A method for reminding congestion ahead based on edge computing nodes

Abstract

The embodiment of the application discloses an edge computing node-based front congestion reminding method, and relates to the technical field of edge computing.The method comprises the following steps: collecting picture information of a road in real time through a plurality of cameras which are distributed on the road; identifying traffic congestion information in the collected picture information based on a preset traffic congestion identification algorithm through an edge computing node connected with the cameras; and sending the traffic congestion information to a terminal designated in advance for display.The application can automatically and intelligently identify traffic congestion information from real-time collected road picture information, realizes real-time and accurate acquisition of traffic congestion information, facilitates route planning in advance, and ensures smoothness of a traffic line.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of edge computing, and particularly relates to a front congestion reminding method based on an edge computing node. BACKGROUND

[0002] With the rapid development of the transportation industry, the most intuitive manifestation of the development is that more and more roads are built, and the vehicles running on the roads are also rapidly increasing, so that the traffic conditions of the roads are changing all the time, especially once the road is congested, the driving time of the vehicles is rapidly increased, which seriously affects the driving experience of the drivers of the vehicles running on the road.

[0003] In order to timely grasp the road congestion condition and facilitate planning of a better driving route, the current road congestion reminding scheme mainly determines the vehicle staying time according to the GPS positioning, and then predicts the road congestion condition according to the staying time, but a large amount of time is spent to determine the staying time of the vehicle, which leads to a long time for obtaining the road congestion information, and a large amount of computing resources are also needed to calculate the congestion information according to the staying time. SUMMARY

[0004] Therefore, the embodiment of the application provides a front congestion reminding method based on an edge computing node, which is used to solve the problem of the existing road congestion reminding scheme that the road congestion information is obtained with a lag and a large amount of computing resources is consumed. The application can automatically and intelligently identify the traffic congestion information from the real-time collected road picture information through the edge computing node, reduce the consumption of computing resources, realize real-time and accurate acquisition of the road congestion data, facilitate early planning of a route, and ensure smooth traffic of the traffic line.

[0005] The embodiment of the application provides a front congestion reminding method based on an edge computing node, which comprises the following steps:

[0006] Collecting picture information of a road in real time through a plurality of cameras distributed on the road;

[0007] Identifying traffic congestion information in the collected picture information through an edge computing node connected with the camera based on a preset traffic congestion identification algorithm;

[0008] Sending the traffic congestion information to a pre-designated terminal for display.

[0009] In an optional embodiment, the step of identifying the traffic congestion information in the collected picture information through the edge computing node connected with the camera based on the preset traffic congestion identification algorithm further comprises the following steps:

[0010] Detecting whether each edge computing node is in an idle state according to a preset period;

[0011] According to a preset allocation strategy, the computing resource of the edge computing node in the idle state is allocated to the edge computing node in the non-idle state.

[0012] In an optional embodiment, the detection of whether each edge computing node is in the idle state according to the preset period comprises:

[0013] At each time when the preset period expires, the current expiration period is obtained, and the interaction record between the current edge computing node and the camera in the current expiration period is obtained; wherein, the interaction record comprises: the data amount transmitted by the camera connected to the current edge computing node to the current edge computing node, the number of times of sending interaction information by the current edge computing node to the connected camera, and the return state value of each interaction information sent by the current edge computing node to the connected camera;

[0014] The idle determination value of each edge computing node is calculated according to the first formula;

[0015] It is judged whether the idle determination value of each edge computing node is equal to 1;

[0016] If the idle determination value of the current edge computing node is equal to 1, it is determined that the current edge computing node is in the idle state; if the idle determination value of the current edge computing node is not equal to 1, it is determined that the current edge computing node is in the non-idle state;

[0017] The first formula is:

[0018]

[0019] In the first formula, E(t) represents the idle determination value of the current edge computing node at the current time; t represents the current time; T represents the preset period; s(t-T,t) represents the data amount transmitted by the camera connected to the current edge computing node to the current edge computing node within t-T time to t time; J(a) represents the return state value of the a-th interaction information sent by the current edge computing node to the connected camera within t-T time to t time, if the current edge computing node receives the return information of the a-th interaction information sent to the connected camera, then J(a)=1, otherwise J(a)=0; a=1,2,…,n(t-T,t); n(t-T,t) represents the total number of times of sending interaction information by the current edge computing node to the connected camera within t-T time to t time; The value of a is taken from 1 to n(t-T,t) in the parentheses, if one or more values of a satisfy the formula in the parentheses, then the overall formula is established, otherwise the overall formula is not established; If all the values of a satisfy the algorithm in the parentheses, the overall algorithm is correct, otherwise, the overall algorithm is incorrect.

[0020] In an optional embodiment, the method further comprises:

[0021] determining whether at least one of the nearby edge computing nodes is in a non-idle state;

[0022] If yes, determining a helping edge computing node corresponding to the edge computing node in the idle state from the nearby edge computing nodes of the edge computing node in the idle state;

[0023] allocating the computing resource of the edge computing node in the idle state to the helping edge computing node according to a preset allocation strategy.

[0024] In an optional embodiment, the method further comprises:

[0025] obtaining the amount of data received from the connected camera and the CPU usage rate of each of the nearby edge computing nodes of the edge computing node in the idle state;

[0026] calculating the relative work occupancy rate of each of the nearby edge computing nodes of the edge computing node in the idle state based on a second formula according to the amount of data received from the connected camera and the CPU usage rate of each of the nearby edge computing nodes of the edge computing node in the idle state, wherein the nearby edge computing nodes of the edge computing node in the idle state are edge computing nodes corresponding to other cameras having a distance less than a preset distance from the camera corresponding to the edge computing node in the idle state;

[0027] determining whether the relative work occupancy rate of at least one of the nearby edge computing nodes of the edge computing node in the idle state is not equal to 0;

[0028] If the relative work occupancy rate of at least one of the nearby edge computing nodes of the edge computing node in the idle state is not equal to 0, it is determined that at least one of the nearby edge computing nodes of the edge computing node in the idle state is in a non-idle state;

[0029] wherein the second formula is:

[0030]

[0031] In the second formula, L(r) represents the relative working occupancy rate of the rth nearest edge computing node of the current idle edge computing node; S(r) represents the data amount received from the connected camera in a unit time by the rth nearest edge computing node of the current idle edge computing node; R represents the total number of the nearest edge computing nodes of the current idle edge computing node; r = 1, 2, …, R; CPU(r) represents the CPU usage rate of the rth nearest edge computing node of the current idle edge computing node; represents the maximum value in the parentheses by taking the value of r from 1 to R.

[0032] In an optional embodiment, the determining of the helping edge computing node corresponding to the current idle edge computing node from the nearest edge computing nodes of the current idle edge computing node comprises:

[0033] obtaining the nearest edge computing node identifier whose relative working occupancy rate is not equal to 0, to obtain a non-idle edge computing node identifier set corresponding to the current idle edge computing node;

[0034] displaying the current idle edge computing node identifier and the non-idle edge computing node identifier set corresponding thereto through a preset selection window on the designated control terminal;

[0035] receiving the selection of the non-idle edge computing node identifier in the selection window, and determining the edge computing node corresponding to the selected non-idle edge computing node identifier as the helping edge computing node corresponding to the current idle edge computing node.

[0036] In an optional embodiment, the determining of the helping edge computing node corresponding to the current idle edge computing node from the nearest edge computing nodes of the current idle edge computing node comprises:

[0037] obtaining the data transmission speed between the current idle edge computing node and its nearest edge computing node;

[0038] determining the serial number value of the helping edge computing node corresponding to the current idle edge computing node based on the third formula according to the relative working occupancy rate of the nearest edge computing node of the current idle edge computing node and the data transmission speed between the current idle edge computing node and its nearest edge computing node.

[0039] wherein the third formula is:

[0040]

[0041] In the third formula, B represents the Bth nearest edge computing node corresponding to the edge computing node currently in an idle state as the helping edge computing node of the edge computing node currently in an idle state; a and k each represent an integer variable, a = 1, 2, 3, …, R; k = 1, 2, 3, …, R; V(r), V(a), and V(k) respectively represent the data transmission speed between the edge computing node currently in an idle state and the rth, ath, and kth nearest edge computing node thereof; L(r), L(a), and L(k) respectively represent the relative working occupancy of the rth, ath, and kth nearest edge computing node of the edge computing node currently in an idle state, represents the maximum value in the parentheses obtained by taking the value of k from 1 to R; Z{} represents a positive number detection function, and the function value is 1 if the value in the parentheses is positive, and the function value is 0 if the value in the parentheses is not positive; represents the value of r when the maximum value in the parentheses is obtained by taking the value of r from 1 to R.

[0042] In an optional embodiment, after determining the helping edge computing node corresponding to the edge computing node currently in an idle state based on the third formula, the method further comprises:

[0043] determining whether the number of serial number values of the helping edge computing node corresponding to the edge computing node currently in an idle state determined based on the third formula is greater than 1;

[0044] If the number of serial number values of the helping edge computing node is greater than 1, the helping edge computing node with the smallest serial number value is determined as the helping edge computing node corresponding to the edge computing node currently in an idle state.

[0045] The edge computing node-based front congestion reminding method provided by the application can automatically and intelligently identify traffic congestion information from real-time collected road picture information through the edge computing node, reduces the consumption of computing resources, realizes real-time and accurate acquisition of road congestion data, facilitates early route planning, and ensures smooth traffic lines. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to make the technical solutions in the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only only some embodiments of the present application, and all other embodiments obtained by those of ordinary skill in the art without creative work based on the embodiments of the present application are within the protection scope of the present application.

[0047] Figure 1 A flow chart of a front congestion reminding method based on an edge computing node is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0048] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0049] It should be clear that the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work are within the protection scope of the present application.

[0050] Figure 1 A flow chart of a front congestion reminding method based on an edge computing node is provided for the embodiments of the present application. Referring to Figure 1 , the method comprises the following steps S101-S103:

[0051] S101: Real-time collection of picture information of a road through a plurality of cameras distributed on the road.

[0052] S102: Identification of traffic congestion information in the collected picture information based on a preset traffic congestion identification algorithm through an edge computing node connected with the camera.

[0053] S103: Sending of the traffic congestion information to a pre-designated terminal for display.

[0054] Among them, the pre-designated terminal can be a road traffic information planning server or a navigation terminal on a vehicle.

[0055] The beneficial effects of the above technical solutions are that: the front congestion reminding method based on an edge computing node provided by the embodiments of the present application first collects picture information of a road through a camera in real time, then identifies traffic congestion information in the collected picture information based on a preset traffic congestion identification algorithm through an edge computing node, and then sends the traffic congestion information to a pre-designated terminal for display. The present application can automatically and intelligently identify traffic congestion information from real-time collected road picture information through an edge computing node, reduce the consumption of computing resources, realize real-time and accurate acquisition of road congestion data, facilitate early route planning, and ensure smooth traffic lines.

[0056] As an optional embodiment, the step S102 can further include steps S201-S202:

[0057] S201: detecting whether each edge computing node is in an idle state according to a preset period;

[0058] S202: allocating the computing resource of the edge computing node in the idle state to the edge computing node in the non-idle state according to a preset allocation strategy.

[0059] The above technical solution has the beneficial effect that when the camera, the connection line between the camera and the edge computing node, etc. fails, the picture information of the road cannot be collected, or the image information from the connected camera cannot be obtained by the edge computing node, and the edge computing node is in an idle state. The computing resource of the edge computing node in the idle state is allocated to the edge computing node in the non-idle state, which effectively improves the utilization rate of the edge computing node resource and further improves the execution efficiency of the system.

[0060] As an optional embodiment, the step S201 can include steps S301-S305:

[0061] S301: obtaining the interaction record between the current edge computing node and the camera in the current period that has expired, which is counted by each edge computing node, at each time when the preset period expires; wherein the interaction record includes the data amount transmitted by the connected camera of the current edge computing node to the current edge computing node, the number of times of sending the interaction information by the current edge computing node to the connected camera, and the return state value of each time of sending the interaction information by the current edge computing node to the connected camera;

[0062] S302: calculating the idle determination value of each edge computing node according to a first formula;

[0063] S303: judging whether the idle determination value of each edge computing node is equal to 1; if yes, executing S304, otherwise executing S305;

[0064] S304: determining that the current edge computing node is in an idle state;

[0065] S305: determining that the current edge computing node is in a non-idle state;

[0066] The first formula is:

[0067]

[0068] In the first formula, E(t) represents the idle determination value of the current edge computing node at the current time. E(t) = 1 indicates that the current edge computing node is in an idle state, and E(t) = 0 indicates that the current edge computing node is in a non-idle state; t represents the current time; T represents the preset period; S(tt,t) represents the amount of data transmitted from the camera connected to the current edge computing node to the current edge computing node between time tT and time t; J(a) represents the return status value of the a-th interaction information sent by the current edge computing node to the connected camera between time tT and time t. If the current edge computing node receives the return information of the a-th interaction information sent to the connected camera, then J(a) = 1, otherwise J(a) = 0; a = 1,,2,…,n(tT,t); n(tT,t) represents the total number of interaction information sent by the current edge computing node to the connected camera between time tT and time t. This means that if the value of a is taken from 1 to n(tT,t) and substituted into the parentheses, the entire expression is true if there is one or more values ​​of a that satisfy the expression in the parentheses; otherwise, the entire expression is false. This means that if the value of a is taken from 1 to n(tT,t) and substituted into the parentheses, the entire expression is true if all the values ​​of a satisfy the expression in the parentheses; otherwise, the entire expression is false.

[0069] The beneficial effects of the above technical solution are as follows: by using the first formula (1) to determine whether the edge computing node is idle (i.e., in an idle state) based on the interaction information between the edge computing node and the corresponding connected camera, firstly, it can promptly detect faulty cameras, and secondly, it can reallocate the resources of idle edge computing nodes to ensure the maximum utilization of system resources.

[0070] As an optional embodiment, step S202 may include the following steps S401-S403:

[0071] S401: Determine whether at least one of the nearest edge computing nodes of the currently idle edge computing node is in a non-idle state; if so, execute S402.

[0072] S402: Determine the supporting edge computing node corresponding to the currently idle edge computing node from the nearest edge computing nodes of the currently idle edge computing node;

[0073] S403: Allocate the computing resources of the currently idle edge computing node to its corresponding supporting edge computing node according to the preset allocation strategy.

[0074] The beneficial effects of the above technical solutions are: when there is an idle edge computing node, it is further determined whether there is an edge computing node in the idle edge computing node in the vicinity of the edge computing node in a non-idle state, if yes, the computing resources of the idle edge computing node are allocated; if no, the computing resources of the idle edge computing node are not allocated, thereby effectively improving the execution efficiency of the present application.

[0075] As an optional embodiment, the step S401 can include steps S501-S504:

[0076] S501: obtaining the amount of data received by each nearby edge computing node of the current idle edge computing node from the connected camera and the CPU usage rate of each nearby edge computing node;

[0077] S502: calculating the relative work occupancy rate of each nearby edge computing node of the current idle edge computing node based on the amount of data received by each nearby edge computing node of the current idle edge computing node from the connected camera and the CPU usage rate of each nearby edge computing node according to a second formula; wherein the nearby edge computing node of the current idle edge computing node is the edge computing node corresponding to the other camera whose distance from the camera corresponding to the current idle edge computing node is less than a preset distance;

[0078] S503: determining whether there is at least one nearby edge computing node whose relative work occupancy rate is not equal to 0 in the nearby edge computing nodes of the current idle edge computing node; yes, then S504;

[0079] S504: determining that at least one nearby edge computing node in the nearby edge computing nodes of the current idle edge computing node is in a non-idle state;

[0080] The second formula is:

[0081]

[0082] In the second formula, L(r) represents a relative working occupancy rate of the rth nearest edge computing node of the current idle edge computing node, L(r) = 0 indicates that the rth nearest edge computing node of the current idle edge computing node is in an idle state, and L(r) ≠ 0 indicates that the rth nearest edge computing node of the current idle edge computing node is in a non-idle state; S(r) represents an amount of data received by the rth nearest edge computing node of the current idle edge computing node from a connected camera in a unit time; R represents a total number of the nearest edge computing nodes of the current idle edge computing node; r = 1, 2,..., R; and CPU(r) represents a CPU utilization rate of the rth nearest edge computing node of the current idle edge computing node. The maximum value in the parentheses is obtained by taking the value of r from 1 to R and substituting it into the parentheses.

[0083] The above technical solution has the beneficial effect that the relative working occupancy rate of the nearest edge computing node of the idle edge computing node is obtained according to the data amount and the calculated data amount of the camera connected to the nearest edge computing node of the idle edge computing node by using the second formula (2), thereby providing a basis for subsequent allocation of resources of the idle edge computing node.

[0084] As an optional embodiment, the step S402 can include the following steps S601-S603.

[0085] S601: Obtain an idle edge computing node identifier corresponding to a nearest edge computing node whose relative working occupancy rate is not equal to 0, to obtain a non-idle state edge computing node identifier set corresponding to the current idle edge computing node;

[0086] S602: Display the idle edge computing node identifier and the non-idle state edge computing node identifier set corresponding thereto through a preset selection window on a specified control terminal;

[0087] S603: Receive a selection of the non-idle state edge computing node identifier in the selection window, and determine an edge computing node corresponding to the selected non-idle state edge computing node identifier as a helping edge computing node corresponding to the current idle edge computing node.

[0088] The beneficial effects of the above technical solutions are: obtaining the just-in-range edge computing node identifier of the just-in-range edge computing node whose relative working occupancy rate is not equal to 0, obtaining the non-idle state edge computing node identifier set, then displaying the non-idle state edge computing node identifier set to the user for selection, and finally allocating the computing resources of the idle state edge computing node to the non-idle state edge computing node selected by the user, which on the one hand effectively improves the computing performance of the selected node, and on the other hand effectively improves the user experience.

[0089] As an optional embodiment, the step S402 can include steps S701-S702.

[0090] S701: obtaining the data transmission speed between the current idle state edge computing node and its just-in-range edge computing node;

[0091] S702: determining the serial number value of the helping edge computing node corresponding to the current idle state edge computing node based on the third formula according to the relative working occupancy rate of the just-in-range edge computing node of the current idle state edge computing node and the data transmission speed between the current idle state edge computing node and its just-in-range edge computing node.

[0092] The third formula is:

[0093]

[0094] In the third formula, B represents that the helping edge computing node corresponding to the current idle state edge computing node is the Bth just-in-range edge computing node of the current idle state edge computing node; a and k both represent integer variables, r=1, 2, 3, …, R; a=1, 2, 3, …, R; k=1, 2, 3, …, R; V(r), V(a) and V(k) respectively represent the data transmission speed between the current idle state edge computing node and its rth, ath and kth just-in-range edge computing node; L(r), L(a) and L(k) respectively represent the relative working occupancy rate of the rth, ath and kth just-in-range edge computing node of the current idle state edge computing node, represents that the value of k is taken from 1 to R to obtain the maximum value in the parentheses; Z{} represents a positive number detection function, and the function value is 1 if the value in the parentheses is positive, and the function value is 0 if the value in the parentheses is not positive; represents that the value of r is taken from 1 to R to obtain the value of r when the maximum value in the parentheses is obtained.

[0095] The beneficial effects of the above technical solutions are that: the third formula (3) is used to calculate the working occupancy rate of the nearest edge computing node according to the idle state edge computing node, and the transmission data speed between the idle state edge computing node and the nearest edge computing node, and the idle state edge computing node is selected as the helping edge computing node in the nearest edge computing node, so that the idle state edge computing node assists the helping edge computing node in identification and calculation, so that the idle state edge computing node can be used to the greatest extent during the idle state of the edge computing node, and the resource utilization of the system is improved.

[0096] As an optional embodiment, after the step S702 of determining the helping edge computing node corresponding to the edge computing node currently in the idle state based on the third formula, the following steps S801-S802 can be further included.

[0097] S801: determining whether the number of the serial number values of the helping edge computing node corresponding to the edge computing node currently in the idle state determined based on the third formula is greater than 1, if yes, performing S802;

[0098] S802: determining the helping edge computing node with the minimum serial number value as the helping edge computing node corresponding to the edge computing node currently in the idle state.

[0099] The beneficial effects of the above technical solutions are that: in the third formula, The r value is obtained by substituting the value of r from 1 to R into the parentheses, and the minimum r value of the maximum r value is selected if there are two or more maximum r values, that is, the unique helping edge computing node is automatically selected, and the implementation method is simple.

[0100] From the above embodiment, through the edge computing node connecting the camera for real-time identification and calculation, and the result is distributed through the edge computing node for distributed transmission, the early warning planning route is realized. In addition, during the process of the edge computing node connecting the camera for real-time identification and calculation, if the edge computing node is idle due to camera failure or other reasons, the idle edge computing node will analyze the data amount of the camera connected to the nearest edge computing node and the calculation data amount to select the edge computing node with relatively high working occupancy rate for auxiliary identification and calculation, until the idle edge computing node corresponding to the camera is repaired, and the real-time identification and calculation for the corresponding camera is continued, so that the idle edge computing node can be used to the greatest extent during the idle state of the edge computing node, and the resource utilization of the system is improved.

[0101] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the methods Figure 1 one or more of the methods described in the flow Figure 1 one or more of the methods described in the flow

[0102] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the methods Figure 1 one or more of the methods described in the flow Figure 1 one or more of the methods described in the flow

[0103] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the methods Figure 1 one or more of the methods described in the flow Figure 1 one or more of the methods described in the flow

[0104] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the apparatuses and manufacturing equipment or processes involving a plurality of discrete steps or stages. Such equipment or processes can be either of an industrial scale or a laboratory scale.

Claims

1. A method for edge computing node based congestion ahead warning, the method comprising: The application relates to a traffic congestion information collection method and system. Real-time collection of picture information of a road through a plurality of cameras distributed on the road; Identification of traffic congestion information in the collected picture information through an edge computing node connected with the cameras based on a preset traffic congestion identification algorithm; Sending of the traffic congestion information to a pre-designated terminal for display; The method further comprises: Periodic detection of whether each edge computing node is in an idle state; According to a preset allocation strategy, the computing resources of the edge computing node in the idle state are allocated to the edge computing node in the non-idle state. The periodic detection of whether each edge computing node is in an idle state comprises: At the end of each preset period, the current edge computing node obtains the interaction record between the current edge computing node and the cameras in the current period from each edge computing node; the interaction record comprises the data amount transmitted by the camera connected with the current edge computing node to the current edge computing node, the number of times of interaction information sent by the current edge computing node to the connected camera, and the return state value of each interaction information sent by the current edge computing node to the connected camera; According to a first formula, the idle determination value of each edge computing node is calculated; It is determined whether the idle determination value of each edge computing node is equal to 1; If the idle determination value of the current edge computing node is equal to 1, it is determined that the current edge computing node is in an idle state; if the idle determination value of the current edge computing node is not equal to 1, it is determined that the current edge computing node is in a non-idle state. The first formula is as follows: In the first formula, E(t) represents the idle determination value of the current edge computing node at the current time; t represents the current time; T represents a preset period; S(t-T, t) represents the data amount transmitted by the connected camera to the current edge computing node within the time from t-T to t; J(a) represents the return state value of the a-th interaction information sent by the current edge computing node to the connected camera within the time from t-T to t, and J(a)=1 if the current edge computing node receives the return information of the a-th interaction information sent to the connected camera, otherwise J(a)=0; a=1, 2, …, n(t-T, t); n(t-T, t) represents the total number of interaction information sent by the current edge computing node to the connected camera within the time from t-T to t; represents that the value of a is taken from 1 to n(t-T, t) and substituted into the parentheses, and the overall formula is true if one or more values of a satisfy the formula in the parentheses, otherwise the overall formula is not true; represents that the value of a is taken from 1 to n(t-T, t) and substituted into the parentheses, and the overall formula is true if all values of a satisfy the formula in the parentheses, otherwise the overall formula is not true. 2.The edge computing node based ahead-of-time congestion warning method of claim 1, wherein, The method further comprises: It is determined whether at least one of the nearby edge computing nodes of the current edge computing node in an idle state is in a non-idle state; If yes, a helping edge computing node corresponding to the current edge computing node in an idle state is determined among the nearby edge computing nodes of the current edge computing node in an idle state; According to a preset allocation strategy, the computing resources of the current edge computing node in an idle state are allocated to the corresponding helping edge computing node. 3.The edge computing node based ahead-of-time congestion warning method of claim 2, wherein, The determination of whether at least one of the nearby edge computing nodes of the current edge computing node in an idle state is in a non-idle state comprises: The data amount received by each nearby edge computing node from the connected camera and the CPU usage rate of each nearby edge computing node are obtained. According to the amount of data received from the connected cameras by each nearby edge computing node of the edge computing node currently in an idle state and the CPU usage of each nearby edge computing node, the relative working occupancy of each nearby edge computing node of the edge computing node currently in an idle state is calculated based on a second formula; wherein the nearby edge computing node of the edge computing node currently in an idle state is an edge computing node corresponding to other cameras with a distance less than a preset distance from the camera corresponding to the edge computing node currently in an idle state; It is judged whether the relative working occupancy of at least one of the nearby edge computing nodes of the edge computing node currently in an idle state is not equal to 0; If the relative working occupancy of at least one of the nearby edge computing nodes of the edge computing node currently in an idle state is not equal to 0, it is determined that at least one of the nearby edge computing nodes of the edge computing node currently in an idle state is in a non-idle state; The second formula is: In the second formula, L(r) represents the relative working occupancy rate of the rth nearby edge computing node of the edge computing node currently in an idle state; S(r) represents the amount of data received from the connected camera per unit time by the rth nearby edge computing node of the edge computing node currently in an idle state; R represents the total number of nearby edge computing nodes of the edge computing node currently in an idle state; r = 1, 2, …, R; CPU(r) represents the CPU usage rate of the rth nearby edge computing node of the edge computing node currently in an idle state; represents the maximum value in the parentheses obtained by substituting the value of r from 1 to R into the parentheses. 4.The edge computing node based ahead-of-time congestion warning method of claim 3, wherein, The determination of the supporting edge computing node corresponding to the edge computing node currently in an idle state among the nearby edge computing nodes of the edge computing node currently in an idle state comprises: The relative working occupancy of at least one of the nearby edge computing nodes of the edge computing node currently in an idle state is not equal to 0, and the non-idle state edge computing node identifier set corresponding to the edge computing node currently in an idle state is obtained; The preset selection window on the designated control terminal displays the edge computing node identifier currently in an idle state and its corresponding non-idle state edge computing node identifier set; The selection of the non-idle state edge computing node identifier in the selection window is received, and the edge computing node corresponding to the currently selected non-idle state edge computing node identifier is determined as the supporting edge computing node corresponding to the edge computing node currently in an idle state. 5.The edge-computing-node-based congestion-ahead reminding method according to claim 3, wherein, The determination of the supporting edge computing node corresponding to the edge computing node currently in an idle state among the nearby edge computing nodes of the edge computing node currently in an idle state comprises: The data transmission speed between the edge computing node currently in an idle state and its nearby edge computing node is obtained; According to the relative working occupancy of the nearby edge computing node of the edge computing node currently in an idle state and the data transmission speed between the edge computing node currently in an idle state and its nearby edge computing node, the serial number value of the supporting edge computing node corresponding to the edge computing node currently in an idle state is determined based on a third formula; The third formula is: In the third formula, B represents the Bth nearest edge computing node of the current idle edge computing node as the helping edge computing node; a and k represent integer variables, a = 1, 2, 3, …, R; k = 1, 2, 3, …, R; V(r), V(a) and V(k) represent the data transmission speeds between the current idle edge computing node and the rth, ath and kth nearest edge computing node of the current idle edge computing node respectively; L(r), L(a) and L(k) represent the relative working occupancy rates of the rth, ath and kth nearest edge computing node of the current idle edge computing node respectively, represents the maximum value in the parentheses by taking the value of k from 1 to R; Z{} represents a positive number detection function, and the function value is 1 if the value in the parentheses is positive, and the function value is 0 if the value in the parentheses is not positive; represents the value of r when the maximum value in the parentheses is obtained by taking the value of r from 1 to R.

6. The edge-compute-node-based congestion-ahead alerting method of claim 5, wherein, After determining the supporting edge computing node corresponding to the edge computing node currently in an idle state based on the third formula, it further comprises: It is judged whether the number of serial number values of the supporting edge computing node corresponding to the edge computing node currently in an idle state determined based on the third formula is greater than 1; If the quantity of the serial number values of the determined helper edge computing nodes is greater than 1, the helper edge computing node with the smallest serial number value is determined as the helper edge computing node corresponding to the edge computing node currently in the idle state.

Images