CN114873387A - Elevator energy-saving dispatching system and method based on reinforcement learning algorithm - Google Patents
Elevator energy-saving dispatching system and method based on reinforcement learning algorithm Download PDFInfo
- Publication number
- CN114873387A CN114873387A CN202210386594.9A CN202210386594A CN114873387A CN 114873387 A CN114873387 A CN 114873387A CN 202210386594 A CN202210386594 A CN 202210386594A CN 114873387 A CN114873387 A CN 114873387A
- Authority
- CN
- China
- Prior art keywords
- elevator
- car
- reinforcement learning
- waiting
- personnel
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000002787 reinforcement Effects 0.000 title claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 36
- 230000008569 process Effects 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 14
- 230000006399 behavior Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims 1
- 239000002994 raw material Substances 0.000 claims 1
- 230000001174 ascending effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 208000035473 Communicable disease Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/02—Control systems without regulation, i.e. without retroactive action
- B66B1/06—Control systems without regulation, i.e. without retroactive action electric
- B66B1/14—Control systems without regulation, i.e. without retroactive action electric with devices, e.g. push-buttons, for indirect control of movements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/34—Details, e.g. call counting devices, data transmission from car to control system, devices giving information to the control system
- B66B1/46—Adaptations of switches or switchgear
- B66B1/468—Call registering systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B2201/00—Aspects of control systems of elevators
- B66B2201/40—Details of the change of control mode
- B66B2201/46—Switches or switchgear
- B66B2201/4607—Call registering systems
- B66B2201/4638—Wherein the call is registered without making physical contact with the elevator system
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B2201/00—Aspects of control systems of elevators
- B66B2201/40—Details of the change of control mode
- B66B2201/46—Switches or switchgear
- B66B2201/4607—Call registering systems
- B66B2201/4638—Wherein the call is registered without making physical contact with the elevator system
- B66B2201/4646—Wherein the call is registered without making physical contact with the elevator system using voice recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B50/00—Energy efficient technologies in elevators, escalators and moving walkways, e.g. energy saving or recuperation technologies
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Elevator Control (AREA)
Abstract
The invention discloses an elevator energy-saving dispatching method based on a reinforcement learning algorithm, which comprises the following steps of S1, obtaining an initial layer and a target layer of elevator waiting personnel and elevator taking personnel through face recognition, voice recognition and gesture recognition; s2, obtaining the position of the car; s3, obtaining an optimal scheduling scheme by using a reinforcement learning algorithm according to the elevator taking routes of elevator taking personnel and elevator waiting personnel and the positions of the cars; and S4, driving the lift car according to the optimal scheduling scheme, and broadcasting the motion condition of the lift car to lift waiting personnel and lift taking personnel. The invention improves the running efficiency of the lift car.
Description
Technical Field
The invention relates to the field of elevator control, in particular to an elevator energy-saving dispatching system and method based on a reinforcement learning algorithm.
Background
Most of traditional elevator dispatching depends on information instructions such as manual floor adding of a user through an elevator dispatching button, information communication with the user is lacked, and therefore the elevator dispatching method is faced with an obvious dispatching short board. For example, when the elevator runs at the first floor in the early peak, more people flow is gathered, when a plurality of cars synchronously receive an ascending request, one car responds, and the rest cars do not respond, so that people flow is detained, and precious time is wasted. The control system of part elevator is gone against its way, as long as the car does not have other instructions, all respond to the ascending and descending instruction of floor, can cause one person to go downstairs, but have many cars to respond, obviously wasted the electric energy, increaseed the loss of elevator.
China is the largest elevator using country in the world, and in recent years, the number of high-rise buildings in many cities is increased dramatically, the population density is high, the elevator load is large, and the defects of non-intelligent elevator dispatching are highlighted. Therefore, how to reduce energy consumption and maintenance cost by increasing the information communication between the elevator and the user is an urgent problem to be solved at present.
Disclosure of Invention
The invention aims to provide an elevator energy-saving dispatching method based on a reinforcement learning algorithm so as to improve the running efficiency of an elevator.
In order to achieve the purpose, the invention provides the following technical scheme: an elevator energy-saving dispatching method based on a reinforcement learning algorithm comprises the following steps,
s1, acquiring the starting layer and the target layer of the elevator waiting personnel and the elevator taking personnel through face recognition, voice recognition and gesture recognition;
s2, obtaining the position of the car;
s3, obtaining an optimal scheduling scheme by using a reinforcement learning algorithm according to the elevator taking routes of elevator taking personnel and elevator waiting personnel and the positions of the cars;
s4, driving the lift car according to the optimal scheduling scheme, and broadcasting the motion condition of the lift car to lift waiting personnel and lift taking personnel;
wherein, the S3 process is concretely,
s301, initializationWeight and current state s of neural network t ;
S302, observing the state S at the time t t And calculating the comprehensive waiting cost R t The calculation formula is as follows,
wherein R is w To average waiting time cost, R r For averaging the time cost of taking the elevator, R c Cost for number of stops; r w 、R r 、R c The calculation formula of (a) is as follows,
wherein p is the number of passengers waiting for the elevator and t i For the time of arrival of the passenger, N is the number of elevators, C i The number of times of stopping the elevator;
s303, using the current state behavior function value Q t Selecting and selecting ladder dispatching scheme u t Will state s t Substituting into the neural network to forward calculate the state behavior value function minQ (s, u), the calculation formula of the state behavior value function is as follows,
ΔQ t+1 (s t ,u t )=Q t (s t ,u t )+α[R t+1 +γminQ t (s t+1 ,u)-Q t (s t ,u t )]
in the formula, alpha is the learning rate of reinforcement learning and gradually attenuates in the learning process; gamma is a discount factor of the cost, and gamma belongs to (0, 1);
s304, calculating new function value Q by using reinforcement learning updating algorithm t ;
S305, using Q t Scheme u for selecting elevator dispatching t ;
And S306, updating the weight and the state of the neural network, and repeating the steps until an optimal scheduling scheme is obtained.
According to the scheme, the face recognition process in the S1 specifically comprises the steps of collecting a face image through a camera, quantizing the face image into vectors of a plurality of dimensions, and determining a face through comparison of the vectors of the plurality of dimensions and the quantized multidimensional vectors in the existing data set; and if the existing data set does not have a corresponding vector, adding the multidimensional vector into the existing data set and forming a new data set.
According to the scheme, the voice recognition process in the S1 specifically includes that voice is collected through a microphone, the voice is subjected to noise reduction processing and then uploaded to a voice recognition cloud server, and the voice recognition cloud server converts voice information into semantic texts.
According to the scheme, the gesture recognition process in the S1 is specifically that the gesture image is intercepted through the camera, and the target floor is judged according to the number of fingers in the gesture image.
According to the scheme, the car is driven according to the optimal scheduling scheme in S4,
s401, the control module acquires the position of the car through a sensor module arranged on the car and transmits the position information of the car to an upper computer;
s402, the upper computer sends an elevator operation instruction to the control module according to the optimal scheduling scheme, and the control module operates the car to operate according to the instruction;
and S403, if the scheduling scheme is changed, the upper computer sends a new elevator operation instruction to the control module.
According to above-mentioned scheme, report in the S4 and specifically carry out pronunciation and picture through setting up speaker and the display screen in waiting the terraced region and car and report.
An elevator energy-saving dispatching system based on the reinforcement learning algorithm for realizing the elevator energy-saving dispatching method based on the reinforcement learning algorithm comprises a car identification module, a control module and a dispatching module, wherein the car identification module comprises a camera and a microphone which are arranged in a car and is used for acquiring the number of people taking the elevator and a destination floor;
the elevator calling identification module comprises a camera and a microphone which are arranged in an elevator waiting area and is used for acquiring the number of people waiting for the elevator and a destination layer;
the broadcasting panel is arranged in the elevator car and in the elevator waiting area, comprises a display screen and a loudspeaker and is used for broadcasting the motion condition of the elevator car to elevator taking personnel and elevator waiting personnel;
the upper computer is used for receiving the number of elevator taking personnel and elevator waiting personnel and a destination floor, appointing an optimal scheduling scheme according to the number of elevator taking personnel and elevator waiting personnel, sending an elevator operation instruction to the control module according to the optimal scheduling scheme, receiving the position information of the elevator car from the control module and forwarding the position information to the broadcasting panel;
the control module is used for controlling the car to move and stop according to the elevator operation instruction, receiving the car position information from the sensor module and transmitting the car position information to the upper computer;
and the sensor module is used for acquiring the position information of the car.
A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing the steps of the reinforcement learning algorithm based elevator energy saving dispatching method as described above.
A readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the reinforcement learning algorithm based elevator energy saving dispatching method as described above.
The invention has the beneficial effects that: the target layer of the elevator waiting personnel and the elevator taking personnel is obtained through voice recognition and gesture recognition, and compared with the traditional buttons, frequent contact of the personnel is avoided, and then the spread risk of partial infectious diseases is reduced. Through a reinforcement learning algorithm, an optimal scheduling scheme of the elevator car is obtained according to the operation condition of the elevator car, the distribution condition of elevator waiting personnel and the target floors of the elevator taking and waiting personnel, so that the waiting time of the elevator waiting personnel is reduced, the operation efficiency of the elevator car is improved, and the failure rate and the loss degree of the elevator are reduced to a certain extent due to the fact that unnecessary back-and-forth operation of the elevator car is reduced.
Drawings
Fig. 1 is a schematic diagram of an elevator energy-saving dispatching system based on a reinforcement learning algorithm according to an embodiment of the invention;
fig. 2 is a flowchart of an elevator energy-saving dispatching method based on a reinforcement learning algorithm according to an embodiment of the invention;
FIG. 3 is a flowchart of a reinforcement learning algorithm according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings of the embodiments of the present disclosure. It is to be understood that the described embodiments are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the disclosure without any inventive step, are within the scope of protection of the disclosure.
Referring to fig. 2, an energy-saving elevator dispatching method based on reinforcement learning algorithm comprises the following steps,
s1, acquiring the starting layer and the target layer of the elevator waiting personnel and the elevator taking personnel through face recognition, voice recognition and gesture recognition;
s2, obtaining the position of the car;
s3, obtaining an optimal scheduling scheme by using a reinforcement learning algorithm according to the elevator taking routes of elevator taking personnel and elevator waiting personnel and the positions of the cars;
s4, driving the lift car according to the optimal scheduling scheme, and broadcasting the motion condition of the lift car to lift waiting personnel and lift taking personnel;
wherein, the S3 process is concretely,
s301, initializing weight and current state S of neural network t ;
S302, observing the state S at the time t t And calculating the comprehensive waiting cost R t The calculation formula is as follows,
wherein R is w To average waiting time cost, R r For averaging the time cost of taking the elevator, R c Cost for number of stops; r w 、R r 、R c The calculation formula of (a) is as follows,
wherein p is the number of passengers waiting for the elevator and t i For the time of arrival of the passenger, N is the number of elevators, C i The number of times of stopping the elevator;
s303, using the current state behavior function value Q t Selecting and selecting ladder dispatching scheme u t Will state s t Substituting into the neural network to forward calculate the state behavior value function minQ (s, u), the calculation formula of the state behavior value function is as follows,
ΔQ t+1 (s t ,u t )=Q t (s t ,u t )+α[R t+1 +γminQ t (s t+1 ,u)-Q t (s t ,u t )]
in the formula, alpha is the learning rate of reinforcement learning and gradually attenuates in the learning process; gamma is a discount factor of the cost, and gamma belongs to (0, 1);
s304, calculating new function value Q by using reinforcement learning updating algorithm t ;
S305, using Q t Scheme u for selecting elevator dispatching t ;
And S306, updating the weight and the state of the neural network, and repeating the steps until an optimal scheduling scheme is obtained.
Further, the face recognition process in S1 is specifically that a face image is acquired by a camera, the face image is quantized into vectors of a plurality of dimensions, and a face is determined by comparing the quantized vectors with the quantized multidimensional vectors in the existing dataset; and if the existing data set does not have a corresponding vector, adding the multidimensional vector into the existing data set and forming a new data set.
Further, in the voice recognition process in S1, specifically, the voice is collected by a microphone, and is uploaded to the voice recognition cloud server after being subjected to noise reduction processing, and the voice recognition cloud server converts the voice information into a semantic text.
Further, in the gesture recognition process in S1, the gesture image is captured by the camera, and the destination floor is determined according to the number of fingers in the gesture image.
Further, driving the car according to the optimal scheduling scheme in S4 is specifically,
s401, the control module acquires the position of the car through a sensor module arranged on the car and transmits the position information of the car to an upper computer;
s402, the upper computer sends an elevator operation instruction to the control module according to the optimal scheduling scheme, and the control module operates the car to operate according to the instruction;
and S403, if the scheduling scheme is changed, the upper computer sends a new elevator operation instruction to the control module.
Further, report in S4 and specifically carry out pronunciation and picture through setting up speaker and the display screen in waiting the terraced region and car inside and report.
Referring to fig. 1, an elevator energy-saving dispatching system based on a reinforcement learning algorithm for implementing the elevator energy-saving dispatching method based on the reinforcement learning algorithm includes a car identification module, including a camera and a microphone arranged inside a car, for acquiring the number of people taking the elevator and a destination floor;
the elevator calling identification module comprises a camera and a microphone which are arranged in an elevator waiting area and is used for acquiring the number of people waiting for the elevator and a destination layer;
the broadcasting panel is arranged in the elevator car and in the elevator waiting area, comprises a display screen and a loudspeaker and is used for broadcasting the motion condition of the elevator car to elevator taking personnel and elevator waiting personnel;
the upper computer is used for receiving the number of elevator taking personnel and elevator waiting personnel and a destination floor, appointing an optimal scheduling scheme according to the number of elevator taking personnel and elevator waiting personnel, sending an elevator operation instruction to the control module according to the optimal scheduling scheme, receiving the position information of the elevator car from the control module and forwarding the position information to the broadcasting panel;
the control module is used for controlling the car to move and stop according to the elevator operation instruction, receiving the car position information from the sensor module and transmitting the car position information to the upper computer;
and the sensor module is used for acquiring the position information of the car.
A computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing the steps of the reinforcement learning algorithm based elevator energy saving dispatching method as described above.
A readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the reinforcement learning algorithm based elevator energy saving dispatching method as described above.
An example of scheduling using the above method and system is as follows:
the initial floors of the elevator 1 and the elevator 2 are on the 4 th floor, at the moment, 9 persons appear on the 4 th floor, the target floors are all the 1 st floor, 9 persons appear on the 3 rd floor, and the target floor is also the 1 st floor. Then 6 people appear in the 2 nd floor, and the destination floor is also the 1 st floor.
The allocation flow of the traditional elevator is as follows: and the elevator 1 and the elevator 2 go to the 3 th floor after the passengers are loaded on the 4 th floor, go to the 2 nd floor after the passengers are loaded on the 3 rd floor, and finally go to the 1 st floor after the passengers are loaded on the 2 nd floor.
The allocation flow of the intelligent elevator is as follows: after confirming the elevator waiting conditions of the 3 rd and 4 th floors, the elevator calling system uploads the data to the upper computer, the upper computer calculates the comprehensive elevator waiting cost to obtain a state behavior value function, and a dispatching scheme is given. Then, the calling system uploads the elevator waiting condition of the 2-stories to the upper computer, the upper computer updates the weight, and the comprehensive elevator waiting cost and state behavior value function are recalculated, so that the following dispatching scheme is finally obtained: elevator 1 goes to floor 2 after loading passengers at floor 4, elevator 2 goes directly to floor 3 to load passengers, then goes to floor 2, and both elevators go to floor 1 after loading passengers at floor 2.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. An elevator energy-saving dispatching method based on a reinforcement learning algorithm is characterized in that: comprises the following steps of (a) carrying out,
s1, acquiring the starting layer and the target layer of the elevator waiting personnel and the elevator taking personnel through face recognition, voice recognition and gesture recognition;
s2, obtaining the position of the car;
s3, obtaining an optimal scheduling scheme by using a reinforcement learning algorithm according to the elevator taking routes of elevator taking personnel and elevator waiting personnel and the positions of the cars;
s4, driving the lift car according to the optimal scheduling scheme, and broadcasting the motion condition of the lift car to lift waiting personnel and lift taking personnel;
wherein, the S3 process is concretely,
s301, initializing weight and current state S of neural network t ;
S302, observing the state S at the time t t And calculating the comprehensive waiting cost R t The calculation formula is as follows,
wherein R is w To average the waiting time cost, R r For averaging the time cost of taking the elevator, R c Cost for number of stops; r w 、R r 、R c The calculation formula of (a) is as follows,
wherein p is the number of passengers waiting for the elevator and t i For the time of arrival of the passenger, N is the number of elevators, C i The number of times of stopping the elevator;
s303, using the current state behavior function value Q t Selecting and selecting ladder dispatching scheme u t Will state s t Substituting into the neural network to forward calculate the state behavior value function minQ (s, u), the calculation formula of the state behavior value function is as follows,
ΔQ t+1 (s t ,u t )=Q t (s t ,u t )+α[R t+1 +γminQ t (s t+1 ,u)-Q t (s t ,u t )]
in the formula, alpha is the learning rate of reinforcement learning and gradually attenuates in the learning process; gamma is a discount factor of the cost, and gamma belongs to (0, 1);
s304, calculating new function value Q by using reinforcement learning updating algorithm t ;
S305, using Q t Scheme u for selecting elevator dispatching t ;
And S306, updating the weight and the state of the neural network, and repeating the steps until an optimal scheduling scheme is obtained.
2. The elevator energy-saving dispatching method based on the reinforcement learning algorithm as claimed in claim 1, characterized in that: the face recognition process in the S1 is specifically to collect a face image through a camera, quantize the face image into vectors of a plurality of dimensions, and determine a face through comparison with the quantized multidimensional vectors in the existing data set; and if the existing data set does not have a corresponding vector, adding the multidimensional vector into the existing data set and forming a new data set.
3. The elevator energy-saving dispatching method based on the reinforcement learning algorithm as claimed in claim 1, characterized in that: the voice recognition process in S1 is specifically that voice is collected by a microphone, and the voice is uploaded to a voice recognition cloud server after noise reduction processing, and the voice recognition cloud server converts voice information into semantic text.
4. The elevator energy-saving dispatching method based on the reinforcement learning algorithm as claimed in claim 1, characterized in that: the gesture recognition process in S1 is specifically to capture a gesture image by a camera, and determine a destination floor according to the number of fingers in the gesture image.
5. The elevator energy-saving dispatching method based on the reinforcement learning algorithm as claimed in claim 1, characterized in that: driving the car according to the optimal scheduling scheme in S4 is embodied in that,
s401, the control module acquires the position of the car through a sensor module arranged on the car and transmits the position information of the car to an upper computer;
s402, the upper computer sends an elevator operation instruction to the control module according to the optimal scheduling scheme, and the control module operates the car to operate according to the instruction;
and S403, if the scheduling scheme is changed, the upper computer sends a new elevator operation instruction to the control module.
6. The elevator energy-saving dispatching method based on the reinforcement learning algorithm as claimed in claim 1, characterized in that: broadcast in S4 and specifically carry out pronunciation and picture through setting up speaker and the display screen in waiting the terraced region and car inside and report.
7. An elevator energy-saving dispatching system based on a reinforcement learning algorithm for realizing the elevator energy-saving dispatching method based on the reinforcement learning algorithm of any one of claims 1-6, which is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the elevator car identification module comprises a camera and a microphone which are arranged in the elevator car and is used for acquiring the number of people taking the elevator and a destination floor;
the elevator calling identification module comprises a camera and a microphone which are arranged in an elevator waiting area and is used for acquiring the number of people waiting for the elevator and a destination layer;
the broadcasting panel is arranged in the elevator car and in the elevator waiting area, comprises a display screen and a loudspeaker and is used for broadcasting the motion condition of the elevator car to elevator taking personnel and elevator waiting personnel;
the upper computer is used for receiving the number of elevator taking personnel and elevator waiting personnel and a destination floor, appointing an optimal scheduling scheme according to the number of elevator taking personnel and elevator waiting personnel, sending an elevator operation instruction to the control module according to the optimal scheduling scheme, receiving the position information of the elevator car from the control module and forwarding the position information to the broadcasting panel;
the control module is used for controlling the car to move and stop according to the elevator operation instruction, receiving the car position information from the sensor module and transmitting the car position information to the upper computer;
and the sensor module is used for acquiring the position information of the car.
8. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein: the processor, when executing the computer program, implements the steps of the reinforcement learning algorithm-based elevator energy-saving dispatching method of any one of claims 1-6.
9. A readable storage medium having stored thereon a computer program, characterized in that: the computer program when being executed by a processor realizes the steps of the reinforcement learning algorithm based elevator energy-saving dispatching method of any one of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210386594.9A CN114873387B (en) | 2022-04-12 | 2022-04-12 | Energy-saving elevator dispatching system and method based on reinforcement learning algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210386594.9A CN114873387B (en) | 2022-04-12 | 2022-04-12 | Energy-saving elevator dispatching system and method based on reinforcement learning algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114873387A true CN114873387A (en) | 2022-08-09 |
CN114873387B CN114873387B (en) | 2024-04-16 |
Family
ID=82669133
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210386594.9A Active CN114873387B (en) | 2022-04-12 | 2022-04-12 | Energy-saving elevator dispatching system and method based on reinforcement learning algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114873387B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116443682A (en) * | 2023-06-20 | 2023-07-18 | 兰州理工大学 | Intelligent elevator control system |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007084237A (en) * | 2005-09-21 | 2007-04-05 | Toshiba Elevator Co Ltd | Elevator |
CN101403891A (en) * | 2008-11-14 | 2009-04-08 | 天津大学 | Elevator group control energy-saving scheduling method |
JP2014189338A (en) * | 2013-03-26 | 2014-10-06 | Hitachi Ltd | Elevator system |
JP2014237493A (en) * | 2013-06-06 | 2014-12-18 | 株式会社日立製作所 | Elevator system |
CN109264518A (en) * | 2018-11-13 | 2019-01-25 | 海南师范大学 | Elevator with multiple compartments Optimized Operation design method |
CN109956376A (en) * | 2019-01-28 | 2019-07-02 | 辽宁工业大学 | The intelligent group control device and its control method of multiple elevator |
CN112279025A (en) * | 2020-10-29 | 2021-01-29 | 湖南大举信息科技有限公司 | Dynamic hierarchical control method for elevator group |
CN112299168A (en) * | 2020-10-29 | 2021-02-02 | 湖南大举信息科技有限公司 | Dynamic zone control method for elevator group |
CN113086789A (en) * | 2021-03-31 | 2021-07-09 | 佛山兴宏工程科技有限责任公司 | Intelligent building control system and control method |
CN113526272A (en) * | 2021-07-08 | 2021-10-22 | 日立楼宇技术(广州)有限公司 | Elevator group control system and elevator group control equipment |
CN113682908A (en) * | 2021-08-31 | 2021-11-23 | 电子科技大学 | Intelligent scheduling method based on deep learning |
CN114030960A (en) * | 2021-05-10 | 2022-02-11 | 永大电梯设备(中国)有限公司 | Elevator destination layer group control system |
-
2022
- 2022-04-12 CN CN202210386594.9A patent/CN114873387B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007084237A (en) * | 2005-09-21 | 2007-04-05 | Toshiba Elevator Co Ltd | Elevator |
CN101403891A (en) * | 2008-11-14 | 2009-04-08 | 天津大学 | Elevator group control energy-saving scheduling method |
JP2014189338A (en) * | 2013-03-26 | 2014-10-06 | Hitachi Ltd | Elevator system |
JP2014237493A (en) * | 2013-06-06 | 2014-12-18 | 株式会社日立製作所 | Elevator system |
CN109264518A (en) * | 2018-11-13 | 2019-01-25 | 海南师范大学 | Elevator with multiple compartments Optimized Operation design method |
CN109956376A (en) * | 2019-01-28 | 2019-07-02 | 辽宁工业大学 | The intelligent group control device and its control method of multiple elevator |
CN112279025A (en) * | 2020-10-29 | 2021-01-29 | 湖南大举信息科技有限公司 | Dynamic hierarchical control method for elevator group |
CN112299168A (en) * | 2020-10-29 | 2021-02-02 | 湖南大举信息科技有限公司 | Dynamic zone control method for elevator group |
CN113086789A (en) * | 2021-03-31 | 2021-07-09 | 佛山兴宏工程科技有限责任公司 | Intelligent building control system and control method |
CN114030960A (en) * | 2021-05-10 | 2022-02-11 | 永大电梯设备(中国)有限公司 | Elevator destination layer group control system |
CN113526272A (en) * | 2021-07-08 | 2021-10-22 | 日立楼宇技术(广州)有限公司 | Elevator group control system and elevator group control equipment |
CN113682908A (en) * | 2021-08-31 | 2021-11-23 | 电子科技大学 | Intelligent scheduling method based on deep learning |
Non-Patent Citations (3)
Title |
---|
蔡晓霞;俞立峰;: "群控电梯目的层调度***的设计", 浙江工业大学学报, no. 01, 25 February 2015 (2015-02-25) * |
郎曼;李国勇;徐晨晨;: "电梯群控***的节能调度优化仿真", 计算机仿真, no. 02, 15 February 2017 (2017-02-15) * |
陈海啸;杨马英;: "目的层预约与多智能体协调的电梯群控调度方法", 计算机***应用, no. 07, 15 July 2012 (2012-07-15) * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116443682A (en) * | 2023-06-20 | 2023-07-18 | 兰州理工大学 | Intelligent elevator control system |
CN116443682B (en) * | 2023-06-20 | 2023-08-25 | 兰州理工大学 | Intelligent elevator control system |
Also Published As
Publication number | Publication date |
---|---|
CN114873387B (en) | 2024-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020238661A1 (en) | Elevator scheduling method, device, computer apparatus, and storage medium | |
CN110654946B (en) | Community elevator dispatching method and system based on artificial intelligence | |
CN105035887A (en) | Intelligent elevator master control system based on computer visual inspection | |
CN106976766B (en) | Elevator dispatching method and device | |
CN104961009A (en) | Multi-elevator parallel operation coordination control method and system based on machine vision | |
CN210103200U (en) | Intelligent elevator calling system | |
CN114873387A (en) | Elevator energy-saving dispatching system and method based on reinforcement learning algorithm | |
CN107176510A (en) | Multiple lift control system and group control method | |
CN211004021U (en) | Intelligent voice authentication calling landing system | |
CN104555629A (en) | Intelligent elevator group control device and control method thereof | |
CN112141833A (en) | Elevator control method based on elevator crowding degree | |
CN102398804A (en) | Elevator group control dispatching method | |
CN110386520A (en) | A kind of Elevator operation control system and method | |
CN214031338U (en) | Construction elevator driver and passenger management system | |
CN110065855B (en) | Multi-car elevator control method and control system | |
CN112938666A (en) | Elevator operation scheduling method and system and elevator equipment | |
CN113896063B (en) | Intelligent elevator dispatching system based on AI intelligence | |
CN107265208A (en) | A kind of multifunctional lift reservation system | |
CN210854833U (en) | Multi-car elevator control system | |
CN202897699U (en) | Construction elevator control system with floor calling function | |
CN112093609A (en) | Intelligent community elevator dispatching method based on artificial intelligence | |
CN207581082U (en) | A kind of energy-saving type elevator control system | |
CN113371562A (en) | Elevator carrying control method and system for passenger shunting | |
CN114890258A (en) | Intelligent speed control method and system for elevator | |
CN114988231B (en) | Elevator intelligent control management system based on artificial intelligence and Internet of things |
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 |