• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.3.2021.tde-08112021-111440
Document
Author
Full name
Mariana Martins de Brito Sousa
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2021
Supervisor
Committee
Mota, Daniel de Oliveira (President)
Botter, Denise Aparecida
Marujo, Lino Guimarães
Title in Portuguese
Previsão espaço-temporal de entregas urbanas na etapa de last-mile utilizando o modelo STARMA.
Keywords in Portuguese
Análise de séries temporais
Demanda (Previsão)
Last-mile
Modelo STARMA
Veículos autônomos
Abstract in Portuguese
O nível de urbanização do mundo está aumentando nos últimos anos e consequentemente cresce o número de movimentos de carga e pessoas nos centros urbanos, desafiando ainda mais a infraestrutura de mobilidade das cidades, durante a etapa de last-mile. Uma alternativa importante em relação ao transporte convencional é a utilização de uma frota de veículos autônomos, que interfere positivamente na sustentabilidade, diminuindo o consumo de combustíveis e as emissões de carbono. A proposta desse trabalho é criar um modelo com a função de realizar a previsão da demanda espaço-temporal das viagens de Yellow Taxi, na cidade de Nova Iorque, com o intuito de reduzir a quantidade de taxis vazios nas ruas, economizando energia e diminuindo o congestionamento de veículos nos grandes centros urbanos. Para modelar o problema foi utilizado o modelo STARMA, de séries temporais, considerando a correlação espaço-temporal dos dados. Os resultados indicaram um erro percentual absoluto médio de aproximadamente 45% para as previsões, demonstrando que a correlação espacial exerce papel importante nos dados.
Title in English
Spatial-temporal forecast of urban deliveries in last-mile using the STARMA model.
Keywords in English
Autonomous vehicles
Forecast
Last-mile
STARMA model
Time series
Abstract in English
The level of urbanization in the world has been increasing in recent years and consequently the number of cargo movements and people in urban centers has grown, further challenging the mobility infrastructure of cities during the last-mile stage. An important alternative in relation to conventional transport is the use of a fleet of autonomous vehicles, which positively interferes with sustainability, reducing fuel consumption and carbon emissions. The purpose of this work is to create a model to forecast the space-time demand for Yellow Taxi trips in New York City, in order to reduce the amount of empty taxis on the streets, saving energy and decreasing the vehicle congestion in large urban centers. To model the problem, it will be used a STARMA model, of time series, considering the spatio-temporal correlation of the data. The results indicated a mean absolute percentage error of approximately 45% for the predictions, demonstrating that the spatial correlation plays an important role in the data.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2021-11-08
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.