Article

New algorithms for parking demand management and a city-scale deployment

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

On-street parking, just as any publicly owned utility, is used inefficiently if access is free or priced very far from market rates. This paper introduces a novel demand management solution: using data from dedicated occupancy sensors an iteration scheme updates parking rates to better match demand. The new rates encourage parkers to avoid peak hours and peak locations and reduce congestion and underuse. The solution is deliberately simple so that it is easy to understand, easily seen to be fair and leads to parking policies that are easy to remember and act upon. We study the convergence properties of the iteration scheme and prove that it converges to a reasonable distribution for a very large class of models. The algorithm is in use to change parking rates in over 6000 spaces in downtown Los Angeles since June 2012 as part of the LA Express Park project. Initial results are encouraging with a reduction of congestion and underuse, while in more locations rates were decreased than increased.

No full-text available

... The messages can be received by the gateway in about 6-7 seconds. LA ExpressPark also applies the dynamic pricing policy to achieve 10-30% of parking spaces being available throughout the day [31]. ...
... Dynamic pricing is currently the most efficient to regulate the parking occupancy status and traffic congestion. Unlike the dynamic pricing policy of SFpark, which changes the parking price on the average occupancy in a review period, Zoeter [31] took the deployment of LA ExpressPark and proposed a dynamic pricing policy with a Markov Chain model. The model can then predict the amount of parking demands and adjust the price before the car park is congested (occupancy rate > 90%) or underused (occupancy rate < 70%). ...
... 31 shows the lifetime of parking sensor in mesh topology. The energy depletion variation of TDMA varies more than the other two topologies because the larger network dimension costs more energy during the signaling period. ...
Thesis
Full-text available
Le parking intelligent, permettant aux conducteurs d'accéder aux informations de stationnement sur leurs appareils mobiles, réduit les difficultés des usagers. Tout d'abord, nous mettons en lumière la manière de recueillir les informations de parking en introduisant une architecture de réseaux de capteurs multi-saut, et les modèles d'intensité applicative en examinant la probabilité d'arrivées et de départs de véhicules. Puis nous étudions la stratégie de déploiement des réseaux de capteurs et définissons un problème multi-objectifs, puis nous le résolvons sur deux cartes de parking réelles. Ensuite, nous définissons un service Publish-Subscribe pour fournir aux conducteurs des informations pertinentes. Nous illustrons le système dans des réseaux véhiculaires et mobiles et soulignons l'importance du contenu et du contexte du message au conducteur. Afin d'évaluer la résilience du système, nous proposons un modèle Publish-Subscribe étendu et nous l'évaluons dans différentes circonstances imprévues. Notre travail est basé sur la prémisse que les capteurs de parking sont déployés à une grande échelle dans la ville. Nous considérons une vue d'ensemble des services urbains du point de vue de la municipalité. Ainsi, nous faisons la lumière sur deux thèmes principaux: la collecte d'informations sur le déploiement de capteurs et un modèle étendu de Publish-Subscribe. Notre travail donne un guide avant de démarrer un projet de parking intelligent ou tout service urbain similaire en temps réel. Il fournit également une plate-forme d'évaluation valable pour tester des jeux de données plus réalistes, comme des traces de véhicules ou de trafic réseau.
... The messages can be received by gateway in about 6-7 seconds. LA ExpressPark also applies a dynamic pricing policy to achieve 10-30% of the available parking spaces throughout the day [85]. ...
... Dynamic pricing is currently the most efficient way to regulate parking occupancy status and traffic congestion. Unlike the dynamic pricing policy of SFpark, which changes the parking price on the average occupancy in a review period, Zoeter et al. [85] took LA ExpressPark deployment and proposed a dynamic pricing policy with a Markov Chain model. The model can then predict a number of parking demands and adjust the price before the car park is congested (occupancy rate > 90%) or underused (occupancy rate < 70%). ...
Data
Full-text available
... The messages can be received by gateway in about 6-7 seconds. LA ExpressPark also applies a dynamic pricing policy to achieve 10-30% of the available parking spaces throughout the day [85]. ...
... Dynamic pricing is currently the most efficient way to regulate parking occupancy status and traffic congestion. Unlike the dynamic pricing policy of SFpark, which changes the parking price on the average occupancy in a review period, Zoeter et al. [85] took LA ExpressPark deployment and proposed a dynamic pricing policy with a Markov Chain model. The model can then predict a number of parking demands and adjust the price before the car park is congested (occupancy rate > 90%) or underused (occupancy rate < 70%). ...
Article
Full-text available
Considering the increase of urban population and traffic congestion, smart parking is always a strategic issue to work on, not only in the research field, but also from economic interests. Thanks to information and communication technology evolution, drivers can more efficiently find satisfying parking spaces with smart parking services. The existing and ongoing works on smart parking are complicated and transdisciplinary. While deploying a smart parking system, cities, as well as urban engineers, need to spend a very long time to survey and inspect all the possibilities. Moreover, many varied works involve multiple disciplines, which are closely linked and inseparable. To give a clear overview, we introduce a smart parking ecosystem and propose a comprehensive and thoughtful classification by identifying their functionalities and problematic focuses. We go through the literature over the period of 2000-2016 on parking solutions as they were applied to smart parking development and evolution, and propose three macro-themes: information collection, system deployment, and service dissemination. In each macro-theme, we explain and synthesize the main methodologies used in the existing works and summarize their common goals and visions to solve current parking difficulties. Finally, we give our engineering insights and show some challenges and open issues. Our survey gives an exhaustive study and a prospect in a multidisciplinary approach. Besides, the main findings of the current state-of-the-art throw out recommendations for future research on smart cities and the Internet architecture.
... Many studies, including ours suggest an approach that focuses on meeting a target occupancy level for every parking area. Ref. [11] presents the public parking pricing algorithm that has been implemented as part of the LA Express Park program. The emphasis of this algorithm is on reducing the amount of time that each block is underused or over-congested. ...
... According to a recent survey [38], cars seeking for parking on average spend 3.5 to 14 minutes on cruising before finding an available spot in downtown areas, which account for 30% of street traffic. Moreover, many cities are experimenting dynamic parking price policies, which are based on real-time parking availability [31,48]. To date, most parking sensing systems are focused on detecting where and when a parking or unparking event happens using various sensors. ...
Article
A main challenge faced by the state-of-the-art parking sensing systems is to infer the state of the spots not covered by participants’ parking/unparking events (called background availability) when the system penetration rate is limited. In this paper, we tackle this problem by exploring an empirical phenomenon that ignoring a spot along a driver’s parking search trajectory is likely due to the unavailability. However, complications caused by drivers’ preferences, e.g. ignoring the spots too far from the driver’s destination, have to be addressed based on human parking decisions. We build a model based on a dataset of more than 55,000 real parking decisions to predict the probability that a driver would take a spot, assuming the spot is available. Then, we present a crowdsourcing system, called ParkScan, which leverages the learned parking decision model in collaboration with the hidden Markov model to estimate background parking spot availability. We evaluated ParkScan with real-world data from both off-street scenarios (i.e., two public parking lots) and an on-street parking scenario (i.e., 35 urban blocks in Seattle). Both of the experiments showed that with a 5% penetration rate, ParkScan reduces over 12.9% of availability estimation errors for all the spots during parking peak hours, compared to the baseline using only the historical data. Also, even with a single participant driver, ParkScan cuts off at least 15% of the estimation errors for the spots along the driver’s parking search trajectory.
... Dynamic pricing of parking has been an area of active study in the transportation literature. In [Zoeter et al., 2014], [Rowe and Fiorucci, 2011], the authors present dynamic pricing schemes for regular parking based on estimated demand to reduce both congestion and underuse. On the other hand, significant work has also been done on dynamic pricing of electric vehicle charging. ...
Article
With the increase in adoption of Electric Vehicles (EVs), proper utilization of the charging infrastructure is an emerging challenge for service providers. Overstaying of an EV after a charging event is a key contributor to low utilization. Since overstaying is easily detectable by monitoring the power drawn from the charger, managing this problem primarily involves designing an appropriate penalty during the overstaying period. Higher penalties do discourage overstaying; however, due to uncertainty in parking duration, less people would find such penalties acceptable, leading to decreased utilization (and revenue). To analyze this central trade-off, we develop a novel framework that integrates models for realistic user behavior into queueing dynamics to locate the optimal penalty from the points of view of utilization and revenue, for different values of the external charging demand. Next, when the model parameters are unknown, we show how an online learning algorithm, such as UCB, can be adapted to learn the optimal penalty. Our experimental validation, based on charging data from London, shows that an appropriate penalty can increase both utilization and revenue while significantly reducing overstaying events.
Article
Real-time parking availability prediction is of great value to optimize the on-street parking resource utilization and improve traffic conditions, while the expensive costs of the existing parking availability sensing systems have limited their large-scale applications in more cities and areas. This paper presents the MePark system to predict real-time citywide on-street parking availability at fine-grained temporal level based on the readily accessible parking meter transactions data and other context data, together with the parking events data reported from a limited number of specially deployed sensors. We design an iterative mechanism to effectively integrate the aggregated inflow prediction and individual parking duration prediction for adequately exploiting the transactions data. Meanwhile, we extract discriminative features from the multi-source data, and combine the multiple-graph convolutional neural network (MGCN) and the long short-term memory (LSTM) network for capturing complex spatio-temporal correlations. The extensive experimental results based on a four-month real-world on-street parking dataset in Shenzhen, China demonstrate the advantages of our approach over various baselines.
Article
To address the increasingly serious parking pain, numerous mobile Apps have emerged to help drivers to find a convenient parking spot with various auxiliary information. However, the phenomenon of "multiple cars chasing the same spot" still exists, especially for on-street parking. Existing reservation-based resource allocation solutions could address the parking competition issue to some extent, but it is impractical to treat all spots as reservable resources. This paper first conducts a qualitative investigation based on the online survey data, which identifies diversified parking requirements involving i) reserved users, who request guaranteed spots with a reservation fee, ii) normal users, who request non-guaranteed spots with a "best-effort" service, and iii) external users, who do not use any guidance service. To this end, we design the D2Park system for diversified demand-aware parking guidance services. We formulate the problem as a novel Heterogeneous-Agent Dynamic Resource Allocation (HADRA) problem, which considers both current and future parking demands, and different constraints for diversified requirements. Two main modules are used in the system: 1) multi-step parking prediction, which makes multi-step parking inflow and occupancy rate predictions given the current parking events data and external factors; and 2) diversified parking guidance, which integrates the cooperation-based and competition-based resource allocation mechanisms based on a model predictive control framework to achieve a better performance balance among different user groups. Extensive experiments with a four-month real-world on-street parking dataset from the Chinese city Shenzhen demonstrate the effectiveness and efficiency of D2Park.
Article
To mitigate congestion caused by drivers cruising in search of parking, performance-based pricing schemes have received a significant amount of attention. However, several recent studies suggest location, time-of-day, and awareness of policies are the primary factors that drive parking decisions. Harnessing data provided by the Seattle Department of Transportation and considering the aforementioned decision-making factors, we analyze the spatial and temporal properties of curbside parking demand and propose methods that can improve traditional policies with straightforward modifications by advancing the understanding of where and when to administer pricing policies. Specifically, we develop a Gaussian mixture model based technique to identify zones with similar parking demand as quantified by spatial autocorrelation. In support of this technique, we introduce a metric based on the repeatability of our Gaussian mixture model to investigate temporal consistency.
Chapter
Finding the vacant space for parking a vehicle during peak hours is becoming a difficult task at ones end. Parking process whether in shopping malls, restaurants, or offices etc. is a long process and also leads to waste of gasoline. Smart car parking helps in finding the parking slot through Vehicular Ad Hoc Networks (VANET’s). For vehicle communication, some devices such as roadside units and on-board units are present that provides parking slot information. In the proposed work, we have introduced an online reservation facility for parking slot. People can reserve their parking space in advance before reaching to their venues in advance. This will help in reducing the waiting time for the parking allocation to the particular vehicle. This will also help to enhance the parking capabilities and will increase the efficiency when compared to other parking strategies. Our proposed approach can minimize the cost of parking on per person basis, exhaust of vehicle, and indirectly it will impact on save of wastage of gasoline and will keep the environment green.
Article
In this paper, we discuss the smart parking system in urban traffic network. In recent years, the decline in vehicle speed when searching for parking lots has been caused traffic jam in urban traffic network. Then, in this paper, we aim at shortening the searching time for parking lots, which is one of the causes of traffic jam, by allocating parking lots being available to drivers. Furthermore, we design the dynamical parking fee and redistribute parking lots to level the multiple parking manager's profit in traffic area. Finally, we confirm the effectiveness of proposed algorithm in numerical simulation.
Conference Paper
Abstract Designing a public urban policy is a demanding process which requires both time and money with no warranty of its efficiency. It involves knowledge about the purpose of urban design, behaviors of users and needs in terms of mobility. We believe that in the near future, decision makers will have to react and more frequently adapt public policies, based on the huge amount of available data, feedbacks from both target users and stakeholders. In this paper, we propose a generic agent-based architecture to model and simulate urban policies, which could facilitate the co-design and assessment of public policies in a specific environment. Two agent-based models are coupled with a micromacro dynamic loop, and they can be adapted either by the system using reinforcement learning, or by the stakeholders using simulation results. A generic formalism is elaborated to represent urban policies, which can be instantiated in a co-design approach between the policymaker and our system. An experimentation is conducted on an urban mobility policy, related to the configuration of parking price system in downtown area. The agent’s behavior and environment are developed to be as realistic as possible, based on a real-world source of modeling. However, our architecture has been designed to be generic, exploiting infrastructure data from any city using available community data (Open Street Map). The scenario of parking pricing shows that the system learns postpolicy behaviors and can propose some adjustments (e.g., specific actions to apply, when and how) to better meet the stakeholders’ objectives (e.g., maximize parking gains). The policy maker can then choose to validate the provided policies, or modified them for additional simulations. Index Terms Agent Based Modeling; Agent Based Simulation; Multi- Agent Systems; Policy Making; Public Policy; Reinforcement Learning; Urban Policy.
Article
Due to rapid expansion of urban areas in recent years, management of curbside parking has become increasingly important. To mitigate congestion, while meeting a city's diverse needs, performance-based pricing schemes have received a significant amount of attention. However, several recent studies suggest location, time-of-day, and awareness of policies are the primary factors that drive parking decisions. In light of this, we provide an extensive data-driven study of the spatio-temporal characteristics of curbside parking. This work advances the understanding of where and when to set pricing policies, as well as where to target information and incentives to drivers looking to park. Harnessing data provided by the Seattle Department of Transportation, we develop a Gaussian mixture model based technique to identify zones with similar spatial parking demand as quantified by spatial autocorrelation. In support of this technique, we introduce a metric based on the repeatability of our Gaussian mixture model to investigate temporal consistency.
Article
This paper draws upon the experience of the City of Los Angeles, California, with a demonstration project, LA Express Park. Since June 2012, the Los Angeles Department of Transportation has been using demand-based pricing to set the hourly parking meter rates in the city's downtown. Drivers were informed of the current parking rates and parking space availability for on-street parking spaces and for city-owned off-street facilities by a robust parking guidance system. For privately owned off-street facilities, the data were limited to location and current parking policies. The objective of the project was to reduce the time spent looking for available parking. Through the project's success, drivers had a better parking experience, and traffic congestion was reduced. For Los Angeles, this intelligent system for parking management was essentially revenue neutral. The paper argues that increasing revenue should not be the primary objective of projects for congestion pricing of parking. New parking meter technologies have shown greater potential for increasing revenue, and public acceptance of pricing projects is greater when revenue growth is not the goal of a project. Cities are more likely to achieve success and acceptance if the goal of these projects is to reduce the number of under- and overoccupied parking spaces and thereby make finding parking easier.
Data
Full-text available
Conference Paper
The field of parking is going through a period of extreme innovation. Cities in the United States are now exploring new technology to improve on-street parking. One such innovation is dynamic pricing based on sensors and smart meters. This paper presents the results of two surveys and an ethnographic study in the context of LA Express ParkTM to understand users’ behaviors, knowledge and perceptions around parking. Survey results demonstrated that a high number of users misunderstood one of three tested stickers that convey time of day pricing. Furthermore, after discovering the availability of cheaper parking spots nearby, people expressed willingness to change their future behavior to park in those places. Ethnographic field studies found that it is common for many parkers to use handicapped placards for over eight hours in one parking session. A percentage of these parkers may be using placards illegally. We propose that increasing some parking restrictions during the day may curb placard use by making it more difficult to park for long periods.
Article
In this paper we address a challenging problem of predicting on-street parking occupancy based on sensors with occasionally missing data. These missing values are most likely not missing at random. However, the exact process behind it is unknown at the outset. For example, an entry in our data stream might read: "at time t, blockface b, which has capacity 20, has 18 working sensors, and of those working sensors 10 indicate that a parking space is occupied." The challenge is to infer as accurately as possible the actual occupancy of blockface b, i.e. the occupancy of all parking spaces, including the ones with inoperative sensors. The fact that sensors are inoperative only occasionally allows us to learn a demand model and a sensor noise model jointly, and use this to "fill in the blanks" in the best possible way. We introduce a series of sensor noise models of increasing complexity that are suited for several sensor characteristics. Cross-validation allows the selection of the suitable model for a particular application. The sensor noise models we introduce are flexible and can be combined with any probabilistic model for demand and hence have a very wide applicability. In our demonstration application we find that sensors are more likely to be inoperative when parking spaces are empty, in particular during busy traffic periods. This supports the hypothesis that drive-by-traffic is an important source of noise for the sensor. Compared to baseline methods based on a missing-at-random assumption our method gives better predictive performance and avoids a systematic bias in the inferred occupancies.
Conference Paper
We study online bipartite matching settings inspired by parking allocation problems, where rational agents arrive sequentially and select their most preferred parking slot. In contrast to standard online matching setting where edges incident to each arriving vertex are revealed upon its arrival, agents in our setting have private preferences over available slots. Our focus is on natural and simple pricing mechanisms, in the form of posted prices. On the one hand, the restriction to posted prices imposes new challenges relative to standard online matching. On the other hand, we employ specific structures on agents' preferences that are natural in many scenarios including parking. We construct optimal and approximate pricing mechanisms under various informational and structural assumptions, and provide approximation upper bounds under the same assumptions. In particular, one of our mechanisms guarantees a better approximation bound than the classical result of Karp et al.[10] for unweighted online matching, under a natural structural restriction.
Article
Let $M(x)$ denote the expected value at level $x$ of the response to a certain experiment. $M(x)$ is assumed to be a monotone function of $x$ but is unknown to the experimenter, and it is desired to find the solution $x = \theta$ of the equation $M(x) = \alpha$, where $\alpha$ is a given constant. We give a method for making successive experiments at levels $x_1,x_2,\cdots$ in such a way that $x_n$ will tend to $\theta$ in probability.
Article
It is important to realize, however, that this result applies only to cases where each bidder is interested in at most a single unit, and there is no collusion among the bidders. As soon as we consider the more general case where an individual bidder may be interested in securing two or more of the units, while the number of bidders is still too few to produce a fully competitive market, the possibility of so arranging things that the Pareto-optimal result is achieved without impairing the expectations of the seller disappears. It is not possible to consider a buyer wanting up to two units as merely an aggregation of two single-unit buyers: combining the two buyers into one introduces a built-in collusion and community of interest, and the bid offered for the second unit will be influenced by the possible effect of this bid on the price to be paid for the first, even under the first-rejected-bid method. Where individual bidders may buy more than one indivisible unit, we are, in effect, back in a variant of the exclusive marketing-agency case, where the interests of the marketing agency are merged with those of a single monopolistic seller. In such a case, while the marketing agency need have no concern for the amounts above the competitive equilibrium price which the Pareto-optimal marketing scheme of pages 10–12 would require to be paid to itself as seller, it would be concerned for the amounts by which the revenues from the purchasers would fall short of the competitive equilibrium price, or at least the amount by which these receipts fall short of the possibly somewhat smaller revenues which could in fact be secured on the basis of any other method of approximating the efficient allocation under imperfectly competitive conditions. Nor could optimal results be obtained merely by restricting all bids to an offer to take up to a given quantity at any price below a specified price, the final terms being a price equal to the price bid by the first unsuccessful bidder, each bidder bidding more than this being allotted the amount which he specified. Under such a scheme, for any quantity that a bidder might decide to specify, it would be advantageous for him to specify as his bid price the full average value of this quantity to him, since he would prefer this quantity to be allotted at any price lower than this bid rather than be excluded altogether, and a change in his bid price within the range in which he would be successful would not affect the contract price. If a particular bidder is sure that changing the quantity he specifies will not affect the contract price, as would be the case if the change is small enough so as not to change the identity of the first unsuccessful bidder and if his demand curve is linear over the relevant range, his quantity specifications would tend to equal the quantity he would demand at the mean of the prices that he expects to result. To the extent that he is mistaken as to the ultimate price, misallocation will result. Even more serious, the resulting bids do not provide in themselves the information necessary to enable the marketing agency to determine the Pareto-optimal result.
Article
We study the classic mathematical economics problem of Bayesian optimal mechanism design where a principal aims to optimize expected revenue when allocating resources to self-interested agents with preferences drawn from a known distribution. In single parameter settings (i.e., where each agent's preference is given by a single private value for being served and zero for not being served) this problem is solved [20]. Unfortunately, these single parameter optimal mechanisms are impractical and rarely employed [1], and furthermore the underlying economic theory fails to generalize to the important, relevant, and unsolved multi-dimensional setting (i.e., where each agent's preference is given by multiple values for each of the multiple services available) [25]. In contrast to the theory of optimal mechanisms we develop a theory of sequential posted price mechanisms, where agents in sequence are offered take-it-or-leave-it prices. We prove that these mechanisms are approximately optimal in single-dimensional settings. These posted-price mechanisms avoid many of the properties of optimal mechanisms that make the latter impractical. Furthermore, these mechanisms generalize naturally to multi-dimensional settings where they give the first known approximations to the elusive optimal multi-dimensional mechanism design problem. In particular, we solve multi-dimensional multi-unit auction problems and generalizations to matroid feasibility constraints. The constant approximations we obtain range from 1.5 to 8. For all but one case, our posted price sequences can be computed in polynomial time. This work can be viewed as an extension and improvement of the single-agent algorithmic pricing work of [9] to the setting of multiple agents where the designer has combinatorial feasibility constraints on which agents can simultaneously obtain each service.
Article
1. Introduction. Consider the problem faced by someone who has an object to sell, and who does not know how much his prospective buyers might be willing to pay for the object. This seller would like to find some auction procedure which can give him the highest expected revenue or utility among all the different kinds of auctions known (progressive auctions, Dutch auctions, sealed bid auctions, discriminatory auctions, etc.). In this paper, we will construct such optimal auctions for a wide class of sellers' auction design problems. Although these auctions generally sell the object at a discount below what the highest bidder is willing to pay, and sometimes they do not even sell to highest bidder, we shall prove that no other auction mechanism can give higher expected utility to the seller. To analyze the potential performance of different kinds of auctions, we follow
LA Express Park-curbing downtown congestion through intelligent parking management
• P Ghent
• D Mitchell