In real Mobility-on-Demand (MoD) systems, demand is subject to high and
dynamic volatility, which is difficult to predict by conventional time-series
forecasting approaches. Most existing forecasting approaches yield the point
value as the prediction result, which ignores the uncertainty that exists in
the forecasting result. This will lead to the forecasting result severely
deviating from the true demand value due to the high volatility existing in
demand. To fill the gap, we propose an extended recurrent mixture density
network (XRMDN), which extends the weight and mean neural networks to recurrent
neural networks. The recurrent neurons for mean and variance can capture the
trend of the historical data-series data, which enables a better forecasting
result in dynamic and high volatility. We conduct comprehensive experiments on
one taxi trip record and one bike-sharing real MoD data set to validate the
performance of XRMDN. Specifically, we compare our model to three types of
benchmark models, including statistical, machine learning, and deep learning
models on three evaluation metrics. The validation results show that XRMDN
outperforms the three groups of benchmark models in terms of the evaluation
metrics. Most importantly, XRMDN substantially improves the forecasting
accuracy with the demands in strong volatility. Last but not least, this
probabilistic demand forecasting model contributes not only to the demand
prediction in MoD systems but also to other optimization application problems,
especially optimization under uncertainty, in MoD applications.

在实际的移动出行需求预测系统中，传统的时间序列预测方法难以准确预测高动态波动的需求。本研究提出了一种扩展循环混合密度网络（XRMDN）模型，通过对历史数据序列的趋势进行捕捉，提高了动态高波动环境下的预测精度，并在真实移动出行数据集上的综合实验证实了其性能优于统计学、机器学习和深度学习模型。该研究不仅对于移动出行需求预测有贡献，也在其他应用领域的优化问题、特别是在不确定环境下的优化中具有重要意义。

XRMDN：基于循环混合密度网络的短期概率性需求预测架构（面向高波动性的移动出行系统）

XRMDN: A Recurrent Mixture Density Networks-based Architecture for  Short-Term Probabilistic Demand Forecasting in Mobility-on-Demand Systems  with High Volatility

Mobility-on-demand (MoD) systems consist of a fleet of shared vehicles that
can be hailed for one-way point-to-point trips. The total distance driven by
the vehicles and the fleet size can be reduced by employing ridesharing, i.e.,
by assigning multiple passengers to one vehicle. However, finding the optimal
passenger-vehicle assignment in an MoD system is a hard combinatorial problem.
In this work, we demonstrate how the VGA method, a recently proposed systematic
method for ridesharing, can be used to compute the optimal passenger-vehicle
assignments and corresponding vehicle routes in a massive-scale MoD system. In
contrast to existing works, we solve all passenger-vehicle assignment problems
to optimality, regularly dealing with instances containing thousands of
vehicles and passengers. Moreover, to examine the impact of using optimal
ridesharing assignments, we compare the performance of an MoD system that uses
optimal assignments against an MoD system that uses assignments computed using
insertion heuristic and against an MoD system that uses no ridesharing. We
found that the system that uses optimal ridesharing assignments subject to the
maximum travel delay of 4 minutes reduces the vehicle distance driven by 57 %
compared to an MoD system without ridesharing. Furthermore, we found that the
optimal assignments result in a 20 % reduction in vehicle distance driven and 5
% lower average passenger travel delay compared to a system that uses insertion
heuristic.

采用 VGA 方法来有效地解决大规模 MoD 系统中的乘客 - 车辆分配和路线问题，实验表明，采用最优化乘客共乘策略相对于没有共乘策略的 MoD 系统，车辆行驶距离减少 57%，平均乘客旅行延迟降低 5%。

大规模在线拼车：指派优化对系统性能的影响

Large-scale Online Ridesharing: The Effect of Assignment Optimality on  System Performance

With the development of mobility-on-demand services, increasing sources of
rich transportation data, and the advent of autonomous vehicles (AVs), there
are significant opportunities for shared-use AV mobility services (SAMSs) to
provide accessible and demand-responsive personal mobility. This paper focuses
on the problem of anticipatory repositioning of idle vehicles in a SAMS fleet
to enable better assignment decisions in serving future demand. The rebalancing
problem is formulated as a Markov Decision Process and a reinforcement learning
approach using an advantage actor critic (A2C) method is proposed to learn a
rebalancing policy that anticipates future demand and cooperates with an
optimization-based assignment strategy. The proposed formulation and solution
approach allow for centralized repositioning decisions for the entire vehicle
fleet but ensure that the problem size does not change with the size of the
vehicle fleet. Using an agent-based simulation tool and New York City taxi data
to simulate demand for rides in a SAMS system, two versions of the A2C AV
repositioning approach are tested: A2C-AVR(A) observing past demand for rides
and learning to anticipate future demand, and A2C-AVR(B) that receives demand
forecasts. Numerical experiments demonstrate that the A2C-AVR approaches
significantly reduce mean passenger wait times relative to an alternative
optimization-based rebalancing approach, at the expense of slightly increased
percentage of empty fleet miles travelled. The experiments show comparable
performance between the A2C-AVR(A) and (B), indicating that the approach can
anticipate future demand based on past demand observations. Testing with
various demand and time-of-day scenarios, and an alternative assignment
strategy, experiments demonstrate the models transferability to cases unseen at
the training stage.

本文关注的是在共享 AV 机动车辆出行服务 (SAMSs) 中，空闲车辆的预测性行驶问题。将该问题建模为马尔可夫决策过程，并提出了一种使用优势 actor-critic (A2C) 方法的强化学习方法，与基于优化的分配策略协作，学习一个预测性均衡策略。实验证明，该方法通过观察过去的需求并能够预测未来的需求，显著降低了乘客的等待时间。