Solution for edge computing operation and maintenance alarm

Abstract

The invention discloses a solution for edge computing operation and maintenance alarm, and relates to the technical field of edge computing. Comprising the following steps: step 1, collecting all equipment information in an edge computing environment, including running states, performance indexes and fault records of equipment; 2, constructing a state model of the equipment according to the running state and the performance index of the equipment; 3, according to the state model of the equipment, constructing an alarm model of the equipment; 4, when the equipment gives an alarm, determining an alarm reason according to the alarm model of the equipment; step 5, taking corresponding measures for processing according to the reason of the alarm; and 6, performing deep learning and pattern recognition on the operation data of the equipment by applying an artificial neural network algorithm. By applying the artificial neural network and the reinforcement learning technology, the complex relation between the equipment state and the alarm can be automatically identified, and automatic detection and classification of the alarm are realized; the need of manual intervention is greatly reduced, and the operation and maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of edge computing technology, and in particular to a solution to edge computing operation and maintenance alarms. Background Art

[0002] Edge computing is one of the key solutions for processing large amounts of data, especially in application scenarios that require fast response and local data processing. Edge computing reduces dependence on central cloud servers by processing and analyzing data near the data source, reduces data transmission latency, and improves processing speed and system reliability. However, the decentralization and heterogeneity of the edge computing environment increase the complexity of system operation and maintenance, especially in terms of device monitoring and fault alarm processing. Since edge devices are usually deployed in resource-constrained environments, and the number of devices is large and the types are diverse, how to effectively monitor device status and handle alarms in a timely and accurate manner is one of the issues that need to be considered.

[0003] Traditional alarm processing methods often rely on predefined thresholds or simple rules, which are difficult to adapt to dynamically changing operating conditions and complex environmental factors. In addition, manually configuring and managing alarm rules for a large number of edge devices is not only inefficient but also prone to errors.

[0004] After searching, the application scheme of Chinese patent application No. 200810118702.4 discloses an operation and maintenance device, a network element device and an alarm reporting and processing method thereof, wherein the operation and maintenance device is used for alarm reporting and processing, and comprises: a storage module, which stores the linkage relationship between all alarms that may be generated by the network element device; an acquisition module, which acquires the original alarm generated during the operation of the network element device; an analysis module, which selects the first alarm and the second alarm from the original alarm according to the linkage relationship, any one of the first alarms is the main alarm of at least one of the original alarms, and is not the slave alarm of any of the original alarms, and any one of the second alarms is neither the main alarm of any of the original alarms nor the slave alarm of any of the original alarms; and a sending module, which sends the first alarm and the second alarm to the management station. The above patent has the following deficiencies: lack of intelligent self-adaptation and learning capabilities, and its analysis module is mainly based on a fixed linkage relationship, which may not accurately capture complex alarm patterns and abnormal behaviors. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a solution to edge computing operation and maintenance alarms.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A solution to edge computing operation and maintenance alarms, including:

[0008] Step 1: Collect all device information in the edge computing environment, including the device’s operating status, performance indicators, and fault records;

[0009] Step 2: Build a status model of the equipment based on the equipment's operating status and performance indicators;

[0010] Step 3: Build the device alarm model based on the device status model;

[0011] Step 4: When an alarm occurs on the device, determine the cause of the alarm based on the device's alarm model;

[0012] Step 5: Take appropriate measures to handle the alarm according to the cause;

[0013] Step 6: Apply artificial neural network algorithms to conduct deep learning and pattern recognition on the equipment’s operating data; automatically identify the complex relationship between equipment status and alarms by building a multi-layer perception network;

[0014] Step 7: Use the logistic regression algorithm to classify the alarms and determine whether a certain state of the device is an abnormal state;

[0015] Step 8: Optimize the alarm processing strategy based on the reinforcement learning algorithm. Through interaction with the edge computing environment, the reinforcement learning algorithm gradually learns and optimizes the behavior strategy for processing alarms to minimize the alarm processing time and maximize system stability.

[0016] Step 9: Use swarm intelligence algorithms to achieve self-organization and collaborative processing of alarm information; solve the distributed alarm processing problem in edge computing;

[0017] Step 10: Repeat the above steps until all alarms are processed.

[0018] Preferably: the step 1 specifically includes:

[0019] Step 1.1: Conduct real-time monitoring of equipment information to ensure the timeliness and accuracy of data collection;

[0020] Step 1.2: Use automated tools to extract key performance indicators from devices and applications.

[0021] Step 1.3: Store the collected data in a unified data management platform to facilitate subsequent analysis and processing;

[0022] The step 2 specifically includes:

[0023] Step 2.1: Preprocess the collected data, including cleaning, normalization and standardization;

[0024] Step 2.2: Use statistical analysis methods to reduce dimensionality and identify key influencing factors;

[0025] Step 2.3: Establish a state model and use mathematical modeling techniques to express device behavior.

[0026] Preferably: the step 3 specifically includes:

[0027] Step 3.1: Define various alarm types and their corresponding relationships with device status;

[0028] Step 3.2: Use threshold setting or pattern recognition techniques to identify state changes that require attention;

[0029] Step 3.3: Build an alarm model to map the operating status to the alarm level to trigger the corresponding alarm notification;

[0030] The step 4 specifically includes:

[0031] Step 4.1: Monitor alarm notifications in real time and start the alarm cause analysis process once an alarm signal is received;

[0032] Step 4.2: Query the current device status and historical data, and use the alarm model to reversely deduce the possible alarm causes;

[0033] Step 4.3: Based on the device characteristics and usage scenarios, further refine the alarm cause to assist in formulating targeted treatment measures.

[0034] Preferably: the step 5 specifically includes:

[0035] Step 5.1: Design a knowledge base for alarm processing, including preset processing strategies and experience summary;

[0036] Step 5.2: Match the solution or suggestion in the knowledge base according to the alarm cause;

[0037] Step 5.3: Automatically or manually execute the selected treatment measures and monitor the execution status and effectiveness.

[0038] Preferably: the step 6 specifically includes:

[0039] Step 6.1: Build a multi-layer perceptron network structure, and the input layer accepts multi-dimensional performance indicators;

[0040] Step 6.2: Train the network weights through the training set data to perform feature learning and pattern recognition;

[0041] Step 6.3: Use the validation set and test set to evaluate the model accuracy and adjust the network parameters to improve the prediction accuracy;

[0042] The input layer of the neural network receives multiple performance indicators of the device, the hidden layer processes these inputs through weighted and activated functions, and the output layer gives the current status of the device or predicts the type of alarm that may occur in the future. The specific formula is:

[0043]

[0044] in:

[0045] Q j is the output of neuron j;

[0046] w ij is the weight of input i to neuron j;

[0047] x i is the input signal;

[0048] θ j is the threshold of neuron j;

[0049] f is the activation function.

[0050] Preferably: the step 7 specifically includes:

[0051] Step 7.1: Prepare label data and mark normal operation and abnormal status;

[0052] Step 7.2: Based on the logistic regression model, learn the mapping relationship from features to alarm categories;

[0053] Step 7.3: Apply the model to classify and predict new data, and take response measures corresponding to different alarm levels according to the prediction results;

[0054] When judging whether a certain state of a device is abnormal, the result of the linear combination is mapped to the interval (0,1) through the sigmoid function and expressed as a probability value, so as to predict the probability of an alarm occurring in the device, specifically:

[0055]

[0056] in:

[0057] P(y=1│x) is the probability that the output is 1 given the input x;

[0058] σ is the sigmoid function;

[0059] w i is the weight;

[0060] c is the bias term.

[0061] Preferably: the step 8 specifically includes:

[0062] Step 8.1: Design the reinforcement learning problem framework, including state space, action space, reward function, and discount factor;

[0063] Step 8.2: Through continuous interactive learning, adjust the action selection strategy to maximize the cumulative reward;

[0064] Step 8.3: Implement the strategy, track its effectiveness, and make adjustments until the optimal solution is found.

[0065] Its state value function and action value function are expressed as follows:

[0066] Q(s,a)=E[R t+1 +r·V(s t+1 )|S t =s,A t =a]

[0067]

[0068] in:

[0069] Q(s,a) is the expected reward of taking action a from state s;

[0070] V(s) is the value of state s, the expected return of acting according to the optimal strategy in state s;

[0071] R t+1 It is the reward of the next moment;

[0072] r is the discount factor.

[0073] Preferably: the step 9 specifically includes:

[0074] Step 9.1: Initialize the ant colony algorithm parameters, including pheromone concentration, heuristic information and evaporation rate;

[0075] Step 9.2: Use the ant colony algorithm to distribute the alarm pheromone in the network and guide the allocation of alarm processing tasks;

[0076] Step 9.3: Dynamically update pheromone tracks, optimize the alarm processing process, and enhance the overall processing capability and robustness of the system.

[0077] Preferably: in step 9, based on the swarm intelligence algorithm, multiple simple individuals generate complex collective behaviors through local interactions, thereby solving the distributed alarm processing problem in edge computing; specifically:

[0078]

[0079] in:

[0080] r ij(t) represents the pheromone concentration on path (i, j) at time t;

[0081] n ij is the heuristic information, which is inversely proportional to the path length;

[0082] N i is the set of neighbors of position i;

[0083] a and β control the relative importance of pheromone and heuristic information, respectively.

[0084] Preferably: the step 10 specifically includes:

[0085] Step 10.1: Establish a feedback loop to regularly check system status and alarm handling results;

[0086] Step 10.2: Adjust the alarm model and response strategy based on the feedback to adapt to the changes in the environment;

[0087] Step 10.3: Maintain the system's ability to continuously learn and continuously improve the alarm detection and processing mechanism.

[0088] The beneficial effects of the present invention are:

[0089] 1. The present invention can automatically identify the complex relationship between equipment status and alarms by applying artificial neural networks and reinforcement learning technology, and realize automatic detection and classification of alarms; it greatly reduces the need for manual intervention and improves operation and maintenance efficiency.

[0090] 2. The present invention utilizes logistic regression and cluster intelligence algorithms to accurately classify and process alarms in real time, and to realize self-organization and collaborative processing of alarm information; the system can quickly respond to various alarms and reduce fault recovery time.

[0091] 3. The application of the reinforcement learning algorithm of the present invention enables the system to self-adjust and optimize the alarm processing strategy according to the changing environmental conditions, thereby improving the overall stability and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] Figure 1 This is a flow chart of a solution to edge computing operation and maintenance alarms proposed by the present invention. DETAILED DESCRIPTION

[0093] The technical solution of the present invention is further described in detail below in conjunction with specific implementation methods.

[0094] Embodiment 1:

[0095] A solution to edge computing operation and maintenance alarms, including:

[0096] Step 1: Collect all device information in the edge computing environment, including the device’s operating status, performance indicators, fault records, etc.

[0097] Step 2: Build a status model of the equipment based on the equipment's operating status and performance indicators;

[0098] Step 3: Build the device alarm model based on the device status model;

[0099] Step 4: When an alarm occurs on the device, determine the cause of the alarm based on the device's alarm model;

[0100] Step 5: Take appropriate measures to deal with the alarm according to the cause. For example, if the alarm is caused by the performance indicator of the device exceeding the threshold, the problem can be solved by adjusting the configuration parameters of the device.

[0101] Step 6: Apply artificial neural network algorithms to conduct deep learning and pattern recognition on the equipment’s operating data; automatically identify the complex relationship between equipment status and alarms by building a multi-layer perception network;

[0102] Step 7: Use the logistic regression algorithm to classify the alarms and determine whether a certain state of the device is an abnormal state;

[0103] Step 8: Use swarm intelligence algorithms to achieve self-organization and collaborative processing of alarm information; solve the distributed alarm processing problem in edge computing;

[0104] Step 9: Repeat the above steps until all alarms are processed.

[0105] Wherein, the step 1 specifically includes:

[0106] Step 1.1: Conduct real-time monitoring of equipment information to ensure the timeliness and accuracy of data collection;

[0107] Step 1.2: Use automated tools to extract key performance indicators from devices and applications, such as CPU usage, memory usage, network traffic, and response time.

[0108] Step 1.3: Store the collected data in a unified data management platform to facilitate subsequent analysis and processing.

[0109] Wherein, the step 2 specifically includes:

[0110] Step 2.1: Preprocess the collected data, including cleaning, normalization and standardization;

[0111] Step 2.2: Use statistical analysis methods, such as principal component analysis (PCA) or factor analysis, to reduce dimensionality and identify key influencing factors;

[0112] Step 2.3: Establish a state model and use mathematical modeling techniques such as regression analysis or state estimation algorithm to express the device behavior.

[0113] Wherein, the step 3 specifically includes:

[0114] Step 3.1: Define various alarm types and their corresponding relationships with device status;

[0115] Step 3.2: Use threshold setting or pattern recognition techniques to identify state changes that require attention;

[0116] Step 3.3: Build an alarm model to map the operating status to the alarm level to trigger the corresponding alarm notification.

[0117] Wherein, the step 4 specifically includes:

[0118] Step 4.1: Monitor alarm notifications in real time and start the alarm cause analysis process once an alarm signal is received;

[0119] Step 4.2: Query the current device status and historical data, and use the alarm model to reversely deduce the possible alarm causes;

[0120] Step 4.3: Based on the device characteristics and usage scenarios, further refine the alarm cause to assist in formulating targeted treatment measures.

[0121] Wherein, the step 5 specifically includes:

[0122] Step 5.1: Design a knowledge base for alarm processing, including preset processing strategies and experience summary;

[0123] Step 5.2: Match the solution or suggestion in the knowledge base according to the alarm cause;

[0124] Step 5.3: Automatically or manually execute the selected treatment measures and monitor the execution status and effectiveness.

[0125] Wherein, the step 6 specifically includes:

[0126] Step 6.1: Build a multi-layer perceptron (MLP) network structure, and the input layer accepts multi-dimensional performance indicators;

[0127] Step 6.2: Train the network weights through the training set data to perform feature learning and pattern recognition;

[0128] Step 6.3: Use the validation set and test set to evaluate the model accuracy and adjust the network parameters to improve the prediction accuracy;

[0129] The input layer of the neural network receives multiple performance indicators of the device, such as CPU usage, memory usage, and network traffic. The hidden layer processes these inputs through weighted and activated functions, and the output layer gives the current status of the device or predicts the type of alarm that may occur in the future. The specific formula is:

[0130]

[0131] in:

[0132] Q j is the output of neuron j;

[0133] w ij is the weight of input i to neuron j;

[0134] x i is the input signal;

[0135] θ j is the threshold of neuron j;

[0136] f is the activation function.

[0137] Wherein, the step 7 specifically includes:

[0138] Step 7.1: Prepare label data and mark normal operation and abnormal status;

[0139] Step 7.2: Based on the logistic regression model, learn the mapping relationship from features to alarm categories;

[0140] Step 7.3: Apply the model to classify and predict new data, and take response measures corresponding to different alarm levels according to the prediction results;

[0141] When judging whether a certain state of a device is abnormal, the result of the linear combination is mapped to the interval (0,1) through the sigmoid function and expressed as a probability value, so as to predict the probability of an alarm occurring in the device, specifically:

[0142]

[0143] in:

[0144] P(y=1│x) is the probability that the output is 1 given the input x;

[0145] σ is the sigmoid function;

[0146] w i is the weight;

[0147] c is the bias term.

[0148] Wherein, the step 8 specifically includes:

[0149] Step 8.1: Initialize the ant colony algorithm parameters, such as pheromone concentration, heuristic information, and evaporation rate;

[0150] Step 8.2: Use the ant colony algorithm to distribute the alarm pheromone in the network and guide the allocation of alarm processing tasks;

[0151] Step 8.3: Dynamically update pheromone tracks, optimize the alarm processing process, and enhance the overall processing capability and robustness of the system;

[0152] Based on the swarm intelligence algorithm, multiple simple individuals can generate complex collective behaviors through local interactions, thereby solving the distributed alarm processing problem in edge computing; specifically:

[0153]

[0154] in:

[0155] r ij (t) represents the pheromone concentration on path (i, j) at time t;

[0156] n ij is the heuristic information, which is inversely proportional to the path length;

[0157] N i is the set of neighbors of position i;

[0158] a and β control the relative importance of pheromone and heuristic information, respectively.

[0159] Wherein, the step 9 specifically includes:

[0160] Step 9.1: Establish a feedback loop to regularly check system status and alarm handling results;

[0161] Step 9.2: Adjust the alarm model and response strategy based on the feedback to adapt to the changes in the environment;

[0162] Step 9.3: Maintain the system's ability to continuously learn and continuously improve the alarm detection and processing mechanism.

[0163] Embodiment 2:

[0164] A solution to edge computing operation and maintenance alarms, including:

[0165] Step 1: Collect all device information in the edge computing environment, including the device’s operating status, performance indicators, fault records, etc.

[0166] Step 2: Build a status model of the equipment based on the equipment's operating status and performance indicators;

[0167] Step 3: Build the device alarm model based on the device status model;

[0168] Step 4: When an alarm occurs on the device, determine the cause of the alarm based on the device's alarm model;

[0169] Step 5: Take appropriate measures to deal with the alarm according to the cause. For example, if the alarm is caused by the performance indicator of the device exceeding the threshold, the problem can be solved by adjusting the configuration parameters of the device.

[0170] Step 6: Apply artificial neural network algorithms to conduct deep learning and pattern recognition on the equipment’s operating data; automatically identify the complex relationship between equipment status and alarms by building a multi-layer perception network;

[0171] Step 7: Use the logistic regression algorithm to classify the alarms and determine whether a certain state of the device is an abnormal state;

[0172] Step 8: Optimize the alarm processing strategy based on the reinforcement learning algorithm. Through interaction with the edge computing environment, the reinforcement learning algorithm gradually learns and optimizes the behavior strategy for processing alarms to minimize the alarm processing time and maximize system stability.

[0173] Step 9: Use swarm intelligence algorithms to achieve self-organization and collaborative processing of alarm information; solve the distributed alarm processing problem in edge computing;

[0174] Step 10: Repeat the above steps until all alarms are processed.

[0175] Wherein, the step 8 specifically includes:

[0176] Step 8.1: Design the reinforcement learning problem framework, including state space, action space, reward function, and discount factor;

[0177] Step 8.2: Through continuous interactive learning, adjust the action selection strategy to maximize the cumulative reward;

[0178] Step 8.3: Implement the strategy, track its effectiveness, and make adjustments until the optimal solution is found.

[0179] Its state value function and action value function are expressed as follows:

[0180] Q(s,a)=E[R t+1 +r·V(s t+1 )|S t =s,A t =a]

[0181]

[0182] in:

[0183] Q(s,a) is the expected reward of taking action a from state s;

[0184] V(s) is the value of state s, the expected return of acting according to the optimal strategy in state s;

[0185] R t+1 It is the reward of the next moment;

[0186] r is the discount factor.

[0187] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A solution to edge computing operation and maintenance alarms, characterized in that: include: Step 1: Collect all device information in the edge computing environment, including the device’s operating status, performance indicators, and fault records; Step 2: Build a status model of the equipment based on the equipment's operating status and performance indicators; Step 3: Build the device alarm model based on the device status model; Step 4: When an alarm occurs on the device, determine the cause of the alarm based on the device's alarm model; Step 5: Take appropriate measures to handle the alarm according to the cause; Step 6: Apply artificial neural network algorithms to conduct deep learning and pattern recognition on the equipment’s operating data; automatically identify the complex relationship between equipment status and alarms by building a multi-layer perception network; Step 7: Use the logistic regression algorithm to classify the alarms and determine whether a certain state of the device is an abnormal state; Step 8: Optimize the alarm processing strategy based on the reinforcement learning algorithm; By interacting with the edge computing environment, the reinforcement learning algorithm gradually learns and optimizes the behavioral strategy for handling alarms to minimize alarm processing time and maximize system stability; Step 9: Use swarm intelligence algorithms to achieve self-organization and collaborative processing of alarm information; Solve the distributed alarm processing problem in edge computing; Step 10: Repeat the above steps until all alarms are processed.

2. A solution to edge computing operation and maintenance alarm according to claim 1, characterized in that: The step 1 specifically includes: Step 1.1: Conduct real-time monitoring of equipment information to ensure the timeliness and accuracy of data collection; Step 1.2: Use automated tools to extract key performance indicators from devices and applications. Step 1.3: Store the collected data in a unified data management platform for subsequent analysis and processing; The step 2 specifically includes: Step 2.1: Preprocess the collected data, including cleaning, normalization and standardization; Step 2.2: Use statistical analysis methods to reduce dimensionality and identify key influencing factors; Step 2.3: Establish a state model and use mathematical modeling techniques to express device behavior.

3. A solution to edge computing operation and maintenance alarm according to claim 1, characterized in that: The step 3 specifically includes: Step 3.1: Define various alarm types and their corresponding relationships with device status; Step 3.2: Use threshold setting or pattern recognition techniques to identify state changes that require attention; Step 3.3: Build an alarm model to map the operating status to the alarm level to trigger the corresponding alarm notification; The step 4 specifically includes: Step 4.1: Monitor alarm notifications in real time and start the alarm cause analysis process once an alarm signal is received; Step 4.2: Query the current device status and historical data, and use the alarm model to reversely deduce the possible alarm causes; Step 4.3: Based on the device characteristics and usage scenarios, further refine the alarm cause to assist in developing targeted treatment measures.

4. A solution to edge computing operation and maintenance alarm according to claim 3, characterized in that: The step 5 specifically includes: Step 5.1: Design a knowledge base for alarm processing, including preset processing strategies and experience summary; Step 5.2: Match the solution or suggestion in the knowledge base according to the alarm cause; Step 5.3: Automatically or manually execute the selected treatment measures and monitor the execution status and effectiveness.

5. A solution to edge computing operation and maintenance alarm according to claim 1, characterized in that: The step 6 specifically includes: Step 6.1: Build a multi-layer perceptron network structure, and the input layer accepts multi-dimensional performance indicators; Step 6.2: Train the network weights through the training set data to perform feature learning and pattern recognition; Step 6.3: Use the validation set and test set to evaluate the model accuracy and adjust the network parameters to improve the prediction accuracy; The input layer of the neural network receives multiple performance indicators of the device, the hidden layer processes these inputs through weighted and activated functions, and the output layer gives the current status of the device or predicts the type of alarm that may occur in the future. The specific formula is: in: Q j is the output of neuron j; w ij is the weight of input i to neuron j; x i is the input signal; θ j is the threshold of neuron j; f is the activation function.

6. A solution to edge computing operation and maintenance alarm according to claim 1, characterized in that: The step 7 specifically includes: Step 7.1: Prepare label data and mark normal operation and abnormal status; Step 7.2: Based on the logistic regression model, learn the mapping relationship from features to alarm categories; Step 7.3: Apply the model to classify and predict new data, and take response measures corresponding to different alarm levels according to the prediction results; When judging whether a certain state of a device is abnormal, the result of the linear combination is mapped to the interval (0,1) through the sigmoid function and expressed as a probability value, so as to predict the probability of an alarm occurring in the device, specifically: in: P(y=1│x) is the probability that the output is 1 given the input x; σ is the sigmoid function; w i is the weight; c is the bias term.

7. A solution to edge computing operation and maintenance alarm according to claim 1, characterized in that: The step 8 specifically includes: Step 8.1: Design the reinforcement learning problem framework, including state space, action space, reward function, and discount factor; Step 8.2: Through continuous interactive learning, adjust the action selection strategy to maximize the cumulative reward; Step 8.3: Implement the strategy, track its effectiveness, and make adjustments until the optimal solution is found. Its state value function and action value function are expressed as follows: Q(s,a)=E[R t+1 +r·V(s t+1 )|S t =s,A t =a] in: Q(s,a) is the expected reward of taking action a from state s; V(s) is the value of state s, the expected return of acting according to the optimal strategy in state s; R t+1 It is the reward of the next moment; r is the discount factor.

8. A solution to edge computing operation and maintenance alarm according to claim 1, characterized in that: The step 9 specifically includes: Step 9.1: Initialize the ant colony algorithm parameters, including pheromone concentration, heuristic information and evaporation rate; Step 9.2: Use the ant colony algorithm to distribute the alarm pheromone in the network and guide the allocation of alarm processing tasks; Step 9.3: Dynamically update pheromone tracks, optimize the alarm processing process, and enhance the overall processing capability and robustness of the system.

9. A solution to edge computing operation and maintenance alarm according to claim 8, characterized in that: In step 9, based on the swarm intelligence algorithm, multiple simple individuals generate complex collective behaviors through local interactions, thereby solving the distributed alarm processing problem in edge computing; specifically: in: r ij (t) represents the pheromone concentration on path (i, j) at time t; n ij is the heuristic information, which is inversely proportional to the path length; N i is the set of neighbors of position i; a and β control the relative importance of pheromone and heuristic information, respectively.

10. A solution to edge computing operation and maintenance alarm according to claim 1, characterized in that: The step 10 specifically includes: Step 10.1: Establish a feedback loop to regularly check system status and alarm handling results; Step 10.2: Adjust the alarm model and response strategy based on the feedback to adapt to the changes in the environment; Step 10.3: Maintain the system's ability to continuously learn and continuously improve the alarm detection and processing mechanism.

Images