Adaptive Time Series Model Research Articles

Identification of parameters of adaptive time series models

The work is devoted to the study of adaptive models of time series and the development of methods for their construction. The most problematic stage in the implementation of algorithms for time series forecasting methods is the identification of unknown parameters, on which the adequacy of the prediction depends. On the basis of economic data, a number of adaptive models have been studied: using exponential smoothing, Brown, Holt-Winters and Theil-Wage models, which take into account seasonality. It was found that the main difficulties arise in the selection of constant smoothing and the choice of coefficients, since no universal algorithm for their task exists.The paper proposes a method for integrating the adaptive method and the method of numerical optimization. As an optimization method, the non-gradient method was chosen - the Particle Swarm Optimization (PSO), the use of which provided less error in the final forecast and convergence in all applications. Algorithms for finding the parameters to be identified, and a predictive model based on real data are presented. It is shown that in some cases the proposed model has an advantage over other models of time series.

Адаптивные модели временных рядов в системах обработки измерительной информации

Адаптивные модели временных рядов в системах обработки измерительной информации

Optimal scheduling of a by-product gas supply system in the iron- and steel-making process under uncertainties

This paper addresses the real-time by-product gas scheduling in an integrated iron- and steel-making industry with uncertainty in by-product gas flows from a rolling horizon algorithm. Adaptive time-series models determined from real data performs forecast for each producer and consumer of by-product gases in main units of the steel-making plant. The individual consumptions of the blast furnace and coke oven gases are modelled using the seasonal Holt-Winters method with smoothing constants estimated via genetic algorithm, whereas the individual productions of the blast furnace and coke oven are identified from autoregressive and integrated moving-average. LDG gas production is forecasted using a heuristic method that leverages the operational information. The model’s parameters are updated periodically due to the nonlinearities present in the time series. After the forecasting phase, the algorithm performs short-term decisions using a MILP optimization model, that minimizes the imbalance between the random dynamics of by-product fuel generation and consumption and maximizes the energy efficiency. Through computational simulations, we show that the operational stability of gas holders and the electrical energy production increase, whereas the waste of gas in flare stack decreases, when the control horizon of the rolling horizon algorithm is reduced.

Statistical Modeling for Real Domestic Hot Water Consumption Forecasting

Abstract In this paper, we study the real domestic hot water (DHW) consumptions from single family houses equipped with solar hot water tank. We model it to understand and forecast the daily needs of inhabitants. Thus, the forecasts can be integrated in a control strategy to optimize the energy cost by heating only the necessary DHW volume. At first, we realize a data analysis from real uses of several dwellings to lay assumptions of the statistical model. This study highlights a weekly periodicity, random fluctuations and the different profiles of consumption following the residence, the season, and the day of the week. Otherwise, having no prior information like the location or the number of residents, we propose an adaptive time series model which does not require strong a priori and computational time. Then, we develop an ARMA model to forecast the daily DHW volume and we apply it on each individual installation. This model allows to take into account the periodicity of one week, the consumption of the previous days and random fluctuations. The results obtained on real data show that this approach is very promising.

Statistical gear health analysis which is robust to fluctuating loads and operating speeds

Condition-based maintenance is concerned with the collection and interpretation of data to support maintenance decisions. The non-intrusive nature of vibration data enables the monitoring of enclosed systems such as gearboxes. It remains a significant challenge to analyze vibration data that are generated under fluctuating operating conditions. This is especially true for situations where relatively little prior knowledge regarding the specific gearbox is available. It is therefore investigated how an adaptive time series model, which is based on Bayesian model selection, may be used to remove the non-fault related components in the structural response of a gear assembly to obtain a residual signal which is robust to fluctuating operating conditions. A statistical framework is subsequently proposed which may be used to interpret the structure of the residual signal in order to facilitate an intuitive understanding of the condition of the gear system. The proposed methodology is investigated on both simulated and experimental data from a single stage gearbox.

Inference for Adaptive Time Series Models: Stochastic Volatility and Conditionally Gaussian State Space Form

In this paper we replace the Gaussian errors in the standard Gaussian, linear state space model with stochastic volatility processes. This is called a GSSF-SV model. We show that conventional MCMC algorithms for this type of model are ineffective, but that this problem can be removed by reparameterising the model. We illustrate our results on an example from financial economics and one from the nonparametric regression model. We also develop an effective particle filter for this model which is useful to assess the fit of the model.

Inference for Adaptive Time Series Models: Stochastic Volatility and Conditionally Gaussian State Space Form

In this paper we model the Gaussian errors in the standard Gaussian linear state space model as stochastic volatility processes. We show that conventional MCMC algorithms for this class of models are ineffective, but that the problem can be alleviated by reparameterizing the model. Instead of sampling the unobserved variance series directly, we sample in the space of the disturbances, which proves to lower correlation in the sampler and thus increases the quality of the Markov chain. Using our reparameterized MCMC sampler, it is possible to estimate an unobserved factor model for exchange rates between a group of n countries. The underlying n + 1 country-specific currency strength factors and the n + 1 currency volatility factors can be extracted using the new methodology. With the factors, a more detailed image of the events around the 1992 EMS crisis is obtained. We assess the fit of competitive models on the panels of exchange rates with an effective particle filter and find that indeed the factor model is strongly preferred by the data.

Adaptive Forecast-Based Monitoring for Dynamic Systems

Several forecast-based monitoring methods have been developed for autocorrelated data. One effective method is to use the forecasts based on the exponentially weighted moving average (EWMA). However, during the transition period of dynamic systems, the forecast-based monitoring procedure becomes inadequate due to its use of constant time series model parameters. In this article we present an adaptive forecast-based monitoring approach that performs well on dynamic systems. We examine two competing procedures: the adaptive time series model and the adaptive EWMA. We use a plastic extrusion process with first-order dynamics to illustrate the application of these two procedures, and we also evaluate the performance of the two procedures via simulation.

A multi-perspective knowledge-based system for customer service management

Abstract The e-business arena is a dynamic, complex and demanding environment. It is essential to make optimal reuse of knowledge of customer services across various functional units of the enterprise. On the other hand, it is also important to ensure that the customer service staff can access and be trained up with dynamically updated knowledge that meets the changing business environment of an enterprise in customer services. However, conventional way of customer service management (CSM) is inadequate to achieve the multi-perspective of an enterprise for achieving knowledge acquisition, knowledge diffusion, business automation and business performance measurement so as to drive the continuous improvement of the customer service quality. In this paper, a multi-perspective knowledge-based system (MPKBS) is proposed for CSM. The MPKBS incorporates various artificial intelligence technologies such as case-based reasoning (CBR) and adaptive time-series model which are used for decision analysis, performance measurement and monitoring. A prototype customer service portal has been built based on the MPKBS and implemented successfully in a consultancy business.

Adaptive modeling and classification of the secondary settling tank

In biological wastewater treatment plants the biomass is separated from the treated wastewater in the secondary settler; thus, efficient operation of the secondary settler is crucial to achieving satisfactory effluent quality in the wastewater treatment process (WWTP). In the present work, system identification and soft-computing techniques were used to formulate a model for predicting the solid volume index (SVI) and classification of the sludge bulking phenomenon in the settler. An adaptive time series model was applied to predict the SVI of the secondary settler; this model uses the recursive least square (RLS) method to update the model parameters. The method for classifying the current state of the secondary settler is based on the strong correlation that was observed between the settler state and the values of the time series model parameters, which enabled the time series model parameters to be used as effective features for monitoring the secondary settler. To classify the current state of the secondary settler, a neural network (NN) was used to classify the adaptive time series model parameters, where a hybrid Genetic Algorithm (GA) was used to decide the number of hidden nodes of the NN classifier. Application of the proposed method to a full-scale WWTP demonstrated the utility of the method for simultaneously predicting the SVI value of the secondary settler and classifying the current state of the settler.