CN113223291B - System and method for predicting number of idle parking spaces in parking lot - Google Patents
System and method for predicting number of idle parking spaces in parking lot Download PDFInfo
- Publication number
- CN113223291B CN113223291B CN202110297639.0A CN202110297639A CN113223291B CN 113223291 B CN113223291 B CN 113223291B CN 202110297639 A CN202110297639 A CN 202110297639A CN 113223291 B CN113223291 B CN 113223291B
- Authority
- CN
- China
- Prior art keywords
- data
- parking lot
- idle
- parking
- parking spaces
- 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.)
- Active
Links
Classifications
-
- 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
- G08G1/0125—Traffic data processing
-
- 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
- G08G1/065—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
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the field of prediction of the number of parking spaces. Aiming at the problem that the existing prediction method is difficult to predict the number of the idle parking spaces in the parking lot in a longer period, the system and the method for predicting the number of the idle parking spaces in the parking lot are provided, and the system comprises a data acquisition module, a data preprocessing module, a data conversion module and an algorithm prediction module. According to the method, historical vehicle access data around a parking lot are firstly obtained, then the historical vehicle access data are cleaned, the cleaned data are converted into parking lot vacancy number information, finally the preprocessed data are input into a model, and the period items in the model and the required prediction length are adjusted to predict the trend. The method can predict the change of the number of the idle parking spaces of the parking lot for a long period of time in the future for a long period of time.
Description
Technical Field
The invention belongs to the field of prediction of the number of parking spaces, and particularly relates to a system and a method for predicting the number of idle parking spaces in a parking lot.
Background
With the acceleration of economic development and urban development, the utilization rate of automobiles is continuously improved, but facilities such as parking lots are limited, so that the problem of difficult parking is gradually highlighted. Since it is very difficult to increase the number of parking spaces in these hot spot areas in a short period of time, rational planning of the use of parking lots becomes a problem that is now urgently needed to be solved. If the number of the idle parking spaces in the parking lot can be accurately predicted, the method is favorable for playing a role in predicting excessive vehicles and even road jams in the area in advance, and corresponding response schemes are made for relieving, so that the method has an important role in relieving traffic jams in the area, effectively utilizing parking space resources and improving the utilization rate of the parking spaces.
In recent years, machine learning has been rapidly developed, and many people apply the machine learning to prediction of parking spaces, such as an artificial neural network, a Kalman filtering model and the like, and mainly realize fitting data characteristics through training of mass data, thereby achieving the purpose of prediction. However, a large amount of data is required for machine learning, under the condition that parking lot data are limited, the machine learning is difficult to achieve learning effect, so that the prediction accuracy is low, the prediction time is short, the prediction result is accurate when the prediction step length is only 5-10 minutes, and the accuracy is reduced along with the increase of the step length, so that the reference value of the prediction result is lower. Thus, the current prediction of free space generally has the following problems: the prediction time is short, and most neural network prediction results are only single prediction of the number of parking places, and the change of the number of idle parking places of the parking lot in the future for a long time cannot be predicted.
Disclosure of Invention
Aiming at the problem that the existing prediction method is difficult to predict the number of the idle parking spaces of the parking lot in a longer period of time, the invention provides a system and a method for predicting the number of the idle parking spaces of the parking lot.
The invention is realized by the following technical scheme:
a system for predicting the number of free spaces in a parking lot, the system comprising:
(1) The data acquisition module is used for acquiring record data of the vehicles entering and exiting the parking lot in a certain time period;
(2) The data preprocessing module is used for cleaning the acquired data and removing vehicle data with continuous parking time longer than 5 days and data with continuous parking time shorter than 10 minutes; merging data of the same vehicle, wherein the interval between the outgoing record and the incoming record is less than 10 minutes; removing data only recorded in or only recorded out;
(3) The data conversion module is used for converting the cleaned parking lot access record data into the number data of the idle parking spaces of the parking lot;
(4) The algorithm prediction module comprises a Holt-winter prediction module and an ARIMA prediction module which are arranged in parallel, wherein the two prediction modules can be independently called and are used for predicting the change trend of the number of the idle parking spaces in the parking lot and drawing a predicted idle vehicle number and historical data idle vehicle number graph.
The invention also provides a method for predicting the number of idle parking spaces in the parking lot, which is based on the prediction system and comprises the following steps:
s1, collecting vehicle access record data of a parking lot 2020.8.24-2020.9.18 all days;
s2, data cleaning is carried out on collected parking lot access record data, and the method comprises the following steps:
1) Removing extreme data: removing vehicle data with continuous parking time exceeding 5 days and data with continuous parking time less than 10 minutes;
2) Merging continuous data: merging the data of the same vehicle with the interval between the output record and the input record being less than 10 minutes, and merging the time of the data into one piece of data;
3) Removing abnormal data: removing data only recorded in or only recorded out;
s3, the number of the parking lots in unit time is used for subtracting the number of vehicles entering and the number of vehicles exiting, and the cleaned parking lot in-out record data is converted into the number of the parking lots in the idle state;
s4, inputting the historical data of the number of the idle parking spaces in the parking lot to a Holt-windows model, and training the Holt-windows model by using the historical data of the number of the idle parking spaces in the parking lot to determine smooth parameters alpha, beta and gamma of the Holt-windows model;
s5, predicting the change trend of the number of the idle parking spaces of the seasonal features of the idle parking spaces of the parking lot, and drawing a map of the number of the predicted idle parking spaces and the number of the idle parking spaces of historical data.
The invention also provides another method for predicting the number of idle parking spaces in the parking lot, which is based on the prediction system and comprises the following steps:
s1, collecting vehicle access record data of a certain parking lot for at least 4 weeks;
s2, data cleaning is carried out on collected parking lot access record data, and the method comprises the following steps:
1) Removing extreme data: removing vehicle data with a continuous parking time of more than 5 days, data with a continuous parking time of less than 10 minutes, and data that has been parked in a parking lot during non-test;
2) Merging continuous data: merging the data of the same vehicle with the interval between the output record and the input record being less than 10 minutes, and merging the time of the data into one piece of data;
3) Removing abnormal data: removing data only recorded in or only recorded out;
s3, the number of the parking lots in unit time is used for subtracting the number of vehicles entering and the number of vehicles exiting, and the cleaned parking lot in-out records are converted into the number data of the parking lots in idle parking spaces;
s4, drawing a historical data time sequence diagram: preliminarily judging whether the sequence fluctuates around a constant according to the graph characteristics, and if so, stabilizing the sequence; if not, the sequence is non-stationary;
s5, judging whether the original sequence is stable or not: if the sequence is not stable, the sequence is changed into a stable sequence through corresponding transformation, and the transformation method is as follows:
1) Linear trend: differentiating;
2) Index trend: taking logarithms and differentiating;
3) Seasonal: season difference;
s6, checking whether the sequence after transformation is stable: looking at a time sequence diagram, a correlation diagram and a unit root of the transformed sequence, checking whether the comprehensive analysis sequence is stable or not; if the time sequence is not stable, carrying out difference again, and recording the difference times of d when the time sequence is stable;
s7, drawing an autocorrelation coefficient and a partial autocorrelation coefficient graph, and determining a parameter autoregressive term number p and a moving average term number q;
s8, constructing an ARIMA model: and verifying the established ARIMA model, testing different combinations of p and q, selecting the optimal model parameters by applying AIC criteria, and inputting the historical data of the number of the idle parking spaces in the parking lot into the optimal ARIMA model to predict the number of the idle parking spaces in the parking lot according to the optimal ARIMA model.
The system and the method for predicting the number of the idle parking spaces in the parking lot are based on a prediction method of time sequence analysis, adopt a Holt-windows model or an ARIMA model, add historical data into the prediction model, and predict the number of the idle parking spaces in the parking lot in a long period of time under the condition of considering seasonal characteristics of the vehicle in and out conditions of the parking lot, so that the change of the number of the idle parking spaces in the parking lot in a long period of time in the future can be predicted.
Drawings
FIG. 1 is a block diagram of a system for predicting the number of idle parking spaces in a parking lot;
FIG. 2 is a predictive flow chart of example 1;
FIG. 3 is a diagram of the number of free spaces history data of embodiment 1;
FIG. 4 shows the prediction results of example 1;
FIG. 5 is a predictive flow chart of example 2;
FIG. 6 is an autocorrelation coefficient diagram of embodiment 2;
FIG. 7 is a partial autocorrelation coefficient diagram in example 2;
FIG. 8 shows the prediction results of example 2.
Detailed Description
The invention will be described in further detail with reference to specific embodiments and drawings.
Taking a parking lot of a certain office building as an example, the method for predicting the number of parking spaces in the parking lot provided by the invention is described in detail.
Example 1
The method for predicting the number of parking spaces in the parking lot based on the Holt-windows model is shown in fig. 2, and comprises the following steps:
s1, collecting parking lot access record data of 2020.8.24-2020.9.18 of a write tower all days;
s2, data cleaning is carried out on collected parking lot access record data, and the method comprises the following steps:
1) Removing extreme data: vehicle data parked for more than 5 days, data for less than ten minutes, and data that had been parked in the parking lot during non-test periods are removed.
2) Merging continuous data: and merging the data of the same vehicle, which are separated from the input record by less than ten minutes, and merging the time of the data into one piece of data.
3) Removing abnormal data: data that is only recorded in or only recorded out is removed.
S3, the number of the parking lots in unit time is used for subtracting the number of vehicles entering and the number of vehicles exiting, and the cleaned parking lot in-out records are converted into the number data of the parking lots in idle parking spaces;
and S4, selecting the serial_period=7×24=168 as repeated weekly data by observing the historical data of the number of idle parking spaces in the graph of FIG. 3.
S4, inputting the historical data of the number of the idle parking spaces in the parking lot and the serial_period=168 into a Holt-windows model, and training the Holt-windows model by using the historical data of the number of the idle parking spaces in the parking lot to determine smooth parameters alpha (horizontal item parameters), beta (trend item parameters) and gamma (season item parameters) of the Holt-windows model, wherein alpha is more than or equal to 0 and less than or equal to 1, beta is more than or equal to 0 and less than or equal to 1, and gamma is more than or equal to 0 and less than or equal to 1. Training the model by utilizing the idle parking space quantity data of the parking lot, and continuously iteratively adjusting the parameter values of the smooth parameters alpha, beta and gamma of the Holt-Winters model to enable the predicted data of the Holt-Winters model to be continuously approximate to real data.
S5, predicting the change trend of the number of the idle parking spaces of the seasonal features of the idle parking spaces of the parking lots of the office building, and drawing a map of the number of the predicted idle parking spaces and the number of the idle parking spaces of the historical data, wherein the result is shown in fig. 4. The change of the number of idle parking spaces in the future week is predicted, the model can carry out seasonal prediction according to the set period, the data of the vehicles on the Saturday and the Sunday are less and unstable, and the change of the data from Monday to friday is more stable and close to the actual data.
Example 2
An autoregressive moving average model (ARIMA) based method for predicting the number of parking spaces in a parking lot, as shown in FIG. 5, comprises the following steps:
s1, collecting parking lot access record data of 2020.8.24-2020.9.18 of a write tower all days;
s2, data cleaning is carried out on collected parking lot access record data, and the method comprises the following steps:
1) Removing extreme data: vehicle data parked for more than 5 days, data for less than ten minutes, and data that had been parked in the parking lot during non-test periods are removed.
2) Merging continuous data: and merging the data of the same vehicle, which are separated from the input record by less than ten minutes, and merging the time of the data into one piece of data.
3) Removing abnormal data: data that is only recorded in or only recorded out is removed.
S3, the number of the parking lots in unit time is used for subtracting the number of vehicles entering and the number of vehicles exiting, and the cleaned parking lot in-out records are converted into the number data of the parking lots in idle parking spaces;
s4, drawing a historical data time sequence diagram (figure 3): the basic trend of the parking lot data can be seen from the time sequence chart to belong to the fluctuation around the horizontal straight line, the seasonality is displayed, and the sequence is primarily judged to be stable according to the graph characteristics;
s5, the smooth sequence does not need to be differentiated, the difference times are 0, and the parameter d=0;
s6, an auto-correlation coefficient (ACF) graph (fig. 6) and a partial auto-correlation coefficient (PACF) graph (fig. 7) are plotted, and it can be seen from fig. 7 that ACF is a tail gradually tending to 0, and PACF has a coefficient of 0 after 4 steps, so the model is AR (4) or AR (5), i.e., ARMA (4, 0) or ARMA (5, 0). An alternative model ARMA (4, 1). Plus d=0 as determined in S5, so the model is ARIMA (4, 0) or ARIMA (5,0,0), an alternative model ARMA (4,0,1);
s8, constructing an ARIMA model: the established ARIMA model was validated and tested for different combinations of p and q, the best model parameters were selected using AIC criteria, and the results for the different combinations of p, q are shown in table 1, with the smallest AIC combination being selected, i.e., p=4, q=0 or p=4, q=1.
TABLE 1 AIC results for different combinations of p, q
| Combination value (p, q) | AIC |
| (4，0) | 6093.6049 |
| (4，1) | 6093.6049 |
| (5，0) | 6095.4917 |
| (5，1) | 6095.4917 |
S9, according to the optimal ARIMA model, the historical data of the number of the idle parking spaces in the parking lot are input into the optimal ARIMA model to predict the number of the idle parking spaces in the parking lot, and a prediction result is shown in FIG. 8. And predicting the change of the number of the idle parking spaces in the future week, and because the historical data of the parking lot is stable, the model can predict the number of the idle parking spaces according to the historical data information, the vehicle data of Saturday, saturday and sunday is less and unstable, and the prediction accuracy of the data from Monday to friday is high and basically coincides with the actual data.
The above examples are only illustrative of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention, and various modifications and improvements made by those skilled in the art to the technical solution of the present invention should fall within the scope of protection defined by the claims of the present invention without departing from the spirit of the present invention.
Claims (1)
1. The method is characterized by comprising a system for predicting the number of idle parking spaces in a parking lot, wherein the system comprises (1) a data acquisition module for acquiring recorded data of vehicles entering and exiting the parking lot in a certain time period;
(2) A data preprocessing module; the module is used for cleaning the collected data;
(3) The data conversion module is used for converting the cleaned parking lot access record data into the number data of the idle parking spaces of the parking lot;
(4) The algorithm prediction module comprises a Holt-windows prediction module and an ARIMA prediction module which are arranged in parallel, wherein the two prediction modules can be independently called and are used for predicting the change trend of the number of idle parking spaces in a parking lot and drawing a predicted idle vehicle number and historical data idle vehicle number graph;
the method comprises the following steps:
s1, collecting vehicle access record data of a certain parking lot for at least 4 weeks;
s2, data cleaning is carried out on collected parking lot access record data, and the method comprises the following steps:
1) Removing extreme data: removing vehicle data with continuous parking time exceeding 5 days and data with continuous parking time less than 10 minutes;
2) Merging continuous data: merging the data of the same vehicle with the interval between the output record and the input record being less than 10 minutes, and merging the time of the data into one piece of data;
3) Removing abnormal data: removing data only recorded in or only recorded out;
s3, the number of the parking lots in unit time is used for subtracting the number of vehicles entering and the number of vehicles exiting, and the cleaned parking lot in-out record data is converted into the number of the parking lots in the idle state;
s4, inputting the historical data of the number of the idle parking spaces in the parking lot to a Holt-windows model, and training the Holt-windows model by using the historical data of the number of the idle parking spaces in the parking lot to determine smooth parameters alpha, beta and gamma of the Holt-windows model;
s5, predicting the change trend of the number of the idle parking spaces of the seasonal features of the idle parking spaces of the parking lot, and drawing a map of the number of the predicted idle parking spaces and the number of the idle parking spaces of historical data;
or S4, drawing a historical data timing diagram: preliminarily judging whether the sequence is stable or not according to the graph characteristics;
s5, judging whether the original sequence is stable or not: if the sequence is not stable, the sequence is changed into a stable sequence through corresponding transformation, and the transformation method is as follows:
1) Linear trend: differentiating;
2) Index trend: taking logarithms and differentiating;
3) Seasonal: season difference;
s6, checking whether the sequence after transformation is stable: looking at a time sequence diagram, a correlation diagram and a unit root of the transformed sequence, checking whether the comprehensive analysis sequence is stable or not; if the time sequence is not stable, carrying out difference again, and recording the difference times of d when the time sequence is stable;
s7, drawing an autocorrelation coefficient and a partial autocorrelation coefficient graph, and determining a parameter autoregressive term number p and a moving average term number q;
s8, constructing an ARIMA model: and verifying the established ARIMA model, testing different combinations of p and q, selecting the optimal model parameters by applying AIC criteria, and inputting the historical data of the number of the idle parking spaces in the parking lot into the optimal ARIMA model to predict the number of the idle parking spaces in the parking lot according to the optimal ARIMA model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110297639.0A CN113223291B (en) | 2021-03-19 | 2021-03-19 | System and method for predicting number of idle parking spaces in parking lot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110297639.0A CN113223291B (en) | 2021-03-19 | 2021-03-19 | System and method for predicting number of idle parking spaces in parking lot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113223291A CN113223291A (en) | 2021-08-06 |
| CN113223291B true CN113223291B (en) | 2023-10-20 |
Family
ID=77083808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110297639.0A Active CN113223291B (en) | 2021-03-19 | 2021-03-19 | System and method for predicting number of idle parking spaces in parking lot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113223291B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115472034A (en) * | 2022-07-20 | 2022-12-13 | 中国交通信息科技集团有限公司 | Layered cloud architecture parking operation management system |
| CN115019551B (en) * | 2022-08-01 | 2022-11-15 | 阿里巴巴（中国）有限公司 | Correction method of redundant bits of field library, training method and device of redundant bit prediction model |
| CN115050188B (en) * | 2022-08-15 | 2022-10-28 | 中交一公局第六工程有限公司 | Method for predicting remaining parking spaces of indoor parking lot |
| CN117649781B (en) * | 2024-01-30 | 2024-04-16 | 泰安市东信智联信息科技有限公司 | Intelligent parking monitoring data intelligent processing method based on data fusion |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2002228814B2 (en) * | 2000-11-09 | 2007-05-03 | International Business Machines Corporation | System and method for building a time series model |
| CN105512447A (en) * | 2014-09-26 | 2016-04-20 | 山西云智慧科技股份有限公司 | Bus passenger volume prediction method based on Holt-Winters model |
| CN107134170A (en) * | 2017-07-04 | 2017-09-05 | 北京悦畅科技有限公司 | A kind for the treatment of method and apparatus of parking position information of park |
| CN107146462A (en) * | 2017-06-23 | 2017-09-08 | 武汉大学 | A kind of idle parking stall number long-term prediction method in parking lot |
| CN107239846A (en) * | 2016-03-29 | 2017-10-10 | 中兴通讯股份有限公司 | parking lot berth prediction processing method and device |
| CN107798871A (en) * | 2017-10-27 | 2018-03-13 | 云南大学 | A kind of freeway toll station traffic flow forecasting method and system |
| CN108536652A (en) * | 2018-03-15 | 2018-09-14 | 浙江大学 | A kind of short-term vehicle usage amount prediction technique based on arma modeling |
| CN109492808A (en) * | 2018-11-07 | 2019-03-19 | 浙江科技学院 | A kind of parking garage residue parking stall prediction technique |
-
2021
- 2021-03-19 CN CN202110297639.0A patent/CN113223291B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2002228814B2 (en) * | 2000-11-09 | 2007-05-03 | International Business Machines Corporation | System and method for building a time series model |
| CN105512447A (en) * | 2014-09-26 | 2016-04-20 | 山西云智慧科技股份有限公司 | Bus passenger volume prediction method based on Holt-Winters model |
| CN107239846A (en) * | 2016-03-29 | 2017-10-10 | 中兴通讯股份有限公司 | parking lot berth prediction processing method and device |
| CN107146462A (en) * | 2017-06-23 | 2017-09-08 | 武汉大学 | A kind of idle parking stall number long-term prediction method in parking lot |
| CN107134170A (en) * | 2017-07-04 | 2017-09-05 | 北京悦畅科技有限公司 | A kind for the treatment of method and apparatus of parking position information of park |
| CN107798871A (en) * | 2017-10-27 | 2018-03-13 | 云南大学 | A kind of freeway toll station traffic flow forecasting method and system |
| CN108536652A (en) * | 2018-03-15 | 2018-09-14 | 浙江大学 | A kind of short-term vehicle usage amount prediction technique based on arma modeling |
| CN109492808A (en) * | 2018-11-07 | 2019-03-19 | 浙江科技学院 | A kind of parking garage residue parking stall prediction technique |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113223291A (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113223291B (en) | System and method for predicting number of idle parking spaces in parking lot | |
| CN106503840B (en) | Available parking space prediction method and system for parking lot | |
| CN116646933B (en) | Big data-based power load scheduling method and system | |
| Thomas et al. | Predictions of urban volumes in single time series | |
| CN106295888B (en) | Method for determining shared time window of public building parking lot configuration based on measured data | |
| CN109376935B (en) | Bus passenger flow time interval combined prediction method based on neural network | |
| JP3352153B2 (en) | Water distribution flow prediction device | |
| CN109697854A (en) | The urban road traffic state assessment method of various dimensions | |
| CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
| CN110852476A (en) | Passenger flow prediction method and device, computer equipment and storage medium | |
| CN101187943A (en) | Automatic update system, automatic updating method, and program therefor | |
| Fidalgo et al. | Load forecasting performance enhancement when facing anomalous events | |
| CN110400462B (en) | Track traffic passenger flow monitoring and early warning method and system based on fuzzy theory | |
| CN115830848A (en) | Shared parking space intelligent distribution system and method based on LSTM model | |
| Srinivasan et al. | Short term load forecasting using multiple correlation models | |
| CN115375205A (en) | Method, device and equipment for determining water user portrait | |
| CN115953186A (en) | Network appointment demand pattern recognition and short-time demand prediction method | |
| CN111985731B (en) | Method and system for predicting number of people at urban public transport station | |
| CN113821547A (en) | Rapid and efficient short-term parking lot occupancy prediction method and system and storage medium | |
| Ghassemi et al. | Optimal surrogate and neural network modeling for day-ahead forecasting of the hourly energy consumption of university buildings | |
| CN111680888A (en) | Method for determining road network capacity based on RFID data | |
| CN109523788B (en) | Road section operation effect evaluation method | |
| JP2003224931A (en) | Distribution system load estimating device | |
| Tu et al. | Analysis and forecast of passenger flow based on public transportation IC card and GPS data | |
| CN115188192B (en) | Automatic control parking system and method based on travel prediction |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |