scholarly journals Rebalancing Autonomous Vehicles using Deep Reinforcement Learning

2022 ◽  
Vol 16 ◽  
pp. 646-652
Author(s):  
Jiajie Dai ◽  
Qianyu Zhu ◽  
Nan Jiang ◽  
Wuyang Wang
Keyword(s):  
Reinforcement Learning ◽  
Autonomous Vehicles ◽  
Supply And Demand ◽  
Efficient Operation ◽  
Demand And Supply ◽  
On Demand ◽  
Demand Information ◽  
Autonomous Mobility ◽  
Demand Patterns

The shared autonomous mobility-on-demand (AMoD) system is a promising business model in the coming future which provides a more efficient and affordable urban travel mode. However, to maintain the efficient operation of AMoD and address the demand and supply mismatching, a good rebalancing strategy is required. This paper proposes a reinforcement learning-based rebalancing strategy to minimize passengers’ waiting in a shared AMoD system. The state is defined as the nearby supply and demand information of a vehicle. The action is defined as moving to a nearby area with eight different directions or staying idle. A 4.6 4.4 km2 region in Cambridge, Massachusetts, is used as the case study. We trained and tested the rebalancing strategy in two different demand patterns: random and first-mile. Results show the proposed method can reduce passenger’s waiting time by 7% for random demand patterns and 10% for first-mile demand patterns.

scholarly journals Deep Reinforcement Learning based Charging Pricing for Autonomous Mobility-on-Demand System

2021 ◽  
pp. 1-1
Author(s):  
Ying Lu ◽  
Yanchang Liang ◽  
Zhaohao Ding ◽  
Qiuwei Wu ◽  
Tao Ding ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Demand System ◽  
On Demand ◽  
Autonomous Mobility

ANALISIS PERMINTAAN DAN PENAWARAN BERAS DI PROPINSI JAMBI

2012 ◽  
Vol 15 (2) ◽  
Author(s):  
. Edison ◽  
Pera Nurfathiyah
Keyword(s):  
Time Series Data ◽  
Supply And Demand ◽  
Research Result ◽  
Primary Data ◽  
Series Data ◽  
Demand And Supply ◽  
On Demand ◽  
Rice Price ◽  
Production Growth ◽  
Per Capita

The rice production growth that was gotten by Jambi Province with production growth rate of 0,54% can not fully contribute society need that was continuously increasing. Therefore, it can cause unbalance between supply and demand. The objective of research is to know the picture of rice supply and demand and influenced variables on rice supply and demand in Jambi. The simultan model was used to predict factors that influenced rice supply and demand. The research was conducted in Jambi Province on September to December 2009. The primary data needed in this research was time series data from 1996 – 2008. The research result showed that simultaneously rice price factor, the number population and income per capita was significant on demand. And also factor of average rice price, Bangkok rice price, import rice price, hybrid seed, acreage, season, and time trend were influencing significantly on supply. From elasticity value was fortunately all variables that was influencing rice demand and supply in Jambi Province was inelastic. Kata Kunci : rice demand and supply, rice price, elasticit

A Learning-Based Optimization Approach for Autonomous Ridesharing Platforms with Service-Level Contracts and On-Demand Hiring of Idle Vehicles

2021 ◽  
Author(s):  
Breno A. Beirigo ◽  
Frederik Schulte ◽  
Rudy R. Negenborn
Keyword(s):  
New York ◽  
Autonomous Vehicles ◽  
Transportation Network ◽  
Supply And Demand ◽  
Service Level ◽  
Third Party ◽  
Optimization Approach ◽  
Marginal Value ◽  
On Demand ◽  
Demand Fluctuations

Current mobility services cannot compete on equal terms with self-owned mobility products concerning service quality. Because of supply and demand imbalances, ridesharing users invariably experience delays, price surges, and rejections. Traditional approaches often fail to respond to demand fluctuations adequately because service levels are, to some extent, bounded by fleet size. With the emergence of autonomous vehicles, however, the characteristics of mobility services change and new opportunities to overcome the prevailing limitations arise. In this paper, we consider an autonomous ridesharing problem in which idle vehicles are hired on-demand in order to meet the service-level requirements of a heterogeneous user base. In the face of uncertain demand and idle vehicle supply, we propose a learning-based optimization approach that uses the dual variables of the underlying assignment problem to iteratively approximate the marginal value of vehicles at each time and location under different availability settings. These approximations are used in the objective function of the optimization problem to dispatch, rebalance, and occasionally hire idle third-party vehicles in a high-resolution transportation network of Manhattan, New York City. The results show that the proposed policy outperforms a reactive optimization approach in a variety of vehicle availability scenarios while hiring fewer vehicles. Moreover, we demonstrate that mobility services can offer strict service-level contracts to different user groups featuring both delay and rejection penalties.

An EOQ Model for Reuse and Recycling Considering the Balance of Supply and Demand

2015 ◽  
Vol 9 (3) ◽  
pp. 303-311 ◽  
Author(s):  
Tomomi Nonaka ◽  
◽  
Nobutada Fujii ◽  
Keyword(s):  
Inventory Management ◽  
Reverse Logistics ◽  
Supply And Demand ◽  
Computer Experiments ◽  
Demand And Supply ◽  
Product Demand ◽  
Eoq Model ◽  
Proposed Model ◽  
Using Data

Inventory management in reverse logistics is more complex than that in conventional logistics because of uncontrollable factors such as inventory levels increasing from reverse logistics, greater-than-expected disposal, and balance of supply and demand with changing market trends. This paper proposes a new economic order quantity (EOQ) model for reuse and recycling by expanding the EOQ model proposed by Dobos and Richter, 2004. The proposed model introduces a sequentially accumulated marginal reuse rate as a parameter in considering the balance of product demand and supply. The marginal reuse rate is calculated by using data on production distribution and disposal distribution of products for every discretized period. This model considers the sequence among recovery options: reuse, recycle and disposal. Parts are reused after having been inspected to determine whether they are reusable or not. Remaining nonreusable parts are recycled and any remaining nonrecycled parts disposed of. The extended EOQ model is applied to a case study using different scenarios for length of use and multiple generations of products. Results of computer experiments confirmed the effectiveness of the proposed method.

How Effective Was the Romanian Labour Market After 2008?

2021 ◽  
Vol 6 (3) ◽  
pp. 27-32
Author(s):  
Nela Steliac
Keyword(s):  
Labour Market ◽  
Unemployment Rate ◽  
Labour Supply ◽  
Supply And Demand ◽  
National Level ◽  
Upward Trend ◽  
Beveridge Curve ◽  
High Stake ◽  
Efficient Operation ◽  
Demand And Supply

The efficient operation of the labour market is a matter of high stake for every state, considering that it reflects the balance between supply and demand. The extent to which such balance is achieved is highlighted by the Beveridge curve. This paper examines the efficient operation of the Romanian labour market, as measured by the relevant indicators of labour demand and supply. In order to capture the evolution of these indicators across the three target sub-periods (the crisis, the rebound and the resumption of an upward trend), the timeline subject to survey was 2008Q2-2016Q3. The survey conducted for this purpose revealed fluctuations in the number and rate of job vacancies, respectively in the unemployment rate. However, in the last part of the surveyed period, the trend of such indicators was downward for the unemployment rate and upward for the number and rate of job vacancies. Even so, these indicators failed to match the levels recorded before the outbreak of the economic crisis. Due to such evolutions, the Beveridge curve presented shifts of direction specific to the three sub-periods. Throughout the last part of the surveyed period, the curve seemed to recover slightly towards the top-left direction at national level. However, regionally, the evolutions of labour supply and demand varied, and the Beveridge curves varied accordingly. Surprisingly, it was not Bucharest-Ilfov, considered the best economically developed area in Romania, which reported the best correlation between labour supply and demand, but the Central region.

scholarly journals Microsimulation of Demand and Supply of Autonomous Mobility On Demand

2016 ◽  
Vol 2564 (1) ◽  
pp. 21-30 ◽  
Author(s):  
Carlos Lima Azevedo ◽  
Katarzyna Marczuk ◽  
Sebastián Raveau ◽  
Harold Soh ◽  
Muhammad Adnan ◽  
...  
Keyword(s):  
Demand And Supply ◽  
On Demand ◽  
Autonomous Mobility
Sign in / Sign up

Export Citation Format

Share Document