CN114021996A

CN114021996A - Vehicle scheduling strategy evaluation method and device, electronic equipment and storage medium

Info

Publication number: CN114021996A
Application number: CN202111317927.4A
Authority: CN
Inventors: 谢意; 蒋先尧; 冯冲; 吴丹阳; 刘志勇
Original assignee: Beijing Lukaizhixing Technology Co ltd
Current assignee: Beijing Lukaizhixing Technology Co ltd
Priority date: 2021-11-08
Filing date: 2021-11-08
Publication date: 2022-02-08

Abstract

The disclosure provides a vehicle dispatching strategy evaluation method and device, electronic equipment and a storage medium. The evaluation method of the vehicle dispatching strategy comprises the following steps: generating a vehicle operating state model on each section of the transportation route based on the probability of occurrence of the vehicle on at least one section of the transportation route; calculating probability distribution of running states of the vehicles on each road section of the transportation line based on the vehicle scheduling strategy and the vehicle running state model; and calculating a performance parameter of the vehicle scheduling strategy based on the probability distribution of the running state of the vehicle on each road section of the transportation route to evaluate the performance of the vehicle scheduling strategy.

Description

Vehicle scheduling strategy evaluation method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence and the field of vehicle scheduling. More specifically, the present disclosure provides an evaluation method, an optimization method, an evaluation apparatus, an electronic device, and a storage medium of a vehicle scheduling policy.

Background

Along with the development of artificial intelligence technology, intelligent transportation systems are more and more emphasized. In an intelligent transportation system, vehicles are often required to run on a certain transportation route (or driving road). In an intelligent transportation system, scheduling of vehicles is indispensable. The quality of the vehicle dispatching strategy has a high impact on the transportation efficiency. In current consideration of vehicle scheduling, vehicle scheduling strategies are often designed and built based on certain factors.

Disclosure of Invention

The embodiment of the disclosure provides an evaluation method of a vehicle dispatching strategy, which comprises the following steps: generating a vehicle operating state model on each section of the transportation route based on the probability of occurrence of the vehicle on at least one section of the transportation route; calculating probability distribution of running states of the vehicles on each road section of the transportation line based on the vehicle scheduling strategy and the vehicle running state model; and calculating a performance parameter of the vehicle scheduling strategy based on the probability distribution of the running state of the vehicle on each road section of the transportation route to evaluate the performance of the vehicle scheduling strategy.

In some embodiments, the vehicle operating state model is dependent on the number of vehicles and the number of segments of the transportation route.

In some embodiments, the vehicle operating state model includes at least one of a single-lane function for only a single vehicle operating on the same road segment, a multi-lane function for multiple vehicles operating on the same road segment, and an exception event lane function for an exception event on a transit lane.

In some embodiments, the bicycle route function is f (o)_i-1，o_i)＝p_δt(o_i|o_i-1) Wherein o is_iRepresents whether the vehicle is present on the section i, o_i-1Representing whether the vehicle is present on the section i-1, p_δt(o_i|o_i-1C) represents the occurrence of the vehicle in the state c on the link i-1 at time t, at t + δ tC belongs to the probability of the vehicle appearing on the road section i, and c belongs to the { appears and does not appear };

the multi-vehicle line function is

Wherein

Representing whether vehicle m is present on road section i,

representing whether vehicle m is present on road segment i-1,

representing whether vehicle n is present on road segment i-1,

representing the occurrence of a vehicle m and a vehicle n, respectively c, on the section i-1 at time t^mAnd cⁿIn the case of (1), the probability of whether the vehicle m appears on the link i at the time t + δ t, c^m，cⁿE { present, absent };

the exceptional line function is h (o)_i，e_i-1)＝p_δt(o_i|e_i-1) Wherein o is_iRepresenting whether a vehicle is present on the section i, e_i-1Representing whether an abnormal condition occurs in the road section i-1, wherein i is an integer larger than 1.

In some embodiments, the probability distribution of the operation time of said vehicles on the same road segment is based on a gaussian model in case only a single vehicle is operated on the same road segment, and/or the probability distribution of the operation time of each vehicle of said plurality of vehicles on said same road segment is based on a gaussian mixture model in case a plurality of vehicles are operated on the same road segment, and/or the probability distribution of the operation time of a vehicle on a certain road segment in case an abnormal event occurs on the road segment is based on a poisson distribution model.

In some embodiments, said calculating a probability distribution of the vehicle's operating state on each segment of the transportation route based on the vehicle scheduling policy and the vehicle operating state model comprises: initializing the running state of the vehicle on each road section at the first moment according to a vehicle scheduling strategy; and calculating the probability of the vehicle running state on each road section at the first moment according to the vehicle running state model.

In some embodiments, said calculating a probability distribution of the vehicle's operating state on each segment of the transportation route based on the vehicle scheduling policy and the vehicle operating state model further comprises: initializing the running state of the vehicle on each road section at the second or more moments according to a vehicle scheduling strategy; and calculating the probability of the vehicle running state on each road section at the second or more moments according to the vehicle running state model.

In some embodiments, the probability of a vehicle operating state on a segment of the transportation route is dependent on the probability of an abnormal event occurring on a segment preceding the segment and the probability of a vehicle operating state on at least one segment adjacent thereto.

In some embodiments, said calculating performance parameters of a vehicle scheduling policy based on a probability distribution of vehicle operation states over respective segments of a transportation route to evaluate performance of the vehicle scheduling policy comprises: the sum of the performance parameters of the vehicle scheduling strategy at a plurality of moments in time is calculated based on the probability distribution of the vehicle's behavior over the respective segments of the transportation route at the plurality of moments in time.

In some embodiments, the performance parameters of the vehicle dispatch strategy include: the volume of the vehicle or the distance traveled by the vehicle.

In some embodiments, the abnormal event comprises a failure of a control unit inside the vehicle or a temporary occurrence of an obstacle in the road segment that needs to be avoided.

In some embodiments, the vehicle operating state model is built directly based on actual vehicle travel measurement data or by fitting parameters of a parameterized model from actual vehicle travel measurement data.

The embodiment of the present disclosure further provides an optimization method of a vehicle scheduling policy, including: evaluating a plurality of vehicle dispatching strategies by using the method of any one of the embodiments; and comparing the plurality of vehicle dispatch strategies to select a preferred strategy.

The embodiment of the present disclosure further provides an evaluation device for a vehicle scheduling policy, including: a vehicle operation state generation module for calculating probability distribution of vehicle operation states on each section of the transportation line based on a vehicle scheduling strategy and a vehicle operation state model on each section of the transportation line, wherein the vehicle operation state model is generated based on the occurrence probability of the vehicle on at least one section of the transportation line; and a performance calculation module for calculating performance parameters of the vehicle scheduling strategy based on the probability distribution of the vehicle operation states on the respective sections of the transportation route to evaluate the performance of the vehicle scheduling strategy.

In some embodiments, the vehicle operating state generating module comprises: the initialization module is used for initializing the running state of the vehicle on each road section at the first moment according to the vehicle scheduling strategy; and the probability calculation module is used for calculating the probability of the vehicle running state on each road section at the first moment according to the vehicle running state model.

In some embodiments, the initialization module is further configured to initialize the operating state of the vehicle on each road segment at the second or more times according to a vehicle dispatch strategy; and the probability calculation module is further configured to calculate the probability of the vehicle operation state on each road segment at the second or more moments in time according to the vehicle operation state model.

In some embodiments, the performance calculation module is configured to calculate a sum of a performance parameter of the vehicle scheduling policy at a plurality of time instants, the performance parameter being a transportation volume of the vehicle or a travel distance of the vehicle, based on a probability distribution of vehicle operation states on respective segments of the transportation route at the plurality of time instants.

In some embodiments, the apparatus for evaluating a vehicle dispatching strategy further comprises: and the data acquisition module is used for acquiring actual vehicle running measurement data and constructing the vehicle running state model.

An embodiment of the present disclosure also provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of any of the preceding embodiments.

Embodiments of the present disclosure also provide a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any of the preceding embodiments.

Embodiments of the present disclosure also provide a computer program product comprising a computer program which, when executed by a processor, implements the method of any of the preceding embodiments.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic diagram of a single vehicle route probabilistic graphical model according to one embodiment of the present disclosure;

FIG. 2 is a schematic diagram of a multi-lane probabilistic graphical model according to one embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a bicycle route probability map model that accounts for anomalous events in accordance with another embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a multi-lane probabilistic graphical model accounting for exceptional events according to yet another embodiment of the present disclosure;

FIG. 5 is a flow diagram of a method of evaluating a vehicle dispatch strategy according to one embodiment of the present disclosure;

FIG. 6 is a flow diagram of a method of optimization of a vehicle dispatch strategy according to one embodiment of the present disclosure;

FIG. 7 is a schematic diagram of an apparatus for evaluating a vehicle dispatch strategy according to one embodiment of the present disclosure;

fig. 8 is a schematic illustration of a vehicle transportation line according to one embodiment of the present disclosure;

fig. 9 is a first diagram of calculating a vehicle occurrence probability for each road segment on a transportation route in an evaluation method of a vehicle scheduling strategy according to an embodiment of the present disclosure;

fig. 10 is a second diagram illustrating the calculation of the vehicle occurrence probability for each section on the transportation route in the evaluation method of the vehicle scheduling policy according to one embodiment of the present disclosure;

FIG. 11 is a system block diagram of a remote control for implementing an evaluation method or optimization method of a vehicle dispatch strategy in accordance with another embodiment of the present disclosure; and

FIG. 12 is a block diagram of an electronic device for implementing an evaluation method of a vehicle dispatch strategy in accordance with one embodiment of the present disclosure.

Detailed Description

To more clearly illustrate the objects, aspects and advantages of the present disclosure, embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It is to be understood that the following description of the embodiments is intended to illustrate and explain the general concepts of the disclosure and should not be taken as limiting the disclosure. In the specification and drawings, the same or similar reference numerals refer to the same or similar parts or components. The figures are not necessarily to scale and certain well-known components and structures may be omitted from the figures for clarity.

Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure belongs. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "a" or "an" does not exclude a plurality. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", "top" or "bottom", etc. are used merely to indicate relative positional relationships, which may change when the absolute position of the object being described changes. When an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, it can be "directly on" or "under" the other element or intervening elements may be present.

In a transportation system, multiple vehicles are often required and multiple road segments are involved. And how to plan the driving route and departure interval of the vehicle, etc. requires a good vehicle dispatching strategy. A vehicle dispatch strategy is a design for when each vehicle appears on a certain road segment in a transportation route. The good vehicle dispatching strategy can more fully utilize the transportation resources, improve the transportation efficiency and reduce the cost. However, the vehicle scheduling strategy needs to consider not only the theoretical route planning, but also various complex situations of vehicle driving on the transportation road section, such as speed fluctuation of the vehicle, vehicle failure, obstacles (such as people, other vehicles, rockfall, etc.) on the road, vehicle congestion, etc. For vehicle transportation systems in more severe and complex scenarios of road environments, such as surface mines, the impact of uncertainty in vehicle travel on vehicle dispatch is more important. Embodiments of the present disclosure provide an evaluation method of a vehicle dispatching strategy, which may be used to evaluate the performance of the vehicle dispatching strategy. In the method, uncertain factors in vehicle running are considered, and the performance of the vehicle scheduling strategy can be more accurately evaluated.

In an embodiment of the present disclosure, as shown in fig. 5, the evaluation method may include:

step S1: generating a vehicle operating state model on each section of the transportation route based on the probability of occurrence of the vehicle on at least one section of the transportation route;

step S2: calculating probability distribution of running states of the vehicles on each road section of the transportation line based on the vehicle scheduling strategy and the vehicle running state model; and

step S3: a performance parameter of a vehicle dispatch strategy is calculated based on a probability distribution of vehicle operation states on respective segments of a transportation route to evaluate performance of the vehicle dispatch strategy.

In embodiments of the present disclosure, the transportation route may include only one or more independent roads, or may include roads that intersect with each other, for example, to form a transportation road network. Fig. 8 gives an example of a transport line. In fig. 8, two roads are shown, a first road R1 and a second road R2. The two roads intersect at point a. Each road is divided into corresponding road sections. In the example of fig. 8, 7 road segments are shown, namely road segment 1, road segment 2, road segment 3, road segment 4, road segment 5, road segment 6, road segment 7. The division of the transportation route in the embodiment of the present disclosure is not limited to the above example, but may have one or more segments of various shapes. Assuming the optimal situation, where the travel time of the vehicle on each road segment is fixed and there are no other uncertainties, it is possible to clearly arrange for the vehicle to appear on that road segment at each moment. However, as described above, the influence of various uncertain factors (such as an obstacle on a road, a failure of equipment, a traffic jam in a queue, and the like) during the traveling of the vehicle is not negligible. In particular, when the vehicle travels a long distance or the road conditions are complicated, the travel time of the vehicle on a certain road section is not completely determined. Therefore, in the above-described embodiments of the present disclosure, the vehicle operation state model on each section of the transportation route is introduced based on the occurrence probability of the vehicle on the section. The vehicle operation state model can be used for constructing and evaluating a vehicle dispatching strategy. The vehicle operating state model may be modeled statistically by stochastic factors.

As an example, the above-mentioned vehicle behavior model may depend on the number of vehicles and the number of segments of the transportation route. When there are multiple vehicles, there may be interactions between the vehicles, changing the probability of a vehicle appearing on a certain road segment. Also, when the number of sections is different, the probability of the presence of a vehicle on different sections of the entire transport route may be affected.

In some embodiments, the vehicle operating state model may be established based on three conditions. The first case is a single-vehicle drive, i.e., a case in which only a single-vehicle drive is considered. Under the condition of single-vehicle driving, a statistical model of the running time of each transportation road section can be constructed on the basis of the historical running data of each vehicle for each transportation road section, the data is fitted by utilizing a probability distribution function (such as a Gaussian distribution function) according to the actual conditions of different routes, and the construction of the statistical model is completed, wherein the model is marked as p^Bicycle(t), i.e. the probability of completing the road segment operation within t hours in the case of a single vehicle.

An example of a probability model in a single-vehicle driving situation is given below by taking a gaussian distribution function as an example. In the process of constructing the model by using the Gaussian distribution function, under the condition that the historical operating data of the vehicle is sufficient, the model parameters can be directly constructed on the basis of the fitting of the historical operating data, namely the mean value and the variance of the Gaussian distribution model are solved. For example, assuming that there are N historical data samples, the data of a single running time of the vehicle on a certain road segment is t_iWhere i ∈ { 1., N }, calculating:

calculating the mean value of Gaussian distribution

Is the variance of the gaussian distribution.

Thus, can obtain

When the historical operating data is insufficient, the model can be constructed in an attributive manner, for example, the mean value of the gaussian probability distribution is solved based on the calibrated operating speed of the vehicle and the calibrated road section length, and the variance of the gaussian probability distribution is calculated based on the time jitter caused by the vehicle load deviation, the time jitter caused by the vehicle control error, the time jitter caused by the road condition and the like. Wherein the time jitter caused by the vehicle load deviation, the time jitter caused by the vehicle control error and the time jitter caused by the road condition may be fitted to their probability distribution based on the actual measurement data.

The probability model for the single vehicle traveling is not limited to the one based on the gaussian distribution, and may be based on another probability distribution model, for example, a uniform distribution, in some cases. For more complex situations, the probabilistic model for single-vehicle driving may further include a series of sub-models, for example, the time jitter caused by road conditions may be divided into a straight line segment sub-model, an uphill route sub-model, a downhill route sub-model, a curve route sub-model, and so on.

The second case is a meeting situation, that is, a situation where a plurality of vehicles travel on the same road section at the same time. This situation is more complicated than a single-vehicle drive. In this case, the vehicle running characteristics, the road characteristics, the meeting rules and the like can be used to construct a statistical model of the meeting time of each vehicle under the condition that the meeting occurs on each transportation section. As an example, the vehicle control and the driving state (e.g. full load/no load, occupied/unoccupied) of different vehicles can be selected according to the driving stateAnd fitting historical data by utilizing a mixed probability distribution function (such as a mixed Gaussian model) to construct information (such as speed limit and road weight) and the like to complete the construction of a statistical model. This model is denoted as p^{Vehicle meeting}(t), i.e. the probability of completing the travel of the road section within t time in the case of meeting.

An example of a probability model in a meeting situation is given below by taking a gaussian mixture probability model as an example. In the process of constructing the model by using the Gaussian mixture probability model, under the condition that historical operating data are sufficient, model parameters can be directly constructed on the basis of fitting of the historical operating data, namely, the mean value and the variance of each Gaussian probability model in the Gaussian mixture probability model are solved, and the number of the Gaussian models in the Gaussian mixture probability model is optimized; for example, the following description shows that N times of historical data sampling are total, and the time data of the vehicle completing the driving of the road section in the meeting situation is t_iWherein i ∈ { 1.,. N }, and a parameterized Gaussian mixture model is constructed as follows:

wherein, the parameter M represents the number of Gaussian probability models in the Gaussian mixture model, and the parameter is initialized

And completing the following total P times of iterative calculation, wherein the k iterative step is calculated as follows:

for any sample t_iAnd (3) calculating:

calculating new parameters:

repeating the above steps P times from the initial value or calculating to function

And (5) before convergence. Thereby determining the various parameters in the model.

When the historical operating data is insufficient, the model can be constructed in an attribution mode, namely a Gaussian mixture probability model is constructed on the basis of a Gaussian probability model under the driving condition of a single vehicle, wherein the number of the Gaussian probability models is the number of the vehicles participating in meeting.

The third case is an abnormal event case, that is, a case where various abnormal events occur while the vehicle travels on a road section, such as falling rocks occurring on a road, a control failure of a person, other vehicles, and vehicles, a communication failure, and the like. These abnormal events may cause the vehicle to pass through a certain road segment for an extended period of time. In this case, the construction of a statistical model, denoted as p, is performed by using a probability distribution function (for example, a poisson distribution model) based on the characteristics of the abnormal event occurring on each transportation section^{Abnormality (S)}(t) is the probability that the vehicle finishes the operation of the road section within t time under the condition that the road section is abnormal. The reason for the occurrence of an abnormal situation in each road section may be different. The distribution of time intervals at which an abnormal event occurs may be, for example, a poisson distribution, the parameters of which are obtained from measurements of historical data. As an example, the specific measurement mode of the data is as follows, and during the running process of the vehicle, the abnormal events are detected based on the vehicle-mounted sensing unitCapturing the events, including but not limited to detecting the events such as falling rocks, vehicles entering a lane, personnel and the like by using sensing equipment such as a camera, a laser radar, a millimeter wave radar and the like, recording the time and the place of the event, and recording the time and the place as external cause abnormal event data; capturing events such as vehicle control failure, communication failure and the like by using a vehicle internal control unit, recording the time and the place of the event, and recording the time and the place as internal cause abnormal event data; and respectively fitting the external cause abnormal event data and the internal cause abnormal event data by using the Poisson distribution model to obtain the Poisson distribution model of the abnormal event. For example, the time delay t caused by a single abnormal event is recorded for N times of historical data sampling_iWherein i ∈ {1,..., N }, and a parameterized poisson model is constructed as follows:

wherein:

based on the analysis of the above three cases, the vehicle operating state model may be established for any one of the above cases, or may be established while considering two or three of the above cases. As an example, the vehicle operating state model may include at least one of a single-lane function for only a single vehicle operating on the same road segment, a multi-lane function for multiple vehicles operating on the same road segment, and an abnormal event lane function for an abnormal event on a transportation lane. The single-vehicle route function corresponds to the single-vehicle driving condition, the multi-vehicle route function corresponds to the meeting condition, and the abnormal event route function corresponds to the abnormal event condition.

FIG. 1 shows a schematic diagram of a single vehicle route probabilistic graphical model according to one embodiment of the present disclosure. Wherein the complete transportation route is divided into K road sections, and the single-vehicle route probability map model can represent the driving state of a single vehicle on the complete road section. Constructing a bicycle line function f (o)_i-1，o_i)＝p_δt(o_i|o_i-1) Wherein o is_iRepresents whether the vehicle is present on the section i, o_i-1Representing whether the vehicle is present on the section i-1, p_δt(o_i|o_i-1C) represents the probability of the vehicle appearing on the link i at time t +6t, c ∈ { appearing, not appearing }, in the case where the vehicle appearance state at time t on the link i-1 is c. This probability distribution follows the following features:

p_δt(o_ioccurrence of | o_i-1Not appearing, 0 (formula 1)

p_δt(o_iNot appearing | o_i-1Not appearing, 1 (formula 2)

From fig. 1, the probability of the occurrence of a vehicle on each route section in the case of a single-vehicle driving can be determined in turn from the single-vehicle route function. O in FIG. 1₁、o₂、o₃、o_K-1、o_KRespectively, indicates whether a vehicle is present on road segment 1, road segment 2, road segment 3, road segment K-1, and road segment K. The blocks in fig. 1 correspond to a single-vehicle route function reflecting a relationship of the occurrence probability of a vehicle between two adjacent road segments. With the aid of the probabilistic graphical model shown in fig. 1 and the aforementioned probabilistic model of the time of passage of the vehicle through the route in the case of a single-vehicle driving situation, a probabilistic model of the complete vehicle path in the case of a single-vehicle driving situation can be derived.

FIG. 2 shows a schematic diagram of a multi-lane probabilistic graphical model according to one embodiment of the present disclosure. In which the complete transport route is also divided into K segments. The multi-lane probabilistic graphical model may represent a driving state of a vehicle on a road segment when a plurality of vehicles are operated together. Constructing multiple vehicle route functions

Wherein

Representing whether vehicle m is present on road section i,

representing whether vehicle m is present on road segment i-1,

representing whether vehicle n is present on road segment i-1,

representing the occurrence of a vehicle m and a vehicle n, respectively c, on the section i-1 at time t^mAnd cⁿIn the case of (1), the probability of whether the vehicle m appears on the link i at the time t + δ t, c^m，cⁿE { present, absent }. This probability distribution follows the following features:

as can be seen from the above equations 5 to 10, when considering a multi-lane route, a case of driving a single car may occur on a road section, and a case of meeting may also occur. Therefore, in calculating the distribution probability of the vehicle on each link in the multi-vehicle traveling situation, the probability distribution model in both the single-vehicle traveling situation and the vehicle-meeting situation needs to be considered.

In FIG. 2

Respectively showing whether the vehicle m is present on the road segment 1, the road segment 2, the road segment K-1 and the road segment K,

respectively, indicates whether a vehicle n is present on road segment 1, road segment 2, road segment K-1, and road segment K. The blocks in fig. 2 correspond to a multi-lane function reflecting a relationship of the occurrence probability of vehicles between two adjacent road segments.

In fig. 2, the probability map of fig. 2 is more complex because only the travel of a single vehicle is no longer taken into account, but the mutual influence of the probabilities of two vehicles (vehicle m and vehicle n) appearing on the respective road sections is taken into account. With the aid of the probability map model shown in fig. 2 and the aforementioned probability model of the time of passage of the vehicle through the road section in the case of one-vehicle driving and the probability model of the time of passage of the vehicle through the road section in the case of a meeting, a complete probability model of the vehicle travel route in the case of multiple-vehicle driving can be derived. For convenience of description, only the case where the occurrence probabilities of the vehicle m and the vehicle n on the road section affect each other is listed in fig. 2 and the above-described examples. Of course, embodiments of the present disclosure are not limited thereto, and the multi-lane function may also be used to represent more complex probability distribution situations where three or more vehicles may be present on the same road segment.

FIG. 3 illustrates a schematic diagram of a bicycle route probability map model that accounts for anomalous events, according to another embodiment of the present disclosure. In which the complete transport route is also divided into K segments. FIG. 3 is a probability model incorporating an abnormal event based on the probability map shown in FIG. 1. Constructing an abnormal event line function h (o)_i，e_i-1)＝p_δt(o_i|e_i-1) Wherein o is_iRepresenting whether a vehicle is present on the section i, e_i-1Representing whether an abnormal condition occurs in the road section i-1, wherein i is an integer larger than 1. In FIG. 3, e₁And e_K-1Respectively, whether an abnormal event occurs in the link 1 and the link K-1. As shown in fig. 3, whether an abnormal event occurs in a previous link or not, resulting in a vehicle traveling delay, may have an influence on the occurrence probability of a vehicle in a subsequent link. This effect can be represented by the above-described exceptional circuit function. For the probability model in the event of an abnormal event, reference may be made to the foregoing description, and details are not repeated here.

FIG. 4 shows a schematic diagram of a multi-lane probabilistic graphical model accounting for exceptional events according to another embodiment of the present disclosure. In which the complete transport route is also divided into K segments. FIG. 4 is a probability model incorporating an abnormal event based on the probability map shown in FIG. 2. In the context of figure 4 of the drawings,

and

respectively indicate whether or not the abnormal event related to the vehicle n occurs on the road segment 1 and the road segment K-1,

and

respectively, indicates whether or not the abnormal event related to the vehicle m occurs in the link 1 and the link K-1. As shown in FIG. 4Whether an abnormal event related to a certain vehicle occurs in a previous road section or not causes vehicle running delay to influence the occurrence probability of the vehicle in a next road section. This effect can also be represented by the above-described exceptional circuit function. The abnormal event may be related to only a certain vehicle, such as a fault of the vehicle itself, or may be related to each vehicle on a certain road section, such as an obstacle like a falling rock on the road. For the probability model in the event of an abnormal event, reference may be made to the foregoing description, and details are not repeated here.

In the embodiment of the present disclosure, the abnormal event includes, for example, a failure of a vehicle interior control unit or a temporary occurrence of an obstacle in a road section that needs to be avoided.

The vehicle behavior model has been discussed above in various situations. The probabilistic graphical models shown in fig. 1-4 may be considered exemplary vehicle operating condition models. However, embodiments of the present disclosure are not limited thereto. Other probabilistic models can be used to construct the vehicle operating state model according to the actual transportation route and the condition of the vehicle.

In some embodiments, the vehicle operating state model is built directly based on actual vehicle travel measurement data or by fitting parameters of a parameterized model from actual vehicle travel measurement data. For example, the time information and the position information of the vehicle in the driving process can be collected in real time by using an information recording system on the vehicle or in a remote place, and the abnormal event early warning information such as an obstacle on a road section can be acquired through sensing equipment such as a vehicle-mounted camera, a laser radar and a millimeter wave radar. As an example, the vehicle running time of each road segment may be calculated based on the prior map information and the time information and the location information provided by the on-board information collection module, and a single-vehicle running time probability model may be constructed through repeated running of the vehicle on the same road segment, and the model may be constructed incrementally, that is, the accuracy of the model is continuously corrected as the collected samples are continuously increased. As an example, the meeting vehicle running time model may be constructed based on meeting vehicle information acquired from the vehicle-mounted information transmission module and time information and position information provided by the vehicle-mounted information acquisition module and through a meeting event that the vehicle repeatedly occurs on the same road segment, and the model may adopt an incremental construction method, that is, the precision of the model is continuously corrected as the number of collected samples increases.

In some embodiments, the probability of a vehicle operating state on a road segment of the transportation route depends on the probability of an abnormal event occurring on a preceding road segment and the probability of a vehicle operating state on at least one road segment adjacent thereto. For example, in the example shown in FIG. 3, at node o₂(o₂Representing whether a vehicle is present on the road section 2, i.e. the running state of the vehicle on the road section 2) and a probability p (o) of the running state of the vehicle₂) Dependent on the probability p (e) of an abnormal event occurring on the road section 1₁) And the probability p (o) of the vehicle operating state on the road segment 1₁). As another example, in the example shown in FIG. 4, at a node

(

Representing whether vehicle m is present on road segment 2, i.e., the running state of vehicle m on road segment 2) of the vehicle m

Dependent on the probability of an abnormal event occurring on the road section 1

And probability of vehicle m's vehicle operating status on road segment 1

And probability of vehicle n being in vehicle operating state on road segment 1

The construction and evaluation of vehicle dispatch strategies will be discussed below.

According to the probabilities discussed aboveThe variables involved in the diagram may completely describe the state of the entire transport line, e.g. a state matrix O may be constructed^(t)And given the following form.

Wherein each row represents the state of a vehicle on the haul road at time t, element

Representing whether vehicle m is present on road section i. The matrix has the following characteristics:

there is no more than one non-zero element per row, i.e., one vehicle will not be present on both road segments at the same time.

The vehicle dispatch strategy may be mapped to a particular state matrix O^(t)E.g. planned at time t_lThe vehicle i is dispatched and enters the haul road from road section k, the state matrix

Element (1) of

Is assigned a value of 1. Will be at t_lThe vehicle scheduling strategy executed at the moment is expressed as a vector

The vector is specified at t₁The road segment location where each vehicle is expected to be present at the time. Wherein N represents the total number of road segments,

indicates that the ith road segment is at t_lThe vehicle that is present at the moment. By defining the vehicle scheduling policy vector over successive time periods, a pre-scheduling policy for a particular vehicle can be given. The vehicle dispatch strategy corresponding to a time instant embodies the distribution of vehicles over various road segments at that time instant.

In the transport shown in fig. 8For example, the transportation route includes 7 sections, which are section 1, section 2, section 3, section 4, section 5, section 6, and section 7. From which a vehicle dispatch strategy vector can be defined as a vector having 7 elements. As an example, assume that the vehicle dispatch strategy vectors at

time

0, 1, 2, 3, 4, and 5 may be s, respectively⁽⁰⁾＝[1，0，0，0，0，0，0]^T，s⁽¹⁾＝[0，1，0，0，0，0，0]^T，s⁽²⁾＝[0，0，1，0，2，0，0]^T，s⁽³⁾＝[0，1，0，2，0，0，0]^T，s⁽⁴⁾＝[1，0，0，0，0，2，0]^T，s⁽⁵⁾＝[0，1，0，0，0，0，2]^T. That is, vehicle 1 (represented by the number 1 in the vector) is located on segment 1 at time 0, segment 2 at time 1, segment 3 at time 2, segment 2 at time 3, segment 1 at time 4, and segment 2 at time 5; while vehicle 2 (indicated by the number 2 in the vector) is not present in any segment at time 0 and time 1, at time 2 on segment 5, at time 3 on segment 4, at time 4 on segment 6, and at time 5 on segment 7. Summarizing, the vehicle dispatching strategy vector of the above 6 moments represents that the dispatching vehicle 1 follows the route from the 0 th moment to the 5 th moment: link 1 → link 2 → link 3 → link 2 → link 1 → link 2, and the vehicle 2 starts to enter the running state at time 2, along the route from time 2 to time 5: road section 5 → road section 4 → road section 6 → road section 7. The impact of the scheduling policy on the state matrix can be expressed as conditional probability

Considering the cutoff t_lThe scheduling policy at all times before the time, the effect of the overall scheduling policy on the state matrix can be expressed as

Wherein

Is the set of scheduling policies for all time instants.

State matrix O at any time t + δ t in the system^(t+δt)Probability distribution p (O)^(t+δt)|S^(t+δt)) All can be derived from the state matrix O at time t^(t)Conditional probability distribution p (O) of^(t)|S^(t)) Latest vehicle scheduling policy vs. state matrix O^(t+δt)Conditional probability p (O) of^(t+δt)|s^(t+δt)) And a bicycle line function f (o)_i-1，o_i) Multiple vehicle route function

And an exceptional circuit function h (o)_i，e_i-1) And (4) calculating.

In some embodiments, the calculating the probability distribution of the vehicle operation state on each road segment of the transportation route based on the vehicle scheduling policy and the vehicle operation state model in the step S2 includes:

step S21: initializing the running state of the vehicle on each road section at the first moment according to a vehicle scheduling strategy; and

step S22: and calculating the probability of the vehicle running state on each road section at the first moment according to the vehicle running state model.

The calculation of the probabilities of the vehicle operation states on the respective road segments at the first time may be performed iteratively using nodes in a probabilistic graphical model. The following describes a specific calculation method by taking the probability map model of the bicycle route in consideration of the abnormal event shown in fig. 3 as an example.

Firstly, step 1 is carried out, namely, each node o in the probabilistic graphical model is subjected to a certain vehicle scheduling strategy_iInitialization is performed. Thus, an initial node function p (o) may be calculated_i) (i.e., node o)_iProbability of) using the abnormal event probability model_j(j > 1) node, a node function p (e) can be calculated_j) (i.e., node e)_jProbability of (d). With the initialization value, an initial message is computed (as indicated by the arrow in fig. 9). In FIG. 9, at node o₁And node o₂Set function section in betweenPoint f_aAt node o₂And node o₃Set function node f between_bAnd at node o₂And node e₁Set function node g in between_u. With node o in FIG. 9₂For example, the node o₂To the function node f_aSending a message m_2，a(may be denoted as m)_2，a(o₂) To function node f)_bEach sending message m_2，b(may be denoted as m)_2，b(o₂)). In the initial state, i.e. the state shown in fig. 9, the transmitted message is calculated as follows:

m_2，a(o₂)＝p(o₂) (formula 12)

m_2，b(o₂)＝p(o₂) (formula 13)

Similarly, all o_iThe messages sent out by the nodes are all equal to the initial node function p (o) of the node_i) Similarly, all e_iThe messages sent out by the nodes are all equal to the initial node function p (e) of the node_i) Thus, all messages marked by arrows in FIG. 9 can be computed.

Next, step 2 is performed to calculate each function node f_m(f_mRepresents the node o shown in FIG. 9_i-1And node o_iFunction node such as f between_a、f_b...f_LEtc.) nodes and g_n(g_nRepresents the node e shown in FIG. 9_i-1And node o_iFunction node in between such as g_u...g_vEtc.) messages sent by the nodes. With f_aNode as an example, the node is from o₁Node receiving message m_1，a(may be denoted as m)_1，a(o₁) Via and function f)_a(o₁，o₂) (Here, f_a(o₁，o₂) Corresponding to the conditional probability p (o)₂|o₁) Obtained after calculation to o₂The message of the node is specifically calculated as follows:

similarly, all f_mNode and g_nThe messages sent by the nodes can be calculated.

Then, step 3 is performed to update each o_iA message at a node. Using FIG. 10 as center o₂Node, for example, at f adjacent from its periphery_aNode, f_bNode and g_nAfter the node receives the new message, o₂The node may update the messages it sends out. E.g. from f_aNode receives message m_a，2(o₂) And from g_uNode receives message m_u，2(o₂) After, o₂Node updatable message m_2，b(o₂) The message is calculated as follows:

m_2，b(o₂)＝m_a，2(o₂)*m_u，2(o₂) (formula 15)

Similarly, all o_iA node may update messages to all its neighbors.

Recalculating and updating function nodes f after messages that sent all oi nodes to all of its neighbors were updated_mNode and g_nA message sent by a node. In updating each function node f_mNode and g_nAfter the message sent by the node, all o are recalculated and updated_iMessages that a node sends to all its neighbors. The above steps 2 and 3 are repeated until all messages are not changed any more, or until iteration (repeated execution of the above steps 2 and 3) is carried out for a certain number of times (for example, more than one hundred or more than ten thousand times).

After the above iterative operations are completed, each o is calculated_iPosterior probability of node, in₂The nodes are taken as examples:

p(o₂)＝m_a，2(o₂)*m_b，2(o₂)*m_u，2(o₂) (formula 16)

I.e. o_iThe posterior probability of a node is the product of the latest messages received from all its neighbors. Similarly, all o_iThe posterior probabilities of the nodes can be calculated, so that the probability value of the vehicle appearing on the road section, namely the probability of the vehicle running state on each road section at a certain moment, can be obtained. E representing an abnormal event_i-1The above message relationship can be established between the node and the adjacent function node. E.g. e₁The node can go to g_uNode sends message m_e1，uFrom g_uNode receiving message m_u，e1. Specific calculation method and_ithe nodes are similar and will not be described in detail herein.

The algorithm is used for reducing the complexity of system implementation and realizing parallel computation.

For convenience of description, the above description is given only by taking the probability map model of the bicycle route in consideration of the abnormal event shown in fig. 3 as an example. However, embodiments of the present disclosure are not limited thereto. Other vehicle operating state models (e.g., fig. 4) may also be calculated in accordance with the above-described method. The method of calculating the probability of the vehicle operation state according to the present disclosure is not limited to the above method, and other calculation methods known in the art may be used to calculate the probability of the vehicle operation state at a certain time.

As described above, the probability of the vehicle operation state on each link at the first time may be calculated from the vehicle operation state model in step S22. This may provide a basis for evaluating the performance of the vehicle dispatch strategy.

In some embodiments, in evaluating the performance of the vehicle dispatching strategy, the probability of the vehicle operation state on each road segment at a plurality of times is required, in which case the step S2 may further include, in addition to the steps S21 and S22:

step S23: initializing the running state of the vehicle on each road section at the second or more moments according to a vehicle scheduling strategy; and

step S24: and calculating the probability of the vehicle running state on each road section at the second or more moments according to the vehicle running state model.

The specific calculation method of steps S23 and S24 is similar to the calculation of steps S21 and S22, and will not be described herein again.

In some embodiments, as previously described, in step S3, performance parameters of the vehicle scheduling policy are calculated based on the probability distribution of the vehicle' S operating states on the various segments of the transportation route to evaluate the performance of the vehicle scheduling policy. The performance parameters of the vehicle dispatch strategy may be any parameter that can be used to measure the efficiency or cost of transportation of the vehicle, and may include, by way of example, the total distance traveled by the vehicle, the transportation volume of the vehicle, and the like. In some embodiments, the step S3 may include: the sum of the performance parameters of the vehicle scheduling strategy at a plurality of moments in time is calculated based on the probability distribution of the vehicle's behavior over the respective segments of the transportation route at the plurality of moments in time.

When evaluating the performance of a vehicle dispatch strategy, it is often the case that the overall condition of the performance parameter over a period of time is counted, for example, the performance parameter is summed over multiple time instants. By way of example, it is possible to resort to the state matrix O at the time t mentioned earlier^(t)(see equation 11) conditional probability distribution p (O)^(t)|S^(t)) To accomplish scheduling policy S^(t)The running history of all the dispatched vehicles is evaluated, so that the performance parameters of the dispatched vehicles, such as the running distance, the transportation volume and the like, can be further calculated.

The vehicle travel distance is specifically calculated as follows:

assume that the link length vector is L ═ L₁ … l_K]^TWherein l is₁ … l_KRepresenting link lengths of the link 1 to the link K, respectively, a travel distance vector is calculated:

the total travel distance of vehicle m on the K road segments is the mth element of the vector d.

The specific calculation method of the vehicle transportation volume is as follows:

assuming that the vector of the transportation vector is W ═ W₁ … w_N]^TWherein w is₁ … w_NRespectively representing the transportation volume of the vehicles 1 to N, and calculating the transportation volume vector of each road section at T moments:

and summing all elements in the vector F to obtain the total transportation volume of all road sections.

Thus using the probability distribution p (O)^(t)|S^(t)) Performance evaluation of vehicle consist scheduling strategies may be accomplished, such as with p (O)^(t)|S^(t)＝S_a) And p (O)^(t)|S^(t)＝S_b) Calculating the expected value of the transportation volume two different vehicle dispatching strategies S can be evaluated and compared_aAnd S_bThe efficiency of transportation of (a). The expected value can be calculated by using the probability map models shown in fig. 1 to 4 in combination with the calculation method described above.

The embodiment of the disclosure also provides an optimization method of the vehicle dispatching strategy. As shown in fig. 6, the optimization method includes:

step S0: evaluating a plurality of vehicle dispatching strategies by using the evaluation method of any one of the embodiments; and

step S4: the plurality of vehicle dispatch strategies are compared to select a preferred strategy.

Specifically, as an example, the probability distribution p (O) described above may be utilized for each vehicle scheduling strategy in step S4^(t)|S^(t)) Corresponding transportation performance indicators are determined and then compared (e.g., vehicle distance traveled, volume of transportation, etc.) to select a preferred vehicle dispatch strategy. In some embodiments, an optimization algorithm may be utilized to solve for a vehicle consist scheduling strategy that maximizes the volume of traffic over a particular time horizon. The solution to the optimization problem may be implemented using probabilistic graphical models, such as those of fig. 1-4, in conjunction with any optimization algorithm known in the art.

According to the evaluation method and the optimization method of the vehicle scheduling strategy, the vehicle waiting time caused by various factors can be reduced, and the actual transportation efficiency is improved. For example, the system can reduce the occurrence of the situation of waiting for tasks in line by vehicles, reduce the occurrence of the situation of stopping or reducing the speed of the vehicles caused by meeting at special road sections, reduce the influence of abnormal situations, such as rockfall or equipment breakdown, on the overall transportation, and improve the actual transportation efficiency.

The evaluation method and the optimization method of the vehicle scheduling strategy according to the embodiment of the disclosure are based on the probability model of the vehicle driving on the road section, are particularly suitable for a road network with fixed transportation lines, are particularly suitable for scenes such as open mines, and can also be used for other road transportation scenes.

The embodiment of the disclosure also provides an evaluation device 10 of the vehicle dispatching strategy. As shown in fig. 7, the evaluation device 10 may include:

a vehicle operation state generation module 11, configured to calculate a probability distribution of an operation state of a vehicle on each segment of a transportation route based on a vehicle scheduling policy and a vehicle operation state model on each segment of the transportation route, wherein the vehicle operation state model is generated based on an occurrence probability of the vehicle on at least one segment of the transportation route; and

a performance calculation module 12 for calculating performance parameters of the vehicle scheduling strategy based on the probability distribution of the vehicle operation status on the respective segments of the transportation route to evaluate the performance of the vehicle scheduling strategy.

In some embodiments, the vehicle operating state generating module 11 includes:

the initialization module 111 is used for initializing the running states of the vehicles on each road section at the first moment according to a vehicle scheduling strategy; and

and the probability calculation module 112 is used for calculating the probability of the vehicle running state on each road section at the first moment according to the vehicle running state model.

In some embodiments, the initialization module 111 is further configured to initialize the operating status of the vehicle on each road segment at the second or more times according to a vehicle dispatch strategy; and

the probability calculation module 112 is further configured to calculate the probability of the vehicle operating state on each road segment at the second or more time instants according to the vehicle operating state model.

In some embodiments, the performance calculation module 12 is configured to calculate a sum of performance parameters of the vehicle scheduling strategy, such as a transportation volume of the vehicle or a travel distance of the vehicle, at a plurality of times based on a probability distribution of the vehicle's behavior of operation on the respective segments of the transportation route at the plurality of times.

In some embodiments, the evaluation device 10 may further include a data acquisition module 13 for acquiring actual vehicle driving measurement data for constructing the vehicle operating state model. The data acquisition module 13 may include, for example, various analog-digital collectors, cameras, radar, and the like.

The evaluation device 10 according to an embodiment of the present disclosure may be used to implement the above-described evaluation method or optimization method of the vehicle scheduling policy. The evaluation device 10 may be a field device or a remote device, for example, may be disposed in the cloud and communicate with a field vehicle and/or a control center via a cloud network.

In some embodiments, the modules in the above-mentioned evaluation apparatus 10 may be respectively disposed in different devices, or may be partially or wholly integrated in the same device.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure. In some embodiments, the electronic device includes at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of evaluating or optimizing a vehicle dispatch strategy according to any of the embodiments described above. In some embodiments, the readable storage medium may be a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method for evaluating or optimizing a vehicle dispatch strategy according to any of the embodiments described above. In some embodiments, the computer program product comprises a computer program which, when executed by a processor, implements a method of evaluating or optimizing a vehicle dispatch strategy according to any of the embodiments described above.

FIG. 11 is a system block diagram of a remote control for implementing an evaluation method or optimization method of a vehicle dispatch strategy in accordance with another embodiment of the present disclosure. It should be noted that fig. 11 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 11, the system architecture 200 according to this embodiment may include a terminal device 201, a network 202, and a server 203. The network 202 serves as a medium for providing a communication link between the terminal device 201 and the server 203. Network 202 may include various connection types, such as wired and/or wireless communication links, and so forth.

A user may use the terminal device 201 to interact with the server 203 via the network 202 to receive or send messages or the like. The terminal device 201 may be a variety of electronic devices including, but not limited to, a smart phone, a tablet computer, a laptop portable computer, and the like. The terminal device 201 may also include a vehicle.

The evaluation method or optimization method of the vehicle scheduling policy provided by the embodiments of the present disclosure may be generally performed by the server 203. The server 203 may be, for example, a cloud server.

FIG. 12 shows a schematic block diagram of an example electronic device 1100 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 12, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)1102 or a computer program loaded from a storage unit 1108 into a Random Access Memory (RAM) 1103. In the RAM 1103, various programs and data necessary for the operation of the device 1100 may also be stored. The calculation unit 1101, the ROM 1102, and the RAM 1103 are connected to each other by a bus 1104. An input/output (I/O) interface 1105 is also connected to bus 1104.

A number of components in device 1100 connect to I/O interface 1105, including: an input unit 1106 such as a keyboard, a mouse, and the like; an output unit 1107 such as various types of displays, speakers, and the like; a storage unit 1108 such as a magnetic disk, optical disk, or the like; and a communication unit 1109 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1109 allows the device 1100 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The computing unit 1101 can be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 1101 performs the respective methods and processes described above, such as a method of predicting traffic flow. For example, in some embodiments, the method of predicting traffic flow may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1100 via ROM 1102 and/or communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the method of predicting traffic flow described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured by any other suitable means (e.g., by means of firmware) to perform the method of predicting traffic flow.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method for evaluating a vehicle dispatch strategy, comprising:

generating a vehicle operating state model on each section of the transportation route based on the probability of occurrence of the vehicle on at least one section of the transportation route;

calculating probability distribution of running states of the vehicles on each road section of the transportation line based on the vehicle scheduling strategy and the vehicle running state model; and

a performance parameter of a vehicle dispatch strategy is calculated based on a probability distribution of vehicle operation states on respective segments of a transportation route to evaluate performance of the vehicle dispatch strategy.

2. The method of claim 1, wherein the vehicle operating state model is dependent on a number of the vehicles and a number of segments of a transportation route.

3. The method of claim 2, wherein the vehicle operating state model includes at least one of a single-lane function for operation of only a single vehicle on the same road segment, a multi-lane function for operation of multiple vehicles on the same road segment, and an exceptional lane function for exceptional events on a transit lane.

4. The method of claim 3, wherein,

the bicycle line function is f (o)_i-1，o_i)＝p_δt(o_i|o_i-1) Wherein o is_iRepresents whether the vehicle is present on the section i, o_i-1Representing whether the vehicle is present on the section i-1, p_δt(o_i|o_i-1C) represents the probability that the vehicle appears on the road section i at the moment t + δ t under the condition that the appearance state of the vehicle on the road section i-1 at the moment t is c, and c belongs to { appears and does not appear };

the multi-vehicle line function is

Wherein

Representing whether vehicle m is present on road section i,

representing whether vehicle m is present on road segment i-1,

representing whether vehicle n is present on road segment i-1,

5. The method according to claim 3, wherein the probability distribution of the operation time of said vehicle on the same road segment is based on a Gaussian mixture model in case only a single vehicle is operated on the same road segment, and/or the probability distribution of the operation time of each vehicle of said plurality of vehicles on the same road segment is based on a Gaussian mixture model in case a plurality of vehicles are operated on the same road segment, and/or the probability distribution of the operation time of a vehicle on a certain road segment in case an abnormal event occurs on the road segment is based on a Poisson distribution model.

6. The method of any one of claims 1 to 5, wherein said calculating a probability distribution of vehicle operating conditions over respective segments of a transportation route based on a vehicle scheduling policy and a vehicle operating condition model comprises:

initializing the running state of the vehicle on each road section at the first moment according to a vehicle scheduling strategy; and

and calculating the probability of the vehicle running state on each road section at the first moment according to the vehicle running state model.

7. The method of claim 6, wherein the calculating a probability distribution of vehicle operating conditions over various segments of a transportation route based on a vehicle dispatch strategy and a vehicle operating condition model further comprises:

initializing the running state of the vehicle on each road section at the second or more moments according to a vehicle scheduling strategy; and

and calculating the probability of the vehicle running state on each road section at the second or more moments according to the vehicle running state model.

8. The method of claim 6, wherein the probability of the vehicle operating state on a section of the transportation route depends on the probability of an abnormal event occurring on a section preceding the section and the probability of the vehicle operating state on at least one section adjacent thereto.

9. The method of any one of claims 1 to 5,

the calculating performance parameters of a vehicle dispatch strategy based on probability distributions of vehicle operation states on respective segments of a transportation route to evaluate performance of the vehicle dispatch strategy comprises:

the sum of the performance parameters of the vehicle scheduling strategy at a plurality of moments in time is calculated based on the probability distribution of the vehicle's behavior over the respective segments of the transportation route at the plurality of moments in time.

10. The method of claim 9, wherein the performance parameters of the vehicle dispatch strategy include: the volume of the vehicle or the distance traveled by the vehicle.

11. The method according to any one of claims 3 to 5, wherein the abnormal event comprises a vehicle interior control unit failure or a temporary occurrence of an obstacle in a road segment that needs to be avoided.

12. The method according to any one of claims 1 to 5, wherein the vehicle operating state model is built directly on the basis of actual vehicle travel measurement data or by fitting parameters of a parameterized model from actual vehicle travel measurement data.

13. A method for optimizing a vehicle dispatch strategy, comprising:

evaluating a plurality of vehicle dispatch strategies using the method of any one of claims 1 to 12; and

the plurality of vehicle dispatch strategies are compared to select a preferred strategy.

14. An apparatus for evaluating a vehicle dispatch strategy, comprising:

a vehicle operation state generation module for calculating probability distribution of vehicle operation states on each section of the transportation line based on a vehicle scheduling strategy and a vehicle operation state model on each section of the transportation line, wherein the vehicle operation state model is generated based on the occurrence probability of the vehicle on at least one section of the transportation line; and

the performance calculation module is used for calculating performance parameters of the vehicle scheduling strategy based on the probability distribution of the running states of the vehicles on each road section of the transportation line so as to evaluate the performance of the vehicle scheduling strategy.

15. The apparatus for evaluating a vehicle dispatch strategy of claim 14, wherein the vehicle operating state model comprises at least one of a single lane function for operation of only a single vehicle on a same road segment, a multiple lane function for operation of multiple vehicles on a same road segment, and an exception event lane function for an exception event on a transit lane.

16. The vehicle dispatch strategy evaluation device of claim 15, wherein the vehicle operating state generation module comprises:

the initialization module is used for initializing the running state of the vehicle on each road section at the first moment according to the vehicle scheduling strategy; and

and the probability calculation module is used for calculating the probability of the vehicle running state on each road section at the first moment according to the vehicle running state model.

17. The vehicle dispatch strategy evaluation apparatus of claim 16, wherein the initialization module is further configured to initialize the operating status of the vehicle on each road segment at a second or more time instants in accordance with the vehicle dispatch strategy; and

the probability calculation module is further configured to calculate the probability of the vehicle operation state on each road segment at the second or more moments in time based on the vehicle operation state model.

18. The apparatus for evaluating a vehicle dispatch strategy of claim 16, wherein the probability of a vehicle operating condition on a segment of a transportation route is dependent on the probability of an anomalous event occurring on a segment preceding the segment and the probability of a vehicle operating condition on at least one segment adjacent thereto.

19. The apparatus for evaluating a vehicle dispatching strategy according to any of claims 14 to 18,

the performance calculation module is configured to calculate a sum of performance parameters of the vehicle scheduling strategy at a plurality of moments, the performance parameters being a transportation volume of the vehicle or a travel distance of the vehicle, based on a probability distribution of vehicle operation states at the plurality of moments on respective segments of the transportation route.

20. The apparatus for evaluating a vehicle dispatching strategy according to any of claims 14 to 18, further comprising:

and the data acquisition module is used for acquiring actual vehicle running measurement data and constructing the vehicle running state model.

21. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-13.

22. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-13.

23. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-13.