Short-term Traffic Flow Forecasting Using Dynamic Linear Models
نویسندگان
چکیده
Intelligent Transportation Systems (ITS) is an emerging concept which has been utilised to improve efficiency and sustainability of existing transportation systems. Short term traffic flow forecasting, the process of predicting future traffic conditions based on historical and realtime observations is an essential aspect of ITS. The existing well-known algorithms used for short-term traffic forecasting include time-series analysis based models. Among the timeseries models, the Seasonal Autoregressive Integrated Moving Average (SARIMA) is one of the most precise statistical models in this field. In the existing literature SARIMA models are mostly used in its multiplicative form and the parameters of the model are mostly estimated using a frequentist approach. Estimation of the large scale multiplicative SARIMA model for traffic flow forecasting often proves to be complex and computationally expensive for researchers and end-users. In this paper, an additive SARIMA model has been employed to predict traffic flow in shortterm or near-term future. The Dynamic Linear Model (DLM) representation of the additive SARIMA model has been used here to reduce the number of latent variables. Traditionally in a frequentist approach, point estimations of the SARIMA model parameters are obtained by maximizing the likelihood, but in this paper the marginal posterior density of each of the parameters has been explored by applying a Bayesian inference framework. Markov Chain Monte Carlo (MCMC) sampling method has been used to develop the Bayesian inference framework. For such sampling method for SARIMA, a problem of serial correlation has proved to be quite serious; however in the additive form, with the help of a carefully designed Metropolis-Hastings algorithm (a type of MCMC algorithm) this problem has been mitigated. The efficiency of the proposed prediction algorithm has been evaluated by modelling realtime traffic flow observations available from a certain junction in the city-centre of Dublin.
منابع مشابه
Analysis and Short-Term Forecasting of Highway Traffic Flow in Slovenia
Analysis and short-term forecasting of traffic flow data for several locations of the Slovenia highway network are presented. Daily and weekly seasonal components of the data are analysed and several features are extracted to support the forecasting. Various short-term forecasting models are developed for one hour ahead forecasting of the traffic flow. Models include benchmark models (random wa...
متن کاملForecasting multivariate road traffic flows using Bayesian dynamic graphical models, splines and other traffic variables
Traffic flow data are routinely collected for many networks worldwide. These invariably large data sets can be used as part of a traffic management system, for which good traffic flow forecasting models are crucial. The linear multiregression dynamic model (LMDM) has been shown to be promising for forecasting flows, accommodating multivariate flow time series, while being a computationally simp...
متن کاملIntervention and causality: forecasting traffic flows using a dynamic Bayesian network
Real-time traffic flow data across entire networks can be used in a traffic management system to monitor current traffic flows so that traffic can be directed and managed efficiently. Reliable short-term forecasting models of traffic flows are crucial for the success of any traffic management system. The model proposed in this paper for forecasting traffic flows is a multivariate Bayesian dynam...
متن کاملThe Open University ’ s repository of research publications and other research outputs Forecasting multivariate road traffic flows using Bayesian dynamic graphical models
Traffic flow data are routinely collected for many networks worldwide. These invariably large data sets can be used as part of a traffic management system, for which good traffic flow forecasting models are crucial. The linear multiregression dynamic model (LMDM) has been shown to be promising for forecasting flows, accommodating multivariate flow time series, while being a computationally simp...
متن کاملresearch publications and other research outputs Forecasting multivariate road traffic flows using Bayesian dynamic graphical models
Traffic flow data are routinely collected for many networks worldwide. These invariably large data sets can be used as part of a traffic management system, for which good traffic flow forecasting models are crucial. The linear multiregression dynamic model (LMDM) has been shown to be promising for forecasting flows, accommodating multivariate flow time series, while being a computationally simp...
متن کامل