CN115440059A - Wisdom parking stall management system based on thing networking - Google Patents
Wisdom parking stall management system based on thing networking Download PDFInfo
- Publication number
- CN115440059A CN115440059A CN202210871748.3A CN202210871748A CN115440059A CN 115440059 A CN115440059 A CN 115440059A CN 202210871748 A CN202210871748 A CN 202210871748A CN 115440059 A CN115440059 A CN 115440059A
- Authority
- CN
- China
- Prior art keywords
- parking
- user
- parking space
- information
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/30—Control
- G16Y40/35—Management of things, i.e. controlling in accordance with a policy or in order to achieve specified objectives
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent parking space management system based on the Internet of things, which comprises a parking space prediction unit, a parking scheduling unit and a parking path planning unit, wherein the parking space prediction unit is used for predicting the future traffic flow about to be parked in a parking lot by fusing various data, the parking scheduling unit is used for performing real-time dynamic scheduling of user parking according to user expectation and a real-time parking space environment, the parking path planning unit is used for planning the optimal path of a vehicle to run to a target parking space after performing parking space matching on the basis of user expectation and parking space parameters, the parking space prediction unit, the parking scheduling unit and the parking path planning unit are in network connection, the dynamic intelligent matching of a parking space and the vehicle to be parked is realized on the basis of the user expectation and the parking space parameters, the turnover time and the distance of vehicle parking are reduced on the whole, and the parking efficiency is improved to the greatest extent.
Description
Technical Field
The invention relates to the technical field of parking space management, in particular to an intelligent parking space management system based on the Internet of things.
Background
The rapid increase of national economy enables the quantity of domestic automobiles to be continuously increased, which causes the quantity of parking spaces in a plurality of domestic cities to become very short, especially in some specific holidays, aiming at the parking problem of parking lots in each large activity place, the problems of long-time waiting of users and long-time congestion of the parking lots can be frequently caused due to the large number of parking spaces and the limited number of parking spaces, the existing method for solving the problem of difficult parking is still a dynamic process for enlarging the parking lots and increasing the parking spaces, but the quantity of fixed-point parking spaces in a plurality of districts in the cities is continuously changed along with time and crowd behaviors, and a single fixed-mode parking space distribution method cannot meet the parking requirements of different groups, so that an intelligent parking space management system based on the internet of things for real-time optimal user parking scheduling and parking space scheme planning is necessary to be designed.
Disclosure of Invention
The invention aims to provide an intelligent parking space management system based on the Internet of things, and aims to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: the intelligent parking space management system based on the Internet of things comprises a parking space prediction unit, a parking scheduling unit and a parking path planning unit, wherein the parking space prediction unit is used for predicting the future traffic flow about to park in a parking lot by fusing various data, the parking scheduling unit is used for performing real-time dynamic scheduling of parking of a user according to user expectation and a real-time parking space environment, the parking path planning unit is used for planning the optimal path of a vehicle running to a target parking space after performing parking space matching based on user expectation and parking lot parameters, and the parking space prediction unit, the parking scheduling unit and the parking path planning unit are in network connection.
According to the technical scheme, the parking space prediction unit comprises a multi-mode data acquisition module, a future traffic flow prediction module and a parking space prediction module, the multi-mode data acquisition module and the future traffic flow prediction module are electrically connected with the parking space prediction module, the multi-mode data acquisition module is used for acquiring various data in a parking lot by combining various sensors and a multi-mode data fusion mode and uploading the data to a cloud server, the future traffic flow prediction module is used for calculating the traffic flow of a parking point in a set period of time accurately according to a data fusion method, and the parking space prediction module is used for calculating the number of parking space prediction requests by utilizing the LSTM to extract parking characteristics.
According to the technical scheme, the parking scheduling unit comprises a user parking demand module, a data center module, a comparison analysis and judgment module and a parking space matching module, the user parking demand module is electrically connected with the data center module, the comparison analysis and judgment module is electrically connected with the parking space matching module, the user parking demand module is used for a user to request for parking and parking expectation through a mobile terminal, the data center module is used for receiving the parking expectation of the user and real-time parking space information and parameters of a parking lot in real time, the comparison analysis and judgment module is used for performing comparison analysis on the parking demand quantity of the user and the current parking space quantity information of the parking lot, and the parking space matching module is used for performing optimal scheduling matching on parking spaces according to comparison analysis results.
According to the technical scheme, the parking path planning unit comprises a global path planning module and a local path planning module, the global path planning module is electrically connected with the local path planning module, the global path planning module is used for planning the optimal distribution path of the parking spaces according to the overall parking space environment of the parking lot, and the local path planning module is used for planning the local optimal path of the nearest parking space according to the parking expectation of a user and the parking space environment.
According to the technical scheme, the operation method of the intelligent parking space management system comprises the following steps:
the method comprises the following steps: predicting the future traffic flow about to stop in the parking lot;
step two: when a user generates a parking demand, a parking request is sent to a data center through a mobile terminal and a parking expectation is informed, a parking lot monitors vehicle condition information in real time, the database information is updated and fed back to the center, and the data center performs parking space matching;
step three: and real-time optimal user parking scheduling and scheme planning are realized through environment interaction and the fitting of the parking model.
According to the technical scheme, in the first step, a specific method for predicting the future traffic flow is as follows:
step A1: counting various types of parking space information in the region through various data fusion methods, and uploading the parking space information to a cloud server;
step A2: the elastic expansion structure of the Aliyun ESC server is used for increasing and reducing the number of parking spaces, and releasing time is selected;
step A3: and matching the corresponding parking space number and the calculation processing capacity of the server according to the dynamic request of the user.
According to the technical scheme, in the step A1, multi-modal data fusion is a concept of integrating information from multiple modalities together, and aims to predict a class through a classification method, different sensors collect various information of a parking lot, the traffic flow and parking space distribution information of each parking lot is calculated through a multi-modal data learning algorithm, a feature fusion mode is usually selected for the traffic flow and parking space distribution calculation of the parking lots, and the feature fusion mode is to extract expression fusion from a network and then access a classification layer.
According to the technical scheme, in the second step, the specific method for the data center to perform parking space matching comprises the following steps:
step B1: a user generates a parking demand and then a warehouse-out demand, and sends parking and warehouse-out requests to a data center through a mobile terminal and informs of parking and warehouse-out expectations;
and step B2: the parking lot monitors the vehicle condition information in real time, updates the database information and feeds the database information back to the data center;
and step B3: acquiring parking demand information and ex-warehouse demand information of a user;
and step B4: acquiring parking space information of a target parking lot;
and step B5: comparing and judging the parking demand quantity of the user with the current parking space quantity information of the parking lot;
and step B6: when the parking demand quantity of the user is smaller than the current parking space quantity of the parking lot, directly allocating the parking spaces of the target parking lot to the user;
step B7: when the parking demand quantity of the user is larger than the current parking space quantity of the parking lot, setting a weight value according to the expectation of the user by using a data center;
and step B8: the data center accumulates the weighted values and synchronously sorts the weighted values of all users;
and step B9: according to the sorting of the previous step, the parking spaces are distributed to users with large weight values;
step B10: meanwhile, the data center uses a kmeans algorithm to perform cluster classification on the rest users by taking the parking range as an index, and the users are distributed to corresponding parking lots P according to the principle of proximity 1 、P 2 、P 3 And sending the information of the corresponding parking lot to the user according to the clustering result.
According to the technical scheme, in the step B1, the data center is responsible for scheduling and calculating information, receiving parking expectation of a user and real-time parking lot parking space information and parameters (number of parking spaces, weight value and price) of a parking lot in real time, the user uses a mobile terminal to use positioning or directly input a target parking lot for searching, the data center receives a user request and then sends the user request to the target parking lot of the user and information of recommended parking lots around the target parking lot of the user according to the real-time parking space information in the database, and the user sends the own parking expectation (parking time, parking space type and the like) to the data center according to the own requirements;
the data center receives user expectation and then carries out fuzzy matching, and accesses the warehouse-out requirement of the user, sets a time value of the same time period, matches the user with the warehouse-out requirement and the user with the parking requirement in the same time period, when the warehouse-out user leaves the parking stall, the parking stall message is sent to the matched user to be parked and warehoused, meanwhile, when the target parking lot has the parking stall meeting the condition, the parking stall can be directly pushed to the user, on the contrary, if the target parking lot is difficult to meet the requirement, the data center can calculate the weighted value expected by the user and sort the weighted value, the weighted value is distributed to the user with the requirement capable of meeting the requirement to the maximum, and in the aspect of user expectation, the starting time, the parking range and duration and the type of the parking stall requirement need are defined in advance.
According to the technical scheme, in the third step, after the parking spaces are matched based on the user expectation and the parking lot parameters, the optimal path of the vehicle running to the target parking space is further planned according to the actual environment and the user expectation
Step C1: constructing a global environment map model by adopting a grid decomposition method;
and C2: initializing various parameters of the mixed ant colony algorithm;
step C3: the ants move forward from the initial grid, when the next node is selected, route finding ants are dispatched to explore the obstacle situation behind the node, then the forward direction is selected according to the pheromone concentration and distance heuristic information on the route and the distribution situation of the obstacles behind the node until the ants reach the end point, and after the ants reach the end point, the route pheromone concentration distribution is updated;
and C4: after all ants complete the step C3, global pheromone updating is carried out by utilizing an optimal worst punishment system, an ant path with a better path is simultaneously selected, guided genetic algorithm variation is carried out, and a generated new optimal path is also simultaneously included in a path set;
and C5: and C3, repeating the step C3 and the step C4 until the set iteration times are reached, finishing path optimization, and sending the calculated optimal path of the vehicle running to the target parking space to a user receiving end.
Compared with the prior art, the invention has the following beneficial effects: the invention starts from the real-time capacity of a plurality of parking lots in the same system by arranging a parking space prediction unit, a parking scheduling unit and a parking path planning unit, realizes dynamic intelligent matching of parking spaces and a vehicle to be parked through nonlinear programming and fuzzy control based on user expectation (parking duration, start-stop time and parking preference) in combination with a plurality of factors of parking lot parameters (number of parking spaces, real-time parking difficulty and cost), classifies and preliminarily divides regions according to parking requests to be processed, preferentially considers and allocates parking points in the same azimuth angle, and locks a preselected parking space in the process from selection of a target parking space to final parking so as to avoid other vehicles from sending parking requests again, so that the target parking space is locked in an unoccupied state, and when the vehicle leaves the parking lot after parking, the parking space is unlocked and is in an available state, so that the turnover time and distance for parking the vehicle are reduced as a whole, and the parking efficiency is improved to the maximum extent.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of the system module composition of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution: the intelligent parking space management system based on the Internet of things comprises a parking space prediction unit, a parking scheduling unit and a parking path planning unit, wherein the parking space prediction unit is used for predicting future traffic flow about to be parked in a parking lot by fusing various data, the parking scheduling unit is used for performing real-time dynamic scheduling of user parking according to user expectation and real-time parking space environment, the parking path planning unit is used for planning an optimal path from vehicle driving to a target parking space after parking space matching is performed on the basis of user expectation and parking lot parameters, and the parking space prediction unit and the parking scheduling unit are in network connection with the parking path planning unit.
The parking space prediction unit comprises a multi-mode data acquisition module, a future traffic flow prediction module and a parking space prediction module, the multi-mode data acquisition module and the future traffic flow prediction module are electrically connected with the parking space prediction module, the multi-mode data acquisition module is used for acquiring various data in a parking space by combining various sensors with a multi-mode data fusion mode and uploading the data to a cloud server, the future traffic flow prediction module is used for calculating the traffic flow of parking points in a precise set time period according to a data fusion method, and the parking space prediction module is used for calculating and predicting the quantity of parking space requests by utilizing the LSTM to extracted parking characteristics.
The parking scheduling unit comprises a user parking demand module, a data center module, a comparison analysis judgment module and a parking space matching module, wherein the user parking demand module is electrically connected with the data center module, the comparison analysis judgment module is electrically connected with the parking space matching module, the user parking demand module is used for a user to request parking and parking expectation through a mobile terminal, the data center module is used for receiving the parking expectation of the user and real-time parking lot parking space information and parameters in real time, the comparison analysis judgment module is used for performing comparison analysis on the parking demand quantity of the user and the current parking space quantity information of the parking lot, and the parking space matching module is used for performing optimal scheduling matching on parking spaces according to comparison analysis results.
The parking path planning unit comprises a global path planning module and a local path planning module, the global path planning module is electrically connected with the local path planning module, the global path planning module is used for planning the optimal distribution path of the parking spaces according to the overall parking space environment of the parking lot, and the local path planning module is used for planning the local optimal path of the nearest parking space according to the parking expectation of a user and the parking space environment.
The operation method of the intelligent parking space management system comprises the following steps:
the method comprises the following steps: the method aims at predicting the future traffic flow about to park in the parking lot, and carries out parking space prediction according to the predicted traffic flow information and the current parking space information of the parking lot, so that the problem of possible blockage caused by short-time traffic flow can be reduced, the traffic flow is predicted in advance to carry out parking space scheduling, and the resource waste is reduced;
step two: when a user generates a parking demand, a parking request is sent to a data center through a mobile terminal and a parking expectation is informed, a parking lot monitors vehicle condition information in real time, the database information is updated and fed back to the center, the data center performs matching of parking spaces, different parking requirements such as destination addresses, a time range of one-time parking in the future, parking type preference, the highest price which the user is willing to spend, walking time which can be tolerated from the parking spaces to the parking lot and the like are input by the user in parking operation, the different requests of the user to be parked are subjected to classification management analysis, and an optimal parking space is decided for the user by combining the number and the occupation condition of the parking spaces of a current parking spot, so that disorder, burst and preemptive processing can be better performed on the parking request of the user, the request and the parking space state of the user are updated in real time, and the efficient operation of a parking task of the whole parking spot is ensured;
step three: and real-time optimal user parking scheduling and scheme planning are realized through environment interaction and the fitting of the parking model.
In the first step, the concrete method for predicting the future traffic flow is as follows:
step A1: the method comprises the steps that various types of parking space information in an area are counted through various data fusion methods and uploaded to a cloud server, the server has the function of receiving basic traffic flow information and parking space distribution information of parking points in the area, the data are processed and stored in an Ali cloud database, and the traffic flow of the parking points in unit time serves as load data and serves as a basis for Ali cloud flexible computing;
step A2: the method comprises the steps that the number of parking places is increased and decreased through calculation by using an elastic expansion structure of an Aliyun ESC server, release time is selected, a database can store basic parking point traffic flow information obtained through a comprehensive flow algorithm of multi-mode data fusion, after parking flow at a future moment is predicted for each parking place by using an LSTM model, the Aliyun server executes elastic expansion service to release (contract) the parking places, meanwhile, bee dynamic parking place balancing algorithm is used for adjusting according to deviation of a predicted value and an actual value, model parameters are adaptively updated, the total parking place number of different parking lots is used as loads of the server, the distribution process of the parking places (parking lot level) is managed through the real-time and predicted parking place request number, the problems of insufficient utilization and excessive utilization of resources are avoided, and the parking lot is kept in a good state with small loads;
step A3: and matching the corresponding parking space number and the calculation processing capacity of the server according to the dynamic request of the user.
In the step A1, multi-mode data fusion is a concept of integrating information from multiple modes, and aims to predict a class through a classification method, different sensors collect various information of a parking lot, the traffic flow and parking space distribution information of each parking lot are calculated through a multi-mode data learning algorithm, a feature fusion mode is usually selected for the traffic flow and parking space distribution calculation of the parking lots, and the feature fusion is to extract expression fusion from a network and then access a classification layer.
In the second step, the concrete method for matching the parking spaces by the data center comprises the following steps:
step B1: a user generates a parking demand and then a warehouse-out demand, and sends parking and warehouse-out requests to a data center through a mobile terminal and informs of parking and warehouse-out expectations;
and step B2: the parking lot monitors the vehicle condition information in real time, updates the database information and feeds the database information back to the data center;
and step B3: the method comprises the steps that parking demand information and ex-warehouse demand information of a user are obtained, and a parking request and a parking expectation are sent by the user through a mobile terminal;
and step B4: the method comprises the steps that parking space information of a target parking lot is obtained, a data center ensures real-time updating of the parking lot information, and in the working process, the data center is responsible for scheduling and calculating the information and receives parking expectation of a user and real-time parking space information and parameters (number of parking spaces, weight value, price and the like) of the parking lot in real time;
and step B5: comparing and judging the parking demand quantity of the user with the current parking space quantity information of the parking lot;
and step B6: when the parking demand quantity of the user is smaller than the current parking space quantity of the parking lot, directly allocating the parking spaces of the target parking lot to the user;
step B7: when the parking demand quantity of the user is larger than the current parking space quantity of the parking lot, the data center is utilized to set a weighted value according to the expectation of the user, and the parking demand quantity of the user is larger than the current parking space quantity of the parking lot and comprises multiple covering conditions: firstly, the total number of orders expected to be parked by a user is larger than the number of available parking spaces in a parking lot, the number of indoor parking orders is larger than the number of available indoor parking spaces, and the number of outdoor parking orders is larger than the number of available indoor parking spaces, so that under the possible presenting conditions, the expected weight value is calculated mainly according to expected factors of the user;
and step B8: the data center accumulates the weighted values and synchronously sorts the weighted values of all users;
and step B9: according to the sorting in the last step, the parking spaces are distributed to users with large weight values, the parking spaces are distributed in the parking lot range as far as possible according to the type of the parking space request, and when special conditions exist, such as insufficient indoor parking spaces, corresponding indoor parking requests are distributed to outdoor parking lots;
and step B10: meanwhile, the data center uses a kmeans algorithm to perform cluster classification on the remaining users by taking the parking range as an index, and the users are distributed to corresponding parking lots P according to the principle of proximity 1 、P 2 、P 3 And sending the information of the corresponding parking lot to the user according to the clustering result.
In the step B1, the data center is responsible for scheduling and calculating information, real-time parking expectation of a user and real-time parking lot parking space information and parameters are received in real time, the user uses a mobile terminal to use positioning or directly input a target parking lot for searching, and the data center receives a user request and then sends the user request to the target parking lot of the user and surrounding recommended parking lot information according to the real-time parking lot information in the database;
the user sends the parking expectation of the user to the data center according to the requirement of the user, the data center carries out fuzzy matching after receiving the user expectation, and accessing the warehouse-out requirement of the user, setting the time value of the same time period, matching the user with the warehouse-out requirement and the user with the parking requirement in the same time period, when the user leaving the parking space, the parking space information is transmitted to the matched user to be parked and put in the parking space in real time, meanwhile, when the target parking lot has qualified parking spaces, the parking spaces are directly pushed to the user, on the contrary, if the target parking lot is difficult to meet the requirements, the data center calculates the weight values expected by the user and sorts the weight values to distribute the weight values to the user with the requirement capable of meeting the requirement to the maximum extent, in the aspect of user expectation, the starting time, the parking range and time and the type of parking space requirement need to be defined in advance, the dynamic intelligent matching of the parking space and the vehicle to be parked is realized through nonlinear programming and fuzzy control by combining various factors of parking space parameters (the number of parking spaces, the difficulty degree of real-time parking and the cost) based on the real-time capacity of a plurality of parking spaces in the same system and based on the user expectation (the parking time, the starting and stopping time and the parking preference), classifying and primarily dividing regions according to the parking requests to be processed, preferentially considering the allocation of parking points in the same azimuth angle, selecting the target parking space to lock the preselected parking space in the process of final parking, avoiding other vehicles from sending the parking requests again, the target parking space is locked to be in an unoccupied state, when the vehicle finishes parking and leaves the parking lot, the parking space is unlocked and is in an available state, the turnover time and distance of vehicle parking are reduced on the whole, and the parking efficiency is improved to the maximum extent.
In the third step, after the parking spaces are matched based on the user expectation and the parking lot parameters, the optimal path of the vehicle running to the target parking space is further planned according to the actual environment and the user expectation
Step C1: the grid decomposition method is adopted to construct the global environment map model, and has the advantages of simplicity, intuition and strong universality due to the characteristics of particularity, irregularity, randomness and the like of the parking lot, is suitable for obstacles in any shape, and is easy to carry out edge treatment;
and step C2: initializing various parameters of the hybrid ant colony algorithm, and optimizing the hybrid ant colony algorithm by using a probability type colony intelligent algorithm according to a rule of probability transfer;
and C3: the ants advance from the initial grid, when the next node is selected, the path finding ants are dispatched to explore the obstacle situation after the node, then the advancing direction is selected according to the pheromone concentration and distance heuristic information on the path and the distribution situation of the obstacles behind the node until the ants reach the end point, and the distribution of the pheromone concentration of the path is updated after the ants reach the end point;
and C4: after all ants finish the step C3, global pheromone is updated by utilizing an optimal worst reward and punishment system, an ant path with a better path is simultaneously selected, guided genetic algorithm variation is carried out, and a generated new optimal path is also included in the path set;
step C5: and C3 and C4 are repeated until the set iteration times are reached, path optimization is completed, the calculated optimal path of the vehicle running to the target parking space is sent to a user receiving end, the mixed ant colony algorithm scientifically solves the path planning problem during parking operation, and the obtained optimal path has excellent results in safety, time consumption and path length.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described above, or equivalents may be substituted for elements thereof. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. Wisdom parking stall management system based on thing networking, including parking stall prediction unit, parking dispatch unit and the route planning unit of parking, its characterized in that: the parking space prediction unit is used for predicting future traffic flow about to be parked in a parking lot by fusing various data, the parking scheduling unit is used for performing real-time dynamic scheduling of user parking according to user expectation and real-time parking space environment, the parking path planning unit is used for planning an optimal path of a vehicle to a target parking space after parking space matching is performed on the basis of the user expectation and parking lot parameters, and the parking space prediction unit and the parking scheduling unit are in network connection with the parking path planning unit.
2. The intelligent parking space management system based on the Internet of things of claim 1, wherein: the parking space prediction unit comprises a multi-mode data acquisition module, a future traffic flow prediction module and a parking space prediction module, the multi-mode data acquisition module and the future traffic flow prediction module are electrically connected with the parking space prediction module, the multi-mode data acquisition module is used for acquiring various data in a parking lot by combining a plurality of sensors with a multi-mode data fusion mode and uploading the data to a cloud server, the future traffic flow prediction module is used for calculating the accurate traffic flow of parking points in a set time period according to a data fusion method, and the parking space prediction module is used for calculating and predicting the number of parking space requests according to the extracted parking characteristics by using the LSTM.
3. The intelligent parking space management system based on the Internet of things of claim 2, wherein: the parking scheduling unit comprises a user parking demand module, a data center module, a comparison analysis and judgment module and a parking space matching module, wherein the user parking demand module is electrically connected with the data center module, the comparison analysis and judgment module is electrically connected with the parking space matching module, the user parking demand module is used for a user to make a request for parking and expected parking through a mobile terminal, the data center module is used for receiving the parking expectation of the user and real-time parking lot parking space information and parameters, the comparison analysis and judgment module is used for performing comparison analysis on the parking demand quantity of the user and the current parking space quantity information of the parking lot, and the parking space matching module is used for performing optimal scheduling matching on parking spaces according to a comparison analysis result.
4. The intelligent parking space management system based on the Internet of things of claim 3, wherein: the parking path planning unit comprises a global path planning module and a local path planning module, the global path planning module is electrically connected with the local path planning module, the global path planning module is used for planning an optimal distribution path of parking spaces according to the overall parking space environment of the parking lot, and the local path planning module is used for planning a local optimal path of the nearest parking space according to the parking expectation of a user and the parking space environment.
5. The intelligent parking space management system based on the Internet of things of claim 4, wherein: the operation method of the intelligent parking space management system comprises the following steps:
the method comprises the following steps: predicting the future traffic flow about to stop in the parking lot;
step two: when a user generates a parking demand, a parking request is sent to a data center through a mobile terminal and a parking expectation is informed, a parking lot monitors vehicle condition information in real time, the database information is updated and fed back to the center, and the data center performs parking space matching;
step three: and real-time optimal user parking scheduling and scheme planning are realized through environment interaction and the fitting of the parking model.
6. The intelligent parking space management system based on the Internet of things of claim 5, wherein: in the first step, a specific method for predicting the future traffic flow is as follows:
step A1: counting various types of parking space information in the region through various data fusion methods, and uploading the parking space information to a cloud server;
step A2: the method comprises the steps that an elastic telescopic framework of an Aliyun ESC server is applied to increase and reduce the number of parking spaces, and release time is selected;
step A3: and matching the corresponding parking space number and the calculation processing capacity of the server according to the dynamic request of the user.
7. The intelligent parking space management system based on the Internet of things of claim 6, wherein: in the step A1, multi-mode data fusion is a concept of integrating information from multiple modes, and aims to predict a class through a classification method, different sensors collect various information of a parking lot, the traffic flow and parking space distribution information of each parking network point are calculated through a multi-mode data learning algorithm, a feature fusion mode is usually selected for the traffic flow and parking space distribution calculation of the parking network points, and the feature fusion is to extract expression fusion from a network and then access a classification layer.
8. The intelligent parking space management system based on the Internet of things of claim 7, wherein: in the second step, the specific method for the data center to perform parking space matching comprises the following steps:
step B1: a user generates a parking demand and then a warehouse-out demand, and sends parking and warehouse-out requests to a data center through a mobile terminal and informs of parking and warehouse-out expectations;
and step B2: the parking lot monitors the vehicle condition information in real time, updates the database information and feeds the database information back to the data center;
and step B3: acquiring parking demand information and ex-warehouse demand information of a user;
and step B4: acquiring parking space information of a target parking lot;
and step B5: comparing and judging the parking demand quantity of the user with the current parking space quantity information of the parking lot;
step B6: when the parking requirement number of the user is smaller than the current parking space number of the parking lot, directly allocating the parking spaces of the target parking lot to the user;
step B7: when the parking demand quantity of the user is larger than the current parking space quantity of the parking lot, setting a weight value according to the expectation of the user by using a data center;
and step B8: the data center accumulates the weighted values and synchronously sorts the weighted values of all users;
step B9: according to the sorting of the previous step, the parking spaces are distributed to users with large weight values;
step B10: meanwhile, the data center uses a kmeans algorithm to perform cluster classification on the remaining users by taking the parking range as an index, and the users are distributed to corresponding parking lots P according to the principle of proximity 1 、P 2 、P 3 And sending the information of the corresponding parking lot to the user according to the clustering result.
9. The intelligent parking space management system based on the Internet of things of claim 8, wherein: in the step B1, the data center is responsible for scheduling and calculating information, receiving parking expectation of a user and real-time parking lot parking space information and parameters in real time, the user uses a mobile terminal to perform searching by positioning or directly inputting a target parking lot, the data center receives a user request and then sends the user target parking lot and surrounding recommended parking lot information according to real-time parking lot information in the database, and the user sends the own parking expectation to the data center according to own requirements;
the data center receives user expectation and then carries out fuzzy matching, and accesses the ex-warehouse demand of the user, sets a time value of the same time period, matches the user with the ex-warehouse demand and the user with the parking demand in the same time period, sends parking space information to the matched user to be subjected to parking and warehousing when the ex-warehouse user leaves the parking space, meanwhile, when a target parking lot has a qualified parking space, the parking space information is directly pushed to the user, on the contrary, if the target parking lot is difficult to meet the requirement, the data center calculates the weighted value expected by the user and sorts the weighted value, and distributes the weighted value to the user needing to meet the requirement to the maximum.
10. The internet of things-based intelligent parking space management system according to claim 9, wherein: in the third step, after the parking spaces are matched based on the user expectation and the parking lot parameters, the optimal path of the vehicle running to the target parking space is further planned according to the actual environment and the user expectation
Step C1: constructing a global environment map model by adopting a grid decomposition method;
and step C2: initializing various parameters of the mixed ant colony algorithm;
and C3: the ants advance from the initial grid, when the next node is selected, the path finding ants are dispatched to explore the obstacle situation after the node, then the advancing direction is selected according to the pheromone concentration and distance heuristic information on the path and the distribution situation of the obstacles behind the node until the ants reach the end point, and the distribution of the pheromone concentration of the path is updated after the ants reach the end point;
and C4: after all ants finish the step C3, global pheromone is updated by utilizing an optimal worst reward and punishment system, an ant path with a better path is simultaneously selected, guided genetic algorithm variation is carried out, and a generated new optimal path is also included in the path set;
and C5: and C3 and C4 are repeated until the set iteration times are reached, path optimization is completed, and the calculated optimal path of the vehicle running to the target parking space is sent to a user receiving end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210871748.3A CN115440059A (en) | 2022-07-22 | 2022-07-22 | Wisdom parking stall management system based on thing networking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210871748.3A CN115440059A (en) | 2022-07-22 | 2022-07-22 | Wisdom parking stall management system based on thing networking |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115440059A true CN115440059A (en) | 2022-12-06 |
Family
ID=84241161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210871748.3A Pending CN115440059A (en) | 2022-07-22 | 2022-07-22 | Wisdom parking stall management system based on thing networking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115440059A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304357A (en) * | 2023-05-16 | 2023-06-23 | 松立控股集团股份有限公司 | Hospital parking lot recommendation method and system and electronic equipment |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004029899A (en) * | 2002-06-21 | 2004-01-29 | Amano Corp | Parking lot management system |
| CN105513414A (en) * | 2015-12-25 | 2016-04-20 | 江苏东大金智信息系统有限公司 | Parking-lot parking space predication and recommendation method based on real-time traffic query and cloud model |
| CN107842234A (en) * | 2017-11-03 | 2018-03-27 | 徐州德坤电气科技有限公司 | A kind of automatic three-dimensional parking garage system |
| CN108986527A (en) * | 2018-07-17 | 2018-12-11 | 新华三云计算技术有限公司 | A kind of parking position guiding method, device, system and electronic equipment |
| CN109242278A (en) * | 2018-08-20 | 2019-01-18 | 北京首钢自动化信息技术有限公司 | A kind of bicycle storage outbound dispatching method and device |
| CN111915923A (en) * | 2020-07-14 | 2020-11-10 | 宝胜系统集成科技股份有限公司 | Multi-mode high-density intelligent parking lot system and vehicle storing and taking method |
| CN112184014A (en) * | 2020-09-28 | 2021-01-05 | 江苏蒎圣屋工业科技有限公司 | Stereo garage parking system management method |
| CN112562408A (en) * | 2020-11-30 | 2021-03-26 | 北京停简单信息技术有限公司 | Global path planning method, device and system based on vehicle-road cooperation |
| CN112836699A (en) * | 2020-11-30 | 2021-05-25 | 爱泊车美好科技有限公司 | Long-time multi-target tracking-based berth entrance and exit event analysis method |
| CN112950984A (en) * | 2021-02-02 | 2021-06-11 | 陕西煤业新型能源科技股份有限公司 | Shared parking service method and system based on Internet of vehicles |
| CN114038202A (en) * | 2021-12-02 | 2022-02-11 | 华录易云科技有限公司 | Parking guidance system and method based on intelligent park traffic flow |
-
2022
- 2022-07-22 CN CN202210871748.3A patent/CN115440059A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004029899A (en) * | 2002-06-21 | 2004-01-29 | Amano Corp | Parking lot management system |
| CN105513414A (en) * | 2015-12-25 | 2016-04-20 | 江苏东大金智信息系统有限公司 | Parking-lot parking space predication and recommendation method based on real-time traffic query and cloud model |
| CN107842234A (en) * | 2017-11-03 | 2018-03-27 | 徐州德坤电气科技有限公司 | A kind of automatic three-dimensional parking garage system |
| CN108986527A (en) * | 2018-07-17 | 2018-12-11 | 新华三云计算技术有限公司 | A kind of parking position guiding method, device, system and electronic equipment |
| CN109242278A (en) * | 2018-08-20 | 2019-01-18 | 北京首钢自动化信息技术有限公司 | A kind of bicycle storage outbound dispatching method and device |
| CN111915923A (en) * | 2020-07-14 | 2020-11-10 | 宝胜系统集成科技股份有限公司 | Multi-mode high-density intelligent parking lot system and vehicle storing and taking method |
| CN112184014A (en) * | 2020-09-28 | 2021-01-05 | 江苏蒎圣屋工业科技有限公司 | Stereo garage parking system management method |
| CN112562408A (en) * | 2020-11-30 | 2021-03-26 | 北京停简单信息技术有限公司 | Global path planning method, device and system based on vehicle-road cooperation |
| CN112836699A (en) * | 2020-11-30 | 2021-05-25 | 爱泊车美好科技有限公司 | Long-time multi-target tracking-based berth entrance and exit event analysis method |
| CN112950984A (en) * | 2021-02-02 | 2021-06-11 | 陕西煤业新型能源科技股份有限公司 | Shared parking service method and system based on Internet of vehicles |
| CN114038202A (en) * | 2021-12-02 | 2022-02-11 | 华录易云科技有限公司 | Parking guidance system and method based on intelligent park traffic flow |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304357A (en) * | 2023-05-16 | 2023-06-23 | 松立控股集团股份有限公司 | Hospital parking lot recommendation method and system and electronic equipment |
| CN116304357B (en) * | 2023-05-16 | 2023-08-11 | 松立控股集团股份有限公司 | Hospital parking lot recommendation method and system and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hua et al. | Joint infrastructure planning and fleet management for one-way electric car sharing under time-varying uncertain demand | |
| Zhang et al. | Intelligent electric vehicle charging recommendation based on multi-agent reinforcement learning | |
| Lin et al. | SPA: Smart parking algorithm based on driver behavior and parking traffic predictions | |
| CN111985835A (en) | Distribution method for shared parking berths in residential area | |
| CN105702082A (en) | Method and system for booking parking stall and selecting parking lot based on App on mobile terminal | |
| Zhang et al. | A distribution model for shared parking in residential zones that considers the utilization rate and the walking distance | |
| CN112016812A (en) | Multi-unmanned aerial vehicle task scheduling method, system and storage medium | |
| Levin et al. | Parking infrastructure design for repositioning autonomous vehicles | |
| CN107680404A (en) | A kind of implementation method of the intelligent screening algorithm of shared stall system | |
| CN110363319B (en) | Resource allocation method, server, resource claim method and client | |
| Angelopoulos et al. | Incentivization schemes for vehicle allocation in one-way vehicle sharing systems | |
| CN115440059A (en) | Wisdom parking stall management system based on thing networking | |
| Duan et al. | Bi-level programming model for resource-shared parking lots allocation | |
| Wang et al. | Record: Joint real-time repositioning and charging for electric carsharing with dynamic deadlines | |
| CN114092176A (en) | Urban commuting regular bus planning method based on bus | |
| Wang et al. | Online operations strategies for automated multistory parking facilities | |
| Wang et al. | Towards accessible shared autonomous electric mobility with dynamic deadlines | |
| Liu et al. | Mining top-n high-utility operation patterns for taxi drivers | |
| Tran et al. | Adaptive passenger-finding recommendation system for taxi drivers with load balancing problem | |
| Benjaafar et al. | Human in the loop automation: Ride-hailing with remote (tele-) drivers | |
| CN112750298B (en) | Truck formation dynamic resource allocation method based on SMDP and DRL | |
| Di Nocera et al. | A Social-Aware Smart Parking Application. | |
| Rad et al. | A smart hybrid system for parking space reservation in VANET | |
| CN109949608A (en) | Stagger the time parking management system and method based on narrowband Internet of Things | |
| Sayarshad | Designing intelligent public parking locations for autonomous vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |