CN115203982A - Parallel computing method and simulation system for intelligent operation of public transport vehicle - Google Patents
Parallel computing method and simulation system for intelligent operation of public transport vehicle Download PDFInfo
- Publication number
- CN115203982A CN115203982A CN202211113264.9A CN202211113264A CN115203982A CN 115203982 A CN115203982 A CN 115203982A CN 202211113264 A CN202211113264 A CN 202211113264A CN 115203982 A CN115203982 A CN 115203982A
- Authority
- CN
- China
- Prior art keywords
- simulation
- user
- client
- scheduling scheme
- travel
- 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
- 238000004088 simulation Methods 0.000 title claims abstract description 172
- 238000004364 calculation method Methods 0.000 title claims abstract description 27
- 230000008447 perception Effects 0.000 claims abstract description 22
- 230000008901 benefit Effects 0.000 claims description 22
- 238000004891 communication Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 10
- 201000010099 disease Diseases 0.000 claims description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 18
- 238000013500 data storage Methods 0.000 description 6
- 230000035945 sensitivity Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 206010063659 Aversion Diseases 0.000 description 1
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008846 dynamic interplay Effects 0.000 description 1
- 230000002650 habitual effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009257 reactivity Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Signal Processing (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Computer Hardware Design (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
Abstract
The invention relates to an intelligent operation simulation system for a bus and a parallel computing method applied to the simulation system; the simulation system is suitable for a fully-automatic scheduling unmanned vehicle scheduling scene; the simulation system comprises a simulation server positioned at the terminal and a client running at the user side; the method comprises the steps that a simulation server obtains a reference scheduling scheme set through simulation operation based on travel demands of a plurality of users, and sends the reference scheduling scheme set to a plurality of clients; the client establishes a user model according to the characteristic set of the user, and carries out multiple times of circulating simulation operation on the user model in a simulation environment with the reference scheduling scheme set as a simulation condition to obtain a highest perception utility index; and performing multiple times of simulation operation in the simulation server in the client side in parallel to optimally obtain a scheduling scheme and a travel scheme with highest total perceived utility and total income.
Description
Technical Field
The invention relates to the technical field of data processing methods. In particular to a parallel computing method and a simulation system for intelligent operation of public transport vehicles.
Background
Along with the popularization of an intelligent public transportation system, public transportation vehicles such as subways, passenger cars and small-sized plug-in vehicles gradually adopt an unmanned operation mode or an intelligent auxiliary driving operation mode, so that a large amount of labor cost can be saved, and the flexibility of bus running shift and time scheduling is greatly improved due to the fact that the intelligent operation is different from the factors related to the previous labor arrangement; the intelligent operation scheduling problem of the public transport vehicle is concerned with the overall benefit of traffic operation and the experience of users; the efficient vehicle operation scheduling scheme can not only provide reliable service, but also reduce the operation cost of an operation department; the traditional vehicle scheduling scheme is designed on the assumption that the one-way time is fixed, however, the scheme is interfered by a complex operation environment and an emergency when being executed, so that the one-way time becomes uncertain; a fixed one-way time based scheme is difficult to implement accurately. At the same time, these emergencies reduce the service level and increase the cost of the enterprise. It becomes crucial how to verify the robustness and execution rate of the scheme in real-world environments.
Furthermore, the unmanned public transport vehicle can save the dispatching requirement on the driver, so that a highly flexible implementation mode can be realized for the arrangement and dispatching of the vehicle; for example, vehicles with various passenger capacities can be arranged to run for different passenger flow periods, more personalized customized running routes can be arranged, different operation management can be performed on each route, such as air-conditioning temperature management, female special carriages, ultra-cheap carriages and the like, and more diversified passenger demands can be met. Evaluating the benefits of the individual requirements and specific scheduling arrangement, and obtaining more referential test data by adopting a simulation operation system; however, as a large number of individuals (vehicles, passengers, road surface random factors, etc.) participate in simulation operation, the operation amount is huge, and in consideration of the fact that a large number of private data of passengers are needed when a more accurate simulation effect is sought, how to combine the above two aspects is also an important problem to be considered in the simulation system.
According to the technical scheme, a large-scale traffic simulation system and method based on parallel computing are provided by referring to related disclosed technical schemes, and the technical scheme with the publication number of CN111856968A, wherein the technical scheme is used for numbering roads and each lane on the roads and carrying out independent simulation computing, so that the simulation effect is refined, and the performance expression of simulation operation is improved; the technical scheme disclosed as JP2011238182A provides a useful simulation operation scheme for the electric automobile, so that the electric automobile can be guaranteed to have the lowest guaranteed operation electric quantity under various road conditions and operation conditions and can find a charging pile in time for electric quantity supplement; the technical scheme disclosed as US09524640B2 is characterized in that the size and performance of a vehicle are digitalized and substituted into a simulation system, and meanwhile, a plurality of nodes of a road network are connected, so that the traffic simulation system can be used for performing detailed expression on behaviors and logics of various simulation participants as far as possible, and a sufficiently detailed simulation effect is achieved.
The technical scheme is that the simulation operation processing is carried out based on a centralized simulation operation system, the calculation capacity of the centralized simulation operation system determines the overall efficiency of the simulation operation, and when a large amount of simulation data are faced, the calculation capacity of the simulation system becomes the bottleneck of the operation, so that extra upgrading cost is generated.
The foregoing discussion of the background art is intended only to facilitate an understanding of the present invention. This discussion is not an acknowledgement or admission that any of the material referred to is part of the common general knowledge.
Disclosure of Invention
The invention aims to provide an intelligent operation simulation system for a bus, and a parallel computing method applied to the simulation system; the simulation system is suitable for a fully-automatic scheduling unmanned vehicle scheduling scene; the simulation system comprises a simulation server positioned at the terminal and a client running at the user side; the method comprises the steps that a simulation server obtains a reference scheduling scheme set through simulation operation based on travel demands of a plurality of users and sends the reference scheduling scheme set to a plurality of clients; the client establishes a user model according to the characteristic set of the user, and carries out multiple times of circulating simulation operation on the user model in a simulation environment with the reference scheduling scheme set as a simulation condition to obtain a highest perception utility index; and performing multiple times of simulation operation in the simulation server in the client side in parallel to finally obtain a scheduling scheme and a travel scheme with the highest total perception utility and total profit.
The invention adopts the following technical scheme:
a simulation system for intelligent operation of a bus, the simulation system comprising:
the simulation server is used for being in communication connection with one or more clients and receiving travel demands from one or more users; running a simulation program for running the bus, and performing simulation operation by using the simulation program to generate a reference scheduling scheme set;
a client: a device configured to run on a user operation for receiving a user's travel demand and receiving and processing the set of benchmark scheduling solutions from the simulation server; the reference scheduling scheme set comprises at least two scheduling schemes; the client performs simulation operation by taking the reference scheduling scheme set and the user characteristic set as source data to obtain a trip scheme for the current client user;
the client establishes an Agent of the user according to the user characteristic set, uses the Agent to perform simulation circulation under a simulation condition environment established by the reference scheduling scheme set, and calculates a perception utility index V of each simulation circulation:
in the formula 1, ∈ 1 Time coefficient, epsilon, reflecting the user's perceived attitude to travel time 2 Cost factor, epsilon, reflecting the perception attitude of the user to the travel cost 1 、ε 2 Fitting calculation is carried out according to the travel demand and the user feature set; t is the total duration of the current journey of the user predicted after simulation operation, T 0 The expected duration of the current journey is the user; c is the cost of predicting the journey after simulation operation, C 0 The expected cost of the current trip for the user;
calculating by the client the highest perceived utility index V for user i i-max Will V i-max And obtaining V i-max The corresponding scheduling scheme is fed back to the simulation server, and the simulation server calculates the total perceptual utility V of the N users total Namely:
and calculating the total profit C obtained from the current journey of N users total Namely:
in formula 3, C i The total cost of the user i in the current trip;
and finally calculating the running benefit W:
in formula 4, λ 1 And λ 2 Setting the operation principle of the simulation system by managers for perceiving utility weight coefficient and income weight coefficient, thereby enabling lambda to be measured 1 And λ 2 Have different values;
performing parallel loop simulation operation in the simulation server and the client, and optimizing the reference scheduling scheme set and the trip scheme to maximize the operation benefit W so as to obtain a final optimal scheduling scheme and N optimal trip schemes of N users corresponding to the optimal scheduling scheme; sending the optimal travel plan to the client of the user;
preferably, the travel demand includes a start point, an end point of the user's travel, and at least one of: travel expected time, travel expected cost;
preferably, each of the scheduling schemes includes a vehicle involved in the scheduling, a departure time/location, an end location, an expected arrival end time, a staging fee in the trip, a trip benefit;
preferably, the user feature set is used to describe a plurality of features of the user, including:
individual characteristics of the user, including at least gender, age, and whether a particular disease is present;
habit characteristics of the user, including at least the longest walking distance, the longest waiting time;
further, a parallel computing method for urban bus intelligence is provided, and the parallel computing method is applied to the simulation system; the parallel computing method comprises the following steps:
s100: inputting a trip demand into a client by a user, and submitting the trip demand of the user to a simulation server by the client;
s200: the simulation server carries out simulation operation in the simulation system based on the travel demands of a plurality of users to obtain a reference scheduling scheme set which accords with the travel demands of the plurality of users; and returning the reference scheduling scheme set to the client;
s300: the client side uses an agent established based on a user characteristic set to carry out simulation circulation under the environment of simulation conditions established by the reference scheduling scheme set, and the perception utility index V of each simulation circulation is calculated;
s400: the client calculates and obtains the highest perception utility index V for the user i i-max Will V i-max And obtaining V i-max Feeding back the corresponding scheduling scheme to the simulation server;
s500: the simulation server calculates the total perceptual utility V of the N users total And the total income C obtained by the journey total ;
S600: and circularly performing the steps S200 to S500 to obtain an optimal scheduling scheme and N optimal travel schemes of N users corresponding to the optimal scheduling scheme by taking the maximum running benefit W as a target.
Preferably, in step S300, after completing the simulation operation of at least one scheduling scheme in the reference scheduling scheme set, the client returns the perceptual utility index V of the completed scheduling scheme to the simulation server, so that step S300 and step S400 run in parallel.
The beneficial effects obtained by the invention are as follows:
1. the simulation server and the client in the simulation system are respectively used for processing the respective simulation operations of the operation terminal and the user terminal, and a large amount of confidential data and operation processes related between the simulation server and the user terminal can be isolated from each other and operated in parallel, so that the resource concentration degree of the simulation operations is ensured, and the respective data privacy of the operation party and the user is protected;
2. the simulation server can make scheduling schemes with different refinement degrees based on the existing vehicle scheduling resources and the own simulation computing capacity, and is suitable for intelligent scheduling application scenes of various types and specifications;
3. the parallel computing method of the invention simultaneously utilizes the high-speed computing power of the centralized terminal and the computing of a plurality of edge nodes of the system, namely a plurality of devices of the user end to carry out parallel computing, and greatly utilizes the available computing power in the system to carry out computing acceleration;
4. the simulation system of the invention adopts modular design and cooperation of all related components, and can flexibly optimize and change through software and hardware in the later period, thereby saving a large amount of later maintenance and upgrading cost.
Drawings
The invention will be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments. Like reference numerals designate corresponding parts throughout the different views.
FIG. 1 is a schematic diagram of a simulation system according to the present invention;
fig. 2 is a schematic diagram of a processing flow of a user travel demand according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a client according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating the parallel computing steps in the embodiment of the present invention.
The drawings illustrate schematically: 100-a simulation server; 200-a client; 210-a central processing unit; 220-a memory component; 221-random access memory; 222-an external memory; 230-a network interface device; 300-network.
Detailed Description
In order to make the technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to embodiments thereof; it should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention. Other systems, methods, and/or features of the present embodiments will become apparent to one with skill in the art upon examination of the following detailed description. It is intended that all such additional systems, methods, features and advantages be included within this description, be within the scope of the invention, and be protected by the accompanying claims. Additional features of the disclosed embodiments are described in, and will be apparent from, the detailed description that follows.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of the description, but not to indicate or imply that the device or component referred to must have a specific orientation.
The first embodiment is as follows:
particularly, a simulation system and a parallel computing method which give consideration to simulation accuracy, simulation operation efficiency and user privacy protection are provided;
as shown in fig. 1 and fig. 2, a simulation system for intelligent operation of a bus, the simulation system comprises:
the simulation server 100 is used for being in communication connection with one or more clients and receiving travel demands from one or more users; running a simulation program for running the bus, and performing simulation operation by using the simulation program to generate a reference scheduling scheme set;
a client 200, wherein the client 200 may comprise a plurality of clients on a plurality of users, such as 200-1, 200-2 … … as shown in fig. 1; the client is configured to run on a user operated device for receiving a user's travel demand and receiving and processing the set of benchmark scheduling solutions from the simulation server; the reference scheduling scheme set at least comprises two scheduling schemes; the client performs simulation operation by taking the reference scheduling scheme set and the user characteristic set as source data to obtain a trip scheme for the current client user;
the client establishes an Agent of the user according to the user feature set, uses the Agent to perform simulation circulation under a simulation condition environment established by the reference scheduling scheme set, and calculates a perception utility index V of each simulation circulation:
in the formula 1, ∈ 1 Time coefficient, epsilon, reflecting the user's perceived attitude to travel time 2 Cost factor, epsilon, reflecting the perception attitude of the user to the travel cost 1 、ε 2 Fitting calculation is carried out according to the travel demand and the user feature set; t is the total duration of the current journey of the user predicted after the simulation operation, T 0 The expected duration of the current journey is the user; c is the cost of the journey predicted after the simulation operation, C 0 The expected cost of the current trip for the user;
calculating by the client to obtain the highest perceptual utility index V for the user i i-max A V is measured i-max And obtaining V i-max The corresponding scheduling scheme is fed back to the simulation server, and the simulation server calculates the total perceptual utility V of the N users total Namely:
and calculating the total profit C obtained from the current journey of N users total Namely:
in formula 3, C i The total cost of the user i in the current trip;
and finally calculating the running benefit W:
in formula 4, λ 1 And λ 2 Setting the operation principle of the simulation system by managers for perceiving utility weight coefficient and income weight coefficient, thereby leading the lambda to be 1 And λ 2 Have different values;
performing parallel loop simulation operation in the simulation server and the client, and maximizing the running benefit W by optimizing the reference scheduling scheme set and the travel scheme to obtain a final optimal scheduling scheme and N optimal travel schemes of N users corresponding to the optimal scheduling scheme; sending the optimal travel plan to the client of the user;
preferably, the travel demand includes a start point, an end point of the user's travel, and at least one of: travel expected time, travel expected cost; furthermore, the travel requirements can also include personalized arrangements such as whether to accept a seatless stand, whether to carry a pet, whether to need a female special carriage, and the like;
preferably, each of the scheduling schemes includes a vehicle involved in the scheduling, a departure time/location, an end location, an expected arrival end time, a staging cost in the trip, a trip benefit; the simulation server carries out vehicle scheduling management according to the travel demand of the user and vehicle resources; in some embodiments, the dispatch plan may schedule vehicles with large passenger loads to pick up as many passengers as possible, improving operational revenue; or, the dispatching scheme can arrange vehicles with small passenger capacity, improve the travel frequency and shorten the distance of each route so as to ensure the travel time of the user and improve the satisfaction degree of the user; preferably, the scheduling scheme needs to balance the benefit and the satisfaction degree of the users, the perception utility index V of a plurality of users under various scheduling schemes can be obtained through simulation operation, and the comprehensive calculation of the operation benefit W is carried out;
further, as shown in fig. 4, a parallel computing method for urban public transport vehicle intelligence is proposed, and the parallel computing method is applied to the simulation system; the parallel computing method comprises the following steps:
s100: inputting a trip demand into a client by a user, and submitting the trip demand of the user to a simulation server by the client;
s200: the simulation server carries out simulation operation in the simulation system based on the travel demands of a plurality of users to obtain a reference scheduling scheme set which accords with the travel demands of the plurality of users; and returning the reference scheduling scheme set to the client;
s300: the client side uses an agent established based on a user characteristic set to perform simulation circulation under the simulation condition environment established by the reference scheduling scheme set, and the perception utility index V of each simulation circulation is calculated;
s400: the client calculates and obtains the highest perception utility index V for the user i i-max Will V i-max And obtaining V i-max Feeding back the corresponding scheduling scheme to the simulation server;
s500: the simulation server calculates the total perceptual utility V of the N users total And the total income C obtained by the journey total ;
S600: circularly performing the steps S200 to S500, and acquiring an optimal scheduling scheme and N optimal travel schemes of N users corresponding to the optimal scheduling scheme by taking the maximum running benefit W as a target;
preferably, in step S300, after completing the simulation operation of at least one scheduling scheme in the reference scheduling scheme set, the client immediately returns the perceptual utility index V of the completed scheduling scheme to the simulation server, so that step S300 and step S400 run in parallel;
wherein the simulation server 100 may be embodied as any type of computer device including functions of data processing, analyzing, and outputting analysis results; as an exemplary depiction, the emulation server 100 may include a processor, memory, I/O subsystems, communication circuitry, data storage devices; of course, in other embodiments, the simulation server 100 may include other more additional components, such as various input, output devices, etc. as are common in computers; further, in some embodiments, one or more of the exemplary components may be incorporated into, or otherwise be incorporated from a portion of, another component; for example, in some embodiments, memory or portions thereof may be incorporated into a processor;
the processor may be embodied as any type of processor, currently known or developed in the future, capable of performing the functions described herein, including simulation operations; for example, a processor may be embodied as a single or multi-core processor, digital signal processor, microcontroller, or other processor or processing/control circuitry; similarly, the memory may be embodied as any type of volatile or non-volatile memory or data storage capable of performing the functions described herein; in operation, the memory may store various data and software used during operation of the emulation server 100, such as operating systems, applications, programs, libraries, and drivers; the memory is communicatively coupled to the processor through the I/O subsystem, which may be embodied as circuitry and/or components to facilitate input/output operations with the processor, the memory, and other components of the emulation server 100; for example, the I/O subsystem may be embodied to include memory controller hubs, input/output control hubs, firmware devices, communication links (e.g., point-to-point links, bus links, wires, cables, light guides, printed circuit board traces, etc.), and/or other components and subsystems to facilitate input/output operations; in some embodiments, the I/O subsystem may form part of a system on a chip (SoC) and be incorporated on a single integrated circuit chip with a processor, memory, or other components of the emulation server 100; for example, the I/O subsystem may be embodied as or otherwise include a memory controller hub, an input/output control hub, a firmware device, a communication link (i.e., a point-to-point link, a bus link, a wire, a cable, a light guide, a printed circuit board trace, etc.), and/or other components and subsystems to facilitate input/output operations;
in some embodiments, the I/O subsystem may form part of a system on a chip (SoC) and be incorporated on a single integrated circuit chip along with the processor, memory, and other components of the emulation server 100; for example, the I/O subsystem may be embodied as or otherwise include a memory controller hub, an input/output control hub, a firmware device, a communication link (e.g., a point-to-point link, a bus link, a wire, a cable, a light guide, a printed circuit board trace, etc.), and/or other components and subsystems to facilitate input/output operations;
the communication circuitry of the simulation server 100 may be embodied as any communication circuitry, device, or collection thereof capable of enabling communication between the simulation server 100 and the client 200 and/or other remote devices; the communication circuitry may be configured to enable such communication using any one or more communication technologies (e.g., wireless or wired communication) and related protocols (e.g., ethernet, bluetooth, wi-Fi, wiMAX, etc.);
further, the data storage device may be embodied as any type of device or device configured for short-term or long-term data storage, such as memory devices and circuits, memory cards, hard drives, solid state drives, or other data storage devices; in some embodiments, the simulation server may store preset algorithms, programs, or the display contents related to the simulation system and the parallel computing method in a data storage device;
further, as shown in FIG. 3, the client 200 is illustratively depicted; the client 200 is any client computing device which can realize the parallel computing method and is arranged on the user side; the client 200 may be, for example, a desktop or laptop computer, or a computing device such as a smartphone, smart watch, wearable computing device, tablet, or the like; preferably, the client 200 may include a bus, through which various main components of the client 200 are interconnected, such as a central processing unit 210, a memory component 220, a display card, an input device (keyboard/mouse), a network interface device 230, and the like;
wherein the bus allows data communication between the central processor and one or more memory components, as previously described, the memory component 220 may include, for example, a random access memory 221, an external memory 222 (e.g., a mechanical hard disk, a solid state hard disk, a flash memory, etc.); application programs resident on the client 200 are typically stored on the memory component 220 and accessed by a central processor or other computing device component; the memory component 220 may be integrated with the client 200, or may be separate and accessed through other interfaces;
further, the network interface device 230 is used for connecting to the network 300 by wire or wirelessly, and establishing a direct or indirect communication connection between the client 200 and the simulation server 100; also, the network interface device may provide communication links for additional sensors, controllers, and/or remote systems; the network interface device may provide such connection using any suitable technology and protocol as would be readily understood by one skilled in the art, including digital cellular networks, radio Frequency (RF), wi-Fi, bluetooth Low Energy (BTLE), near Field Communication (NFC), etc.; optionally, the network interface device may allow the device to communicate with other computers over one or more local, wide-area, or other communication networks;
further, in the client, an agent can be used as a main body of simulation operation instead of a user; the intelligent agent is an abstract intelligent agent which is constructed by taking cloud computing as a basis and taking artificial intelligence as a core and has the advantages of three-dimensional perception, global cooperation, accurate judgment, continuous evolution and openness; macroscopically, any independent entity that can think about and interact with the environment can be abstracted as an agent; the intelligent agent refers to a computing entity which can continuously and autonomously play a role and has the characteristics of autonomy, reactivity, sociality, initiative, progressiveness and the like, and any independent entity which can realize ideas and interact with the environment can be abstracted into the intelligent agent; the agents have intelligence, usually own knowledge base and inference engine, and the agents can autonomously decide whether to respond to information from other agents; therefore, when the knowledge base and the logic tree of the intelligent agent are set, the intelligent agent can be put into a simulation environment with basic objective rules to serve as a main body of simulation operation, the experiences of the intelligent agent on various conditions in the simulation environment are collected, and the experiences are digitized, so that the preference and aversion reactions of the intelligent agent similar to human beings in the simulation environment are judged;
the intelligent agent has strong intelligent characteristics, can interact and coordinate with the environment, makes decisions, changes the action and the state of the intelligent agent, gradually adapts to the change of the environment, judges and determines the 'benefit and the disadvantage' of the intelligent agent according to the calculated value in each step of decision, and further makes the action selection of the next step; the simulation based on the intelligent agent adopts a bottom-up modeling idea, and the micro individual behaviors emerge behaviors or phenomena on the system macro level by describing the interaction between the micro main body and the environment where the micro main body is located according to a certain discrete space-time rule; the vehicle dispatching traffic simulation system is a dynamic complex system, and passengers and a traffic environment are in a continuous dynamic interaction process; the distribution of traffic flow is the result displayed after the superposition of the travel routes of each participant on the traffic network, including vehicles and passengers, and the rule of the result accords with the operation principle of intelligent agent simulation;
further, the client 200 may have a function of collecting a large amount of personalized data of the user, for example, a mobile phone, a personal computer, etc. owned by the user, including a large amount of life and travel data, work data, social data, etc. of the user, and may generate the user feature set with user features to be described; the user feature set is used for describing a plurality of features of a user, and comprises the following steps: (1) Individual characteristics of the user, including at least gender, age, and whether a particular disease is present; (2) Habitual characteristics of the user, including at least a longest walking distance, a longest waiting time, and the like; by utilizing the user feature set, the intelligent body for replacing the user can be generated in an individual manner, and a knowledge base and a logic tree are established, so that the intelligent body can become a digital abstract body of the user to participate in simulation operation;
by implementing the simulation system and the parallel computing method, the simulation operation is carried out in parallel by adopting a multi-operation device between the simulation server and the client, so that the real feeling of passengers can be paid more attention to in public transport vehicle scheduling with intelligent unmanned vehicles as main bodies, and meanwhile, the benefit of operation enterprises is considered.
The second embodiment:
this embodiment should be understood to include at least all of the features of any of the foregoing embodiments and further modifications thereon;
in the process that users actually use public transport vehicles, the preferences and behavior patterns of different types of users are different, and the users expect to obtain better traffic experience as much as possible within the expected time and cost; the user mainly makes decision behaviors and use feelings according to the perceived ambient environment and the maximum benefit principle; therefore, different traffic modes, travel time lengths and expenses have different utilities for different users, and the difference of the utilities reflects the personalized preference of the users;
therefore, a perception utility index V of the user is calculated, and the perception utility index V is used for judging the travel feeling of the user in the current journey, namely;
comparing the expected travel time with the actual travel time during simulation operation, and simultaneously comparing the expected travel cost with the actual travel cost during simulation operation to obtain a perception utility index V of a user;
wherein epsilon 1 Time coefficient, epsilon, reflecting the user's perceived attitude to travel time 2 A cost coefficient reflecting the perception attitude of the user to the travel expense; both can be obtained by counting and fitting the user characteristic set;
in some embodiments, a deep learning manner may be adopted to obtain a plurality of feature quantities describing the sensitivity of the user to time and cost from the user feature set; the method comprises the steps of calculating the difference between actual departure time and expected departure time in a user historical trip, a trip expense interval of a user and a trip time interval of the user; and further including the nature of the user's job, e.g., the user is a free-job employee, which is likely to be less time sensitive; the user is used as a teacher, so that the time sensitivity is high;
in some embodiments, the method includes determining a cost sensitivity of the user based on an age level of the user;
in some embodiments, the method comprises the steps of judging the cost sensitivity of the user according to the average consumption level of the city and the region where the user is located;
go toStep one, adopting deep learning model, inputting a plurality of characteristics and characteristic quantities thereof embodied by user characteristic set, thereby determining the time sensitivity and cost sensitivity attributes of the user, and further calculating the epsilon 1 and epsilon of the user 2 The numerical value of (c).
Example three:
this embodiment should be understood to include at least all of the features of any of the foregoing embodiments and modifications thereto;
in the above formula 4, λ is set 1 And λ 2 As perceptual utility weight coefficients and revenue weight coefficients; the operator can influence the final scheduling scheme by setting different values of the two parameters; in the case of equation 4, it is preferable to first obtain a plurality of sets of V obtained by performing a plurality of simulation operations total And C total Normalizing the numerical values to eliminate the influence caused by dimension difference;
in some embodiments, the operator tends to gain greater economic benefit, while partly reducing user travel awareness considerations, thus setting λ 2 Numerical ratio λ of 1 Slightly larger, so that the highest scheduling scheme will tend to gain greater revenue;
in some embodiments, the revenue generated by various types of scheduling schemes is not far apart, so λ can be adjusted 2 Is set to a smaller value, and λ is set 1 The value of (2) is adjusted to be a larger value so as to ensure that the perception utility of the user is the most important target;
further, in some embodiments, since the trip demand of the individual user cannot be responded to in the simulation operation, and therefore the final trip plan cannot be made for the individual user, V needs to be adjusted total And C total The calculation method of (2) is used for enabling users who cannot affect the travel demand to go from V total And C total Step improvement is ignored in the summation process of (1).
In the above embodiments, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described or recited in any embodiment.
Although the invention has been described above with reference to various embodiments, it should be understood that many changes and modifications can be made without departing from the scope of the invention. That is, the methods, systems, and devices discussed above are examples. Various configurations may omit, substitute, or add various procedures or components as appropriate. For example, in alternative configurations, the methods may be performed in an order different than that described, and/or various components may be added, omitted, and/or combined. Moreover, features described with respect to certain configurations may be combined in various other configurations, as different aspects and elements of the configurations may be combined in a similar manner. Further, elements therein may be updated as technology evolves, i.e., many elements are examples and do not limit the scope of the disclosure or claims.
Specific details are given in the description to provide a thorough understanding of example configurations, including implementations. However, configurations may be practiced without these specific details, for example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary detail in order to avoid obscuring the configurations. This description provides example configurations only, and does not limit the scope, applicability, or configuration of the claims. Rather, the foregoing description of the configurations will provide those skilled in the art with an enabling description for implementing the described techniques. Various changes may be made in the function and arrangement of elements without departing from the spirit or scope of the disclosure.
In conclusion, it is intended that the foregoing detailed description be regarded as illustrative rather than limiting, and that it be understood that these examples are illustrative only and are not intended to limit the scope of the invention. After reading the description of the present invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (6)
1. A simulation system for intelligent operation of a bus, the simulation system comprising:
the simulation server is used for being in communication connection with one or more clients and receiving travel demands from one or more users; running a simulation program for running the bus, and performing simulation operation by using the simulation program to generate a reference scheduling scheme set;
a client: a device configured to run on a user operation for receiving a user's travel demand and receiving and processing the set of benchmark scheduling solutions from the simulation server; the reference scheduling scheme set comprises at least two scheduling schemes; the client performs simulation operation by taking the reference scheduling scheme set and the user characteristic set as source data to obtain a trip scheme for the current client user;
the client establishes an Agent of the user according to the user feature set, uses the Agent to perform simulation circulation under a simulation condition environment established by the reference scheduling scheme set, and calculates a perception utility index V of each simulation circulation:
in the formula 1, ∈ 1 Time coefficient, epsilon, reflecting the user's perceived attitude to travel time 2 Cost factor, epsilon, reflecting the perception attitude of the user to the travel cost 1 、ε 2 Fitting calculation is carried out according to the travel demand and the user feature set; t is the total duration of the current journey of the user predicted after simulation operation, T 0 The expected duration of the current journey is the user; c is the cost of predicting the journey after simulation operation, C 0 The expected cost of the user for the journey;
calculating by the client the highest perceived utility index V for user i i-max A V is measured i-max And obtaining V i-max The corresponding scheduling scheme is fed back to the simulation server, and the simulation server calculates the total perceptual utility V of the N users total Namely:
and calculating the total profit C obtained from the current journey of N users total Namely:
in formula 3, C i The total cost of the user i in the current journey;
and finally calculating the running benefit W:
in formula 4, λ 1 And λ 2 Setting the operation principle of the simulation system by managers for perceiving utility weight coefficient and income weight coefficient, thereby leading the lambda to be 1 And λ 2 Have different values;
performing parallel loop simulation operation in the simulation server and the client, and optimizing the reference scheduling scheme set and the trip scheme to maximize the operation benefit W so as to obtain a final optimal scheduling scheme and N optimal trip schemes of N users corresponding to the optimal scheduling scheme; and sending the optimal trip plan to the client of the user.
2. The simulation system for intelligent operation of public transport vehicles according to claim 1, wherein said travel demand includes a start point, an end point of a user's travel, and at least one of: travel expected time, travel expected cost.
3. A simulation system for intelligent operation of mass-transit vehicles according to claim 2, wherein each of said scheduling schemes includes scheduling of involved vehicles, departure time/location, destination location, expected arrival destination time, staging costs in the journey and journey revenue.
4. The simulation system for intelligent operation of mass-transit vehicles as claimed in claim 3, wherein said set of user characteristics is used to describe a plurality of characteristics of a user, including:
individual characteristics of the user, including at least gender, age, whether a particular disease is present;
the habit characteristics of the user at least comprise the longest walking distance and the longest waiting time.
5. A parallel computing method for intelligent operation of buses, characterized in that the parallel computing method is applied to a simulation system for intelligent operation of buses according to claims 1 to 4; the parallel computing method comprises the following steps:
s100: inputting a trip demand into a client by a user, and submitting the trip demand of the user to a simulation server by the client;
s200: the simulation server carries out simulation operation in the simulation system based on the travel demands of a plurality of users to obtain a reference scheduling scheme set which accords with the travel demands of the plurality of users; and returning the reference scheduling scheme set to the client;
s300: the client side uses an agent established based on a user characteristic set to perform simulation circulation under the simulation condition environment established by the reference scheduling scheme set, and the perception utility index V of each simulation circulation is calculated;
s400: the client calculates and obtains the highest perception utility index V for the user i i-max Will V i-max And obtaining V i-max Feeding back the corresponding scheduling scheme to the simulation server;
s500: the simulation server calculates the total perceptual utility V of the N users total And the total income C obtained by the journey total ;
S600: and circularly performing the steps S200 to S500 to obtain an optimal scheduling scheme and N optimal travel schemes of N users corresponding to the optimal scheduling scheme by taking the maximum running benefit W as a target.
6. The parallel computing method for intelligent operation of buses as claimed in claim 5, wherein in step S300, after the simulation operation of at least one scheduling scheme in the reference scheduling scheme set is completed, the client returns the perceptual utility index V of the completed scheduling scheme to the simulation server, so that step S300 and step S400 are operated in parallel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211113264.9A CN115203982B (en) | 2022-09-14 | 2022-09-14 | Parallel computing method and simulation system for intelligent operation of public transport vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211113264.9A CN115203982B (en) | 2022-09-14 | 2022-09-14 | Parallel computing method and simulation system for intelligent operation of public transport vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115203982A true CN115203982A (en) | 2022-10-18 |
CN115203982B CN115203982B (en) | 2022-11-29 |
Family
ID=83572441
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211113264.9A Active CN115203982B (en) | 2022-09-14 | 2022-09-14 | Parallel computing method and simulation system for intelligent operation of public transport vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115203982B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104881992A (en) * | 2015-06-12 | 2015-09-02 | 天津大学 | Urban public transport policy analysis platform based on multi-agent simulation |
US20160364645A1 (en) * | 2015-06-12 | 2016-12-15 | Xerox Corporation | Learning mobility user choice and demand models from public transport fare collection data |
US20180349547A1 (en) * | 2017-06-02 | 2018-12-06 | TuSimple | Large scale distributed simulation for realistic multiple-agent interactive environments |
CN109409560A (en) * | 2018-08-16 | 2019-03-01 | 北京交通大学 | Urban track traffic for passenger flow abductive approach based on Multi-Agent simulation |
CN110363358A (en) * | 2019-07-23 | 2019-10-22 | 马妍 | Public transportation mode share prediction technique based on multi-agent simulation |
CN110458456A (en) * | 2019-08-12 | 2019-11-15 | 上海同济城市规划设计研究院有限公司 | The dispatching method and system of demand response formula public transit system based on artificial intelligence |
CN112182901A (en) * | 2020-10-10 | 2021-01-05 | 福建船政交通职业学院 | Urban tourist trip simulation method and system |
CN112418574A (en) * | 2019-08-21 | 2021-02-26 | 上海宝信软件股份有限公司 | Artificial intelligence-based urban rail transit operation simulation system and method |
CN112580951A (en) * | 2020-12-09 | 2021-03-30 | 北京交通大学 | Urban ground bus operation monitoring key index screening method based on passenger trip |
CN114707404A (en) * | 2022-03-14 | 2022-07-05 | 北京电子工程总体研究所 | Distributed parallel multi-agent cooperative training system and method |
-
2022
- 2022-09-14 CN CN202211113264.9A patent/CN115203982B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104881992A (en) * | 2015-06-12 | 2015-09-02 | 天津大学 | Urban public transport policy analysis platform based on multi-agent simulation |
US20160364645A1 (en) * | 2015-06-12 | 2016-12-15 | Xerox Corporation | Learning mobility user choice and demand models from public transport fare collection data |
US20180349547A1 (en) * | 2017-06-02 | 2018-12-06 | TuSimple | Large scale distributed simulation for realistic multiple-agent interactive environments |
CN109409560A (en) * | 2018-08-16 | 2019-03-01 | 北京交通大学 | Urban track traffic for passenger flow abductive approach based on Multi-Agent simulation |
CN110363358A (en) * | 2019-07-23 | 2019-10-22 | 马妍 | Public transportation mode share prediction technique based on multi-agent simulation |
CN110458456A (en) * | 2019-08-12 | 2019-11-15 | 上海同济城市规划设计研究院有限公司 | The dispatching method and system of demand response formula public transit system based on artificial intelligence |
CN112418574A (en) * | 2019-08-21 | 2021-02-26 | 上海宝信软件股份有限公司 | Artificial intelligence-based urban rail transit operation simulation system and method |
CN112182901A (en) * | 2020-10-10 | 2021-01-05 | 福建船政交通职业学院 | Urban tourist trip simulation method and system |
CN112580951A (en) * | 2020-12-09 | 2021-03-30 | 北京交通大学 | Urban ground bus operation monitoring key index screening method based on passenger trip |
CN114707404A (en) * | 2022-03-14 | 2022-07-05 | 北京电子工程总体研究所 | Distributed parallel multi-agent cooperative training system and method |
Non-Patent Citations (3)
Title |
---|
KHOA NGUYEN 等: ""On Developing A More Comprehensive Decision-Making Architecture for Empirical Social Research: Lesson from Agent-Based Simulation of Mobility Demands in Switzerland"", 《THE 20TH INTERNATIONAL WORKSHOP ON MULTI-AGENT-BASED SIMULATION (MABS 2019)》 * |
TADAHIRO TANIGUCHI 等: ""Multi-agent simulation on relationship between individuals’ travel behavior and residential choice behavior"", 《SICE ANNUAL CONFERENCE 2010 》 * |
张钰等: "基于多智能体的城市居民通勤仿真研究", 《测绘工程》 * |
Also Published As
Publication number | Publication date |
---|---|
CN115203982B (en) | 2022-11-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109478364B (en) | Method and system for determining estimated arrival time | |
CN105894847B (en) | The real-time bus dynamic dispatching system and method for unsupervised learning under a kind of cloud platform environment | |
CN106126556A (en) | Information processor, information processing method and computer program | |
CN108357461A (en) | Controller of vehicle and control method for vehicle | |
CN103299340A (en) | System for managing vehicle energy, and method and apparatus for same | |
TWI704508B (en) | Systems, methods, and computer readable media for online to offline service | |
Cohen et al. | Technological advances relevant to transport–understanding what drives them | |
US11587004B2 (en) | System and method for placement optimization of public electric vehicle charging stations using telematics data | |
CN111261017B (en) | Map fence display method and device | |
EP3637357A1 (en) | Information processing device and information processing method | |
CN110570127B (en) | Intelligent public transportation system, and vehicle operation scheduling method and device | |
Kamel et al. | A modelling platform for optimizing time-dependent transit fares in large-scale multimodal networks | |
Peña et al. | A novel multi-objective optimization approach to guarantee quality of service and energy efficiency in a heterogeneous bus fleet system | |
CN115203982B (en) | Parallel computing method and simulation system for intelligent operation of public transport vehicle | |
CN114662730A (en) | Transport operator collaboration for enhanced user experience and operational efficiency | |
CN112581184A (en) | Air-iron combined transport fare formulation method, system, equipment and readable storage medium | |
Quan et al. | An optimized task assignment framework based on crowdsourcing knowledge graph and prediction | |
Xi | Data-driven optimization technologies for MaaS | |
CN113793195B (en) | Network about vehicle order processing method and device, computer equipment and readable storage medium | |
CN107331156A (en) | Urban transportation comprehensive survey cloud platform and system | |
Panagiotopoulos et al. | Cognitive intelligence of highly automated vehicles in a car‐sharing context | |
Karakitsiou et al. | Optimal location problems for electric vehicles charging stations: models and challenges | |
CN117455727B (en) | Whole journey tourism wisdom integrated management system on line | |
CN112088106A (en) | Method and device for providing vehicle navigation simulation environment | |
Chen et al. | Scaling Laws of Dynamic High-Capacity Ride-Sharing |
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 |