical methods based on a discrete-type Lyapunov function are proposed to determine the varied learning rates of the RFNN. Then, the RFNN is implemented in a PC-based computer control system, and the LUSM is driven by a unipolar switching full bridge voltage source inverter using LC resonant technique. Finally, the effectiveness of the RFNN-controlled LUSM drive system is demonstrated by some experimental results. Accurate tracking response and superior dynamic performance can be obtained because of the powerful on-line learning capability of the RFNN controller. Furthermore, the RFNN control system is robust with regard to parameter variations and external disturbances.

Recurrent neural network control for LCC-resonant ultrasonic motor drive

A newly designed driving circuit for the traveling wave-type ultrasonic motor (USM), which consists of a push-pull DC-DC power converter and a two-phase voltage source inverter using one inductance and two capacitances (LCC) resonant technique, is presented in this study. Moreover, because the dynamic characteristics of the USM are difficult to obtain and the motor parameters are time varying, a recurrent neural network (RNN) controller is proposed to control the USM drive system. In the proposed controller, the dynamic backpropagation algorithm is adopted to train the RNN on-line using the proposed delta adaptation law. Furthermore, to guarantee the convergence of tracking error, analytical methods based on a discrete-type Lyapunov function are proposed to determine the varied learning rates for the training of the RNN. Finally, the effectiveness of the RNN-controlled USM drive system is demonstrated by some experimental results.