CN115103331B - A method for determining the working efficiency of a roadside unit and a related device - Google Patents

Abstract

The application provides a method and a related device for determining the working efficiency of a road side unit, wherein the method comprises the following steps: acquiring the working state of a first road side unit; when the working state of the first road side unit is an on state, distributing all or part of communication demand flow in the target communication demand flow to the first road side unit, wherein the communication flow distributed to the first road side unit is smaller than or equal to a first threshold value; determining a first combination according to the working state of the first road side unit, wherein the first combination is used for representing a value arrangement of the working state of each road side unit in the N road side units in a first time period; and determining a first numerical value corresponding to the first combination according to the product of the distribution completion degree of the total communication demand flow and the communication flow transmitted by each unit energy consumption of the N road side units, wherein the first numerical value is in direct proportion to the working efficiency of the N road side units. And the working efficiency of the road side unit is represented by the first numerical value.

Description

A method for determining the working efficiency of a roadside unit and a related device

Technical Field

The present application relates to the field of computers, and in particular to a method for determining the working efficiency of a roadside unit and related products.

Background technique

As the core of the future intelligent transportation system, vehicle-to-infrastructure (V2I) communication achieves collaboration through information exchange between vehicles and road infrastructure, significantly improving traffic safety and efficiency.

Due to the uneven temporal and spatial distribution of V2I communication services, a large number of roadside units may be in a low-load or no-load state for a long time, but they still need to consume basic energy to maintain their normal operation. The basic power of the roadside unit accounts for more than 60% of the total power, resulting in huge energy waste. When the roadside unit is in a sleep state, the average power consumption can be reduced by more than 75%.

In one implementation method, some idle RSUs are turned off in scenarios with sparse traffic flow, such as late at night or in suburbs, and only some RSUs are left on duty for communication. For example, one RSU is turned on for every other RSU. However, among the many RSU scheduling schemes, there is no criterion to judge which scheduling scheme can make the RSU work more efficiently, resulting in most RSU on-duty scheduling schemes being too simple and fixed, and unable to make corresponding changes considering the specific characteristics of traffic flow.

Therefore, how to determine the working efficiency of the roadside unit under the roadside unit scheduling scheme has become an important research topic in the technical field.

Summary of the invention

In the first aspect, the present application provides a method for determining the working efficiency of a roadside unit, the method comprising: obtaining the working state of a first roadside unit, the first roadside unit being any one of N roadside units sequentially distributed in a first driving direction, the first driving direction being the direction of passage of a first lane, and the working state of the first roadside unit being an open state or a closed state; when the working state of the first roadside unit is the open state, all or part of the target communication demand flow is allocated to the first roadside unit, and the communication flow allocated to the first roadside unit is less than or equal to a first threshold, the target communication demand flow is the sum of a first cumulative unallocated flow and a first communication demand flow of traffic flow within a first time period within the communication coverage range of the first roadside unit, and the first cumulative unallocated flow is one or more communication demand flows before the first roadside unit in the opposite direction of the first driving direction. The communication demand flow that has not been allocated and completed is determined in the communication demand flow of the traffic flow within the communication range of the first roadside unit, and the first threshold is the maximum communication flow that can be completed by the traffic flow within the communication coverage range of the first roadside unit; when the working state of the first roadside unit is the closed state, the communication demand flow is not allocated to the first roadside unit; a first combination is determined according to the working state of the first roadside unit, and the first combination is used to represent a value arrangement of the working state of each of the N roadside units in the first time period; a first value corresponding to the first combination is determined according to the degree of completion of the allocation of the total communication demand flow and the product of the communication flow transmitted by the N roadside units per unit energy consumption, and the first value is proportional to the working efficiency of the N roadside units, and the total communication demand flow is the sum of the communication demand flows of the traffic flow within the communication coverage range of each of the N roadside units.

It can be understood that by adopting the preset allocation method provided in the present application (that is, when the working state of the first roadside unit is the open state, all or part of the target communication demand flow is allocated to the first roadside unit, and the communication flow allocated to the first roadside unit is less than or equal to the first threshold), on the one hand, it is determined that the communication demand flow allocated to the first roadside unit is less than or equal to the maximum communication demand flow that can be completed by the traffic flow at the first roadside unit; on the other hand, since the vehicle always passes through the first roadside unit first and then passes through the roadside unit in front of the first driving direction of the first roadside unit during the movement, the communication flow generated by the vehicle at the first roadside unit needs to be allocated to the first roadside unit or the roadside unit in front of the first roadside unit to complete; that is, by adopting the allocation method of the present application, it can be ensured that the communication demand flow of the first roadside unit is allocated to the first roadside unit or the roadside unit in front of the first driving direction of the first roadside unit, which complies with the travel rules of the traffic flow.

It can be understood that the product of the degree of completion of the distribution of the above-mentioned total communication demand flow and the communication flow transmitted by N roadside units per unit energy consumption is used as an indicator to measure work efficiency. On the one hand, it is considered that the communication demand flow generated by the traffic flow within the communication coverage of the roadside unit should be completed as much as possible. On the other hand, energy consumption is saved while meeting the communication needs. Therefore, the first numerical indicator is to achieve optimal energy consumption while ensuring the quality of V2I communication, and to achieve a balance between V2I communication quality and roadside unit energy consumption. Therefore, the use of the first numerical value as an indicator of work efficiency is objective and accurate.

Therefore, the method provided in the embodiment of the present application can characterize the working efficiency of the roadside unit by the above-mentioned first numerical value (that is, the product of the degree of completion of the allocation of the total communication demand flow and the communication flow transmitted by N roadside units per unit energy consumption). Even if the existing scheduling scheme is simple and fixed, the method for determining the working efficiency of the roadside unit provided in the present application can be used to select a scheduling scheme with better working efficiency from a plurality of simple and fixed scheduling schemes to perform operations.

In a possible implementation, the determining of the first value corresponding to the first combination according to the product of the degree of completion of the allocation of the total communication demand flow and the communication flow transmitted by the N roadside units per unit energy consumption includes: determining the first value corresponding to the target moment, the target moment being any preset moment in the process of allocating all or part of the communication demand flow in the target communication demand flow to the first roadside unit to determine the first combination; determining a first loss value corresponding to the target moment, wherein the first loss value is 0 when the first cumulative unallocated flow is 0 at the target moment, and the first loss value is a preset loss value when the first cumulative unallocated flow is greater than 0 at the target moment; and determining the reward value corresponding to the target moment according to the difference between a third value and a fourth value, the third value being the product of a first weight and the first value, and the fourth value being the product of a second weight and the first loss value; calculating a first long-term reward value corresponding to the first combination according to a preset discount factor and the reward value corresponding to each of the at least two target moments corresponding to the first combination; the first long-term reward value is proportional to the working efficiency of the N roadside units.

Therefore, by characterizing the working efficiency of the roadside unit through the above-mentioned first long-term reward value, the indicator for evaluating the working efficiency of the roadside unit under the roadside unit scheduling scheme can be made more accurate.

In a possible implementation, obtaining the working state of the first roadside unit includes: determining to set the working state of the first roadside unit to one of the on state and the off state according to the first communication demand flow and/or the first accumulated unallocated flow.

Exemplarily, it can be based on whether the size of the first communication demand flow and/or the first accumulated unallocated flow is greater than a preset threshold value used to indicate that the communication demand flow of the traffic flow within the communication coverage of the first roadside unit is large. If so, the first roadside unit is turned on. Otherwise, it is not turned on, or if otherwise, there are two situations: trying to turn it on and not turning it on. Exemplarily, it can also be based on whether a traffic light is installed within the communication coverage of the first roadside unit. If so, the first roadside unit is turned on.

Generally, the commonly used energy optimization strategy is to shut down some idle RSUs in scenarios with sparse traffic flow such as late at night or in suburbs, leaving only some RSUs on duty for communication. Obviously, this RSU scheduling scheme is too simple and rigid without considering the specific characteristics of traffic flow, and cannot adapt to real-time changes in traffic flow.

By adopting the method provided in the embodiment of the present application, it is determined whether to turn on the first roadside unit according to the specific communication requirements of the traffic flow for the first roadside unit, and after each of the N roadside units performs the same operation of determining whether to turn on as the first roadside unit, each value in the above-mentioned first combination can be completely determined, and the working efficiency corresponding to the first combination can be determined according to the method for determining the working efficiency of the roadside unit provided in the present application. Therefore, it can be determined whether the scheduling scheme corresponding to the first combination needs to be used according to the corresponding working efficiency, so as to implement a scheduling scheme with better working efficiency to adapt to the real-time changes in traffic flow.

In a possible implementation, the determining, according to the first communication demand flow and/or the first accumulated unallocated flow, to set the working state of the first roadside unit to one of the open state and the closed state comprises: determining whether the target communication demand flow is greater than a second threshold, the second threshold being determined according to one half of the first threshold; if it is determined that the target communication demand flow is greater than the second threshold, setting the working state of the first roadside unit to the open state; if it is determined that the target communication demand flow is greater than the second threshold, respectively trying to set the working state of the first roadside unit to a value combination of the open state or the closed state, and respectively obtaining corresponding two or more first combinations; the calculating, according to a preset discount factor and the reward value corresponding to each of the at least two target moments corresponding to the first combination, the first long-term reward value corresponding to the first combination comprises: determining the first long-term reward value corresponding to each of the two or more first combinations; determining the maximum value of the first long-term reward values corresponding to each of the two or more first combinations as the target long-term reward value; and determining the working states of the N roadside units in the first time period based on the first combination corresponding to the long-term reward value.

Optionally, the value of the second threshold may be half of the first threshold, or other suitable values. Exemplarily, the value of the second threshold may also be four-fifths of the first threshold, which is not limited in this document.

Therefore, through the method for determining the working efficiency of the roadside unit provided by the embodiment of the present application, on the one hand, through the preset opening mode (when it is determined that the target communication demand flow is greater than the second threshold, the working state of the first roadside unit is set to the opening state; when it is determined that the target communication demand flow is greater than the second threshold, the working state of the first roadside unit is respectively tried to be set to the combination of the values of the opening state or the closing state), according to the specific communication demand of the traffic flow for the first roadside unit, it is determined whether to turn on the first roadside unit, so as to avoid the problem that the roadside unit scheduling scheme is too simple and rigid and cannot adapt to the real-time changes of the traffic flow. On the other hand, the optimal working efficiency among the working efficiencies corresponding to multiple scheduling schemes (that is, two or more first combinations) is determined by the corresponding preset opening mode, preset allocation mode, and the index (that is, the first value) for evaluating the working efficiency of the roadside unit under the scheduling scheme, and the scheduling scheme of the roadside unit is determined by the optimal working efficiency, so as to further solve the problem of poor working efficiency of the roadside unit scheduling scheme.

In one possible implementation, the first communication demand flow is the average communication demand flow in the communication demand flow data of the traffic flow within the communication coverage of the first roadside unit in at least two historical time periods corresponding to the first time period. The method also includes: determining that the stay time of the traffic flow within the communication coverage of the first roadside unit in at least two historical time periods corresponding to the first time period satisfies the first expected stay time of the normal distribution, determining that the number of communication requests per minute of the traffic flow within the communication coverage of the first roadside unit in at least two historical time periods corresponding to the first time period satisfies the first expected number of requests of the Poisson distribution, and determining that the communication demand flow per minute of the traffic flow within the communication coverage of the first roadside unit in at least two historical time periods corresponding to the first time period satisfies the first expected communication demand flow of the normal distribution; determining the first communication demand flow based on the product of the first expected stay time, the first expected number of requests and the first expected communication demand flow.

Therefore, through the method for determining the working efficiency of the roadside unit provided by the embodiment of the present application, on the one hand, the traffic flow characteristics of the traffic flow in the first time period can be characterized by the traffic flow characteristics reflected in two or more historical time periods corresponding to the first time period, and the changing characteristics of the traffic flow can be comprehensively considered to determine a scheduling plan that maximizes the working efficiency of the roadside unit corresponding to the traffic flow conditions in the first time period, further solving the problem that the roadside unit scheduling plan is too simple and rigid and cannot adapt to the real-time changes in traffic flow. On the other hand, by using data statistics, the traffic flow characteristics of the traffic flow in the first time period obtained based on the traffic flow characteristics of the historical time periods that have a consistent relationship with the first time period and the mathematical function statistics are more representative, which can make the calculated working efficiency of the roadside unit scheduling plan more accurate.

In a possible implementation, before obtaining the working status of the first roadside unit, the method also includes: obtaining any one element in a combination set as the first combination, the combination set including at least one element for indicating the working status of each of the N roadside units; obtaining the working status of the first roadside unit includes: determining the working status of the first roadside unit according to the first combination; calculating the first long-term reward value corresponding to the first combination according to a preset discount factor and the reward value corresponding to each of the at least two target moments corresponding to the first combination, including: determining the first long-term reward value corresponding to each of the first combinations in the combination set; determining the maximum value of the first long-term reward values corresponding to each of the first combinations in the combination set as the target long-term reward value; and determining the working status of the N roadside units based on the first combination corresponding to the target long-term reward value.

In one possible implementation, the degree of completion of the allocation of the total communication demand is the ratio of the sum of the communication demand flows allocated to each of the N roadside units to the total communication demand flow; the communication flow transmitted by the N roadside units per unit energy consumption is the ratio of the total communication demand flow to the sum of the energy consumption of each of the N roadside units.

In one possible implementation, allocating all or part of the target communication demand traffic to the first roadside unit, and the communication traffic allocated to the first roadside unit is less than or equal to a first threshold, includes: determining whether the target communication demand traffic is less than or equal to the first threshold; if it is determined that the target communication demand traffic is less than or equal to the first threshold, allocating all of the target communication demand traffic to the first roadside unit; if it is determined that the target communication demand traffic is greater than the first threshold, allocating all or part of the target communication demand traffic to the first roadside unit according to a strategy in which the priority assigned to the first accumulated unallocated traffic is higher than the priority assigned to the first communication demand traffic, and the communication traffic allocated to the first roadside unit is equal to the first threshold.

In a possible implementation, the method also includes: determining the first threshold; the determining the first threshold includes: when the product of the first stay time and the communication rate of the first roadside unit is less than or equal to the maximum bandwidth of the first roadside unit, the first threshold is taken as the product of the first stay time and the communication rate of the first roadside unit; the first stay time is the stay time of the traffic flow within the communication coverage of the first roadside unit; when the product of the first stay time and the communication rate of the first roadside unit is greater than the maximum bandwidth of the first roadside unit, the first threshold is taken as the maximum bandwidth of the first roadside unit.

In a possible implementation, the first lane belongs to a first road, and the first road also includes at least one second lane, and the travel direction of the second lane is opposite to the travel direction of the first lane; the target communication demand flow is the sum of the first cumulative unallocated flow, the first communication demand flow, and the second cumulative unallocated flow, and the second cumulative unallocated flow is the unallocated communication demand flow in the communication demand flow of the traffic flow within the communication range of one or more roadside units before the first roadside unit in the opposite direction of the second driving direction, and the second driving direction is the travel direction of the second lane.

In a possible implementation, the energy consumption of each of the N roadside units is calculated in the following manner: for the i-th roadside unit among the N roadside units, when the working state of the i-th roadside unit is the closed state, the energy consumption of the i-th roadside unit is the preset sleep energy consumption, and i is a positive integer greater than or equal to 1 and less than or equal to N; when the working state of the i-th roadside unit is the open state, the energy consumption of the i-th roadside unit is the sum of the product of the preset communication energy consumption and the degree of use of the bandwidth resources of the i-th roadside unit and the preset basic energy consumption; the degree of use of the bandwidth resources of the i-th roadside unit is the ratio of the total communication demand flow allocated to the i-th roadside unit to the maximum communication flow corresponding to the i-th roadside unit, the maximum communication flow is determined according to the product of the average stay time of the traffic flow in the first direction within the communication coverage range of the i-th roadside unit and the communication rate of the i-th roadside unit, and the maximum communication flow is used to represent the maximum communication flow that can be completed by the traffic flow within the communication coverage range of the i-th roadside unit.

In a second aspect, the present application provides a device for determining working efficiency of a roadside unit, the device comprising: an acquisition unit, configured to acquire a working state of a first roadside unit, the first roadside unit being any one of N roadside units sequentially distributed in a first driving direction, the first driving direction being a passing direction of a first lane, and the working state of the first roadside unit being an on state or a off state;

an allocation unit, for allocating all or part of the target communication demand flow to the first roadside unit when the working state of the first roadside unit is the on state, and the communication flow allocated to the first roadside unit is less than or equal to a first threshold value, the target communication demand flow is the sum of a first cumulative unallocated flow and a first communication demand flow of the traffic flow within the communication coverage of the first roadside unit in a first time period, the first cumulative unallocated flow is the communication demand flow that has not been allocated in the communication demand flow of the traffic flow within the communication range of one or more roadside units before the first roadside unit in the opposite direction of the first driving direction, and the first threshold value is the maximum communication flow that can be completed by the traffic flow within the communication coverage of the first roadside unit; and, when the working state of the first roadside unit is the off state, not allocating the communication demand flow to the first roadside unit;

A first determining unit, configured to determine a first combination according to the working state of the first roadside unit, wherein the first combination is used to represent a value arrangement of the working state of each roadside unit of the N roadside units in the first time period;

The second determination unit is used to determine a first value corresponding to the first combination based on the degree of completion of the allocation of the total communication demand flow and the product of the communication flow transmitted by the N roadside units per unit energy consumption, wherein the first value is proportional to the working efficiency of the N roadside units, and the total communication demand flow is the sum of the communication demand flows of the traffic flow within the communication coverage range of each of the N roadside units.

In a third aspect, the present application provides an electronic device, comprising: a memory and a processor, wherein the memory stores program instructions; when the program instructions are executed by the processor, the processor executes the method described in the first aspect and any possible implementation method of the first aspect.

In a fourth aspect, an embodiment of the present application provides a chip system, which is applied to an electronic device, and the chip system includes one or more processors, which are used to call computer instructions so that the electronic device executes the method shown in the first aspect or any possible implementation of the first aspect.

In a fifth aspect, the present application provides a computer-readable storage medium, which stores a computer program; when the computer program runs on one or more processors, the terminal device executes the method described in the first aspect and any possible implementation method of the first aspect.

In a sixth aspect, the present application provides a computer program product comprising instructions, which, when executed on a terminal device, enables the terminal device to execute the method described in the first aspect and any possible implementation manner of the first aspect.

It can be understood that the device for determining the working efficiency of the roadside unit provided in the second aspect, the electronic device provided in the third aspect, the chip system provided in the fourth aspect, the computer storage medium provided in the fifth aspect, and the computer program product provided in the sixth aspect are all used to execute the method shown in the first aspect of the embodiment of the present application or any implementation of the first aspect. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below.

FIG1 is a schematic diagram of an application environment of a method for determining working efficiency of a roadside unit provided in an embodiment of the present application;

FIG2 is a flow chart of a method for determining the working efficiency of a roadside unit provided in an embodiment of the present application;

FIG3A is a schematic diagram related to traffic flow provided in an embodiment of the present application;

FIG3B is a schematic diagram of a direction opposite to the first driving direction provided by an embodiment of the present application;

FIG3C is a schematic diagram of another direction opposite to the first driving direction provided by an embodiment of the present application;

FIG3D is a schematic diagram of a direction opposite to the first driving direction and a direction opposite to the second driving direction provided by an embodiment of the present application;

FIG4 is a flow chart of another method for determining the working efficiency of a roadside unit provided in an embodiment of the present application;

FIG5 is a flow chart of another method for determining the working efficiency of a roadside unit provided in an embodiment of the present application;

FIG6 is a schematic diagram of the principle of model solving provided in an embodiment of the present application;

FIG7 is a schematic diagram of an experimental environment provided in an embodiment of the present application;

FIG8 is a schematic diagram of the length of time that a traffic flow stays within the coverage area of each roadside unit provided in an embodiment of the present application;

FIG9 is a schematic diagram of a communication demand flow of a traffic flow within the coverage area of each roadside unit provided in an embodiment of the present application;

FIG10 is a schematic diagram of the working efficiency of a roadside unit scheduling solution determined by using different models provided in an embodiment of the present application;

FIG11 is a schematic diagram of the structure of a device for determining the working efficiency of a roadside unit provided in an embodiment of the present application;

FIG. 12 is a schematic diagram of the structure of another device for determining the working efficiency of a roadside unit provided in an embodiment of the present application

FIG13 is a schematic diagram of the structure of another device for determining the working efficiency of a roadside unit provided in an embodiment of the present application.

Detailed ways

The present application is described in further detail below in conjunction with the accompanying drawings.

The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations on the present application. As used in the specification and appended claims of the present application, the singular expressions "a", "a", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context.

In the present application, "at least one (item)" means one or more, "more than one" means two or more, "at least two (items)" means two or three and more than three, and "and/or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and/or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character "/" generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c".

FIG1 is a schematic diagram of an application environment of a method for determining working efficiency of a roadside unit provided in the present application.

As shown in Figure 1, the Road Side Unit (RSU) is installed on the roadside of highways, expressways or parking lot management, and the most common RSU is a base station type RSU. The main task of the RSU is to communicate with roadside sensing equipment (such as speed sensors, etc.), traffic lights, electronic signs and other terminals through the communication network to collect current road conditions, traffic conditions and other information. When the on-board unit in the vehicle sends a communication request to the RSU, it will promptly process the communication request of the on-board unit to realize functions such as vehicle-road interconnection and real-time interaction of traffic signals, assist the driver in driving, and ensure the safety of people and vehicles in the entire transportation field.

The method for determining the working efficiency of a roadside unit provided in this application is applicable to both 4G roadside units and 5G roadside units, and this document does not limit this.

Embodiment 1:

The following is a detailed description of the method for determining the working efficiency of a roadside unit provided in an embodiment of the present application in conjunction with FIG. 2 .

In an embodiment of the present application, the method for determining the working efficiency of a roadside unit provided in an embodiment of the present application can be executed by a device for determining the working efficiency of a roadside unit. For ease of description below, the execution subject of the step of determining the working efficiency of a roadside unit will be omitted.

As shown in FIG2 , the method for determining the working efficiency of the roadside unit includes the following steps:

S201, obtaining a working status of a first roadside unit, where the first roadside unit is any one of N roadside units sequentially distributed in a first driving direction.

It is understandable that in different regions, the first driving direction may be that the vehicle drives on the left side of the road or the vehicle drives on the right side of the road, which is determined according to the specific regional environment. This article does not limit the specific definition of the first driving direction.

In the embodiment of the present application, the first driving direction is the passing direction of the first lane. Exemplarily, the first lane belongs to the first road, the first road includes at least one first lane, a first lane has a passing direction, and the passing directions of each first lane may be the same or opposite.

Exemplarily, the working state of the first roadside unit can be an on state or an off state. The on state can also be understood as a duty state, and the off state can also be understood as a sleep state. When the working state of the roadside unit is the duty state, the energy consumption of the roadside unit includes basic energy consumption and communication energy consumption, wherein the basic energy consumption is generally a constant, and the communication energy consumption is positively correlated with the workload. When the working state of the roadside unit is the sleep state, the energy consumption of the roadside unit is the sleep power consumption, and the sleep power consumption is generally a constant.

In the embodiment of the present application, there are three ways to obtain the working status of the first roadside unit:

Method 1: Acquire the working status of the first roadside unit according to a combination of the working statuses of the N roadside units input by the user.

Exemplarily, every other roadside unit is turned on. For this user-defined turning-on method, the working state of the first roadside unit can be determined according to the user's input.

Method 2: The device for determining the working efficiency of the roadside unit traverses different value combinations of the above-mentioned N roadside units, and determines the working state of the above-mentioned first roadside unit according to the currently traversed combination.

Exemplarily, different value combinations of the above-mentioned N roadside units form a combination set, and any element in the combination set is used to indicate the working status of each roadside unit in the above-mentioned N roadside units. The combination set can include at most 2 to the power of N elements and at least one element.

Method 3: Determine the working status of the first roadside unit according to the activation rule.

Exemplarily, the activation rule is to determine whether the working state of the first roadside unit is set to one of the on state and the off state based on whether the sum of the first communication demand flow and the first accumulated unallocated flow (collectively referred to as the target communication demand flow) of the traffic flow within the communication coverage area of the first roadside unit is greater than or equal to a second threshold.

For example, the first accumulated unallocated traffic is the unallocated communication demand traffic among the communication demand traffic within the communication range of one or more roadside units in the opposite direction of the first driving direction of the first roadside unit, and the second threshold is determined based on half of the first threshold, which is the maximum communication traffic that can be completed by the traffic flow within the communication coverage range of the first roadside unit.

If the target communication demand flow is greater than the second threshold, the working state of the first road side unit is set to the on state. If the target communication demand flow is less than the second threshold, the working state of the first road side unit is tried to be set to the on state or the off state, respectively, and two or more corresponding first combinations are obtained.

S202: when the working state of the first roadside unit is the on state, all or part of the target communication demand flow is allocated to the first roadside unit.

In the embodiment of the present application, it is also necessary to meet the requirement that the communication demand flow allocated to the first roadside unit is less than or equal to the maximum communication flow that can be completed by the traffic flow within the communication coverage area of the first roadside unit (represented as the first threshold).

In the embodiment of the present application, when the working state of the first roadside unit is the closed state, the communication demand flow is not allocated to the first roadside unit.

In an embodiment of the present application, the traffic flow includes one or more vehicles, and the first dwell time represents the time required for the one or more vehicles included in the communication coverage distance of the first roadside unit in the first driving direction to pass through the first roadside unit. Exemplarily, as shown in FIG3A , if the communication distance of the first roadside unit in the corresponding first driving direction is L, the length of the traffic flow is L. It is understandable that at the same time, the first roadside unit can only provide communication services for a traffic flow with a length equal to L at most, that is, at the same time, the first roadside unit only needs to meet the communication demand flow of one traffic flow at most.

The first vehicle (first vehicle) entering the first roadside unit is taken as the starting point of L, and the end point of L is the point at a distance L from the first roadside unit. The number of vehicles included from the starting point of L to the end point of L is the number of vehicles included in the traffic flow. The duration of time that the vehicles included in the traffic flow pass through the first roadside unit is the required duration of the traffic flow passing through the roadside unit. It can be understood that the average of the length of time that two or more traffic flows stay in the first roadside unit in the first time period is recorded as the average length of time that they stay, the average of the number of communication requests when the two or more traffic flows stay in the first roadside unit in the first time period is recorded as the average number of communication requests, and the average of the communication demand flow of each communication request when the two or more traffic flows stay in the first roadside unit in the first time period is recorded as the average communication demand flow. The product of the above average length of time, the average communication demand flow and the average number of communication requests can represent the average communication demand flow of each traffic flow for the first roadside unit in the first time period. Thus, the communication demand flow of the traffic flow to the first roadside unit at each moment in the first time period is obtained, that is, the communication demand flow of the traffic flow within the communication coverage of the first roadside unit.

In the embodiment of the present application, the first threshold is the maximum communication flow that can be completed by the traffic flow within the communication coverage of the first roadside unit. In some implementations, the first threshold is determined by the maximum bandwidth of the first roadside unit, and in other implementations, the first threshold is determined by the maximum communication demand flow that can be completed by the traffic flow passing through the first roadside unit.

Exemplarily, the length of time that the traffic flow stays within the communication coverage of the first roadside unit is recorded as the first length of stay. If the product of the first length of stay and the communication rate of the first roadside unit (indicating the maximum communication demand flow that the traffic flow can complete through the first roadside unit) is less than or equal to the maximum bandwidth of the first roadside unit, then the first threshold value is the product of the first length of stay and the communication rate of the first roadside unit. If the product of the first length of stay and the communication rate of the first roadside unit is greater than the maximum bandwidth of the first roadside unit, then the first threshold value is the maximum bandwidth of the first roadside unit.

In an embodiment of the present application, the above-mentioned target communication demand flow includes a first communication demand flow and a first accumulated unallocated flow of traffic flow within the communication coverage of the first roadside unit in a first time period, and the first accumulated unallocated flow is the unallocated communication demand flow of the traffic flow corresponding to the first driving direction within the communication range of one or more roadside units in the opposite direction of the above-mentioned first driving direction of the above-mentioned first roadside unit.

Exemplarily, if the direction of travel of the first lane is from left to right, then the above-mentioned first driving direction is from left to right. For the convenience of description, the traffic flow traveling from left to right is also referred to as forward traffic flow in some descriptions of this article. Exemplarily, as shown in FIG3B , the first driving direction is from left to right; wherein, RSU3 is the above-mentioned first roadside unit, then the above-mentioned first accumulated unallocated flow is the communication demand flow of the traffic flow within the communication coverage range of the roadside unit before RSU3 (that is, RSU1 and RSU2) in the first driving direction that has not been allocated.

If the driving direction of the first lane is from right to left, then the above-mentioned first driving direction is from right to left. For the convenience of description, the traffic flow passing from right to left is also referred to as reverse traffic flow in some descriptions of this article. Exemplarily, as shown in FIG3C , the first driving direction is from right to left; wherein RSU3 is the above-mentioned first roadside unit, then the above-mentioned first accumulated unallocated flow is the communication demand flow of the traffic flow within the communication coverage range of the roadside unit before RSU3 (that is, RSU4 and RSU5) in the first driving direction that has not been allocated.

In a possible implementation, the first lane belongs to a first road, and the first road also includes at least one second lane, and the travel direction of the second lane is opposite to the travel direction of the first lane; the target communication demand flow is the sum of the first cumulative unallocated flow, the first communication demand flow, and the second cumulative unallocated flow, and the second cumulative unallocated flow is the unallocated communication demand flow in the communication demand flow of the traffic flow within the communication range of one or more roadside units before the first roadside unit in the opposite direction of the second driving direction, and the second driving direction is the travel direction of the second lane.

That is to say, if the first road also includes a second lane, and the travel direction of the second lane is opposite to that of the first lane, then the target communication demand flow also includes the second accumulated unallocated flow. Exemplarily, as shown in FIG3D , the first driving direction is from left to right, and the second driving direction is from right to left; wherein RSU3 is the first roadside unit, then the first accumulated unallocated flow includes the communication demand flow of the traffic flow within the communication coverage of the roadside unit (i.e., RSU1 and RSU2) before RSU3 in the first driving direction, and the second accumulated unallocated flow includes the communication demand flow of the traffic flow within the communication coverage of the roadside unit (i.e., RSU4 and RSU5) before RSU3 in the second driving direction, and the communication demand flow of the traffic flow within the communication coverage of the roadside unit (i.e., RSU4 and RSU5) before RSU3 in the second driving direction.

It is understandable that the first time period is any time period. For example, if the user wants to determine the working efficiency of the first combination from 9:00 to 10:00 on the same day through the method for determining the working efficiency of the roadside unit provided in the embodiment of the present application, the first time period is from 9:00 to 10:00 on the same day. In the embodiment of the present application, the communication demand flow of the traffic flow to the first roadside unit in the first time period can be characterized by the communication demand flow of the traffic flow to the first roadside unit in some historical time before the first time period.

Exemplarily, the first time period is from 9:00 to 10:00 on the same day, and the communication demand flow of traffic flow to the first roadside unit from 8:00 to 9:00 on the same day can be used to characterize the communication demand flow of traffic flow to the first roadside unit from 9:00 to 10:00 on the same day.

Exemplarily, the first time period is 9:00 to 10:00 on the same day (current time). The communication demand flow of the traffic flow to the first roadside unit in the first time period can also be characterized by the average communication demand flow of the traffic flow to the first roadside unit in the 15 days before the current time that has a consistent relationship with the first time period (9:00 to 10:00) (for example, the time period from 9:00 to 10:00 every day of the 15 days).

In a possible implementation, the above-mentioned allocating all or part of the target communication demand traffic to the first roadside unit, and the communication traffic allocated to the first roadside unit is less than or equal to the first threshold, specifically includes: determining whether the target communication demand traffic is less than or equal to the first threshold; if so, allocating all of the target communication demand traffic to the first roadside unit; if not, allocating all or part of the target communication demand traffic to the first roadside unit based on the priority of the first accumulated unallocated traffic being allocated being higher than the priority of the first communication demand traffic being allocated.

Exemplarily, if the target communication demand flow is greater than the first threshold, the magnitude relationship between the first cumulative unallocated flow and the first threshold is determined. If the first cumulative unallocated flow is equal to the first threshold, the first cumulative unallocated flow is allocated to the first roadside unit; and the first communication demand flow is used as the remaining unallocated communication demand flow in the communication coverage of the roadside unit up to the first roadside unit (including the first roadside unit). If the first cumulative unallocated flow is less than the first threshold, the first cumulative unallocated flow is allocated to the first roadside unit, and the first threshold is subtracted from the first cumulative unallocated flow to obtain the first allocated flow, and the communication demand flow in the first communication demand flow that is consistent with the first allocated flow is allocated to the first roadside unit, and then the first communication demand flow is subtracted from the first allocated flow to obtain the remaining unallocated flow, and the remaining unallocated flow is used as the communication demand flow that has not been allocated to the first roadside unit. If the above-mentioned first accumulated unallocated flow is greater than the above-mentioned first threshold, the communication demand flow in the above-mentioned first accumulated unallocated flow that is consistent with the size of the first threshold will be allocated to the first road side unit, and the sum of the difference between the first accumulated allocated flow and the first threshold and the above-mentioned first communication demand flow will be used as the communication demand flow that has not been allocated until the first road side unit.

It is understandable that in another possible implementation method, if the target communication demand flow is greater than the above-mentioned first threshold, all or part of the target communication demand flow can be allocated to the first road side unit in a manner in which the priority assigned to the first communication demand flow is higher than the priority assigned to the first accumulated unallocated flow. This document does not limit this.

S203: Determine a first combination according to the working status of the first roadside unit.

In an embodiment of the present application, the first combination is used to represent a value arrangement of the working state of each roadside unit among the N roadside units in the first time period.

It is understandable that if the method for obtaining the working state of the first roadside unit in the above step S201 is the above method 1 or method 2, then the first combination can be determined in the above step S201, that is, the first combination does not need to be determined in step S203. If the method for obtaining the working state of the first roadside unit in the above step S201 is the above method 3, then the first combination needs to be determined after the above target communication demand flow of each first roadside unit is allocated to the corresponding first roadside unit, and step S203 needs to be executed.

In an embodiment of the present application, the communication demand flow of the first time period can be characterized by the communication demand flow of the traffic flow within the communication coverage of the roadside unit in some historical time before the first time period, and the above-mentioned first combination corresponding to the first time period can be determined based on the communication demand flow of the traffic flow within the communication coverage of the roadside unit in the historical time.

S204, determining a first value corresponding to the first combination according to the degree of completion of the allocation of the total communication demand flow and the product of the communication flow transmitted by the N roadside units per unit energy consumption, and the first value is proportional to the working efficiency of the N roadside units.

In the embodiment of the present application, the above-mentioned total communication demand flow is the sum of the communication demand flow of the traffic flow within the communication coverage area of each roadside unit among the N roadside units.

In the embodiment of the present application, the first value is proportional to the working efficiency of the N roadside units. Therefore, the working efficiency of the N roadside units can be determined by the first value, and according to the working efficiency corresponding to the first combination, it is determined whether to determine the working status of the N roadside units in the first time period according to the first combination.

In one possible implementation, the degree of completion of the allocation of the total communication demand is the ratio of the sum of the communication demand flows allocated to each of the N roadside units to the total communication demand flow; the communication flow transmitted by the N roadside units per unit energy consumption is the ratio of the total communication demand flow to the sum of the energy consumption of each of the N roadside units.

Therefore, the method for determining the working efficiency of the roadside unit provided in the embodiment of the present application can determine which combination of roadside units can make the working efficiency of the roadside unit better, so that the roadside unit can be turned on according to the working efficiency corresponding to different combinations in different time periods, avoiding blindly and fixedly using the same opening method to turn on the roadside unit, resulting in communication needs not being met, or increasing the energy consumption of the roadside unit.

Embodiment 2:

In a possible implementation, the method of determining the first value corresponding to the first combination according to the product of the degree of completion of the allocation of the total communication demand flow and the communication flow transmitted by the N roadside units per unit energy consumption includes: determining the first value corresponding to the target moment, the target moment being any preset moment in the process of allocating all or part of the communication demand flow in the target communication demand flow to the first roadside unit to determine the first combination; determining a first loss value corresponding to the target moment, wherein the first loss value is 0 when the first cumulative unallocated flow is 0 at the target moment, and the first loss value is a preset loss value when the first cumulative unallocated flow is greater than 0 at the target moment; and determining the reward value corresponding to the target moment according to the difference between a third value and a fourth value, the third value being the product of a first weight and the first value, and the fourth value being the product of a second weight and the first loss value; calculating a first long-term reward value corresponding to the first combination according to a preset discount factor and the reward value corresponding to each of the at least two target moments corresponding to the first combination; the first long-term reward value is proportional to the working efficiency of the N roadside units.

In a possible implementation, obtaining the working state of the first roadside unit includes: determining to set the working state of the first roadside unit to one of the on state and the off state according to the first communication demand flow and/or the first accumulated unallocated flow.

Specifically, it is assumed below that the first road includes the above-mentioned first lane, and there are N roadside units with communication coverage areas that are evenly arranged without duplication and without intervals on the above-mentioned first road (or the area around the first road), and the method for determining the working efficiency of the roadside units provided in the present application is executed. In an embodiment of the present application, the device for determining the working efficiency of the roadside units determines the optimal combination A of the working states of the N roadside units based on the statistical data of the traffic flow in the same time period from the 1st day to the Dth day, and uses the optimal combination A as the working state of the N roadside units in the same time period on the D+1th day. Similarly, based on the statistical data of the traffic flow in the same time period from the 2nd day to the D+1th day, the optimal combination B of the N roadside units is determined, and the optimal combination B is used as the working state of the N roadside units in the same time period on the D+2th day.

For example, based on the traffic flow characteristics of the same time period (for example, 7:00 to 8:00) from the 1st day to the 15th day, the communication demand flow generated by the traffic flow traveling within the communication coverage of each roadside unit in the time period from 7:00 to 8:00 is counted, and the allocation process is simulated according to the preset opening rule of the roadside unit and the allocation rule for allocating the communication demand flow to the roadside unit, and multiple first combinations of the corresponding N roadside unit working states and the allocation results corresponding to the first combinations are obtained, and the first reward value after the first value corresponding to each of the first combinations and the allocation results is calculated, and the working states of the N roadside units are determined according to the target first combination corresponding to the maximum first value or the first reward value. And the target first combination is used as the combination of the working states of the N roadside units in the time period from 7:00 to 8:00 on the 16th day.

In a possible implementation, before obtaining the working status of the first roadside unit, the method also includes: obtaining any one element in a combination set as the first combination, the combination set including at least one element for indicating the working status of each of the N roadside units; obtaining the working status of the first roadside unit includes: determining the working status of the first roadside unit according to the first combination; calculating the first long-term reward value corresponding to the first combination according to a preset discount factor and the reward value corresponding to each of the at least two target moments corresponding to the first combination, including: determining the first long-term reward value corresponding to each of the first combinations in the combination set; determining the maximum value of the first long-term reward values corresponding to each of the first combinations in the combination set as the target long-term reward value; determining the working status of the N roadside units based on the first combination corresponding to the target long-term reward value.

Exemplarily, in combination with the method flow chart shown in FIG4 , the method for determining the working efficiency of a roadside unit provided in an embodiment of the present application is described in detail.

As shown in Figure 4 below, the method includes the following steps:

Phase 1: Collect traffic flow characteristic data based on historical data.

S401, determining the stay time and communication demand flow of traffic flow at each roadside unit in the current time period according to sample data.

It is understandable that the above sample data is historical data. This application uses historical data of the same target time period as the current time period to statistically analyze traffic flow characteristics, and uses the mean of traffic flow characteristics in the historical data as the traffic flow characteristics of the current time period.

For example, the current date is May 20, 2022, and the current time period is 7:00-9:00 on May 20, 2022; the above target time period can be the same time period within 15 days, that is, 7:00-9:00 every day for 15 days from May 4, 2022 to May 19, 2022.

Exemplarily, for one of the i-th roadside units, the length of stay of the traffic flow from 7:00 to 9:00 every day within 15 days within the communication coverage of the i-th roadside unit is counted to satisfy the expected length of stay of the normal distribution function f(RSU _i ,μ _i ,δ _i ). For example, the expected length of stay corresponding to 7:00 to 9:00 every day within 15 days of the i-th roadside unit includes 15 expected lengths of stay of μ _i1 , μ _i2 , μ _i3 , μ _i4 , μ _i5 , μ _i6 , μ _i7 , μ _i8 , μ _{i9 , μ i10 ,} μ _{i11 , μ i12} , μ _i13 , μ _i14 and μ _{i15 ,} and the mean value of these 15 expected lengths of stay ( μ _ij represents the expected stay time of the ith roadside unit corresponding to the jth day within 15 days) as the average stay time μ _i of the traffic flow within the communication coverage of the ith roadside unit during the above-mentioned target time period (the unit of μ _i can be a time unit, such as hour, minute or second), and the average stay time μ _i is used as the stay time of the traffic flow within the communication coverage of the ith roadside unit during the above-mentioned current time period.

Thus, the length of stay μ of the traffic flow in the communication coverage of each of the N roadside units in the current time period can be obtained. For example, as shown in the following Table 1:

Table 1

In the embodiment of the present application, in order to count the average communication demand flow of the traffic flow in each roadside unit during the target time period, for one of the i-th roadside units, it is also necessary to count the number of communication requests per minute of the traffic flow within the communication coverage of the i-th roadside unit from 7:00 to 9:00 every day within 15 days, which satisfies the expected number of communication requests (P(RSU _i ,λ _i )). For example, the expected number of communication requests per minute corresponding to 7:00 to 9:00 every day within 15 days includes λ _i1 , λ _i2 , λ _i3 , λ _i4 , λ _i5 , λ _i6 , λ _i7 , λ _i8 , λ _i9 , λ _i10 , λ i11 , λ _i12 , λ _i13 , λ _i14 and λ _{i15 ,} which are the 15 expected number of communication requests per minute, and the average value of these 15 expected number of communication requests per minute ( λ _ij represents the expected number of communication requests per minute corresponding to the jth day of the ith roadside unit within 15 days) as the average number of requests per minute λ _i of the traffic flow within the communication coverage of the ith roadside unit during the target time period.

And, count the communication demand flow of each request of the traffic flow within the communication coverage of the i-th roadside unit from 7:00 to 9:00 every day within 15 days, and the expected communication demand flow of each request satisfies the normal distribution (g(RSU _i ,ρ _i ,σ _i )). For example, the expected communication demand flow corresponding to each request from 7:00 to 9:00 every day within 15 days includes ρ _i1 , ρ _i2 , ρ _i3 , ρ _i4 , ρ _i5 , ρ _i6 , ρ _i7 , ρ _i8 , ρ _i9 , ρ _i10 , ρ _i11 , ρ _i12 , ρ _i13 , ρ _i14 and ρ _i15 , which are 15 expected communication demand flows per request, and the average value of these 15 expected communication demand flows per request ( ρ _ij represents the expected communication demand flow per request corresponding to the jth day within 15 days of the ith roadside unit) as the average communication demand flow per request ρ _i of the traffic flow within the communication coverage of the ith roadside unit during the target time period.

Then, the average communication demand flow k _i of the traffic flow in the i-th roadside unit in the target time period is calculated according to the product of the average stay time μ _i , the average number of requests per minute λ _i and the average communication demand flow per request ρ _i (k _i =μ _i *λ _i *ρ _i ). And, the average communication demand flow k _i is used as the communication demand flow k _i of the traffic flow in the communication range of the i-th roadside unit in the current time period.

Thus, the communication demand flow k of the traffic flow in the communication coverage area of each roadside unit in the N roadside units in the current time period can be obtained. For example, as shown in the following Table 2:

Table 2

RSU k RSU ₁ k ₁ RSU ₂ k ₂ RSU ₃ k ₃ RSU ₄ k ₄ ... ... _RSU k _i ... ... RSU _N k _N

Phase 2: Based on the traffic flow characteristic data, the opening rules of the roadside unit working status and the allocation rules of the communication demand flow, simulate the allocation of the communication demand flow to the corresponding roadside unit.

S402, according to the length of stay of traffic flow at each roadside unit and the communication demand flow, the first activation rule and the first allocation rule in the current time period, the working status of each roadside unit is determined, and the communication demand flow of traffic flow within the communication range of each roadside unit in the current time period is simulated and allocated to the roadside units in the working state of the duty state, to obtain one or more first combinations and the allocation results corresponding to each first combination.

For ease of description, the i-th roadside unit is referred to as RSU _i , and the communication demand flow of the traffic flow within the communication range of the i-th roadside unit in the current time period is referred to as k _i . The i-1th accumulated unallocated communication flow is referred to as D _i-1 . The D _i-1 is the unallocated communication demand flow in the communication demand flow of the traffic flow within the communication range of the roadside unit in the opposite direction of the first driving direction of the i-th roadside unit. The maximum achievable communication demand flow of the traffic flow in the i-th roadside unit is referred to as the i-th maximum achievable communication demand flow or simply as μ _i *ω, where μ _i is the average residence time μ _i of the traffic flow within the communication coverage range of the i-th roadside unit in the current time period (target time period), and ω is the communication rate of the i-th roadside unit.

Exemplarily, the working state of the i-th roadside unit is first determined according to the first activation rule. For example:

Determine whether the sum of k _i and D _i-1 is greater than a second threshold. For example, the second threshold is half of the maximum communication demand flow that the traffic flow can complete at RSU _i (μ _i *ω/2); if so, set the working state of RSU _i to the duty state; if not, try to set the working state of RSU _i to the duty state and the sleep state. For both cases, determine whether to allocate the corresponding communication demand flow to RSU _i according to the working state of RSU _i and the first allocation rule.

It is understandable that the first activation rule may also include other rules. Exemplarily, it may also include determining whether to set the working state of the roadside unit to the duty state according to whether a traffic light is deployed within the communication coverage of the roadside unit. For example, if a traffic light is deployed on a road within the communication coverage of RSU _i , the length of stay and communication demand of the traffic flow within the coverage of RSU _i will be relatively greater than the communication demand within the coverage of other roadside units, and the working state of RSU _i is determined to be the on state.

Then, according to the working state of the i-th roadside unit and the first allocation rule, it is determined whether to allocate the communication demand flow to RSU _i . For example:

When the working state of RSU _i is determined to be the sleep state, no communication demand flow is allocated to RSU _i . When the working state of RSU _i is determined to be the duty state, determine whether the sum of k _i and D _i-1 is less than or equal to the i-th maximum communication demand flow (μ _i *ω);

If so, k _i and D _i-1 are equally distributed to RSU _i ;

If not, and _Di-1 is equal to _μi *ω, Di _-1 is assigned to _RSUi and k _i is taken as _Di ;

Or, if not, and D _i-1 is less than μ _i *ω, then the first allocated flow is determined according to the difference between μ _i *ω and D _i-1 , and the communication demand flow in D _i-1 and k _i that is consistent with the first allocated flow is allocated to RSU _i , and the difference between k _i and the first allocated flow is taken as D _i ;

Or, if not, and Di _-1 is greater than the i-th maximum achievable communication demand flow, the communication demand flow in _Di-1 that is consistent with the i-th maximum achievable communication demand flow is allocated to RSU _i , and the sum of the difference between _Di-1 and μ _i *ω and k _i is taken as the i-th cumulative unallocated communication demand flow _Di.

Therefore, the working status of each RSU _i is determined according to the first startup rule, and whether to allocate communication demand traffic to RSU _i is determined according to the working status of RSU _i and the first allocation rule, and a first combination and a first allocation result are obtained. The first combination includes the value of the working status of each RSU _i , and the first allocation result corresponds to the first combination one by one. The first allocation result includes an allocation record of the communication demand traffic allocated to each RSU _i whose working status is on duty.

It is understandable that if the working state of RSU _i is set to the duty state (or sleep state) in the above “then try to set the working state of RSU _i to the duty state (or sleep state)”, then the working state of RSU _i will be set to the sleep state in the next attempt, and for each case, it is determined whether to allocate the communication demand flow to RSU _i according to the working state of RSU _i and the first allocation rule. This is true for each of the N roadside units (e.g., RSU ₁ , RSU ₂ , RSU ₃ , RSU _i , etc.). Therefore, one or more of the above first combinations and the allocation results corresponding to each first combination can be obtained by the above first activation rule and the first allocation rule.

Phase 3: Evaluate the working efficiency of the roadside unit based on each activation combination and the allocation results corresponding to each activation combination.

S403: When the number of the one or more first combinations is not 1, calculate the long-term reward value corresponding to each first combination in the multiple first combinations.

Exemplarily, the first performance indicator WEPE corresponding to the first combination is determined according to the product of the distribution completion degree β of the total communication demand and the communication flow TPE transmitted by N roadside units per unit energy consumption, wherein the total communication demand flow is the sum of the communication demand flow of the traffic flow within the communication coverage range of each roadside unit in the N roadside units at the current moment (that is, ).

Exemplarily, the calculation formula of the above β is shown in the following formula 1:

Wherein M is the sum of the communication demand flows allocated to each of the N roadside units.

Exemplarily, the calculation formula of the above TPE is shown in the following formula 2:

Where _Pi represents the energy consumption of RSU _i . Specifically, the energy consumption of RSU _i is calculated as follows:

When the working state of RSU _i is off, the energy consumption of RSU _i is the preset sleep energy consumption P _sleep , i is a positive integer greater than or equal to 1 and less than or equal to the N; when the working state of the i-th roadside unit is on, the energy consumption of the i-th roadside unit is the product of the preset communication energy consumption P _com and the usage degree _Ci of the bandwidth resources of RSU _i and the sum of the preset basic energy consumption P ₀ (that is, P ₀ + _Ci *P _com ); Ci _is the ratio of the total communication demand flow allocated to RSU _i to the maximum communication flow (μ _i *ω) corresponding to RSU _i . Exemplarily, the calculation formula of P _i is shown in the following formula 3.

It can be understood that simulating and allocating the communication demand flow of traffic within the communication range of each of the N roadside units to the roadside units on duty according to the first activation rule and the first allocation rule is a gradual process, that is, it takes a period of time to obtain the first combination mentioned above.

For example, the allocation status corresponding to the preset time can be determined, and the allocation status includes but is not limited to: which road side unit the allocation process proceeds to, the communication demand flow allocated to each road side unit, and the degree of completion of the total communication demand flow. The preset time is the preset time for obtaining the allocation status.

For example, at time t, the current simulated allocation process proceeds to RSU _i (for example, RSU ₅ ), at time t+1, the current simulated allocation process proceeds to RSU _i+3 , at time t+2, the current simulated allocation process proceeds to RSU _i+8 , and so on. Before the simulated allocation is completed, a preset time can be specified to obtain the corresponding allocation status.

It is understandable that if the sum of k _i and D _i-1 corresponding to RSU _i is less than or equal to the second threshold, the device for determining the working efficiency of the roadside unit will try to set the working state of RSU _i to the duty state or the sleep state. Thus, at least two first combinations can be obtained, including combination A (for the first combination corresponding to setting the working state of RSU _i to the duty state) and combination B (the first combination corresponding to setting the working state of RSU _i to the sleep state), and the allocation process from RSU ₁ to RSU _i is consistent in the process of generating the combination A and the combination B. If the time when the allocation process is carried out to RSU ₁ is t1=0, and the time when the allocation process is carried out to RSU _i is t2=100ms, and there are one or more of the above-mentioned preset moments between t1 and t2, then the allocation state corresponding to each preset moment between t1 and t2 of the combination A and the combination B is consistent.

In the embodiment of the present application, according to the multiple allocation states corresponding to the multiple preset moments, WEPE _t corresponding to a first combination at different preset moments is calculated, and a reward value r(t) associated with the WEPE _t of the first combination at different preset moments is calculated.

Exemplarily, at a preset time (time t), the calculation formula of the reward value r(t) corresponding to the first combination is as shown in the following formula 4:

r(t)＝λ ₁ WEPE _t -λ ₂ G(D _N ) Formula 4

Here, _λ1 represents the weight of the first performance indicator, _λ2 represents the loss of the unfinished communication demand flow portion, and _WEPEt is the performance indicator corresponding to time t (for the calculation method of the performance indicator, please refer to the above, which will not be described in detail here).

Optionally, during the allocation process of the simulated allocation for determining the first combination, if it is detected that the preset time t has been reached, the corresponding WEPE _t is calculated. In other words, during the process of determining the combination arrangement of the first combination, multiple WEPE _t of the first combination to be determined can be calculated.

Alternatively, after the simulated allocation is completed and the first combination is determined, the allocation process can be traced back to calculate the corresponding WEPE _t at the corresponding preset time t. That is, after the combination arrangement of the first combination is completely determined, the corresponding multiple WEPE _t of the first combination can be calculated.

Then, the long-term reward Q corresponding to the first combination is calculated according to the r(t) corresponding to each of the preset moments and the preset discount factor γ. Exemplarily, the calculation formula is shown in the following formula 5, where E represents the average of the values in the brackets.

Q＝E[r _t +γr _t+1 +γ ² r _t+2 +γ ³ r _t+3 +...] Formula 5

Thus, the long-term reward value Q corresponding to each first combination can be obtained.

S404, determining a maximum long-term reward value among the long-term reward values corresponding to each of the plurality of first combinations as a target long-term reward value, and determining the working states of N roadside units according to the first combination corresponding to the target long-term reward value.

For example, it can be expressed as the following formula 6:

Where s _t is used to represent the allocation state at time t, including the communication demand flow generated within the coverage of the current roadside unit RSU _i corresponding to t, the cumulative communication demand flow D _i that has not been allocated in the communication demand flow within the communication coverage of the roadside units including RSU _i before the roadside unit RSU _i , and the communication demand flow allocated to RSU _i . _{a t} is used to represent the above first combination corresponding to time t. π(π＝arg maxQ(s,a)) represents the search for a scheduling method that maximizes the long-term reward value of the roadside unit (best working efficiency).

It can be understood that the above-mentioned first activation rule is a combination of the working states of the traversal roadside units. Specifically, in a possible implementation, the determining, based on the first communication demand flow and/or the first accumulated unallocated flow, to set the working state of the first roadside unit to one of the open state and the closed state comprises: determining whether the sum of the first communication demand flow and the first accumulated unallocated flow is greater than a second threshold, the second threshold being determined based on half of the first threshold; if so, setting the working state of the first roadside unit to the open state; if not, respectively attempting to set the working state of the first roadside unit to a combination of values of the open state or the closed state, and obtaining two or more corresponding first combinations respectively; the calculating, based on a preset discount factor and the reward value corresponding to each of the at least two target moments corresponding to the first combination, of the first long-term reward value corresponding to the first combination comprises: determining the first long-term reward value corresponding to each of the two or more first combinations; determining the maximum value of the first long-term reward values corresponding to each of the two or more first combinations as the target long-term reward value; and determining the working states of the N roadside units in the first time period based on the first combination corresponding to the long-term reward value.

For ease of description, this article refers to the combination of roadside unit working states as a roadside unit scheduling scheme.

Generally, the commonly used energy optimization strategy is to shut down some idle roadside units in scenarios with sparse traffic flow, such as late at night or in suburbs, and only keep some roadside units on duty for communication. For example, in the simple "α-RSU duty" model, α represents the proportion of roadside units that are turned on at the same interval (when α=50%, one roadside unit is turned on for every other roadside unit). Although this simple and fixed roadside unit duty scheduling scheme is feasible, the effect is average. Because it is too simple and rigid and does not take into account the specific characteristics of traffic flow, it cannot adapt to real-time changes in traffic flow, and it cannot adaptively choose between the quality of vehicle-road communication and the energy consumption of roadside units.

However, through the method for determining the working efficiency of the roadside unit provided in the embodiment of the present application, the working efficiency of the roadside unit scheduling plan can be evaluated. At the same time, according to the method provided in the embodiment of the present application, the changing characteristics of the traffic flow can be comprehensively considered to determine an activation combination that maximizes the working efficiency of the roadside unit under the traffic flow conditions in the corresponding time period, thereby solving the problem that the roadside unit scheduling plan is too simple and rigid and cannot adapt to the real-time changes in traffic flow.

Embodiment 3:

The following assumes that the first road includes the first lane and the second lane, and there are N roadside units whose communication coverage areas are evenly arranged without duplication and without intervals on the first road, and executes the method for determining the working efficiency of the roadside units provided in the present application.

As shown in FIG5 , the method comprises the following steps:

Phase 1: Collect traffic flow characteristic data based on historical data.

S501, obtaining traffic flow characteristic data reflected by each roadside unit in the forward traffic flow and the reverse traffic flow corresponding to the first time period.

In the embodiment of the present application, the traffic flow characteristic data corresponding to the forward traffic flow and the reverse traffic flow of each roadside unit in the historical time period corresponding to the first time period is used to characterize the traffic flow characteristic data corresponding to the forward traffic flow and the reverse traffic flow of each roadside unit in the first time period. For example, the dates of the historical time period and the first time period are different, but the historical time period and the first time period are the same time period in a day.

The above-mentioned traffic flow characteristic data include the length of time that the traffic flow stays within the communication coverage of each roadside unit in the forward traffic flow and the reverse traffic flow in the first time period, the number of communication requests for V2I communication in the communication coverage of each roadside unit in the forward traffic flow and the reverse traffic flow, and the V2I communication demand flow for each communication request in the communication coverage of each roadside unit in the forward traffic flow and the reverse traffic flow.

Exemplarily, traffic flow characteristic data in two or more historical time periods corresponding to the first time period can be determined through road trajectory information corresponding to the roadside unit and/or driving trajectory records reported to the vehicle control center by the T-BOX in the vehicle (driving trajectory records include current time and current location).

Specifically, obtaining traffic flow characteristic data reflected by each roadside unit in the forward traffic flow and the reverse traffic flow corresponding to the first time period includes the following steps:

S5011, obtaining the length of time that the traffic flow in the forward traffic flow corresponding to the first time period stays within the coverage of each roadside unit, and obtaining the length of time that the traffic flow in the reverse traffic flow stays within the coverage of each roadside unit.

According to the acquired stay time within the coverage of each roadside unit in the forward traffic flow corresponding to the first time period, the normal distribution of the stay time of the traffic flow within the coverage of the roadside unit in the forward traffic flow (for ease of description, in the description of some functions, F is used to represent the forward traffic flow), and the normal distribution functions f(RSU _i ,μ _iF ,δ _iF ) used to represent the stay time of the traffic flow within the coverage of the i-th roadside unit are obtained one by one. Wherein, i represents the i-th target roadside unit, the value of i is a positive integer greater than or equal to 1 and less than or equal to N, N is used to represent the total number of roadside units included in the test road, μ _iF is used to represent the expected (mean) stay time of the traffic flow in the forward traffic flow within the coverage of the i-th target roadside unit, and δ _iF is the standard deviation of the stay time of the traffic flow in the forward traffic flow within the coverage of the i-th target roadside unit. And,

According to the acquired residence time of the traffic flow in the reverse traffic flow corresponding to the first time period within the coverage of each roadside unit, the normal distribution of the residence time of the traffic flow in the reverse traffic flow (for the convenience of description, in the description of some functions, R is used to represent the reverse traffic flow) within the coverage of the roadside unit is calculated, and the normal distribution functions f(RSU _i ,μ _iR ,δ _iR ) used to represent the residence time of the traffic flow within the coverage of the i-th roadside unit are obtained one by one. Wherein, i represents the i-th roadside unit, the value of i is a positive integer greater than or equal to 1 and less than or equal to N, N is used to represent the total number of roadside units included in the test road, μ _iR is used to represent the expected (mean) residence time of the traffic flow in the reverse traffic flow within the coverage of the i-th roadside unit, that is, the average residence time of the traffic flow within the communication coverage of the i-th roadside unit, and δ _iR is the standard deviation of the residence time of the traffic flow in the reverse traffic flow within the coverage of the i-th roadside unit.

For specific methods of obtaining μ _iF or μ _iR according to the historical time period corresponding to the first time period, reference may be made to the relevant descriptions of other embodiments herein (eg, the relevant descriptions in S401 in Embodiment 2), which will not be described in detail here.

S5012, obtaining the number of V2I communication requests for each traffic flow within the coverage area of a roadside unit in the forward traffic flow corresponding to the first time period, and obtaining the number of V2I communication requests for each traffic flow within the coverage area of the above roadside unit in the reverse traffic flow corresponding to the first time period.

According to the obtained number of V2I communication requests of the traffic flow within the coverage range of each of the above-mentioned roadside units in the above-mentioned forward traffic flow, the Poisson distribution request situation of the number of V2I communication requests of the traffic flow within the coverage range of the roadside unit in the forward traffic flow is calculated, and the Poisson distribution function P(RSU _i ,λ _iF ) used to represent the number of V2I communication requests of the traffic flow within the coverage range of the i-th roadside unit is obtained one by one. Among them, the parameter i represents the i-th roadside unit, the value of i is a positive integer greater than or equal to 1 and less than or equal to N, N is used to represent the total number of roadside units included in the test road, and λ _iF is used to represent the expected (mean) and standard deviation of the number of V2I communication requests of the traffic flow in the forward traffic flow within the coverage range of the i-th roadside unit. And,

According to the obtained number of V2I communication requests of each traffic flow within the coverage of the above roadside unit in the above reverse traffic flow, the Poisson distribution request of the number of V2I communication requests of the traffic flow within the coverage of the roadside unit in the reverse traffic flow is calculated, and the Poisson distribution function P(RSU _i ,λ _iR ) used to represent the number of V2I communication requests of the traffic flow within the coverage of the i-th roadside unit is obtained one by one. Among them, the parameter i represents the i-th roadside unit, the value of i is a positive integer greater than or equal to 1 and less than or equal to N, N is used to represent the total number of roadside units included in the test road, and λ _iR is used to represent the expectation (mean) and standard deviation of the number of V2I communication requests of the traffic flow in the reverse traffic flow within the coverage of the i-th roadside unit.

For specific methods of obtaining λ _iF or λ _iR according to the historical time period corresponding to the first time period, reference may be made to the relevant descriptions of other embodiments herein (eg, the relevant descriptions in S401 in Embodiment 2), which will not be described in detail here.

S5013, obtaining the V2I communication demand flow requested each time by each traffic flow within the coverage area of the above-mentioned roadside unit in the forward traffic flow corresponding to the first time period, and obtaining the V2I communication demand flow requested each time by each traffic flow within the coverage area of the above-mentioned roadside unit in the reverse traffic flow corresponding to the first time period.

According to the obtained V2I communication demand flow requested each time by the traffic flow within the coverage area of each roadside unit in the above-mentioned forward traffic flow, the normal distribution of the V2I communication demand flow requested each time by the traffic flow within the coverage area of the above-mentioned roadside unit in the forward traffic flow is calculated, and the normal distribution functions g(RSU _i , ρ _iF , σ _iF ) used to represent the V2I communication demand flow requested each time by the traffic flow within the coverage area of the i-th roadside unit are obtained one by one. Among them, the parameter i represents the i-th roadside unit, the value of i is a positive integer greater than or equal to 1 and less than or equal to N, N is used to represent the total number of roadside units included in the test road, ρ _iF is used to represent the expected (mean) V2I communication demand flow requested each time by the traffic flow in the forward traffic flow within the coverage area of the i-th roadside unit, and σ _iF is used to represent the standard deviation of the V2I communication demand flow requested each time by the traffic flow in the forward traffic flow within the coverage area of the i-th roadside unit. And,

According to the acquired V2I communication demand flow within the coverage of each roadside unit in the reverse traffic flow, the normal distribution of the V2I communication demand flow requested by the traffic flow within the coverage of the roadside unit in the reverse traffic flow is calculated, and the normal distribution functions g(RSU _i ,ρ _iR ,σ _iR ) for representing the V2I communication demand flow requested by the traffic flow within the coverage of the i-th roadside unit are obtained one by one. Among them, the parameter i represents the i-th roadside unit, the value of i is a positive integer greater than or equal to 1 and less than or equal to N, N is used to represent the total number of roadside units included in the test road, ρ _iR is used to represent the expected (mean) V2I communication demand flow requested by the traffic flow in the reverse traffic flow within the coverage of the i-th roadside unit, and σ _iR is used to represent the standard deviation of the V2I communication demand flow requested by the traffic flow in the reverse traffic flow within the coverage of the i-th roadside unit.

For specific methods of obtaining ρ _iR or σ _iF according to the historical time period corresponding to the first time period, reference may be made to the relevant descriptions of other embodiments herein (eg, the relevant descriptions in S401 in Embodiment 2), which will not be described in detail here.

Combining the above distribution functions of the dwell time, the number of V2I communication requests, and the V2I communication demand flow of each traffic flow request, we can get:

The average communication demand flow generated by the forward traffic flow within the coverage area of the i-th roadside unit in the first time period at each moment It can be expressed as the following formula 7, that is, the product of the expected stay time of the traffic flow in the forward traffic flow within the coverage of the i-th roadside unit (μ _iF ), the expected number of V2I communication requests of the traffic flow in the forward traffic flow within the coverage of the i-th roadside unit (λ _iF ), and the expected V2I communication demand flow of each request of the traffic flow in the forward traffic flow within the coverage of the i-th roadside unit (ρ _{iF ) (specifically, the product of the expected stay time of the traffic flow in the forward traffic flow within the coverage of the i-th roadside unit (μ iF} )). express).

The average communication demand flow generated by the reverse traffic flow within the coverage area of the i-th roadside unit in the first time period It can be expressed as the following formula 8: the product of the expected stay time of the traffic flow in the reverse traffic flow within the coverage of the i-th roadside unit (μ _iR ), the expected number of V2I communication requests of the traffic flow in the reverse traffic flow within the coverage of the i-th roadside unit (λ _iR ), and the expected V2I communication demand flow of each request of the traffic flow in the reverse traffic flow within the coverage of the i-th roadside unit (ρ _iR ).

S502: Determine a communication demand flow set of a forward traffic flow and a communication demand flow set of a reverse traffic flow according to traffic flow characteristic data.

It can be understood that the average communication demand flow generated by the forward traffic flow within the coverage area of the i-th roadside unit in the first time period is The communication demand flow set of the forward traffic flow can be determined, and the communication demand flow generated by the reverse traffic flow within the coverage area of the i-th roadside unit at each moment in the first time period can be determined. The aggregate set of communication demands for the reverse traffic flow may be determined.

For example, the total communication demand set Q _F of the forward traffic flow can be expressed as The communication demand set _QR of the reverse traffic flow can be expressed as

Phase 2: Based on the traffic flow characteristic data, the opening rules of the roadside unit working status and the allocation rules of the communication demand flow, simulate the allocation of the communication demand flow to the corresponding roadside unit.

S503, based on the first activation rule and the first allocation rule, determine the working status of each roadside unit, and decompose the communication demand set of the above-mentioned forward traffic flow and the communication demand set of the above-mentioned reverse traffic flow into sub-tasks and assign them to the roadside units on duty, so as to obtain one or more first combinations and the allocation results corresponding to each first combination.

It can be understood that if the working state of the roadside unit is on duty, it means that the roadside unit can perform V2I communication tasks; if the working state of the roadside unit is sleep, it means that the roadside unit is not in working state (for example, power off, etc.) and cannot process V2I communication tasks.

For the description of the first activation rule and the first allocation rule, reference may be made to the relevant descriptions of other embodiments herein (eg, the relevant descriptions in S402 in Embodiment 2).

For example, let Q _F Decompose into multiple And, change _the Decomposed into And distribute to multiple disjoint subsets Make where i represents the corresponding subtask ( or ) belongs to the communication task of the original i-th roadside unit, j is used to represent the j-th roadside unit, or Indicates that the communication task belonging to the original i-th roadside unit is assigned to the j-th roadside unit. It can be understood that j can be any positive integer from 1 to N, and the working state of the j-th roadside unit can be either a sleeping state or a duty state, but the communication demand flow can only be assigned to the j-th roadside unit in the duty state.

Understandably, the above and It is used to characterize the allocation result obtained by simulating the allocation of the corresponding communication demand flow to the roadside unit in the duty state based on the first opening rule and the first allocation rule, rather than for characterizing the allocation of and Decomposed and The decomposed communication demand flow is then allocated to the corresponding roadside unit based on the first activation rule and the first allocation rule.

Exemplarily, as shown in the following formula 9, a value of _yj of 1 indicates that the j-th roadside unit is scheduled to be in the duty state, and a value of _yj of 0 indicates that the j-th roadside unit is scheduled to be in the sleep state.

In one possible implementation, during the allocation process, in order to ensure that the V2I communication demand flow generated within the coverage area of each roadside unit is allocated as much as possible, it is necessary to satisfy that the sum of the V2I communication demand flow generated in the original i-th roadside unit and allocated to one or more j-th roadside units should be as close as possible to the V2I communication demand flow generated in the original i-th roadside unit.

For example, as shown in the following formula 10, The value is 1. Decomposing communication tasks into parts Assigned to RSU _j , using A value of 0 indicates Decomposing communication tasks into parts Not assigned to RSU _j . Result of communication task allocation for reverse traffic flow allocation Similarly, due to the movement characteristics of traffic flow, the communication needs generated within the coverage of a roadside unit can only be allocated to the roadside unit after it (including this one) to complete, so in the forward traffic flow, j must be greater than or equal to i; in the reverse traffic flow, j must be less than or equal to i.

Exemplarily, the sum of the V2I communication demand traffic generated in the original i-th roadside unit and allocated to one or more j-th roadside units should be as close as possible to the V2I communication demand traffic generated in the original i-th roadside unit, which can be expressed as shown in the following formula 11.

In one possible implementation, during the allocation process, in order for the corresponding roadside unit to complete the communication task assigned to the roadside unit, it is necessary to ensure that the total communication task assigned to each roadside unit is less than its maximum bandwidth (for example, c is used to represent the maximum bandwidth of the roadside unit).

Exemplarily, the sum of the communication tasks of the forward traffic flow and the communication tasks of the reverse traffic flow assigned to any j-th roadside unit is less than the maximum bandwidth of the j-th roadside unit, which can be expressed as shown in the following formula 12.

In one possible implementation, in order for the roadside unit to complete the communication task assigned to the corresponding roadside unit, it is also necessary to ensure that the communication duration corresponding to the communication task assigned to the roadside unit (the communication task is also the communication demand flow) is less than the length of time the traffic flow stays in its coverage area. Otherwise, if the communication duration is greater than the length of time the traffic flow stays in the traffic flow, the traffic flow may have left the coverage area of the roadside unit, but the communication task has not been completed.

Exemplarily, as shown in the following formula 13, for any forward traffic flow communication task assigned to the j-th roadside unit The ratio of the communication flow constant transmitted per second by the roadside unit is less than or equal to the expected (mean) length of stay of the traffic flow within the coverage area of the jth roadside unit, and the same is true for the reverse traffic flow.

For specific descriptions of one or more first combinations obtained after allocating the communication demand traffic to the corresponding roadside units according to the first activation rule and the first allocation rule and the allocation results corresponding to each first combination, please refer to the relevant descriptions of other embodiments of this document, such as the relevant descriptions in S402 in Embodiment 2, which will not be described in detail here.

Phase 3: Evaluate the working efficiency of the roadside unit based on each activation combination and the allocation results corresponding to each activation combination.

S504: When the number of the one or more first combinations is not 1, calculate the performance index corresponding to each first combination in the multiple first combinations.

In an embodiment of the present application, the product of the energy efficiency (indicator 1) of different roadside unit scheduling schemes and the degree of completion of the total V2I communication demand (indicator 2) can be used as a comprehensive indicator (WEPE) to describe the working efficiency of the roadside unit per unit energy consumption, where the comprehensive indicator is proportional to the working efficiency of the roadside unit.

Exemplarily, as shown in the following formula 14, the above-mentioned indicator 1 can be represented by the V2I communication traffic (TPE) transmitted per unit energy consumption. The larger the value of TPE, the better the performance of the above-mentioned indicator 1.

Wherein, _Pj is the energy consumption of the j-th roadside unit (the j-th roadside unit may be in a duty state or in a sleep state). That is, it is the total energy consumption generated by all roadside units. M is the sum of the communication demand flows allocated to each of the N roadside units.

In another possible implementation, M can also be taken as the maximum total amount of V2I communication traffic that all on-duty roadside units can theoretically transmit. It is understandable that in practical applications, as long as the roadside unit is in the on state, the roadside unit will be used to the maximum extent to complete the communication task, that is, the communication demand traffic allocated to the roadside unit will usually be as close as possible to the maximum V2I communication demand traffic that the roadside unit can theoretically transmit. Exemplarily, the calculation method of M is shown in the following formula 15.

Wherein, ω is the communication flow constant transmitted by the roadside unit on average per second. (μ _jF +μ _jR )*ω (i.e., the product of the average duration of the traffic flow in the jth roadside unit in the forward traffic flow and the reverse traffic flow and the communication flow transmitted by the roadside unit on average per second) is used to represent the V2I communication flow transmitted by the jth roadside unit in the traffic flow. In _{y j} *(μ _jF +μ _jR )*ω, when y _j takes the value of 1, y _j *(μ _jF +μ _jR )*ω represents the V2I communication flow required to be transmitted when the jth roadside unit is scheduled as the duty state, and when y _j takes the value of 0, y _j *(μ _jF +μ _jR )*ω represents that the jth roadside unit is scheduled as the sleep state and does not need to transmit V2I communication flow. Therefore, the total amount of V2I communication flow that all duty roadside units can theoretically transmit can be represented by the sum of y _j *(μ _jF +μ _jR )*ω when j takes the value of 1 to N.

It is understandable that the calculation method of energy consumption _Pj is different for different working states of the roadside unit. When the roadside unit is on duty, _Pj usually includes basic energy consumption _P0 and communication energy consumption _Pcom . When the roadside unit is on duty, the basic energy consumption is constant _P0 , and the communication energy consumption _Pcom corresponds to the workload of the roadside unit. When the roadside unit is not scheduled to be on duty, it immediately goes to sleep. In the sleep state, the function of the roadside unit is constant _Psleep .

Exemplarily, the energy consumption _Pi is calculated as shown in the following formula 16. In formula 16, the communication task _kij of RSU _j is composed of the subtask of RSU _j in the forward traffic flow and the subtask of RSU _j in the reverse traffic flow. Specifically, the calculation method of _kij is: That is, It is used to represent the communication demand flow assigned to RSU _j in the forward traffic flow and the reverse traffic flow. _{μ j} *ω represents the maximum communication task that can be completed in RSU _j in the forward traffic flow and the reverse traffic flow.

In the embodiment of the present application, the above-mentioned indicator 2 (the degree of completion of the total V2I communication demand) can be represented by the performance index β. The calculation method of β is shown in the following formula 17, which is equal to the ratio of the communication demand flow that can be completed by N roadside units to the communication demand flow generated by the traffic flow in the N roadside units. The closer the value of β is to 1 (the larger the value), the better the performance of indicator 2.

Therefore, the calculation method of the comprehensive working efficiency index (WEPE) of the roadside unit per unit energy consumption is as shown in the following formula 18. The larger the value of the WEPE is, the better the working efficiency is.

S505, determining a maximum performance indicator among the performance indicators corresponding to the plurality of first combinations as a target performance indicator, and determining the working states of N roadside units according to the first combination corresponding to the target performance indicator.

In a possible implementation, the optimization goal of optimizing the roadside unit is to maximize WEPE. It can also be understood as how to find a target combination among multiple value combinations of the duty state or sleep state of each roadside unit, and the target combination is the combination that maximizes the value of the above WEPE among multiple combinations, so as to maximize the working efficiency of the roadside unit under the premise of satisfying V2I communication.

In another implementation, the long-term reward value corresponding to the first combination can also be calculated according to the efficiency index WEPE corresponding to the first combination, and the maximum value of the long-term reward value is used as the optimization target of optimizing the roadside unit. Specifically, the calculation method of the long-term reward value can refer to the relevant description of other embodiments of this invention (such as the relevant description in S403 in Embodiment 2), which will not be described in detail here.

Embodiment 4:

The following introduces a specific implementation of the method for determining the working efficiency of a roadside unit provided in this application in combination with a deep learning model.

In the deep learning model system, the statistically obtained average residence time of the traffic flow in the forward traffic flow or the reverse traffic flow corresponding to the first time period within the communication coverage of each roadside unit, and the average communication demand flow generated by the traffic flow in the forward traffic flow or the reverse traffic flow corresponding to the first time period within the communication coverage of each roadside unit can be used as input. For how to obtain the average residence time and the average communication demand flow, please refer to the relevant description of stage 1 (traffic flow feature data based on historical data) in other embodiments of this document, which will not be described in detail here.

The deep learning model is then used to implement the technical contents of the above-mentioned stage 2 (simulating the allocation of communication demand traffic to corresponding roadside units based on traffic flow characteristic data, the activation rules of the roadside unit working status, and the allocation rules of communication demand traffic) and stage 3 (evaluating the working efficiency of the roadside unit based on each activation combination and the allocation results corresponding to each activation combination), and finally determines a combination with the best working efficiency as the output.

Specifically, it is assumed that a central proxy cloud node is responsible for acquiring the dwell time learning of traffic flow within the coverage area of each roadside unit and the V2I communication demand flow generated by traffic flow, and assembling the information into the system state of the model and sending it to the deep Q network. The optimal action strategy π = argmaxQ (x, a) is the feedback at the current time t, where x is the system state, a is the executed action, and π is the strategy. When the system takes different actions to schedule the working state of the roadside unit according to the input of the model, the V2I communication demand is continuously divided into multiple communication tasks and assigned to different roadside units scheduled for duty. At the same time, the system reward is set to the long-term reward value corresponding to the first combination mentioned above, so that different reward values can be obtained according to different scheduling actions. The system will continue to try to pursue the scheduling plan with the maximum reward value as the output. The specific schematic diagram of the model solution is shown in Figure 6.

In deep reinforcement learning, the system mainly includes the main elements such as agent, state, action and reward: π = argmaxQ(s _t ; a _t ; θ), where

①Agent: Each of the N roadside units.

② Status: V2I communication demand k _i generated within the coverage of roadside unit RSU _i ; communication demand flow generated by the roadside unit before RSU _j and V2I communication demand D _j that has not been allocated until RSU _j ; communication task C _j allocated by roadside unit RSU _j .

The initial value of the V2I communication demand k _i generated within the coverage of the roadside unit RSU _i is obtained from the input of the model, and then decreases continuously with the allocation; when the simulation allocation is carried out to an RSU _j , all the accumulated V2I communication demands D _j that have not yet been allocated are first added to the V2I communication demand k _j within the coverage of this roadside unit, indicating that k _j is not allocated, and then whether to allocate a communication task to it is determined based on whether this roadside unit is turned on. If a communication task is allocated to the roadside unit, D _j needs to be subtracted from the corresponding allocated task.

The communication task _Cj assigned to the roadside unit RSU _j has an initial value of 0 and a maximum value of its bandwidth c.

③Action: The system performs actions on each roadside unit in turn according to the input of the model: A = [0, 1], where 1 is on and 0 is off.

When the simulation allocation reaches an RSU _j , all the accumulated unallocated V2I communication demands D _j are first added to the V2I communication demands k _j within the coverage of this RSU, indicating that k _j is not allocated. Then, whether to allocate communication tasks to it is determined based on whether this RSU is turned on. If the RSU _j is turned on, the system can allocate a maximum of μ _j *ω communication tasks to the RSU _j . If the RSU _j is in sleep mode, C _j = 0. As the system continues to schedule, each k _n will be decomposed and allocated into multiple k _nj . Different scheduling strategies will also result in different RSU working efficiencies, thereby obtaining different rewards.

④ Reward: The goal of the present invention is to maximize the working efficiency of the roadside unit while ensuring the quality of V2I communication. The reward function consists of two parts. The first part aims to maximize the working efficiency WEPE of the roadside unit, and the second part represents the loss of the unfinished V2I communication demand part. λ ₁ and λ ₂ are the weights of each part to balance the income and penalty.

In a possible implementation, the above It can also be understood as G(D ₁ )+G(D _N ). Among them, G(D ₁ ) is the communication task that has not been completed by the last roadside unit that the reverse traffic flow reaches (the last roadside unit is the first roadside unit RSU _j=1 of the road section), and G(D _N ) is the communication task that has not been completed by the last roadside unit that the forward traffic flow reaches (the last roadside unit is the last roadside unit RSU _j=N of the road section).

Among them, G(x) is a piecewise function, and W is set to a large positive number to represent the penalty.

The goal of the training process is to maximize the expected long-term reward through the optimal strategy, which can be obtained through the Q value:

The following shows some experimental data in actual application of using the method for determining the working efficiency of a roadside unit provided in an embodiment of the present application to determine a combination corresponding to the optimal working efficiency among the combinations of working states of multiple roadside units.

In the embodiment of the present application, the Pingshan test site of Shenzhen Smart City Technology Development Group Co., Ltd. is selected as the experimental scene for the experiment. Each road in the site is evenly paved with roadside units at intervals of 200 meters. R14LTE-V2X is used for V2I communication in the test park, and the maximum number of accessible users is 500. The present invention selects a section from the intersection of Juqing Road and Linhui Road to the intersection of Danqing Road as the experimental road, and regards the traffic flow from the starting point to the end point as a forward traffic flow. The total length L of the experimental section is 2210m (meters), and a total of 11 roadside units are deployed along the way. The specific experimental environment is shown in Figure 7, and other main experimental parameters are shown in Table 1 below.

Table 1

parameter Value ω (communication rate of the roadside unit) 30Mbps P ₀ (basic energy consumption) 2300W P _com (communication energy consumption) 1600W P _sleep (sleep energy consumption) 460W W (penalty value) 40

The trajectory information and V2I communication flow of each road in the experimental park are collected for 15 days, with a sampling interval of 5 minutes. Through statistical analysis, the distribution of the traffic flow stay time f(RSU _i , μ _i , δ _i ) and the V2I communication demand (RSU _i , k _i ) within the coverage area of each roadside unit is obtained, as shown in the bar chart of Figure 8. The embodiment of the present application takes the expected value of the distribution to describe the movement state of the traffic flow. Similarly, the V2I communication demand within the coverage area of each roadside unit is shown in Figure 9 (where forward traffic flow represents forward traffic flow and reverse traffic flow represents reverse traffic flow). Among them, the time taken for the forward traffic flow to pass through the entire road section is 270s, while the reverse traffic flow is 223s. At this time, the total communication demand on the entire road section is 200MB.

Based on the deep reinforcement learning framework, the present invention designs a five-layer neural network model structure, including an input layer, an output layer and three hidden layers. The number of neurons in the three hidden layers is set to 400, 200 and 100 respectively, ReLu is used as the activation function, and RMSprop is used as the optimizer. The learning rate is set to 0.001. After training, we can get a duty roadside unit scheduling scheme as output. The output of the model includes the minimum number of required roadside units and the location of the selected roadside units. As shown in Table 2 below, roadside units RSU ₂ , RSU ₄ , RSU ₆ and RSU ₁₀ are scheduled to work during this period, where 1 is on and 0 is off. At this time, the V2I communication traffic transmitted by the scheduling scheme is 193MB, the total energy consumption of all roadside units is 15.844KW, and the work efficiency index WEPE is 11.75MB/KW. In contrast, the "α-RSU duty" model (α=1) indicates that all roadside units on the road are fully turned on to meet the service. At this time, the V2I communication demand can undoubtedly be fully met, and the total energy consumption of all roadside units is 28.884KW, so the work efficiency index WEPE is 6.92MB/KW. Compared with the α-RSU duty model (α＝1), this scheduling scheme saves 45.15% of energy consumption while ensuring 96.5% of V2I quality, and the work efficiency index WEPE is improved by about 1.7 times.

Table 2 Input and output of the model

The output of the scheduling scheme is further analyzed in combination with the road conditions. Since traffic lights are deployed on roads within the coverage of RSU ₄ , RSU ₆ and RSU ₈ to regulate traffic flow, the length of stay and V2I communication requirements within the coverage of these roadside units will be relatively longer than other roadside units. The system will also evaluate and consider these when executing actions, and finally determine that roadside units RSU ₂ , RSU ₄ , RSU ₆ and RSU ₁₀ are scheduled to work during this period in combination with other road conditions.

The present invention also further conducted multiple groups of experiments to study the adaptability of the model in different time periods and compared it with the α-RSU duty model. Multiple groups of experiments were conducted using the traffic flow information of Juqing Road from 17:00 to 2:00 as input. The work efficiency index WEPE of each scheme is shown in Figure 10.

Further experiments show that the work efficiency index WEPE of the model proposed in the present invention is always higher than that of other models. During 17:00-19:00, the traffic on the road is relatively dense, and all roadside units need to be turned on to provide communication services for vehicles. Therefore, the work efficiency index WEPE of our model is basically consistent with the α-RSU duty model (α=1), and is higher than other models. As time goes by, the traffic flow becomes more and more sparse. In this case, our model can adaptively adjust the scheduling strategy by flexibly selecting the roadside unit in the best position and shutting down the idle part. In this way, the total energy consumption of the roadside unit can be greatly reduced while ensuring the quality of V2I communication service. The main reason why the work efficiency index WEPE of the model proposed in the present invention decreases during 20:00-22:00 is that a small part of the V2I communication demand is lost, resulting in the utility index β being less than 1. After that, the work efficiency index WEPE will continue to increase due to the significant reduction in the total energy consumption of the roadside unit. For the α-RSU duty model, when the traffic flow is dense, due to insufficient open roadside units, some models (α = 1/2, 1/3, 1/4) cannot meet all V2I communication needs, resulting in too little V2I communication traffic and low work efficiency. On the contrary, when the traffic flow is sparse, even if some models (α = 1, 1/2, 1/3) can complete all V2I communication tasks, they will consume a lot of unnecessary energy, resulting in low work efficiency. Therefore, as the traffic flow becomes more sparse, the work efficiency index WEPE will continue to decrease.

The following will introduce a device for determining the working efficiency of a roadside unit provided by an embodiment of the present invention.

Please refer to Figure 11, which is a schematic diagram of a structure of a device for determining the working efficiency of a roadside unit according to an embodiment of the present invention. As shown in Figure 11, the device for determining the working efficiency of a roadside unit according to an embodiment of the present invention may include:

An acquiring unit 1101 is configured to acquire a working state of a first roadside unit, where the first roadside unit is any one of N roadside units sequentially distributed in a first driving direction, and the working state of the first roadside unit is an on state or an off state;

an allocating unit 1102, configured to allocate all or part of the target communication demand flow to the first roadside unit when the working state of the first roadside unit is the on state, and the communication flow allocated to the first roadside unit is less than or equal to a first threshold value, the target communication demand flow is the sum of the first cumulative unallocated flow and the first communication demand flow of the traffic flow within the communication coverage of the first roadside unit in a first time period, the first cumulative unallocated flow is the unallocated communication demand flow in the communication demand flow within the communication range of one or more roadside units in the opposite direction of the first driving direction of the first roadside unit, and the first threshold value is the maximum communication flow that can be completed by the traffic flow within the communication coverage of the first roadside unit;

A first determining unit 1103 is configured to determine a first combination according to the working state of the first roadside unit, wherein the first combination is used to represent a value arrangement of the working state of each roadside unit of the N roadside units in the first time period;

The second determination unit 1104 is used to determine a first value corresponding to the first combination based on the degree of completion of the allocation of the total communication demand flow and the product of the communication flow transmitted by the N roadside units per unit energy consumption, wherein the first value is proportional to the working efficiency of the N roadside units, and the total communication demand flow is the sum of the communication demand flows of the traffic flow within the communication coverage range of each of the N roadside units.

In a possible implementation, the second determination unit 1104 is specifically used to determine the first numerical value corresponding to a target moment, the target moment being any preset moment in the process of allocating all or part of the target communication demand flow to the first roadside unit to determine the first combination; determine a first loss value corresponding to the target moment, wherein the first loss value is 0 when the first cumulative unallocated flow is 0 at the target moment, and the first loss value is a preset loss value when the first cumulative unallocated flow is greater than 0 at the target moment; and determine a reward value corresponding to the target moment according to a difference between a third numerical value and a fourth numerical value, the third numerical value being the product of a first weight and the first numerical value, and the fourth numerical value being the product of a second weight and the first loss value; calculate a first long-term reward value corresponding to the first combination according to a preset discount factor and the reward value corresponding to each of the at least two target moments corresponding to the first combination; the first long-term reward value is proportional to the working efficiency of the N roadside units.

In a possible implementation, the acquisition unit 1101 is specifically used to determine, based on the first communication demand flow and/or the first accumulated unallocated flow, whether to set the working state of the first road side unit to one of the on state and the off state.

In a possible implementation, the acquisition unit 1101 is specifically used to determine whether the target communication demand flow is greater than a second threshold, and the second threshold is determined according to one half of the first threshold; when it is determined that the target communication demand flow is greater than the second threshold, the working state of the first roadside unit is set to the on state; when it is determined that the target communication demand flow is greater than the second threshold, attempts are made to set the working state of the first roadside unit to a combination of values of the on state or the off state, respectively, to obtain corresponding two or more first combinations; according to the preset discount factor and the reward value corresponding to each of the at least two target moments corresponding to the first combination, the first long-term reward value corresponding to the first combination is calculated, including: determining the first long-term reward value corresponding to each of the two or more first combinations; determining the maximum value of the first long-term reward values corresponding to each of the two or more first combinations as the target long-term reward value; determining the working states of the N roadside units in the first time period based on the first combination corresponding to the long-term reward value.

In one possible implementation, the allocation unit 1102 is specifically used to determine whether the target communication demand flow is less than or equal to the first threshold; when it is determined that the target communication demand flow is less than or equal to the first threshold, the target communication demand flow is allocated to the first road side unit; when it is determined that the target communication demand flow is greater than the first threshold, all or part of the target communication demand flow is allocated to the first road side unit according to a strategy in which the priority allocated to the first accumulated unallocated flow is higher than the priority allocated to the first communication demand flow, and the communication flow allocated to the first road side unit is equal to the first threshold.

In a possible implementation, as shown in FIG12 , the apparatus for determining the working efficiency of the roadside unit may further include:

The third determination unit 1105 is used to determine the first threshold; the third determination unit 1105 is specifically used to determine that the first threshold is the product of the first stay time and the communication rate of the first roadside unit when the product of the first stay time and the communication rate of the first roadside unit is less than or equal to the maximum bandwidth of the first roadside unit; the first stay time is the stay time of the traffic flow within the communication coverage of the first roadside unit; when the product of the first stay time and the communication rate of the first roadside unit is greater than the maximum bandwidth of the first roadside unit, the first threshold is the maximum bandwidth of the first roadside unit.

In a possible implementation, as shown in FIG12 , the apparatus for determining the working efficiency of the roadside unit may further include:

The calculation unit 1106 is used to calculate the energy consumption of each of the N roadside units in the following manner: for the i-th roadside unit among the N roadside units, when the working state of the i-th roadside unit is the closed state, the energy consumption of the i-th roadside unit is the preset sleep energy consumption, and i is a positive integer greater than or equal to 1 and less than or equal to N; when the working state of the i-th roadside unit is the open state, the energy consumption of the i-th roadside unit is the sum of the product of the preset communication energy consumption and the utilization degree of the bandwidth resources of the i-th roadside unit and the preset basic energy consumption; the utilization degree of the bandwidth resources of the i-th roadside unit is the ratio of the total communication demand flow allocated to the i-th roadside unit to the maximum communication flow corresponding to the i-th roadside unit, the maximum communication flow is determined according to the product of the average stay time of the traffic flow in the first direction within the communication coverage range of the i-th roadside unit and the communication rate of the i-th roadside unit, and the maximum communication flow is used to represent the maximum communication flow that can be completed by the traffic flow within the communication coverage range of the i-th roadside unit.

In a possible implementation, as shown in FIG12 , the apparatus for determining the working efficiency of the roadside unit may further include:

The fourth determination unit 1107 is used to determine whether the length of stay of the traffic flow in at least two historical time periods corresponding to the first time period within the communication coverage of the first roadside unit satisfies the first expected length of stay of the normal distribution, whether the number of communication requests per minute of the traffic flow in at least two historical time periods corresponding to the first time period within the communication coverage of the first roadside unit satisfies the first expected number of requests of the Poisson distribution, and whether the communication demand flow per minute of the traffic flow in at least two historical time periods corresponding to the first time period within the communication coverage of the first roadside unit satisfies the first expected communication demand flow of the normal distribution; and determine the first communication demand flow based on the product of the first expected length of stay, the first expected number of requests and the first expected communication demand flow.

It should be noted that the specific execution process can refer to the specific description of the method embodiment shown in Figure 2, Figure 4 or Figure 5, and will not be repeated here.

It is understandable that the device for determining the working efficiency of the roadside unit shown in FIG. 11 or FIG. 12 may have a variety of product forms. Exemplarily, the device for determining the working efficiency of the roadside unit may also be a device for determining the working efficiency of the roadside unit including a processor, a communication interface, a memory, and a communication bus as shown in FIG. 13. Specifically, as shown in FIG. 13, the device 130 for determining the working efficiency of the roadside unit may include:

At least one processor 1301, such as a CPU, at least one communication interface 1303, a memory 1304, and at least one communication bus 1302. Among them, the communication bus 1302 is used to realize the connection and communication between these components. The communication interface 1303 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface or a Bluetooth interface, etc.). The memory 1304 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 1304 may optionally be at least one storage device located away from the aforementioned processor 1301. As shown in Figure 13, the memory 1304 as a computer storage medium may include an operating system and program instructions.

Exemplarily, the communication interface 1303 may be used to implement the steps or functions performed by the acquisition unit 1101 in FIG. 11. The processor 1301 may be used to implement the steps or functions performed by the allocation unit 1102, the first determination unit 1103, and the second determination unit 1104. The communication interface 1303 may be a chip pin or a transceiver.

In the apparatus 130 for determining the working efficiency of a roadside unit shown in FIG13 , the processor 1301 may be used to load the program instructions stored in the memory 1304 and specifically perform the following operations:

Acquire a working state of a first roadside unit, where the first roadside unit is any one of N roadside units sequentially distributed in the first driving direction, and the working state of the first roadside unit is an on state or a off state;

In the case where the working state of the first roadside unit is the on state, all or part of the target communication demand flow is allocated to the first roadside unit, and the communication flow allocated to the first roadside unit is less than or equal to a first threshold value, the target communication demand flow is the sum of the first cumulative unallocated flow and the first communication demand flow of the traffic flow within the communication coverage of the first roadside unit in the first time period, the first cumulative unallocated flow is the unallocated communication demand flow in the communication demand flow within the communication range of one or more roadside units in the opposite direction of the first driving direction of the first roadside unit, and the first threshold value is the maximum communication flow that can be completed by the traffic flow within the communication coverage of the first roadside unit;

Determine a first combination according to the working state of the first roadside unit, the first combination being used to represent a value arrangement of the working state of each roadside unit of the N roadside units in the first time period;

A first value corresponding to the first combination is determined based on the degree of completion of the allocation of the total communication demand flow and the product of the communication flow transmitted by the N roadside units per unit energy consumption. The first value is proportional to the working efficiency of the N roadside units. The total communication demand flow is the sum of the communication demand flows of the traffic flow within the communication coverage range of each of the N roadside units.

It should be noted that the specific execution process can refer to the specific description of the embodiment shown in Figure 2, Figure 4 or Figure 5, and will not be repeated here.

An embodiment of the present invention also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing the method steps of the embodiments shown in Figures 2, 4 or 5 above. The specific execution process can refer to the specific description of the embodiments shown in Figures 2, 4 or 5, which will not be repeated here.

As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

A person skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by a computer program to instruct the relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. The aforementioned storage medium includes: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims (13)

1. A method of determining the efficiency of a roadside unit, the method comprising:

Acquiring the working state of a first road side unit, wherein the first road side unit is any one of N road side units distributed in sequence in a first driving direction, the first driving direction is the passing direction of a first lane, and the working state of the first road side unit is an on state or an off state;

When the working state of the first road side unit is the on state, distributing all or part of communication demand traffic in target communication demand traffic to the first road side unit, wherein the communication traffic distributed to the first road side unit is smaller than or equal to a first threshold value, the target communication demand traffic is the sum of first accumulated unassigned traffic and first communication demand traffic of traffic flow in the communication coverage area of the first road side unit in a first time period, the first accumulated unassigned traffic is communication demand traffic which is unassigned in the communication demand traffic of traffic flow in the communication coverage area of one or more road side units before the first road side unit in the opposite direction of the first driving direction, and the first threshold value is communication traffic which can be completed maximally in the communication coverage area of the first road side unit;

under the condition that the working state of the first road side unit is the closed state, communication demand flow is not distributed for the first road side unit;

Determining a first combination according to the working state of the first road side unit, wherein the first combination is used for representing a value arrangement of the working state of each road side unit in the N road side units in the first time period;

And determining a first numerical value corresponding to the first combination according to the product of the distribution completion degree of the total communication demand flow and the communication flow transmitted by the N road side units per unit energy consumption, wherein the first numerical value is in direct proportion to the working efficiency of the N road side units, and the total communication demand flow is the sum of the communication demand flows of the traffic flow in the communication coverage area of each road side unit in the N road side units.

2. The method according to claim 1, wherein determining the first value corresponding to the first combination according to a product of a degree of allocation completion of the total communication demand traffic and the communication traffic transmitted by the N roadside units per unit energy consumption includes:

Determining the first value corresponding to a target time, wherein the target time is any preset time in the process of distributing all or part of target communication demand flows to the first road side unit to determine the first combination;

Determining a first loss value corresponding to the target time, wherein the first loss value is 0 when the first accumulated unassigned flow is 0 at the target time, and the first loss value is a preset loss value when the first accumulated unassigned flow is greater than 0 at the target time; and

Determining a corresponding reward value at the target time according to a difference value between a third value and a fourth value, wherein the third value is a product of a first weight and the first value, and the fourth value is a product of a second weight and the first loss value;

Calculating a first long-term rewards value corresponding to the first combination according to a preset discount factor and the rewards value corresponding to each of at least two target moments corresponding to the first combination; the first long-term prize value is proportional to the operating efficiency of the N roadside units.

3. The method of claim 2, wherein the obtaining the operating state of the first roadside unit comprises:

and determining to set the working state of the first road side unit to one of the opening state and the closing state according to the first communication demand flow and/or the first accumulated unassigned flow.

4. A method according to claim 3, wherein said determining to set the operating state of the first road side unit to one of the on state and the off state based on the first communication demand traffic and/or the first accumulated unallocated traffic comprises:

Determining whether the target communication demand flow is greater than a second threshold, the second threshold being determined according to one half of the first threshold;

setting the working state of the first road side unit to be the opening state under the condition that the target communication demand flow is determined to be greater than a second threshold value;

Under the condition that the target communication demand flow is determined to be greater than a second threshold value, respectively attempting to set the working state of the first road side unit as the value combination of the opening state or the closing state, and respectively obtaining two or more corresponding first combinations;

The calculating a first long-term prize value corresponding to the first combination according to a preset discount factor and the prize value corresponding to each of at least two target moments corresponding to the first combination, including:

Determining the first long-term prize value corresponding to each of the two or more first combinations;

determining a maximum value of the first long-term prize values corresponding to each of the two or more first combinations as a target long-term prize value;

and determining the working states of the N road side units in the first time period based on the first combination corresponding to the long-term rewards value.

5. The method according to any one of claims 1 to 4, wherein the allocation completion degree of the total communication demand is a ratio of a sum of communication demand flows allocated to each of the N roadside units to the total communication demand flow rate; the communication flow transmitted by each unit energy consumption of the N road side units is the ratio of the total communication demand flow to the sum of the energy consumption of each of the N road side units.

6. The method according to any one of claims 1 to 4, wherein the first lane belongs to a first road, the first road further comprising at least one second lane, the second lane having a direction of traffic opposite to the direction of traffic of the first lane; the target communication demand flow is a sum of the first accumulated unallocated flow, the first communication demand flow, and a second accumulated unallocated flow, the second accumulated unallocated flow being a communication demand flow that is not allocated to completion among communication demand flows of traffic flows in a communication range of one or more preceding roadside units of the first roadside unit in an opposite direction of a second traveling direction, the second traveling direction being a traveling direction of the second lane.

7. The method of claim 6, wherein the allocating all or a portion of the target communication demand traffic to the first roadside unit and the communication traffic allocated to the first roadside unit is less than or equal to a first threshold comprises:

determining whether the target communication demand flow is less than or equal to the first threshold;

under the condition that the target communication demand flow is less than or equal to the first threshold value, distributing the target communication demand flow to the first road side unit;

And if the target communication demand traffic is determined to be greater than the first threshold, distributing all or part of the target communication demand traffic to the first road side unit according to a strategy that the distributed priority of the first accumulated unassigned traffic is higher than that of the first communication demand traffic, wherein the communication traffic distributed to the first road side unit is equal to the first threshold.

8. The method according to claim 4 or 7, characterized in that the method further comprises:

Determining the first threshold;

the determining the first threshold includes:

When the product of the first residence time length and the communication rate of the first road side unit is smaller than or equal to the maximum bandwidth of the first road side unit, the first threshold value is the product of the first residence time length and the communication rate of the first road side unit; the first stay time is the stay time of the traffic flow in the communication coverage area of the first road side unit;

And under the condition that the product of the first stay time length and the communication rate of the first road side unit is larger than the maximum bandwidth of the first road side unit, the first threshold value is the maximum bandwidth of the first road side unit.

9. The method of claim 8, wherein the method further comprises:

The energy consumption of each of the N roadside units is calculated by:

for an ith road side unit in the N road side units, when the working state of the ith road side unit is the closed state, the energy consumption of the ith road side unit is preset sleep energy consumption, and i is a positive integer greater than or equal to 1 and less than or equal to N;

When the working state of the ith road side unit is the opening state, the energy consumption of the ith road side unit is the sum of the product of the preset communication energy consumption and the use degree of the bandwidth resource of the ith road side unit and the preset basic energy consumption; the using degree of the bandwidth resource of the ith road side unit is the ratio of all communication demand flows distributed to the ith road side unit to the maximum communication flow corresponding to the ith road side unit, the maximum communication flow is determined according to the product of the average stay time of the traffic flow in the first direction in the communication coverage area of the ith road side unit and the communication speed of the ith road side unit, and the maximum communication flow is used for representing the maximum communication flow which can be completed by the traffic flow in the communication coverage area of the ith road side unit.

10. The method of claim 1 or 2, wherein the first communication demand traffic is an average communication demand traffic in communication demand traffic data within a communication coverage area of the first roadside unit for at least two historical time periods corresponding to the first time period, the method further comprising:

Determining that the stay time of traffic flows in at least two historical time periods corresponding to the first time period in the communication coverage area of the first road side unit meets first expected stay time of normal distribution, determining that the communication request times of traffic flows in at least two historical time periods corresponding to the first time period in the communication coverage area of the first road side unit meet first expected request times of poisson distribution, and determining that the communication demand flow of traffic flows in at least two historical time periods corresponding to the first time period in the communication coverage area of the first road side unit meets first expected communication demand flow of normal distribution;

The first communication demand traffic is determined based on a product of the first desired residence time, the first desired number of requests, and the first desired communication demand traffic.

11. An apparatus for determining the efficiency of a roadside unit, the apparatus comprising:

the system comprises an acquisition unit, a first road side unit and a second road side unit, wherein the acquisition unit is used for acquiring the working state of the first road side unit, the first road side unit is any one of N road side units which are sequentially distributed in a first driving direction, the first driving direction is the passing direction of a first lane, and the working state of the first road side unit is an opening state or a closing state;

An allocation unit, configured to allocate all or part of communication demand traffic in a target communication demand traffic to the first road side unit when the working state of the first road side unit is the on state, where the communication demand traffic allocated to the first road side unit is less than or equal to a first threshold, where the target communication demand traffic is a sum of a first accumulated unallocated traffic and a first communication demand traffic of traffic flows in a first time period within a communication coverage area of the first road side unit, and the first accumulated unallocated traffic is a communication demand traffic of traffic flows in a communication demand traffic of one or more road side units preceding the first road side unit in a direction opposite to the first driving direction, and the first threshold is a communication traffic of traffic flows that can be completed maximally within the communication coverage area of the first road side unit; and under the condition that the working state of the first road side unit is the closed state, not distributing communication demand flow for the first road side unit;

The first determining unit is used for determining a first combination according to the working state of the first road side unit, and the first combination is used for representing a value arrangement of the working state of each road side unit in the N road side units in the first time period;

And the second determining unit is used for determining a first numerical value corresponding to the first combination according to the product of the distribution completion degree of the total communication demand flow and the communication flow transmitted by the N road side units per unit energy consumption, wherein the first numerical value is in direct proportion to the working efficiency of the N road side units, and the total communication demand flow is the sum of the communication demand flows of the traffic flow in the communication coverage area of each road side unit in the N road side units.

12. An electronic device, comprising: a memory, a processor, wherein the memory stores program instructions; the program instructions, when executed by the processor, cause the processor to perform the method of any of claims 1 to 10.

13. A computer-readable storage medium, wherein the computer-readable storage medium has a computer program stored therein; the method of any one of claims 1 to 10 being performed when the computer program is run on one or more processors.