Short-Term Traffic Forecasting Using High-Resolution Traffic Data

Network dimensioning is a critical task in current mobile networks, as any failure in this process leads to degraded user experience or unnecessary upgrades of network resources. For this purpose, radio planning tools often predict monthly busy-hour data traffic to detect capacity bottlenecks in advance. Supervised Learning (SL) arises as a promising solution to improve predictions obtained with legacy approaches. Previous works have shown that deep learning outperforms classical time series analysis when predicting data traffic in cellular networks in the short term (seconds/minutes) and medium term (hours/days) from long historical data series. However, long-term forecasting (several months horizon) performed in radio planning tools relies on short and noisy time series, thus requiring a separate analysis. In this work, we present the first study comparing SL and time series analysis approaches to predict monthly busy-hour data traffic on a cell basis in a live LTE network. To this end, an extensive dataset is collected, comprising data traffic per cell for a whole country during 30 months. The considered methods include Random Forest, different Neural Networks, Support Vector Regression, Seasonal Auto Regressive Integrated Moving Average and Additive Holt–Winters. Results show that SL models outperform time series approaches, while reducing data storage capacity requirements. More importantly, unlike in short-term and medium-term traffic forecasting, non-deep SL approaches are competitive with deep learning while being more computationally efficient.

Download Full-text

Short-term forecast model of taxi demand based on time and space heterogeneity

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-210872 ◽

2021 ◽

pp. 1-12

Author(s):

Zhiyu Yan ◽

Shuang Lv

Keyword(s):

New York ◽

New York City ◽

York City ◽

Urban Traffic ◽

Percentage Error ◽

Density Level ◽

Traffic Data ◽

Short Term ◽

Time And Space ◽

Density Data

Accurate prediction of traffic flow is of great significance for alleviating urban traffic congestions. Most previous studies used historical traffic data, in which only one model or algorithm was adopted by the whole prediction space and the differences in various regions were ignored. In this context, based on time and space heterogeneity, a Classification and Regression Trees-K-Nearest Neighbor (CART-KNN) Hybrid Prediction model was proposed to predict short-term taxi demand. Firstly, a concentric partitioning method was applied to divide the test area into discrete small areas according to its boarding density level. Then the CART model was used to divide the dataset of each area according to its temporal characteristics, and KNN was established for each subset by using the corresponding boarding density data to estimate the parameters of the KNN model. Finally, the proposed method was tested on the New York City Taxi and Limousine Commission (TLC) data, and the traditional KNN model, backpropagation (BP) neural network, long-short term memory model (LSTM) were used to compare with the proposed CART-KNN model. The selected models were used to predict the demand for taxis in New York City, and the Kriging Interpolation was used to obtain all the regional predictions. From the results, it can be suggested that the proposed CART-KNN model performed better than other general models by showing smaller mean absolute percentage error (MAPE) and root mean square error (RMSE) value. The improvement of prediction accuracy of CART-KNN model is helpful to understand the regional demand pattern to partition the boarding density data from the time and space dimensions. The partition method can be extended into many models using traffic data.

Download Full-text

High Resolution Sequence Stratigraphic Frameworks Research in the XII Group of the Member III of Qing Shankou Formation in the Qian'an Oilfield

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.339.728 ◽

2013 ◽

Vol 339 ◽

pp. 728-731 ◽

Cited By ~ 2

Author(s):

Cun Lei Li ◽

Lei Qin ◽

Xue Li ◽

Xi Long Zhang

Keyword(s):

High Resolution ◽

Stratigraphic Correlation ◽

Short Term ◽

Middle Term ◽

Sequence Stratigraphic ◽

Base Level ◽

Mud Logging ◽

High Resolution Sequence Stratigraphy ◽

Symmetric Structures

With the instruction of the high resolution sequence stratigraphy and sedimentology theory, and the comprehensive application of 11 wells core, more than 800 mud logging and log data, high resolution sequence stratigraphic characteristics research in the XII Group of the Member III of Qing Shankou Formation in the Qianan oilfield has been finished. The results show that the study area can be divided into one middle-term base level cycle and five short-term base level cycles. The only sequence structure of middle term cycle is (B type) and the short term cycle mainly consists of B types meanwhile there are small mounts of upward deepening structures (A type) and symmetric structures (C type). Based on the classification of base-level cycles, fine stratigraphic correlation is conducted by using isochronous cycle correlations. In addition, 15 high resolution sequence stratigraphic frameworks are established which unify the study area and provide the solid geological basis for the sandstone distribution, the identification of mainly oil-bearing sand bodies and potential oil reservoirs.

Download Full-text

Joint Discussion 4 UV astronomy: stars from birth to death

Proceedings of the International Astronomical Union ◽

10.1017/s1743921307010083 ◽

2006 ◽

Vol 2 (14) ◽

pp. 169-194

Author(s):

Ana I. Gómez de Castro ◽

Martin A. Barstow

Keyword(s):

High Resolution ◽

Uv Spectroscopy ◽

Broad Band ◽

Mission Planning ◽

High Resolution Spectroscopy ◽

Low Resolution ◽

Short Term ◽

Uv Astronomy ◽

Optical Telescope ◽

The Moment

AbstractThe scientific program is presented as well a the abstracts of the contributions. An extended account is published in “The Ultraviolet Universe: stars from birth to death” (Ed. Gómez de Castro) published by the Editorial Complutense de Madrid (UCM), that can be accessed by electronic format through the website of the Network for UV Astronomy (www.ucm.es/info/nuva).There are five telescopes currently in orbit that have a UV capability of some description. At the moment, only FUSE provides any medium- to high-resolution spectroscopic capability. GALEX, the XMM UV-Optical Telescope (UVOT) and the Swift. UVOT mainly delivers broad-band imaging, but with some low-resolution spectroscopy using grisms. The primary UV spectroscopic capability of HST was lost when the Space Telescope Imaging Spectrograph failed in 2004, but UV imaging is still available with the HST-WFPC2 and HST-ACS instruments.With the expected limited lifetime of sl FUSE, UV spectroscopy will be effectively unavailable in the short-term future. Even if a servicing mission of HST does go ahead, to install COS and repair STIS, the availability of high-resolution spectroscopy well into the next decade will not have been addressed. Therefore, it is important to develop new missions to complement and follow on from the legacy of FUSE and HST, as well as the smaller imaging/low resolution spectroscopy facilities. This contribution presents an outline of the UV projects, some of which are already approved for flight, while others are still at the proposal/study stage of their development.This contribution outlines the main results from Joint Discussion 04 held during the IAU General Assembly in Prague, August 2006, concerning the rationale behind the needs of the astronomical community, in particular the stellar astrophysics community, for new UV instrumentation. Recent results from UV observations were presented and future science goals were laid out. These goals will lay the framework for future mission planning.

Download Full-text

Short-Term Traffic Forecasting using LSTM-based Deep Learning Models

10.1109/mercon52712.2021.9525670 ◽

2021 ◽

Author(s):

Dilantha Haputhanthri ◽

Adeesha Wijayasiri

Keyword(s):

Deep Learning ◽

Learning Models ◽

Short Term ◽

Traffic Forecasting

Download Full-text

Secure and Efficient Framework for High-Resolution, Short-Term Numerical Simulations of Weather Phenomena on Mobile Platforms

2015 20th International Conference on Control Systems and Computer Science ◽

10.1109/cscs.2015.120 ◽

2015 ◽

Author(s):

Adelina Vidovici ◽

Razvan Dobre ◽

Emil-Ioan Slusanschi ◽

Rodica Dumitrache

Keyword(s):

High Resolution ◽

Numerical Simulations ◽

Mobile Platforms ◽

Short Term

Download Full-text

Taxi Booking Mobile App Order Demand Prediction Based on Short-Term Traffic Forecasting

Transportation Research Record Journal of the Transportation Research Board ◽

10.3141/2634-10 ◽

2017 ◽

Vol 2634 (1) ◽

pp. 57-68 ◽

Cited By ~ 12

Author(s):

Yunxuan Li ◽

Jian Lu ◽

Lin Zhang ◽

Yi Zhao

Keyword(s):

High Frequency ◽

Demand Forecasting ◽

Low Frequency ◽

Original Data ◽

Mobile App ◽

Support Vector ◽

Short Term ◽

Traffic Demand ◽

Traffic Forecasting ◽

Demand Prediction

The Didi Dache app is China’s biggest taxi booking mobile app and is popular in cities. Unsurprisingly, short-term traffic demand forecasting is critical to enabling Didi Dache to maximize use by drivers and ensure that riders can always find a car whenever and wherever they may need a ride. In this paper, a short-term traffic demand forecasting model, Wave SVM, is proposed. It combines the complementary advantages of Daubechies5 wavelets analysis and least squares support vector machine (LS-SVM) models while it overcomes their respective shortcomings. This method includes four stages: in the first stage, original data are preprocessed; in the second stage, these data are decomposed into high-frequency and low-frequency series by wavelet; in the third stage, the prediction stage, the LS-SVM method is applied to train and predict the corresponding high-frequency and low-frequency series; in the last stage, the diverse predicted sequences are reconstructed by wavelet. The real taxi-hailing orders data are applied to evaluate the model’s performance and practicality, and the results are encouraging. The Wave SVM model, compared with the prediction error of state-of-the-art models, not only has the best prediction performance but also appears to be the most capable of capturing the nonstationary characteristics of the short-term traffic dynamic systems.

Download Full-text