Industrial Internet of Things equipment collaborative scheduling system based on edge computing

Abstract

The invention relates to the technical field of data processing, in particular to an industrial Internet of Things equipment collaborative scheduling system based on edge computing. The system comprises a data acquisition module which is used for acquiring the load and delay time of each node in a data stream transmission node graph at each transmission moment, the path length between the nodes and the time window of each transmission moment; the volatilization rate calculation module is used for calculating the initial volatilization rate of the node at the transmission moment; the target volatilization speed calculation module is used for calculating the target volatilization speed of the node at the transmission moment; and the scheduling module is used for controlling path selection by using the target volatilization speed of the node at the transmission moment in the ant colony algorithm so as to realize cooperative scheduling of the industrial Internet of Things equipment, and the accuracy and efficiency of cooperative scheduling of the industrial Internet of Things equipment are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing. More specifically, the present invention relates to an industrial Internet of Things device collaborative scheduling system based on edge computing. Background Art

[0002] Edge computing aims to transfer computing and data processing from the cloud to edge devices closer to the data source. With the continuous development of the Internet of Things technology, edge computing has gradually become one of the important means to realize the industrial Internet of Things. Edge computing and cloud computing complement each other in the industrial Internet of Things. Edge computing is close to the data source and can provide low-latency real-time processing capabilities; while cloud computing has powerful computing and storage capabilities and is suitable for processing large-scale data. By coordinating the two, efficient task offloading and optimal utilization of resources can be achieved.

[0003] The ant colony algorithm is a heuristic algorithm that simulates the foraging behavior of ants. By simulating the behavior of ants releasing pheromones during the process of finding food, the solution is gradually optimized. In the industrial Internet of Things environment, data usually passes through multiple routers from the acquisition node to the termination node of the system platform. In the edge computing environment, the ant colony algorithm can optimize the routing selection at the edge gateway, reduce the length of the data transmission path, avoid congested nodes, thereby reducing network latency and improving the collaborative scheduling efficiency of industrial Internet of Things devices.

[0004] However, the evaporation rate of pheromones in the ant colony algorithm is fixed. When facing a complex or dynamically changing environment, too fast an evaporation rate will cause the algorithm to converge prematurely and miss the global optimal solution; too slow an evaporation rate will cause the algorithm to converge slowly and be inefficient, ultimately affecting the collaborative scheduling accuracy of industrial Internet of Things devices. Therefore, how to accurately adjust the evaporation rate of pheromones in the ant colony algorithm when obtaining the best scheduling result of industrial Internet of Things devices is an urgent problem to be solved at present. Summary of the Invention

[0005] To solve the above technical problem of how to accurately adjust the evaporation rate of pheromones in the ant colony algorithm when obtaining the best scheduling result of industrial Internet of Things devices, the present invention proposes an industrial Internet of Things device collaborative scheduling system based on edge computing. The system includes the following modules: A data acquisition module, configured to acquire the load, delay time, and path length between nodes at each transmission moment in a data flow transmission node graph; acquire the time window of each node at each transmission moment; A volatility rate calculation module, configured to calculate the volatility adjustment factor of a node at a transmission moment according to the maximum load, load variance, and maximum delay time in the time window of the node at the transmission moment; adjust a preset reference volatility rate according to the volatility adjustment factor of the node at the transmission moment to obtain the initial volatility rate of the node at the transmission moment; A target volatility speed calculation module, configured to calculate the target volatility speed of a node at a transmission moment: ; is the target volatility speed of the th node at the i-th transmission moment, , are respectively the maximum and minimum values of the data flow transmission path, is the data flow transmission path length passing through the th node, is the initial volatility rate of the th node at the i-th transmission moment; A scheduling module, configured to use the target volatility speed of a node at a transmission moment to control path selection in the ant colony algorithm to achieve collaborative scheduling of industrial Internet of Things devices.

[0006] The present invention can effectively improve the efficiency and accuracy of collaborative scheduling of industrial Internet of Things devices by dynamically adjusting the pheromone evaporation rate in the process of selecting nodes of industrial Internet of Things devices. In the process of dynamic adjustment, the present invention determines its volatility adjustment factor by acquiring the load and delay time of device nodes, and can accurately achieve dynamic load balancing, increasing the pheromone evaporation rate on high-load or high-delay nodes, so as to accurately adjust the traffic to low-load or low-delay paths, avoid network congestion, and effectively improve the collaborative scheduling efficiency of industrial Internet of Things devices. In addition, the present invention takes into account that the path length between nodes is a static feature of node selection. Therefore, when determining the target volatility rate of a node, the present invention also corrects the initial volatility rate through the path length, sets a smaller volatility speed for nodes with shorter paths, which can increase the probability of ants selecting node paths, so as to quickly converge to the optimal path, and effectively improve the collaborative scheduling accuracy and efficiency of industrial Internet of Things devices.

[0007] A collaborative scheduling system for industrial Internet of Things devices based on edge computing provided by the present invention. Before obtaining the load, delay time, and path length between nodes at each transmission moment in the data flow transmission node graph, it further includes: taking the local terminal as the starting node, the cloud platform as the ending node, the router between the local terminal and the cloud platform as the intermediate node, and the direction from the starting node to the ending node as the transmission direction to construct the data flow transmission node graph.

[0008] A collaborative scheduling system for industrial Internet of Things devices based on edge computing provided by the present invention. The obtaining of the load, delay time, and path length between nodes at each transmission moment in the data flow transmission node graph includes: obtaining the load and delay time of the node from the log of the node-related device at each transmission moment, and obtaining the path length between nodes according to the number of hops between nodes.

[0009] A collaborative scheduling system for industrial Internet of Things devices based on edge computing provided by the present invention. The obtaining of the time window of each node at each transmission moment includes: presetting the time window length of the node as m, and obtaining m historical transmission moments from the historical transmission moments before the transmission moment to construct the time window of this transmission moment.

[0010] The present invention takes into account that network load and delay have dynamics, temporal correlation, and statistical regularity, which will be reflected in the historical period. Therefore, by analyzing the stability of the load and delay time of each node at the historical transmission moments before the current transmission moment, the present invention can accurately obtain the difference between the load and delay time at the current acquisition moment and the historical data, and thus accurately obtain the evaporation adjustment factor.

[0011] A collaborative scheduling system for industrial Internet of Things devices based on edge computing provided by the present invention. The calculating of the evaporation adjustment factor of the node at this transmission moment includes: ; is the evaporation adjustment factor of the th node at the i-th transmission moment, 、 、 are respectively the maximum load, load variance, and maximum delay time in the time window of the th node at the i-th transmission moment, 、 、 are respectively the maximum load, maximum load variance, and maximum delay time in the time window of all nodes at the i-th transmission moment, is the exponential function with the base of e.

[0012] The present invention calculates a volatility adjustment factor by obtaining the load and latency time characteristics in the time window at the current transmission moment of a node. When adjusting the pheromone evaporation rate based on this, it can effectively reduce the attractiveness of high-load paths or high-latency paths, avoid the deterioration of latency caused by more traffic influx, reduce the possibility of congestion spread, thereby breaking the local optimum and finding a more balanced transmission path.

[0013] According to an industrial Internet of Things device collaborative scheduling system based on edge computing provided by the present invention, adjusting a preset reference evaporation rate according to the volatility adjustment factor of a node at the transmission moment to obtain the initial evaporation rate of the node at the transmission moment includes: ; is the initial evaporation rate of the th node at the i-th transmission moment, is the preset reference evaporation rate, is the th node's volatility adjustment factor at the i-th transmission moment.

[0014] According to an industrial Internet of Things device collaborative scheduling system based on edge computing provided by the present invention, using the target evaporation speed of a node at the transmission moment to control path selection in the ant colony algorithm includes: obtaining the next adjacent node of the node in the transmission direction of the node; using the target evaporation speed of the node at the transmission moment as the pheromone target evaporation speed on the path between the node and its next adjacent node at the transmission moment; calculating the path selection probability according to the pheromone target evaporation speed on the path between the node and its next adjacent node at each transmission moment.

[0015] The present invention uses the target evaporation speed of a node at the transmission moment as the pheromone target evaporation speed on the path between the node and its next adjacent node at the transmission moment. When the dynamic load or latency fluctuates violently due to sudden traffic, using the static path length as a benchmark can avoid excessive oscillation of the evaporation rate. And the static path length can prevent the algorithm from converging prematurely to a certain dynamically good but non-shortest path, thereby effectively improving the accuracy of path selection and the efficiency of the algorithm.

[0016] A collaborative scheduling system for industrial Internet of Things devices based on edge computing according to the present invention, calculating the path selection probability according to the target evaporation speed of pheromone on the path between each node and its next adjacent node at each transmission moment, includes: substituting the target evaporation speed of the node at the transmission moment into the iterative update formula to obtain the pheromone concentration on the path between the node and its next adjacent node at this transmission moment; calculating the selection probability of the path between the node and its next adjacent node at this transmission moment according to the pheromone concentration, path length, preset pheromone importance factor and heuristic information importance factor on the path between the node and its next adjacent node at this transmission moment.

[0017] A collaborative scheduling system for industrial Internet of Things devices based on edge computing according to the present invention, using the target evaporation speed of the node at the transmission moment to control path selection in the ant colony algorithm to achieve the collaborative scheduling of industrial Internet of Things devices, includes: setting the number of ants, each ant randomly selects a starting point, determining the next node of the ant according to the selection probability of the path between each node and its next adjacent node at each transmission moment, after the ant reaches the next node, updating the pheromone concentration on the path between this node and the next node in the data stream transmission node graph to achieve the collaborative scheduling of industrial Internet of Things devices.

[0018] A collaborative scheduling system for industrial Internet of Things devices based on edge computing according to the present invention, after achieving the collaborative scheduling of industrial Internet of Things devices, further includes: determining the maintenance method of the node according to the selection probability of the node.

[0019] The present invention considers that the higher the selection probability of a node, the higher the possibility of being selected as the path passed by the ant, and the higher the possibility of loss. Therefore, the present invention sets the maintenance method corresponding to the node according to the selection probability of the node, thereby effectively improving the service life and use effect of the device node.

[0020] The present invention has the following technical effects: Based on the above technical solution, the present invention can effectively improve the efficiency and accuracy of the collaborative scheduling of industrial Internet of Things (IIoT) devices by dynamically adjusting the pheromone evaporation rate in the process of selecting IIoT device nodes. During the dynamic adjustment process, the present invention determines its evaporation adjustment factor by obtaining the load and delay time of device nodes, which can accurately achieve dynamic load balancing. By increasing the pheromone evaporation rate on high-load or high-delay nodes, the traffic can be accurately adjusted to low-load or low-delay paths, avoiding network congestion and effectively improving the collaborative scheduling efficiency of IIoT devices. In addition, considering that the path length between nodes is a static feature of node selection, when determining the target evaporation rate of nodes, the present invention also corrects the initial evaporation rate through the path length, sets a smaller evaporation speed for nodes on shorter paths, which can increase the probability of ants selecting node paths, thus quickly converging to the optimal path and effectively improving the collaborative scheduling accuracy and efficiency of IIoT devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 FIG. is a system block diagram of a collaborative scheduling system for industrial Internet of Things devices based on edge computing according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention.

[0023] The present invention provides a collaborative scheduling system for industrial Internet of Things devices based on edge computing, which can accurately achieve the collaborative scheduling of industrial Internet of Things devices through the ant colony algorithm, thereby effectively improving the resource utilization rate.

[0024] As Figure 1 shown, Figure 1 FIG. is a system block diagram of a collaborative scheduling system for industrial Internet of Things devices based on edge computing according to an embodiment of the present invention. The system includes modules 101-104, which are specifically described below.

[0025] The data acquisition module 101 is configured to obtain the load, delay time, path length between nodes, and time window of each node at each transmission moment in the data stream transmission node graph.

[0026] Exemplarily, in the embodiment of the present invention, the local terminal can be used as the starting node, the cloud platform can be used as the ending node, the router between the local terminal and the cloud platform can be used as the intermediate node, and the direction from the starting node to the ending node can be used as the transmission direction to construct the data stream transmission node graph.

[0027] Specifically, the transmission direction is obtained according to the data flow direction and the protocol.

[0028] It should be noted that in the data flow transmission node graph, the data collection device of the data flow is the starting node, and the cloud device receiving the data flow is the ending node. There are usually multiple nodes between the starting node and the ending node where the data flow reaches. For example, during the process of a local device camera collecting a video stream and uploading it to the cloud, there are multiple routing device nodes to choose from, and the connection method of these routing device nodes is usually a complex topology, that is, the number of other nodes connected to each node may not be unique. And the task allocation and data routing among multiple devices require nanosecond-level collaborative scheduling, otherwise it may cause control instruction lag or production process interruption.

[0029] It should be further noted that the ant colony algorithm can achieve the collaborative scheduling of industrial Internet of Things devices by obtaining the path selection probabilities between nodes. In the data flow transmission node graph, by real-time monitoring the network load of each node (such as bandwidth utilization rate, data traffic), high-load areas can be dynamically avoided to prevent delays, packet losses, and even system crashes caused by data transmission congestion. In the industrial Internet of Things, too high node latency may lead to device action lag, instruction loss, or execution misalignment.

[0030] Therefore, in the embodiment of the present invention, when obtaining the optimal pheromone evaporation rate between nodes, it can be determined by the load size, load stability degree, and the size and stability degree of the delay time of the nodes. When the node load is high, the load is relatively unstable, the delay time is long and unstable, it is necessary to increase the pheromone evaporation rate, thereby reducing the probability of the node being selected by the data flow in the next transmission.

[0031] Exemplarily, in the embodiment of the present invention, obtaining the load and delay time of each node at each transmission moment in the data flow transmission node graph includes: obtaining the load and delay time of the node from the logs of the node-related devices at each transmission moment.

[0032] Among them, the unit of the load of the node can be a percentage, and the unit of the delay time is milliseconds.

[0033] Specifically, when obtaining the delay time, since the computing power of the edge device is low, a lower transmission frequency can be set.

[0034] Exemplarily, the interval of the transmission moment can be set to one minute, and it can be specifically set according to the data flow size, the load of the related devices, and the delay time. The embodiment of the present invention does not limit this too much here.

[0035] It can be understood that network load and latency are dynamic, time-sequentially correlated, and statistically regular. Therefore, in the embodiments of the present invention, the evaporation adjustment factor of each node can be obtained by statistically analyzing the load metrics and latency metrics within the historical time period before the current transmission moment of each node.

[0036] Exemplarily, in the embodiments of the present invention, obtaining the time window of each transmission moment of a node includes: presetting the time window length of the node as m, and obtaining m historical transmission moments from the historical transmission moments before the current transmission moment to construct the time window of the current transmission moment.

[0037] Among them, m can be set to 5; the value of m can be specifically set according to actual needs, and the embodiments of the present invention do not impose too many restrictions here.

[0038] The evaporation rate calculation module 102 is configured to calculate the evaporation adjustment factor of the node at the current transmission moment according to the maximum load, load variance, and maximum latency time in the time window of the node at the current transmission moment; adjust the preset reference evaporation rate according to the evaporation adjustment factor of the node at the current transmission moment to obtain the initial evaporation rate of the node at the current transmission moment.

[0039] Among them, the reference evaporation rate can be preset to 0.1; the value range of the reference evaporation rate is from 0 to 1, and it can be specifically set according to actual needs.

[0040] It should be noted that the probability of an ant choosing a path is positively correlated with the pheromone concentration. The higher the pheromone concentration of a path, the more likely it is to be selected by subsequent ants. If the load of a node at the current transmission moment has a greater difference from the overall load of all nodes in the data stream transmission node graph at the current transmission moment, and the load fluctuation is greater, it indicates that the load of this node is overweight. Continuing to select this node will cause packet backlog, a sharp increase in latency, and even lead to network congestion and collapse. Correspondingly, if the latency of a node is relatively high (such as approaching the maximum network latency), continuing to select this node will cause the packet queuing time to extend, and even lead to the end-to-end latency exceeding the application tolerance threshold.

[0041] Therefore, if the values of the load and latency time of a node are both large and the stability is worse, it is more necessary to increase the evaporation rate to accelerate the attenuation of pheromone on the path of this node, reduce the probability of it being selected by subsequent ants, so as to guide the traffic to a path with lower latency and load, and avoid the chain reaction of overweight latency and load.

[0042] Exemplarily, in the embodiments of the present invention, calculating the evaporation adjustment factor of the node at the current transmission moment includes: ; is the evaporation adjustment factor of the th node at the i-th transmission moment, is the The maximum load of a node in the time window at the i-th transmission moment, is the variance of the load of a node in the time window at the i-th transmission moment, is the maximum delay time of a node in the time window at the i-th transmission moment, is the maximum load of all nodes in the time window at the i-th transmission moment, is the maximum load variance of all nodes in the time window at the i-th transmission moment, is the maximum delay time of all nodes in the time window at the i-th transmission moment, is the exponential function with base e.

[0043] Among the above, is to perform normalization. If is closer to , it indicates that the maximum load of the -th node in the time window at the i-th transmission moment is closer to the global maximum load, the higher the load intensity, and the higher the possibility of high load on this node.

[0044] is to perform normalization. If is closer to , it indicates that the maximum load variance of the -th node in the time window at the i-th transmission moment is closer to the global maximum load variance of all nodes, and the higher the possibility of high load fluctuation on this node.

[0045] is to perform normalization. If is closer to , it indicates that the maximum delay time of the -th node in the time window at the i-th transmission moment is closer to the global maximum delay time, the higher the delay, and the higher the possibility of high delay on this node.

[0046] In summary, when the maximum load of the -th node in the time window at the i-th transmission moment is closer to the global maximum, if the maximum load variance of the -th node in the time window at the i-th transmission moment is closer to the global maximum load variance of all nodes, and the maximum delay time is closer to the global maximum delay time, it indicates that the possibility of high load and high delay of this node at the current transmission moment is greater. In order to reduce the probability of ants choosing this path in the future, it is necessary to increase the evaporation speed of pheromone concentration, that is, increase the evaporation adjustment factor.

[0047] After obtaining the evaporation adjustment factor of the node at the transmission moment based on the above method, the reference evaporation rate can be adjusted according to the evaporation adjustment factor of the node at each transmission moment, so as to accurately obtain the initial evaporation rate.

[0048] Exemplarily, in the embodiment of the present invention, adjusting the preset reference evaporation rate according to the evaporation adjustment factor of the node at the transmission moment to obtain the initial evaporation rate of the node at this transmission moment includes: ; is the initial evaporation rate of the th node at the i-th transmission moment, is the preset reference evaporation rate, is the th evaporation adjustment factor of the node at the i-th transmission moment.

[0049] In the above formula, is less than or equal to 1, so the value range of the initial evaporation rate of the th node at the i-th transmission moment finally obtained is: , ensuring that the path pheromone will not be quickly cleared due to too high initial evaporation rate.

[0050] Based on the above steps, the initial evaporation rate of each node at each transmission moment can be obtained. It can be understood that the load and delay time of the node are dynamically changing, and the evaporation speed of the pheromone is also dynamically changing. Therefore, the evaporation speed of the pheromone of the node can be dynamically adjusted according to the load and delay time of the node. In addition, the path length of the node is in a static state and is also an important factor affecting the evaporation speed of the pheromone. The lower the path length of the node, the higher the path preference degree of the node. At this time, it is necessary to reduce the evaporation speed of its pheromone to provide a basis for the selection of subsequent ants.

[0051] Therefore, the evaporation speed of the path pheromone is not only related to the device load and delay time of the node, but also related to the path length. In the embodiment of the present invention, the path length of the node is obtained through the following steps. By combining static and dynamic, the evaporation speed of the pheromone of the node at each transmission moment can be effectively improved, that is, continue to execute the following steps.

[0052] The target evaporation speed calculation module 103 is used to calculate the target evaporation speed of the node at the transmission moment according to the path length and the initial evaporation rate of the node.

[0053] Exemplarily, in the embodiment of the present invention, obtaining the path length between each node in the data flow transmission node graph includes: obtaining the path length between nodes according to the number of hops between nodes.

[0054] Among them, if the node is a router, the path length between nodes can be obtained according to the number of hops between nodes through a routing protocol, which can be specifically set according to actual needs, and the embodiments of the present invention will not elaborate here.

[0055] It can be understood that by transmitting the node graph of the data stream, a complete path from the starting node to the ending node can be obtained. If the data stream transmission path passing through the th node is not unique, then the average value of all data stream transmission paths passing through the th node can be used as the data stream transmission path length passing through the th node. For nodes with shorter paths, the evaporation rate of pheromone needs to be reduced to increase the probability of ants choosing this node, thereby accelerating convergence; for nodes with longer paths, the evaporation rate of pheromone needs to be enhanced to reduce the probability of ants choosing this node, thereby accelerating convergence. In addition, since the transmission direction of the data stream in the data stream transmission node graph is from the starting node to the ending node, therefore, in the embodiments of the present invention, the path length of the node refers to the path length between this node and the next adjacent node in its transmission direction, while the data stream transmission path length is the complete data stream transmission path length from the starting node to the ending node.

[0056] Exemplarily, in the embodiments of the present invention, to calculate the target evaporation speed of a node at the transmission moment, the following relational expression can be specifically referred to: ; is the target evaporation speed of the th node at the i-th transmission moment, is the maximum value of the data stream transmission path, is the minimum value of the data stream transmission path, is the data stream transmission path length passing through the th node, is the initial evaporation rate of the th node at the i-th transmission moment.

[0057] In the above formula, is the extreme difference of the transmission path, which is used as a reference value for different nodes to facilitate comparison between different nodes. represents the correction factor of the path of the node to the initial evaporation rate. The closer the data stream transmission path length passing through the th node is to the maximum value of the data stream transmission path, it indicates that the data stream transmission path length of the th node is higher, and the preference degree of the path length is lower. At this time, the initial evaporation rate needs to be increased according to the correction factor of the initial evaporation rate, the pheromone evaporation speed of the node is increased, and the possibility of subsequent ants choosing this path is reduced.

[0058] Based on the above method, the target evaporation rate of each node at each transmission moment can be accurately obtained. By updating the pheromone concentration after evaporation based on its target evaporation rate, ants can be made to tend to nodes with low load, low latency, and short path length during each path node selection, effectively improving the collaborative scheduling effect and accuracy of ants during each node selection.

[0059] The scheduling module 104 is used to control path selection using the target evaporation rate of nodes at the transmission moment in the ant colony algorithm to achieve collaborative scheduling of industrial Internet of Things devices.

[0060] It can be understood that during the collaborative scheduling process of industrial Internet of Things devices in edge computing, the ants in the ant colony algorithm are data streams, and the path nodes selected by the ants are the devices selected by the data streams.

[0061] Exemplarily, in the embodiments of the present invention, controlling path selection using the target evaporation rate of nodes at the transmission moment in the ant colony algorithm includes: obtaining the next adjacent node of the node in the node transmission direction; using the target evaporation rate of the node at the transmission moment as the target evaporation rate of pheromone on the path between the node and its next adjacent node at the transmission moment; calculating the path selection probability according to the target evaporation rate of pheromone on the path between the node and its next adjacent node at each transmission moment.

[0062] Exemplarily, in the embodiments of the present invention, calculating the path selection probability according to the target evaporation rate of pheromone on the path between the node and its next adjacent node at each transmission moment includes: substituting the target evaporation rate of the node at the transmission moment into the iterative update formula to obtain the pheromone concentration on the path between the node and its next adjacent node at the transmission moment; calculating the selection probability of the path between the node and its next adjacent node at the transmission moment according to the pheromone concentration, path length, preset pheromone importance factor, and heuristic information importance factor on the path between the node and its next adjacent node at the transmission moment.

[0063] Specifically, the iterative update formula is: ; In the above formula, is the pheromone concentration on the path between the th node and its next adjacent node at the i-th transmission moment, is the initial evaporation rate of the th node at the i-th transmission moment, is the preset initial value of pheromone concentration.

[0064] Among them, the initial value of the pheromone concentration can be set to 13; specifically, the initial value of the pheromone concentration can be set according to the number of nodes and the average path length.

[0065] Specifically, the number of ants can be set to 30. The pheromone importance factor controls the importance of pheromone in path selection and can be set to 1. The heuristic information importance factor controls the importance of the heuristic function in path selection and can be set to 1. The iteration termination condition can be preset as that each ant has completed route selection, or the iteration reaches a predetermined number of iterations, and the number of iterations can be set to 500.

[0066] Exemplarily, according to the pheromone concentration, path length, preset pheromone importance factor, and heuristic information importance factor on the path between a node and its next adjacent node at the current transmission moment, calculate the selection probability of the path between the node and its next adjacent node at the current transmission moment, including: ; is the selection probability of the path between the -th node and its next adjacent node at the i-th transmission moment, is the pheromone concentration on the path between the -th node and its next adjacent node at the i-th transmission moment, is the pheromone importance factor, is the heuristic information importance factor, is the heuristic function of the path between the -th node and its next adjacent node at the i-th transmission moment, is the set of neighbor nodes of the -th node, is the node index in the set of neighbor nodes of the -th node, is the pheromone concentration on the path between the -th node and the -th adjacent node in its set of neighbor nodes at the i-th transmission moment, is the heuristic function of the path between the

[0067] Among them, the heuristic function can be the reciprocal of the path length.

[0068] Exemplarily, in an embodiment of the present invention, in the ant colony algorithm, the target evaporation rate of a node at the transmission moment is used to control path selection to achieve the collaborative scheduling of industrial Internet of Things devices, including: setting the number of ants, each ant randomly selects a starting point, determines the next node of the ant according to the selection probability of the path between the node and its next adjacent node at each transmission moment. After the ant reaches the next node, the pheromone concentration of the path between the node and the next node in the data flow transmission node graph is updated to achieve the collaborative scheduling of industrial Internet of Things devices.

[0069] Specifically, the ant performs random sampling according to the selection probability of the path between the node and its next adjacent node at each transmission moment to determine the next node to be reached, and updates the pheromone concentration according to the pheromone concentration on the path between the node and its next adjacent node at the current transmission moment.

[0070] It can be understood that in the process of determining the pheromone evaporation rate, the ant comprehensively considers the load, delay time, and path length of the node, and based on this, path selection is achieved. This selection process is the process of collaborative scheduling.

[0071] Exemplarily, in an embodiment of the present invention, after achieving the collaborative scheduling of industrial Internet of Things devices, it further includes: determining the maintenance method of the node according to the selection probability of the node.

[0072] It can be understood that the higher the selection probability of the node, the greater the possibility that the node is selected as the forward route of the ant in random selection, that is, the greater the possibility of being used as the data flow transmission path. Long-term and high-frequency use of some nodes is likely to cause performance degradation or even failure due to overload. Therefore, when determining the maintenance method according to the selection probability of the node, a more perfect maintenance method is required for nodes with a higher selection probability.

[0073] Exemplarily, for high-probability nodes carrying the main business, the port utilization rate can be monitored once per hour, and when it exceeds 70%, it is automatically diverted to other top-of-rack switches.

[0074] Among them, the maintenance method can be specifically set according to actual needs, and the embodiments of the present invention do not limit this too much here.

[0075] It can be seen that in the embodiments of the present invention, when realizing the collaborative scheduling of industrial Internet-connected devices based on edge computing, it may include a data acquisition module, which is used to acquire the load, delay time, and path length between nodes at each transmission moment in the data flow transmission node graph; acquire the time window of each node at each transmission moment; a volatility calculation module, which is used to calculate the volatility adjustment factor of the node at this transmission moment according to the maximum load, load variance, and maximum delay time in the time window of the node at the transmission moment; adjust the preset reference volatility rate according to the volatility adjustment factor of the node at the transmission moment to obtain the initial volatility rate of the node at this transmission moment; a target volatility speed calculation module, which is used to calculate the target volatility speed of the node at the transmission moment: ; is the target volatility speed of the th node at the i-th transmission moment, , are the maximum and minimum values of the data flow transmission path respectively, is the data flow transmission path length passing through the th node, is the initial volatility rate of the th node at the i-th transmission moment; a scheduling module, which is used to control the path selection using the target volatility speed of the node at the transmission moment in the ant colony algorithm to realize the collaborative scheduling of industrial Internet of Things devices, effectively improving the accuracy and efficiency of the collaborative scheduling of industrial Internet-connected devices.

[0076] The above are all the preferred embodiments of the present invention. Without limiting the protection scope of the present invention accordingly, therefore: Any equivalent changes made according to the structure, shape, and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. An industrial Internet of Things device collaborative scheduling system based on edge computing, characterized in that, It includes the following modules: A data acquisition module, which is used to acquire the load, delay time, and path length between nodes at each transmission moment in the data flow transmission node graph; and acquire the time window of each node at each transmission moment. A volatility rate calculation module, which is used to calculate the volatility adjustment factor of a node at a transmission moment according to the maximum load, load variance, and maximum delay time in the time window of the node at the transmission moment; and adjust the preset reference volatility rate according to the volatility adjustment factor of the node at the transmission moment to obtain the initial volatility rate of the node at the transmission moment. A target volatility speed calculation module, which is used to calculate the target volatility speed of a node at a transmission moment. ； is the target evaporation rate of the -th node at the i-th transmission moment, , are the maximum and minimum values of the data stream transmission path respectively, is the length of the data stream transmission path passing through the -th node, is the initial evaporation rate of the -th node at the i-th transmission moment; A scheduling module, which is used to control path selection using the target volatility speed of a node at a transmission moment in the ant colony algorithm to achieve collaborative scheduling of industrial Internet of Things devices.

2. The collaborative scheduling system for industrial Internet of Things devices based on edge computing according to claim 1, wherein, Before acquiring the load, delay time, and path length between nodes at each transmission moment in the data flow transmission node graph, it further includes: Taking the local terminal as the starting node, the cloud platform as the ending node, the router between the local terminal and the cloud platform as the intermediate node, and the direction from the starting node to the ending node as the transmission direction to construct the data flow transmission node graph.

3. An industrial Internet of Things device collaborative scheduling system based on edge computing according to claim 1, characterized in that, Acquiring the load, delay time, and path length between nodes at each transmission moment in the data flow transmission node graph includes: Acquiring the load and delay time of a node from the log of the node-related device at each transmission moment, and obtaining the path length between nodes according to the number of hops between nodes.

4. An industrial Internet of Things device collaborative scheduling system based on edge computing according to claim 1, characterized in that, Acquiring the time window of each node at each transmission moment includes: Presetting the time window length of the node as m, and acquiring m historical transmission moments in the historical transmission moments before the transmission moment to construct the time window of the transmission moment.

5. An industrial Internet of Things device collaborative scheduling system based on edge computing according to claim 1, characterized in that, Calculating the volatility adjustment factor of the node at the transmission moment includes: ； is the volatilization adjustment factor of the th node at the i-th transmission moment, , , are respectively the maximum load, load variance, and maximum delay time in the time window of the th node at the i-th transmission moment, , , are respectively the maximum load, maximum load variance, and maximum delay time in the time window of all nodes at the i-th transmission moment, is the exponential function with base e.

6. The collaborative scheduling system for industrial Internet of Things devices based on edge computing according to claim 1, wherein Adjusting the preset reference volatility rate according to the volatility adjustment factor of the node at the transmission moment to obtain the initial volatility rate of the node at the transmission moment includes: ； is the initial volatilization rate of the th node at the i-th transmission moment, is the preset reference volatilization rate, is the volatilization adjustment factor of the th node at the i-th transmission moment.

7. An industrial Internet of Things device collaborative scheduling system based on edge computing according to claim 2, characterized in that, Using the target volatility speed of a node at a transmission moment to control path selection in the ant colony algorithm includes: Acquiring the next adjacent node of the node in the node transmission direction; taking the target volatility speed of the node at the transmission moment as the pheromone target volatility speed on the path between the node and its next adjacent node at the transmission moment; and calculating the path selection probability according to the pheromone target volatility speed on the path between the node and its next adjacent node at each transmission moment.

8. An industrial Internet of Things device collaborative scheduling system based on edge computing according to claim 7, characterized in that, Calculating the path selection probability according to the pheromone target volatility speed on the path between the node and its next adjacent node at each transmission moment includes: Substituting the target volatility speed of the node at the transmission moment into the iterative update formula to obtain the pheromone concentration on the path between the node and its next adjacent node at the transmission moment. Calculating the selection probability of the path between the node and its next adjacent node at the transmission moment according to the pheromone concentration on the path between the node and its next adjacent node at the transmission moment, the path length, the preset pheromone importance factor, and the heuristic information importance factor.

9. The collaborative scheduling system for industrial Internet of Things devices based on edge computing according to claim 1, wherein Using the target evaporation speed of nodes at the transmission moment in the ant colony algorithm to control path selection to achieve the collaborative scheduling of industrial Internet of Things devices, including: Setting the number of ants, each ant randomly selects a starting point, determines the next node of the ant according to the selection probability of the path between the node and its next adjacent node at each transmission moment. After the ant reaches the next node, update the pheromone concentration of the path between this node and the next node in the data flow transmission node graph to achieve the collaborative scheduling of industrial Internet of Things devices.

10. A collaborative scheduling system for industrial Internet of Things devices based on edge computing according to claim 9, characterized in that, After the collaborative scheduling of industrial Internet of Things devices is implemented, it further includes: Determining the maintenance method of the node according to the selection probability of the node.

Images