Power over ethernet switch, control method, device, storage medium and program product thereof

Abstract

The application discloses an Ethernet power supply switch and a control method, equipment, storage medium and program product thereof, relates to the technical field of intelligent switch management, and the Ethernet power supply switch comprises an Ethernet intelligent control module, an artificial intelligence management and control module and a sensing module. Since the multi-dimensional environment data and the service traffic data are acquired through the sensing module, active sensing of various types of service data is realized, the Ethernet power supply switch actively determines the service priority, and the terminal negotiation result is no longer relied on, thereby providing a basis for subsequent scheduling. The artificial intelligence management and control module generates a bandwidth allocation strategy and a power supply priority adjustment instruction according to the multi-dimensional data, realizes intelligent decision of resource scheduling, makes the power supply priority and the bandwidth allocation cooperate, guarantees the end-to-end quality of core services, can realize rapid response to emergencies, and avoids the problem of unbalanced bandwidth allocation during peak periods.

Description

Technical Field

[0001] This application relates to the field of intelligent switch management technology, and in particular to Power over Ethernet (PoE) switches and their control methods, devices, storage media and software products. Background Technology

[0002] Power over Ethernet (PoE) switches are network devices that transmit both data and power to external devices (such as IP cameras, wireless access points, and industrial sensors) via network cables. Due to their advantages such as simplified cabling, cost savings, flexibility, security, and centralized power supply, PoE switches have become increasingly popular in numerous fields.

[0003] Currently, traditional PoE switches mainly follow the IEEE 802.3af / at / bt standard to achieve basic power supply negotiation and rate adaptation. However, this method relies primarily on Auto-MDI / MDIX and physical layer handshakes between the two ends of the device for rate negotiation. This passive rate adaptation, dependent on terminal negotiation, is prone to bandwidth imbalance during peak periods. Summary of the Invention

[0004] The main purpose of this application is to provide a Power over Ethernet (PoE) switch and its control method, device, storage medium and program products, which aims to solve the technical problem that existing PoE switches have passive speed adaptation, rely on terminal negotiation, and are prone to bandwidth allocation imbalance during peak hours.

[0005] To achieve the above objectives, this application proposes a Power over Ethernet (PoE) switch, which includes: the PoE switch is connected to an external device, and the PoE switch includes: an Ethernet intelligent control module, an artificial intelligence management module, and a sensing module;

[0006] The sensing module is used to acquire multi-dimensional environmental data and the business traffic data of the external device, and send the multi-dimensional environmental data and the business traffic data to the artificial intelligence control module. The artificial intelligence management module is used to generate a bandwidth allocation strategy and a power supply priority adjustment instruction based on the multi-dimensional environmental data and the service traffic data, and send the bandwidth allocation strategy and the power supply priority adjustment instruction to the Ethernet intelligent control module. The Ethernet intelligent control module is used to allocate bandwidth to the external device according to the bandwidth allocation strategy, adjust the power supply priority of the external device according to the power supply priority adjustment instruction, and supply power to the external device according to the power supply priority.

[0007] In one embodiment, the artificial intelligence management module is further configured to determine the current service type of the external device based on the service traffic data; The AI ​​management module is also used to generate bandwidth allocation strategies and power supply priority adjustment instructions based on the current service type and the multi-dimensional environmental data.

[0008] In one embodiment, the Power over Ethernet switch further includes: a fault diagnosis and self-healing module; The fault diagnosis and self-healing module is used to perform preliminary matching of the multi-dimensional environmental data based on the rule base matching model to obtain preliminary identification results. The fault diagnosis and self-healing module is also used to generate a fault detection report based on the preliminary identification result when the preliminary identification result indicates that a fault exists.

[0009] In one embodiment, the fault diagnosis and self-healing module is further configured to identify the multi-dimensional environmental data based on a fault classification model to obtain the fault type and fault assessment value. The fault diagnosis and self-healing module is also used to classify the fault according to the fault type and the fault assessment value to obtain the fault level; The fault diagnosis and self-healing module is also used to repair faults based on the fault level.

[0010] In one embodiment, the fault diagnosis and self-healing module is further configured to acquire historical fault data and train a fault classification model using the historical fault data through a decision tree algorithm and a random forest fusion algorithm.

[0011] In one embodiment, the fault diagnosis and self-healing module is further configured to perform a restart operation on the external device corresponding to the fault when the fault level is the fault level corresponding to a minor fault. The fault diagnosis and self-healing module is also used to collaboratively repair the fault based on the Ethernet intelligent control module and the artificial intelligence management module when the fault level is the fault level corresponding to a general fault. The fault diagnosis and self-healing module is also used to handle faults through the core business keep-alive mechanism when the fault level is the fault level corresponding to a core fault.

[0012] Furthermore, to achieve the above objectives, this application also proposes a control method for a Power over Ethernet (PoE) switch. The method is applied to the PoE switch described above, which is connected to an external device. The PoE switch includes: an Ethernet intelligent control module, an artificial intelligence management module, and a sensing module; the method includes: The sensing module acquires multi-dimensional environmental data and the service traffic data of the external device, and sends the multi-dimensional environmental data and the service traffic data to the artificial intelligence management module; The artificial intelligence management module generates a bandwidth allocation strategy and a power supply priority adjustment instruction based on the multi-dimensional environmental data and the service traffic data, and sends the bandwidth allocation strategy and the power supply priority adjustment instruction to the Ethernet intelligent control module. The Ethernet intelligent control module allocates bandwidth to the external device according to the bandwidth allocation strategy, adjusts the power supply priority of the external device according to the power supply priority adjustment instruction, and supplies power to the external device according to the power supply priority.

[0013] In addition, to achieve the above objectives, this application also proposes a Power over Ethernet (PoE) switch device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the PoE switch as described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the Ethernet power supply switch as described above.

[0015] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the Power over Ethernet switch as described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This application discloses a Power over Ethernet (PoE) switch that connects to external devices. The PoE switch includes an Ethernet intelligent control module, an artificial intelligence (AI) management module, and a sensing module. The sensing module acquires multi-dimensional environmental data and service traffic data from external devices, and sends this data to the AI ​​management module. The AI ​​management module generates bandwidth allocation strategies and power priority adjustment instructions based on the multi-dimensional environmental data and service traffic data, and sends these to the Ethernet intelligent control module. The Ethernet intelligent control module allocates bandwidth to external devices according to the bandwidth allocation strategy, adjusts the power priority of external devices according to the power priority adjustment instructions, and supplies power to external devices according to their power priority. Because the sensing module acquires multi-dimensional environmental data and service traffic data, it achieves proactive sensing of various service data. The PoE switch proactively determines service priorities, no longer relying on terminal negotiation results, providing a basis for subsequent scheduling. The AI ​​management module generates bandwidth allocation strategies and power priority adjustment instructions based on multi-dimensional data, enabling intelligent decision-making in resource scheduling. This ensures coordinated power priority and bandwidth allocation, guaranteeing end-to-end quality of core services and enabling rapid response to emergencies, avoiding bandwidth imbalance during peak hours. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the Ethernet Power over Ethernet switch provided in this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the Ethernet Power over Ethernet switch provided in this application; Figure 3 This is a flowchart illustrating the Ethernet Power over Ethernet (PoE) switching method according to an embodiment of this application. Figure 4 This is a schematic diagram of the hardware operating environment of the Power over Ethernet (PoE) switch in this application embodiment.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] Based on this, this application provides a Power over Ethernet (PoE) switch, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the Ethernet Power over Ethernet switch provided in this application.

[0024] In this embodiment, the Power over Ethernet (PoE) switch is connected to an external device, and the PoE switch includes: an Ethernet intelligent control module, an artificial intelligence management and control module, and a sensing module.

[0025] It should be noted that the external devices connected to the Ethernet power switch in this application embodiment may include industrial control devices (such as industrial control hosts, industrial robot control units, automated production line sensor hubs, etc.), video surveillance devices (such as high-definition network cameras, video encoders, thermal imagers, etc.), network communication devices (such as wireless access points, VoIP phones, wireless bridges, etc.), IoT and sensor devices (such as environmental sensors, smart lighting controllers, access control card readers, smart meter data collectors, etc.), etc., and this application embodiment does not limit them.

[0026] In this embodiment of the application, the perception module is used to acquire multi-dimensional environmental data and the business traffic data of the external device, and send the multi-dimensional environmental data and the business traffic data to the artificial intelligence management module.

[0027] It should be noted that the aforementioned sensing module can be the "sensing organ" of the Power over Ethernet (PoE) switch, used to collect real-time data on the operating environment of external devices connected to the PoE switch, such as temperature data, humidity data, electromagnetic interference data, etc., thereby obtaining multi-dimensional environmental data.

[0028] In some embodiments of this application, the sensing module may further include a traffic monitoring unit, which can monitor the service traffic data transmitted between the Power over Ethernet switch and external devices.

[0029] For example, the service traffic data collected by the traffic monitoring unit in this application embodiment may include terminal attribute data (such as terminal type, manufacturer model, rated power, network interface type, etc.), traffic data (such as traffic bandwidth requirement value, data packet size, transmission protocol, etc.), time characteristic data (such as service start time, data transmission frequency, service transmission duration, etc.), and instruction data (such as service instruction type, etc.).

[0030] The artificial intelligence management module is used to generate bandwidth allocation strategies and power supply priority adjustment instructions based on the multi-dimensional environmental data and the service traffic data, and send the bandwidth allocation strategies and power supply priority adjustment instructions to the Ethernet intelligent control module.

[0031] It should be noted that the AI ​​management module in this embodiment can be used to realize functions such as service type identification, priority determination, and bandwidth and power supply policy generation for the Power over Ethernet (PoE) switch. Specifically, the AI ​​management module can parse service traffic data to identify the device types of different external devices connected to the PoE switch, as well as the service types of these external devices at that time. Then, based on the multi-dimensional environmental data of the external devices, device types, and service types, it generates bandwidth allocation policies and power supply priority adjustment instructions, enabling real-time adjustment of bandwidth and power supply policies in response to service peaks and sudden demands when service traffic data or environmental changes occur.

[0032] It is understandable that the aforementioned bandwidth allocation strategy can be a strategy that can be used to dynamically adjust the data transmission control parameters of each port of a Power over Ethernet (PoE) switch. Through the bandwidth allocation strategy, the transmission flow control between the PoE switch and various external devices can be achieved. The aforementioned power priority adjustment command is a command that can be used to dynamically adjust the power priority of each port of a PoE switch. Through the power priority adjustment command, the power distribution method of the PoE switch to various external devices can be dynamically adjusted.

[0033] In some embodiments of this application, the artificial intelligence management module is further configured to determine the current service type of the external device based on the service traffic data; the artificial intelligence management module is further configured to generate bandwidth allocation strategies and power supply priority adjustment instructions based on the current service type and the multi-dimensional environmental data.

[0034] It is understandable that the above-mentioned current business type can be used as a parameter or attribute to determine the type of business being performed by the external device.

[0035] For example, the service types corresponding to the external devices in this application embodiment may include: industrial control services, high-definition video services, Internet of Things data acquisition services, ordinary data services, voice communication services, wireless network access services, remote control services, alarm / event reporting services, etc., and this application embodiment does not limit them.

[0036] In this application embodiment, the method of generating bandwidth allocation strategy and power supply priority adjustment instructions based on the current service type and multi-dimensional environmental data can be based on rule matching model generation, or it can be implemented based on machine learning, neural network model, etc. This application embodiment does not limit this.

[0037] For example, different business types can have different business priorities. For instance, industrial control business has the highest priority and can be allocated bandwidth / power to ensure operation. IoT business has the lowest priority and can be allocated only the minimum bandwidth / power or not at all during peak hours.

[0038] The Ethernet intelligent control module is used to allocate bandwidth to the external device according to the bandwidth allocation strategy, adjust the power supply priority of the external device according to the power supply priority adjustment instruction, and supply power to the external device according to the power supply priority.

[0039] In some embodiments of this application, the artificial intelligence management module can use an integrated power balancing algorithm and an environment-adaptive power supply to dynamically allocate redundant power, stabilize output voltage, avoid power waste, and ensure power supply to core external devices (such as industrial control hosts, video surveillance core devices, etc.).

[0040] Understandably, this application aggregates power demand data collected from each port in real time, and uses this data to calculate the current total power consumption and remaining redundant power of the Ethernet power supply switch. It allocates bandwidth and power to each external device based on the service priority corresponding to the current service type, prioritizing the supply of rated power to core terminals (such as industrial control hosts, high-definition surveillance core cameras, etc.). It dynamically compresses the redundant power consumption of non-core terminals, allocates surplus power to high-demand ports, avoids power excess or deficiency on a single port, and maximizes the overall power utilization rate.

[0041] For example, when a high-definition video transmission service is identified, the power supply priority of the corresponding port is automatically increased to avoid video stuttering due to power fluctuations; when a low-priority IoT data collection service is identified, its non-core power supply redundancy is appropriately reduced in power-constrained scenarios to prioritize the protection of critical services.

[0042] This embodiment of the Power over Ethernet (PoE) switch connects to external devices. The PoE switch includes an Ethernet intelligent control module, an artificial intelligence (AI) management module, and a sensing module. The sensing module acquires multi-dimensional environmental data and service traffic data from external devices, and sends this data to the AI ​​management module. The AI ​​management module generates a bandwidth allocation strategy and a power supply priority adjustment command based on the multi-dimensional environmental data and service traffic data, and sends these commands to the Ethernet intelligent control module. The Ethernet intelligent control module allocates bandwidth to external devices according to the bandwidth allocation strategy, adjusts the power supply priority of external devices according to the power supply priority adjustment command, and supplies power to external devices according to the power supply priority. Because the sensing module acquires multi-dimensional environmental data and service traffic data, it achieves proactive sensing of various service data. The PoE switch proactively determines service priorities, no longer relying on terminal negotiation results, providing a basis for subsequent scheduling. The AI ​​management module generates a bandwidth allocation strategy and a power supply priority adjustment command based on multi-dimensional data, achieving intelligent decision-making for resource scheduling. This ensures coordinated power supply priority and bandwidth allocation, guaranteeing end-to-end quality of core services, and enabling rapid response to emergencies, avoiding bandwidth imbalance during peak hours.

[0043] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating Embodiment 2 of the Ethernet Power over Ethernet switch provided in this application.

[0044] like Figure 2 As shown in the embodiment of this application, the Ethernet power switch further includes a fault diagnosis and self-healing module.

[0045] It is understandable that a fault diagnosis and self-healing module is a functional module that can identify faults and locate the fault type and degree through preset rules or algorithms, thereby realizing self-healing or shutdown of the faulty part.

[0046] In this embodiment of the application, the fault diagnosis and self-healing module is used to perform preliminary matching of the multi-dimensional environmental data based on the rule base matching model to obtain preliminary identification results; the fault diagnosis and self-healing module is also used to generate a fault detection report based on the preliminary identification results when the preliminary identification results indicate the existence of a fault.

[0047] It should be noted that the aforementioned rule-based matching model can be a dataset composed of predefined fault feature rules, where each fault feature rule can consist of a fault type, its corresponding data feature threshold, rule identification number, etc. In this embodiment, the collected multi-dimensional environmental data can be compared with each data feature threshold in the rule-based matching model. When the monitoring data of a certain port simultaneously meets all the conditions of a certain rule, the matching of that rule is triggered, and it is determined that the external device corresponding to that port has a fault corresponding to that rule.

[0048] For example, the embodiments of this application can cover 20+ known faults (such as port disconnection, power overload, rate negotiation failure, power module failure, etc.) by pre-building a "fault feature-rule base", with each fault type corresponding to a clear data feature threshold.

[0049] For example, when a port collects "voltage < 44V (PoE standard lower limit) and current = 0A" three times in a row, it triggers the "port power supply disconnection" rule matching and initially determines that the port power supply line is faulty; when the switching core collects "a port packet loss rate > 5% and latency jitter > 100ms", it matches the "rate adaptation failure" rule and initially locates the rate scheduling abnormality.

[0050] It should be noted that, in order to achieve accurate fault identification and root cause location in this embodiment, a two-layer identification mechanism can be used to diagnose faults in the data corresponding to each port. The above preliminary identification results are the identification results obtained based on the rule base matching model of the preliminary identification. Through the rule base matching model, common faults can be quickly identified.

[0051] Furthermore, embodiments of this application can construct a fault classification model based on historical fault data to identify complex latent faults. Specifically, in embodiments of this application, the fault diagnosis and self-healing module is further used to identify the multi-dimensional environmental data based on the fault classification model to obtain fault types and fault assessment values; the fault diagnosis and self-healing module is further used to classify faults according to the fault types and fault assessment values ​​to obtain fault levels; the fault diagnosis and self-healing module is further used to perform fault repair based on the fault levels.

[0052] It should be noted that the embodiments of this application can be trained based on historical fault data to identify hidden faults not covered by the rule base matching model (such as intermittent power supply fluctuations caused by electromagnetic interference, bandwidth allocation imbalances caused by core chip aging, etc.). In application, the fault classification model of the embodiments of this application can receive multi-dimensional environmental data collected in real time, and through feature extraction (such as "when the electromagnetic interference intensity is >100dBμV / m, the port power fluctuation frequency is >5 times / minute"), output the probability of fault type (such as "92% probability of power supply instability caused by electromagnetic interference"), and locate the associated influencing modules (such as the environmental perception module failing to trigger the anti-interference mode in time).

[0053] It is understandable that the above-mentioned fault assessment value can be a parameter used to assess the severity of a fault. Based on the fault type and the fault assessment value, the fault can be classified into different levels, and then different fault handling methods can be adopted according to different fault levels.

[0054] It should be noted that the fault classification model in this embodiment can be constructed by training a decision tree algorithm and a random forest algorithm based on collected historical fault data. Specifically, the fault diagnosis and self-healing module is also used to acquire historical fault data and train the model using the historical fault data through the decision tree algorithm and the random forest algorithm to obtain the fault classification model. In particular, the fault diagnosis and self-healing module in this embodiment can randomly select some features (such as electromagnetic interference intensity features or end power fluctuation frequency features) from the historical fault data, calculate the information gain of each feature, and determine the optimal feature as the classification basis for the current node based on the information gain. Further, the selected features can be used as judgment conditions to divide the historical fault data into two subsets, such as classifying historical fault data with electromagnetic interference intensity features >100dBμV / m into the left subset and historical fault data with electromagnetic interference intensity features ≤100dBμV / m into the right subset.

[0055] Understandably, by repeatedly performing the step of determining the optimal feature based on information gain as the classification criterion for the current node in each subset, the system can be divided into several subsets, which together form a decision tree. The decision tree algorithm can quickly identify fault modes with clear feature thresholds and process multi-feature combination data, thus improving recognition accuracy.

[0056] It should be noted that the random forest fusion algorithm is an algorithm that can improve classification accuracy and robustness by constructing multiple decision trees and combining the voting results of these decision trees. Through sampling of these decision trees and random feature selection, differentiated training can be achieved, thereby enabling the fused model to identify latent features that do not have a clear single threshold and are not covered by the rule base.

[0057] In some embodiments of this application, when the diagnosis is completed, the fault diagnosis and self-healing module can automatically generate a structured fault detection report, which may include the detection results of the preliminary detection, the detection results of the further detection, etc., and specifically include: fault type (such as "PoE port power supply overload"), scope of impact (such as "ports 3-5, involving high-definition camera terminals"), root cause (such as "the actual power of the terminal connected to port 5 exceeds the configuration limit"), and fault level.

[0058] In some embodiments of this application, the Ethernet power supply switch includes industrial-grade protection components, specifically including electromagnetic shielding, 8KV surge protection, and a waterproof and dustproof structure. Its core function is to enhance the device's anti-interference and resistance to harsh environments, adapting it to complex scenarios.

[0059] In some embodiments of this application, the Power over Ethernet (PoE) switch may further include a dual-mode remote management module, which supports different access methods (such as 5G / Wi-Fi dual access). The dual-mode remote management module enables batch management and remote control of devices.

[0060] In some embodiments of this application, the fault diagnosis and self-healing module is further configured to restart the external device corresponding to the fault when the fault level is a minor fault; the fault diagnosis and self-healing module is further configured to collaboratively repair the fault based on the Ethernet intelligent control module and the artificial intelligence management module when the fault level is a general fault; the fault diagnosis and self-healing module is further configured to handle the fault through the core business keep-alive mechanism when the fault level is a core fault.

[0061] It should be noted that, in the embodiments of this application, faults can be classified into: fault level corresponding to minor faults, i.e., level 4 faults; fault level corresponding to general faults, i.e., level 3 faults; fault level corresponding to serious faults, i.e., level 2 faults; and fault level corresponding to core faults, i.e., level 1 faults.

[0062] In some embodiments of this application, for level 4 minor faults (such as single-port instantaneous rate negotiation failure or power supply fluctuations in low-priority terminals), a local rapid repair mechanism can be adopted without remote intervention. Specifically, when the fault level is level 4 and the affected external device is a non-core device (such as a common IoT sensor), different self-healing actions are selected according to the fault type of the affected external device. For example, in the case of a rate-related fault, the rate negotiation process of the corresponding port can be automatically restarted, forcibly triggering the AI ​​intelligent management module to reallocate the optimal rate (such as switching the original 100M negotiation failure port to a 10M / 100M adaptive mode); in the case of a power supply-related fault, a "soft restart" of the port power supply can be initiated (power is restored after a 0.5-second power outage), while adjusting the power supply voltage compensation value of the port (such as increasing it by 0.5V) to avoid fluctuations. Upon completion of the repair, the port status can be continuously monitored for 10 seconds. If the data returns to normal (such as successful rate negotiation and stable power supply parameters), the fault self-healing is marked as complete; if it fails, the fault is upgraded to level 3.

[0063] In some embodiments of this application, for Level 3 general faults (such as power outages on a single core port or local bandwidth imbalances), the Ethernet Power Supply intelligent control module and the artificial intelligence management module can be linked for collaborative repair. Specifically, when the fault level is Level 3 and the number of core terminals (such as industrial control sub-nodes) among the affected external devices does not exceed one, the impact type of the affected external devices can be considered. In the case of a power supply fault, the Ethernet Power Supply intelligent module can temporarily generate power supply priority adjustment instructions for each port using the above method, thereby temporarily adjusting the ports that may be faulty. In the case of a transmission fault, the artificial intelligence management module can temporarily increase the service priority of the corresponding port, thereby temporarily adjusting the bandwidth allocation strategy, such as increasing its bandwidth share from 10% to 20%, while suppressing the bandwidth occupation of low-priority services (such as file transfers).

[0064] Understandably, within a certain timeframe (e.g., 30 seconds) after a Level 3 general fault has been repaired, core indicators of the port (such as power supply stability and bandwidth utilization) can be monitored. If the fault returns to normal, power supply priority adjustment commands and bandwidth allocation strategies can be temporarily retained to prevent the fault from recurring within a certain period. If the repair fails, the fault can be escalated to a Level 2 fault.

[0065] In some embodiments of this application, for Level 2 severe faults (such as power outages at multiple core ports, single-path power module failures, or partial anomalies in the switching core), reconfiguration and repair can be achieved by linking redundant hardware resources and a dual-mode remote management module. Specifically, when the fault level is Level 2 and the affected external devices are multiple core devices (such as high-definition video surveillance systems or industrial control master nodes), different fault self-healing actions can be taken according to the fault type. For example, when the fault is a power module failure, it can automatically switch to the backup power supply and simultaneously shut down non-core ports (such as office terminal ports), concentrating all power to supply the core ports to ensure uninterrupted core services. As another example, when the fault is a partial anomaly in the switching core, the backup processing unit of the multi-rate switching core can be activated to switch the service traffic in the affected area to the backup path, while the rate allocation can be adjusted through the artificial intelligence management module (such as temporarily reducing the high-definition video service rate to 720P to reduce traffic pressure). For example, when the fault is a multi-port power supply fault, the power supply path switching function can be activated through the Ethernet power supply intelligent control module to connect the faulty port to the backup Ethernet power supply circuit. At the same time, the stability of the power supply voltage can be improved through the environmental adaptation power supply unit (such as increasing the voltage compensation value by 1V).

[0066] It should be noted that the operational status of the business (such as the high-definition video stuttering rate and the response latency of industrial control commands) can be continuously monitored for a period of time after the repair. If it returns to normal, a "self-healing completed" notification can be pushed to the AI ​​operation and maintenance platform; if it fails, the fault is upgraded to a level 1 fault.

[0067] In some embodiments of this application, for Level 1 core faults (such as simultaneous failure of two power modules, offline of the artificial intelligence management module, risk of power outage for the entire machine, etc.), since the local self-healing capability cannot resolve the core fault, it will affect the core business of the entire machine, and can trigger "alarm + remote collaboration". Specifically, the fault diagnosis and self-healing module can trigger the core business keep-alive mechanism, such as shutting down all non-core modules (except environmental perception module and dual-mode remote management module), and concentrating the remaining power consumption to supply the core control layer and core ports, delaying the business interruption time (ensuring at least 10 minutes of core business operation). At the same time, alarms can also be pushed to the artificial intelligence operation and maintenance platform through the dual-mode remote management module (prioritizing 5G to ensure stable communication). The alarms can include fault diagnosis reports, locally implemented protection measures, recommended repair solutions, etc., so that operation and maintenance personnel can conduct remote collaboration or cooperate with local personnel for on-site operation and maintenance.

[0068] The Ethernet power switch in this embodiment further includes a fault diagnosis and self-healing module. This module performs preliminary matching of multi-dimensional environmental data based on a rule-based matching model to obtain preliminary identification results. When the preliminary identification result indicates the presence of a fault, the module generates a fault detection report based on the preliminary identification result. Since preliminary matching is performed using a rule-based matching model with predefined fault characteristic thresholds, complex calculations are unnecessary, thus improving the response speed to common faults.

[0069] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the Ethernet power supply switch of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0070] This application also provides a method for using a Power over Ethernet switch; please refer to [reference needed]. Figure 3 , Figure 3 This is a flowchart illustrating a Power over Ethernet (PoE) switching method according to an embodiment of this application. The PoE switching method includes: Step S10: The perception module acquires multi-dimensional environmental data and the service traffic data of the external device, and sends the multi-dimensional environmental data and the service traffic data to the artificial intelligence management module; Step S20: The artificial intelligence management module generates a bandwidth allocation strategy and a power supply priority adjustment instruction based on the multi-dimensional environmental data and the service traffic data, and sends the bandwidth allocation strategy and the power supply priority adjustment instruction to the Ethernet intelligent control module. In step S30, the Ethernet intelligent control module allocates bandwidth to the external device according to the bandwidth allocation strategy, adjusts the power supply priority of the external device according to the power supply priority adjustment instruction, and supplies power to the external device according to the power supply priority.

[0071] The Ethernet Power over Ethernet (PoE) switching method provided in this application, applied to the PoE switch in the above embodiments, can solve the technical problem that existing PoE switches have passive rate adaptation, rely on terminal negotiation, and are prone to bandwidth allocation imbalance during peak hours. Compared with the prior art, the beneficial effects of the Ethernet Power over Ethernet (PoE) switching method provided in this application are the same as those of the Ethernet Power over Ethernet (PoE) switch provided in the above embodiments, and other technical features in the Ethernet Power over Ethernet (PoE) switching method are the same as those disclosed in the above embodiments, and will not be repeated here.

[0072] This application provides a Power over Ethernet (PoE) switch device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to execute the PoE switch in the above embodiment 1.

[0073] The following is for reference. Figure 4 The diagram illustrates a structural schematic of a Power over Ethernet (PoE) switch device suitable for implementing embodiments of this application. The PoE switch device in this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The illustrated Power over Ethernet (PoE) switch device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0074] like Figure 4As shown, the Power over Ethernet (PoE) switch device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the PoE switch device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tape, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the Power over Ethernet (PoE) switch to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows PoE switch devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0075] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0076] The Ethernet Power over Ethernet (PoE) switch device provided in this application, employing the PoE switch described in the above embodiments, can solve the technical problem of existing PoE switches having passive rate adaptation, relying on terminal negotiation, and easily experiencing bandwidth allocation imbalance during peak hours. Compared with the prior art, the beneficial effects of the Ethernet Power over Ethernet (PoE) switch device provided in this application are the same as those of the Ethernet Power over Ethernet (PoE) switch device provided in the above embodiments, and other technical features of this Ethernet Power over Ethernet (PoE) switch device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0077] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0078] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0079] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the Power over Ethernet switch in the above embodiments.

[0080] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0081] The aforementioned computer-readable storage medium may be included in a Power over Ethernet (PoE) switch device; or it may exist independently and not be assembled into a PoE switch device.

[0082] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a Power over Ethernet (PoE) switch device, cause the PoE switch device to: The sensing module acquires multi-dimensional environmental data and the service traffic data of the external device, and sends the multi-dimensional environmental data and the service traffic data to the artificial intelligence management module; The artificial intelligence management module generates a bandwidth allocation strategy and a power supply priority adjustment instruction based on the multi-dimensional environmental data and the service traffic data, and sends the bandwidth allocation strategy and the power supply priority adjustment instruction to the Ethernet intelligent control module. The Ethernet intelligent control module allocates bandwidth to the external device according to the bandwidth allocation strategy, adjusts the power supply priority of the external device according to the power supply priority adjustment instruction, and supplies power to the external device according to the power supply priority.

[0083] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0084] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0085] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0086] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the aforementioned Power over Ethernet (PoE) switch. This addresses the technical problem of existing PoE switches having passive rate adaptation, relying on terminal negotiation, and being prone to bandwidth allocation imbalances during peak hours. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the Power over Ethernet (PoE) switch provided in the above embodiments, and will not be elaborated upon here.

[0087] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the Power over Ethernet switch as described above.

[0088] The computer program product provided in this application can solve the technical problem of existing PoE switches having passive rate adaptation, relying on terminal negotiation, and being prone to bandwidth allocation imbalance during peak hours. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the Ethernet power supply switch provided in the above embodiments, and will not be repeated here.

[0089] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A Power over Ethernet (PoE) switch, characterized in that, The Power over Ethernet (PoE) switch is connected to external devices, and the PoE switch includes: an Ethernet intelligent control module, an artificial intelligence management module, and a sensing module; The sensing module is used to acquire multi-dimensional environmental data and the business traffic data of the external device, and send the multi-dimensional environmental data and the business traffic data to the artificial intelligence control module. The artificial intelligence management module is used to generate a bandwidth allocation strategy and a power supply priority adjustment instruction based on the multi-dimensional environmental data and the service traffic data, and send the bandwidth allocation strategy and the power supply priority adjustment instruction to the Ethernet intelligent control module. The Ethernet intelligent control module is used to allocate bandwidth to the external device according to the bandwidth allocation strategy, adjust the power supply priority of the external device according to the power supply priority adjustment instruction, and supply power to the external device according to the power supply priority.

2. The Ethernet power supply switch as described in claim 1, characterized in that, The artificial intelligence control module is also used to determine the current service type of the external device based on the service traffic data; The AI ​​management module is also used to generate bandwidth allocation strategies and power supply priority adjustment instructions based on the current service type and the multi-dimensional environmental data.

3. The Ethernet power supply switch as described in claim 1, characterized in that, The Power over Ethernet switch also includes: a fault diagnosis and self-healing module; The fault diagnosis and self-healing module is used to perform preliminary matching of the multi-dimensional environmental data based on the rule base matching model to obtain preliminary identification results. The fault diagnosis and self-healing module is also used to generate a fault detection report based on the preliminary identification result when the preliminary identification result indicates that a fault exists.

4. The Ethernet power supply switch as described in claim 3, characterized in that, The fault diagnosis and self-healing module is also used to identify the multi-dimensional environmental data based on the fault classification model to obtain the fault type and fault assessment value. The fault diagnosis and self-healing module is also used to classify the fault according to the fault type and the fault assessment value to obtain the fault level; The fault diagnosis and self-healing module is also used to repair faults based on the fault level.

5. The Power over Ethernet switch as described in claim 4, characterized in that, The fault diagnosis and self-healing module is also used to acquire historical fault data and train a fault classification model using the historical fault data through a decision tree algorithm and a random forest fusion algorithm.

6. The Power over Ethernet switch as described in claim 4, characterized in that, The fault diagnosis and self-healing module is also used to restart the external device corresponding to the fault when the fault level is the fault level corresponding to a minor fault. The fault diagnosis and self-healing module is also used to collaboratively repair the fault based on the Ethernet intelligent control module and the artificial intelligence management module when the fault level is the fault level corresponding to a general fault. The fault diagnosis and self-healing module is also used to handle faults through the core business keep-alive mechanism when the fault level is the fault level corresponding to the core fault.

7. A control method for a Power over Ethernet (PoE) switch, characterized in that, The method is applied to a Power over Ethernet (PoE) switch as described in any one of claims 1-6, wherein the PoE switch is connected to an external device, and the PoE switch includes: an Ethernet intelligent control module, an artificial intelligence management module, and a sensing module; the method includes: The sensing module acquires multi-dimensional environmental data and the service traffic data of the external device, and sends the multi-dimensional environmental data and the service traffic data to the artificial intelligence management module; The artificial intelligence management module generates a bandwidth allocation strategy and a power supply priority adjustment instruction based on the multi-dimensional environmental data and the service traffic data, and sends the bandwidth allocation strategy and the power supply priority adjustment instruction to the Ethernet intelligent control module. The Ethernet intelligent control module allocates bandwidth to the external device according to the bandwidth allocation strategy, adjusts the power supply priority of the external device according to the power supply priority adjustment instruction, and supplies power to the external device according to the power supply priority.

8. A control device for a Power over Ethernet (PoE) switch, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the control method for a Power over Ethernet switch as described in claim 7.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the control method for a Power over Ethernet switch as described in claim 7.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the control method for a Power over Ethernet switch as described in claim 7.

Images