Fault prevention method and device for power internet of things, and storage medium

Abstract

The invention discloses a power Internet of Things fault prevention method and device and a storage medium, and the method comprises the steps: collecting the system state, system operation data and historical fault data of the power Internet of Things; inputting the system operation data and the historical fault data into a preset fault detection model to predict a fault event and a fault part when the electric power Internet of Things has a potential fault in the future, generating a preventive strategy report according to the fault event and the fault part, and optimizing the preventive strategy report according to the system state, the fault event and the fault part. And executing a repair operation according to the fault-tolerant strategy to obtain a repair result, if the repair result is repair failure, starting a standby system for the fault part, and optimizing the fault-tolerant strategy according to the repair result. According to the embodiment of the invention, the system operation data and the historical fault data are monitored and analyzed in real time through the electric power Internet of Things acquisition system, so that potential faults can be accurately predicted, a more comprehensive fault-tolerant strategy can be generated, and the accuracy of fault prediction is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of electric power technology, and in particular to a method, device and storage medium for preventing faults in an electric power Internet of Things. Background Art

[0002] With the continuous expansion of power system scale and the increase of complexity, modern power system is gradually moving towards intelligent development. The introduction of Internet of Things technology makes the monitoring, management and operation of power system more refined and real-time.

[0003] Traditional fault detection methods mainly rely on manual inspections, regular maintenance, basic monitoring instruments, historical data analysis, and user feedback. These methods are inefficient, rely on manual experience, have long fault response times, low fault prediction accuracy, and are prone to missed or delayed fault detection. Summary of the invention

[0004] The present invention provides a method, device and storage medium for preventing faults in an electric power Internet of Things, so as to improve the accuracy of fault prediction.

[0005] In a first aspect, an embodiment of the present invention provides a method for preventing faults in an electric power Internet of Things, comprising:

[0006] Collect system status, system operation data and historical fault data of the power Internet of Things;

[0007] Input the system operation data and the historical fault data into a preset fault detection model to predict the fault events and fault locations of the power Internet of Things when a potential fault occurs in the future;

[0008] Generate a preventive strategy report based on the fault event and the fault location;

[0009] Optimizing the preventive strategy report according to the system state, the fault event, and the fault location to generate a fault-tolerant strategy;

[0010] Performing a repair operation according to the fault-tolerant strategy to obtain a repair result;

[0011] If the repair result is a repair failure, activating a backup system for the faulty part;

[0012] The fault-tolerance strategy is optimized according to the repair result.

[0013] In a second aspect, an embodiment of the present invention further provides a device for preventing faults in an electric power Internet of Things, comprising:

[0014] Data acquisition module, used to collect system status, system operation data and historical fault data of the power Internet of Things;

[0015] A fault prediction module, used for inputting the system operation data and the historical fault data into a preset fault detection model to predict the fault events and fault locations of the electric power Internet of Things when a potential fault occurs in the future;

[0016] A preventive strategy report generating module, used for generating a preventive strategy report according to the fault event and the fault location;

[0017] A fault-tolerant strategy generation module, configured to optimize the preventive strategy report according to the system state, the fault event, and the fault location to generate a fault-tolerant strategy;

[0018] A repair result acquisition module, used to perform a repair operation according to the fault-tolerant strategy to obtain a repair result;

[0019] A backup system startup module, used for activating a backup system for the faulty part if the repair result is a repair failure;

[0020] A fault-tolerant strategy optimization module is used to optimize the fault-tolerant strategy according to the repair result.

[0021] In a third aspect, an embodiment of the present invention further provides a computer device, including:

[0022] one or more processors;

[0023] A storage device for storing one or more programs;

[0024] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for preventing faults in the electric power Internet of Things as provided in the first aspect of the present invention.

[0025] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for preventing faults in the electric power Internet of Things as provided in the first aspect of the present invention.

[0026] In a fifth aspect, an embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the method for preventing faults in the electric power Internet of Things as provided in the first aspect of the present invention.

[0027] In the embodiment of the present invention, the system status, system operation data and historical fault data of the power Internet of Things are collected, and the system operation data and historical fault data are input into a preset fault detection model to predict the fault events and fault locations of the power Internet of Things when potential faults occur in the future. A preventive strategy report is generated based on the fault events and fault locations. The preventive strategy report is optimized based on the system status, fault events and fault locations to generate a fault-tolerant strategy. A repair operation is performed based on the fault-tolerant strategy to obtain a repair result. If the repair result is a repair failure, a backup system is enabled for the fault location, and the fault-tolerant strategy is optimized based on the repair result. This embodiment can accurately predict potential faults and generate targeted preventive strategies through real-time monitoring and analysis of system operation data and historical fault data by the power Internet of Things collection system, and dynamically generate a more comprehensive fault-tolerant strategy from the preventive strategy, thereby enhancing the reliability and stability of the system and improving the accuracy of fault prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A flowchart of a method for preventing faults in an electric power Internet of Things provided in Embodiment 1 of the present invention;

[0029] Figure 2 A structural block diagram of a device for preventing faults in the power Internet of Things provided in Embodiment 2 of the present invention;

[0030] Figure 3 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can cover sequential implementations other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1

[0034] See also Figure 1 , shows a flow chart of a method for preventing faults in the electric power Internet of Things provided by the first embodiment of the present invention. The method can be executed by a device for preventing faults in the electric power Internet of Things. The device for preventing faults in the electric power Internet of Things can be implemented in the form of hardware and / or software. The device for preventing faults in the electric power Internet of Things can be configured in a computer device. Figure 1 As shown, the method includes:

[0035] Step 101: Collect system status, system operation data and historical fault data of the power Internet of Things.

[0036] The power Internet of Things is the application of Internet of Things technology to the power system, which realizes intelligent monitoring, management and optimization of power equipment and networks through sensors, communication networks and data analysis. This system can improve the efficiency, reliability and safety of electricity, and realize functions such as smart grid, real-time data monitoring and fault warning.

[0037] System status refers to the current operating status of the power Internet of Things system, including real-time information such as the working status of the equipment, load conditions, communication connections, and energy consumption.

[0038] System operation data refers to the real-time collection of system operation data through sensors and monitoring equipment, including current, voltage, temperature, load and other parameters.

[0039] Historical fault data refers to the records of faults that occurred in the past, including fault type, occurrence time, impact scope and repair status, etc., which are used to analyze the causes of faults, optimize maintenance strategies and improve system reliability.

[0040] In this embodiment, by comprehensively analyzing the power Internet of Things acquisition system status, system operation data and historical fault data, real-time monitoring and fault diagnosis are achieved, system performance is optimized, predictive maintenance is supported, and a basis for management decisions is provided, thereby improving the safety and reliability of the system.

[0041] Step 102: Input the system operation data and historical fault data into a preset fault detection model to predict the fault events and fault locations of potential future faults in the power Internet of Things.

[0042] The fault detection model is a system that identifies potential faults by analyzing system operation data and historical fault data. It uses machine learning, statistical methods or signal processing technology to model the characteristics of normal and abnormal states. It can monitor equipment status in real time and predict potential future faults, thereby improving equipment reliability, reducing downtime, and optimizing maintenance strategies.

[0043] In this embodiment, the system operation data and historical fault data are input into a preset and trained fault detection model to predict possible faults in the power Internet of Things. By analyzing the system operation data and historical fault data, the fault detection model can identify potential problems, thereby realizing pre-fabricated protection strategies and effective maintenance.

[0044] Faults include fault events and fault locations. Fault events refer to specific abnormal conditions that occur during the operation of a system or device, causing it to malfunction or degrade in performance. These fault events may include equipment downtime, performance degradation, or the generation of error signals.

[0045] The fault location refers to the specific location or component where the fault occurs. In the power Internet of Things, the fault location can be electrical equipment, sensors, communication modules and other components.

[0046] In one embodiment of the present invention, step 102 may include the following steps:

[0047] Step 1021: Load a preset fault detection model.

[0048] In this embodiment, the fault prediction model adopts a long short-term memory network (LSTM), including a first long short-term memory network, a second long short-term memory network, a first fully connected layer and a second fully connected layer. The first long short-term memory network and the second long short-term memory network both belong to the long short-term memory network (LSTM).

[0049] Long Short-Term Memory (LSTM) is a special type of recurrent neural network (RNN) designed to process and predict sequence data. LSTM overcomes the gradient vanishing and exploding problems faced by traditional RNNs when processing long sequences by introducing memory cells and gating mechanisms (input gate, forget gate, and output gate) to effectively manage information flow. This enables LSTM to learn long-term dependencies.

[0050] In this embodiment, a preset and trained fault detection model is loaded in the power Internet of Things to analyze the system operation data and historical fault data input into the fault detection model, and the potential fault risks in the power Internet of Things are predicted based on the analysis of the system operation data and historical fault data by the fault detection model.

[0051] Step 1022: perform preprocessing operations on the system operation data and historical fault data to obtain target sequence data.

[0052] In this embodiment, corresponding preprocessing operations may be performed on the system operation data and the historical fault data respectively to improve the quality of the system operation data and the historical fault data, and the preprocessed system operation data and the historical fault data may be combined into target sequence data.

[0053] Exemplarily, the preprocessing of the system operation data may include at least one of the following:

[0054] 1. Data standardization

[0055] The system operation data is standardized to eliminate the scale differences between different data features.

[0056] 2. Time window division

[0057] The LSTM model is good at processing sequence data and can divide the system operation data into multiple time series according to time windows. The length of the time window can be selected according to the time characteristics of the fault and the sampling frequency of the data.

[0058] 3. Filling missing values

[0059] If there is missing data in the system operation data, it can be processed by forward filling, backward filling or interpolation methods to ensure the continuity of the system operation data.

[0060] In this embodiment, the system operation data and historical fault data are preprocessed to remove noise, fill missing values ​​and standardize data formats, thereby generating target sequence data. The target sequence data is an optimized data set that can more accurately reflect the system status and fault characteristics, provide high-quality input for subsequent fault detection models, and ensure the prediction accuracy and reliability of the model.

[0061] Step 1023: Input the target sequence data into the first long short-term memory network to extract the first time series feature.

[0062] In this embodiment, the preprocessed target sequence data is input into the first long short-term memory network, which includes 64 neurons and is configured with return_sequences = True. The time series characteristics of the preprocessed target sequence data are analyzed to extract the first time series characteristics that can describe the time-varying pattern of the target sequence data. These first time series characteristics will be used for subsequent second long short-term memory network processing to help identify potential fault events and fault locations.

[0063] Step 1024: Input the first time series feature into the second long short-term memory network to extract the second time series feature.

[0064] In this embodiment, the first time series feature is input into the second long short-term memory network, which includes 32 neurons and is configured with return_sequences = False to further extract more complex time dependencies. This step enables the second long short-term memory network to capture higher-order dynamic changes in the first time series feature, which helps to improve the sensitivity and accuracy of fault detection.

[0065] Step 1025 inputs the second time series feature into the first fully connected layer and maps it into the first fault feature.

[0066] In this embodiment, the second time series features are input into the first fully connected layer, which uses 128 nodes for linear transformation and feature extraction. This process converts the second time series features into first fault features, which contain information about the system operation status and provide a basis for subsequent probability prediction.

[0067] Step 1026: Activate the first fault feature to predict the first probability of each fault location when a potential fault occurs in the power Internet of Things in the future.

[0068] In this embodiment, after obtaining the first fault feature, an activation function (such as ReLU (rectified linear unit)) is used to activate the first fault feature, and the first probability of each fault location when a potential fault occurs in the power Internet of Things in the future is output, and the shape is (batch_size, num_locations), where num_locations is the number of fault locations, and batch_size is the number of data samples contained in each batch.

[0069] Step 1027: input the second time series feature into the second fully connected layer and map it into a second fault feature.

[0070] In this embodiment, the second time series feature is input into the second fully connected layer, which uses 64 nodes to perform linear transformation and feature extraction to obtain the second fault feature. The second fault feature is different from the first fault feature. The first fault feature usually extracts basic information related to a specific fault event and fault location, while the second fault feature may focus on more complex fault events and fault locations or different types of fault events and fault locations. This multi-feature extraction strategy can comprehensively capture different fault events and fault locations.

[0071] Step 1028: Activate the second fault feature to predict the second probability of each fault event when a potential fault occurs in the electric power Internet of Things in the future.

[0072] In this embodiment, after obtaining the second fault feature, an activation function (such as ReLU) is used to activate the second fault feature, and the second probability of each fault event when a potential fault occurs in the power Internet of Things in the future is output, and the shape is (batch_size, num_event_types), where num_event_types is the number of fault events, and batch_size is the number of data samples contained in each batch.

[0073] In this embodiment, the fault detection model is trained before being applied.

[0074] Specifically, the total loss function is used to train the fault detection model, and the back propagation algorithm is used to update the fault detection model with the loss value calculated by the total loss function. When the training of the fault detection model meets the preset conditions, the training of the fault detection model is determined to be completed, and the trained fault detection model is preset in the power Internet of Things to predict potential fault events and fault locations in the future.

[0075] Among them, the total loss function is expressed as:

[0076]

[0077] Fault Tolerance Loss=γ·(1-η);

[0078] Final Loss=α×Location Loss+β×Event Loss+Fault Tolerance Loss;

[0079] Among them, Final Loss is the total loss function, Location Loss is the location loss function, Event Loss is the event loss function, Fault Tolerance Loss is the fault tolerance loss function, and w i is the part weight of the i-th fault part, y location,i represents the i-th real fault location, represents the first probability of predicting the i-th fault location, t j represents the actual time to handle the jth fault event, T represents the time scale, and y event,j represents the jth real fault event, represents the second probability of predicting the jth fault event, γ is the fault tolerance loss coefficient, η represents the success rate of executing the fault tolerance strategy, α and β represent adjustment coefficients, i∈num_locations, num_locations is the number of fault locations, j∈num_event_types, num_event_types is the number of fault events.

[0080] In this embodiment, the fault location loss function assigns location weights to different fault locations, so that the fault detection model can perform differentiated prediction optimization according to the importance of each location in the power system; the introduction of location weights can make the fault detection model pay more attention to key fault locations, improve the accuracy and reliability of the prediction, and reduce system collapse or major economic losses caused by incorrect prediction of key locations.

[0081] The event loss function emphasizes the importance of timely handling of fault events by introducing an exponential function (exp); the exponential function (exp) is adjusted according to the actual time of handling the fault event, and the penalty for timely handling of faults is smaller, while the penalty for delayed handling is larger. This design can effectively encourage the fault detection model to prioritize the prediction and handling of fault events that may cause greater consequences during the optimization process, thereby enhancing the safety and stability of the system.

[0082] The fault-tolerant loss function uses the execution success rate of the fault-tolerant strategy as the main measurement criterion; by setting the fault-tolerant loss coefficient, the fault-tolerant loss function can dynamically adjust the focus on fault-tolerant processing during the optimization process of the fault detection model; the higher the success rate, the smaller the loss, which prompts the fault detection model to generate more effective fault-tolerant strategies to ensure that the system can recover quickly and operate stably when a fault occurs.

[0083] In this embodiment, the total loss function organically combines the fault location loss, fault event loss and fault tolerance strategy loss, and weighs the impact of different losses by adjusting the weight coefficients (α, β). This comprehensive total loss function design enables the fault detection model to take into account prediction accuracy, event response speed and fault tolerance processing effect in the multi-objective optimization process, thereby comprehensively improving the fault management capability of the power system.

[0084] Step 103: Generate a preventive strategy report based on the fault event and the fault location.

[0085] In this embodiment, the fault events and fault locations predicted by the fault detection model are used to generate a preventive strategy report. The fault events can provide the preventive strategy report with the events of the fault, help identify the risk areas and their distribution probabilities, and reveal potential causes. The fault locations can provide detailed information on key components or systems, so that preventive measures can be targeted and focused on vulnerable links, thereby improving the effectiveness and pertinence of the strategy.

[0086] Specifically, a first fault threshold is set. If the first probability is greater than or equal to the preset first fault threshold, the fault part is determined to be a candidate part. Each fault part is assigned a part weight so as to screen out multiple candidate parts with the highest weight as the target part. A second fault threshold is set. If the second probability is greater than or equal to the preset second fault threshold, the fault event is determined to be a target event, and the loss information caused by the target part and the target event in the power Internet of Things is calculated. The loss information includes economic losses, downtime, etc. A preventive strategy report is formulated based on the loss information.

[0087] Exemplarily, the results of fault location prediction and fault event prediction are obtained from the fault detection model. Specifically, the fault location prediction of each time step is obtained from the first fully connected layer, and the fault event prediction probability distribution of each time step is obtained from the second fully connected layer. These fault location prediction and fault event prediction results include the fault locations and fault events that may occur in the system in a certain time period in the future.

[0088] The first fault threshold and the second fault threshold are set, for example, 0.7 or 0.8, to screen high-probability fault parts and fault events. If the probability of the predicted result exceeds the set first fault threshold and the second fault threshold, it is considered that the fault has a high probability of occurrence and should be paid attention to.

[0089] According to the set first fault threshold and second fault threshold, the most likely fault parts and fault events are screened out from the prediction results. Combined with the weights of different fault parts in actual applications (such as the weights set in Location Loss), the fault prediction results of key parts are focused.

[0090] Conduct impact analysis on the potential fault locations and fault events that have been screened out, and evaluate the impact of these fault locations and fault events on the overall operation of the system. Based on the prediction results and impact analysis of the fault locations and fault events, design a preventive strategy report for each potential fault location and fault event, including but not limited to the following:

[0091] 1. Preventive maintenance plan: formulate preventive maintenance measures for predicted medium and high risk failure parts, and arrange regular inspections and repairs.

[0092] 2. Backup plan: Prepare backup resources or systems in advance for possible critical failures so that they can be quickly switched when a failure occurs to minimize the impact.

[0093] 3. Fault warning: Generate warning notifications based on the fault location and predicted time and possibility of the fault event to remind operation and maintenance personnel to pay attention to the system operation status in advance.

[0094] 4. System adjustment suggestions: If it is predicted that certain parts will have high risks for a long time, it can be recommended to adjust or upgrade the system architecture to reduce the probability of future failures.

[0095] The generated report template includes summary: an overview of the prediction results of the fault detection model, describing potential fault locations and fault events; fault prediction results: a detailed list of each prediction result, including fault location, fault event type, probability of occurrence, time window and other information; preventive strategy report: for each high-risk fault, detailed description of preventive measures, including maintenance plans, backup plans, early warning notifications, etc.; appendix: contains detailed prediction data, analysis methods, and any relevant technical details.

[0096] Generating automated reports involves writing scripts or programs to automatically generate preventive strategy reports based on the above steps. Preventive strategy reports can be generated periodically when the system is running, or they can be generated in real time based on the needs of the operation and maintenance personnel.

[0097] After the report is generated, the effectiveness of the preventive strategy report is verified regularly, and the fault detection model and preventive strategy report are updated based on the system's real-time operation data and new fault data.

[0098] Step 104: Optimize the preventive strategy report based on the system status, fault events, and fault locations to generate a fault-tolerant strategy.

[0099] In this embodiment, the system status provides the health of the current operating environment, the fault events reveal potential risks and problems, and the fault location indicates the weak links of the location. By integrating this information, a more targeted and effective fault tolerance strategy can be formulated, thereby improving the reliability of the system, reducing the probability of faults, and ensuring smooth operation.

[0100] In one embodiment of the present invention, step 104 may include the following steps:

[0101] Step 1041: Calculate the risk level when a fault occurs in the power Internet of Things according to the system status, fault event, and fault location.

[0102] In this embodiment, when a system failure occurs, the calculation of the risk level can help quickly identify the severity and potential impact of the failure. By analyzing the system status, fault events and fault locations, the risk level is calculated when a fault occurs in the power Internet of Things, and the nature and scope of the fault events and fault locations are understood. This multi-dimensional data analysis can provide more reliable information than a single data source, ensuring that the response measures are based on a comprehensive and in-depth understanding.

[0103] The risk levels are:

[0104] R i =P i ×I i ×S i ;

[0105]

[0106] Where: R i Indicates the risk level of the failure, P i is the average value between the first probability of the fault location and the second probability of the fault event, I i Indicates the impact of the fault on the power Internet of Things, S i Indicates the sensitivity of the system state, L i is the load level of the power Internet of Things, L max is the maximum load capacity of the power Internet of Things, O norm is the standard operating status value of the power Internet of Things, O i is the real-time operating status value of the power Internet of Things in the system state, M i is the redundancy of the power Internet of Things, M max is the maximum redundancy of the power Internet of Things, and α, β, and γ are adjustment coefficients.

[0107] Step 1042: Generate an objective function and constraints for the preventive strategy report based on the risk level.

[0108] In this embodiment, the risk level reflects the possibility of failure and affects the priority of resource allocation. By converting the risk level into an objective function, the optimization direction can be clarified, while the constraints can formulate a feasible preventive strategy report under limited resources.

[0109] Exemplarily, the objective function is:

[0110]

[0111] Where: C is the objective function, Minimize is the goal of optimizing the objective function to minimize the output value of the objective function, T i is the fault-tolerant time consumed by the power Internet of Things to perform the i-th fault-tolerant operation, D i is the delay event of the power Internet of Things switching to the backup resource, and λ represents the weight coefficient.

[0112] Exemplarily, the constraint condition includes at least one of: a time constraint condition, a resource constraint condition, and an operation order constraint condition.

[0113] Among them, the time constraint condition means that the fault tolerance time is less than or equal to the maximum time for handling faults in the power Internet of Things;

[0114] The resource constraint condition indicates that the amount of resources consumed in executing the fault-tolerant operation is less than or equal to the amount of resources available in the power Internet of Things;

[0115] The operation order constraint condition indicates that the execution order between multiple fault-tolerant operations conforms to the preset standard order.

[0116] Step 1043, with the optimization of the objective function as the goal, under the constraints of the constraints, the preventive strategy report is revised into a fault-tolerant strategy.

[0117] In this embodiment, by optimizing the defined objective function, these preventive strategy reports are not only theoretical, but also play a role in actual operation. The core of the optimization process is to use the calculated risk level and constraints to adjust the preventive strategy report and improve it into a fault-tolerant strategy. The risk level helps identify high-risk failures, thereby adjusting the preventive strategy report to ensure that resources are prioritized. The objective function is used to measure and optimize the overall effect of these preventive strategy reports, so the actual adjustment is mainly based on the risk level and specific constraints.

[0118] For example, suppose an electric power IoT system responds to possible equipment failures. The system monitors the status of each device in real time and uses fault detection models to predict possible future failures. The system needs to generate a fault-tolerant strategy based on these predictions and the current system status, with the goal of minimizing the losses caused by failures.

[0119] The input data are: System status: real-time monitored current, voltage, temperature, load and other parameters.

[0120] Fault detection model prediction results: including the probability of each device failure and the time point when it may occur.

[0121] Preventive strategy report: Based on historical fault data and fault detection model prediction results, it provides an assessment of the impact of fault events and fault locations on the system and recommended preventive measures.

[0122] Resource constraints: The resources available to the system (e.g., number of spare equipment, repair personnel).

[0123] Time constraint: The maximum time the system can use to handle a failure.

[0124] The goal is to generate a set of actions (such as repairing equipment, switching to a backup system, etc.) based on the input data so as to minimize the loss of the system due to failure while satisfying resource and time constraints.

[0125] For example, the optimization objective function uses a dynamic programming algorithm to define states and state transitions. The defined state represents the minimum loss that the system can achieve after consuming resources r within time t. Assume that there are three devices A, B, and C, and the failure probability P of each device is A , P B , P C Predicted by the fault detection model; the impact of each device failure on the system is I A ,I B ,I C ; The repair time of each device is T A 、T B 、T C ; The repair resource consumption of each device is R A , R B , R C .

[0126] The state transfer equation is as follows:

[0127] S(t,r)=min{S(tT A ),(rR A )+P A ×I A ,S(tT B ),(rR B )+P B ×I B ,S(tT C ),(rR C )+P C ×I C};

[0128] It represents the transition of the system from the current state S(t,r) to the state after performing the repair operation of device A, B or C, and the operation that causes the least loss is selected.

[0129] The initial condition is set to: S(0,0)=0, which means that the system loss is 0 at the initial time and when no resources are consumed.

[0130] Constraint: See timing constraint, resource constraint, and operation order constraint.

[0131] Use the dynamic programming algorithm to recursively calculate the optimal state at each time point and resource consumption, assuming: t max = 10 hours; r available = 100 units of resources, t max represents the maximum time point, r available Represents the number of available unit resources; starting from the initial state S(0,0)=0, calculate S(t,r) under r for each t, ​​and finally get the minimum loss within the constraints.

[0132] According to the dynamic programming results, backtracking obtains the optimal decision path, for example:

[0133] At t = 3 hours, equipment A is repaired first;

[0134] At t = 5 hours, repair equipment B;

[0135] At t=8 hours, switch to backup system C.

[0136] Step 105: Perform a repair operation according to the fault-tolerant strategy to obtain a repair result.

[0137] In this embodiment, the repair operation is performed according to the fault tolerance strategy, and key data after the execution of the fault tolerance strategy is collected in real time, such as repair time, repair success rate, system stability and business continuity, etc. The repair result is judged to be successful or failed based on the collected key data.

[0138] Step 106: If the repair result is a repair failure, the backup system is activated for the faulty part.

[0139] In this embodiment, if the repair operation fails, the system will automatically enable the backup system for the faulty part. This process is to ensure the continuity and reliability of the system and avoid long downtime caused by failures. The backup system can be redundant hardware or backup software functions, which can quickly take over the work of the faulty part to maintain the normal operation of the system. This design not only improves the system's risk resistance, but also reduces the impact on users or businesses, ensuring the availability and stability of services.

[0140] Step 107: Optimize the fault tolerance strategy based on the repair result.

[0141] In this embodiment, the fault-tolerant strategy is optimized based on the repair results. The system analyzes the reasons for the repair failure, identifies potential problems, and adjusts the existing fault-tolerant strategy. This optimization may include updating the fault detection model, improving the repair process, or strengthening the response capability of the backup system. Through such a feedback mechanism, the system can be more efficient in future fault handling, reduce the occurrence of similar problems, and improve overall reliability and performance. This process reflects the ability of continuous improvement and learning, and is one of the important components of realizing intelligent systems.

[0142] Specifically, multiple effect evaluation indicators are calculated based on the repair effect, and the effect evaluation indicators include actual repair time, repair success rate and actual stability. The product between the time difference and the first repair weight, the product between the repair success rate and the preset second repair weight, and the product between the stability difference and the preset third repair weight are added to obtain the repair effect value. If the repair effect value is less than or equal to the preset repair threshold, the worst one is selected from multiple effect evaluation indicators as the target evaluation indicator, and the cause of the target evaluation indicator (such as too long repair time or repair failure) is analyzed. With the goal of optimizing the target evaluation indicator, the parameters of the fault-tolerant strategy are adjusted to optimize its performance. For example, the repair time threshold is modified or redundant paths are added, and the parameters in the fault-tolerant strategy are adjusted. The adjusted fault-tolerant strategy is applied, and the system is retested to observe its effect.

[0143] The time difference is the difference between the preset standard repair time and the actual repair time, and the stability difference is the ratio between the actual stability and the preset standard stability.

[0144] Repair effect value = (preset standard repair time - actual repair time) × first repair weight + repair success rate × preset second repair weight + (actual stability / preset standard stability) × third repair weight.

[0145] In the embodiment of the present invention, the system status, system operation data and historical fault data of the power Internet of Things are collected, and the system operation data and historical fault data are input into a preset fault detection model to predict the fault events and fault locations of the power Internet of Things when potential faults occur in the future. A preventive strategy report is generated based on the fault events and fault locations. The preventive strategy report is optimized based on the system status, fault events and fault locations to generate a fault-tolerant strategy. A repair operation is performed based on the fault-tolerant strategy to obtain a repair result. If the repair result is a repair failure, a backup system is enabled for the fault location, and the fault-tolerant strategy is optimized based on the repair result. This embodiment can accurately predict potential faults and generate targeted preventive strategies through real-time monitoring and analysis of system operation data and historical fault data by the power Internet of Things collection system, and dynamically generate a more comprehensive fault-tolerant strategy from the preventive strategy, thereby enhancing the reliability and stability of the system and improving the accuracy of fault prediction.

[0146] Embodiment 2

[0147] Figure 2 A schematic diagram of the structure of a device for preventing faults in the power Internet of Things provided in the second embodiment of the present invention is shown in FIG. Figure 2 As shown, the device comprises:

[0148] The data collection module 201 is used to collect system status, system operation data and historical fault data of the power Internet of Things;

[0149] A fault prediction module 202 is used to input the system operation data and the historical fault data into a preset fault detection model to predict the fault event and fault location of the power Internet of Things when a potential fault occurs in the future;

[0150] A preventive strategy report generating module 203, used to generate a preventive strategy report according to the fault event and the fault location;

[0151] A fault-tolerant strategy generating module 204, configured to optimize the preventive strategy report according to the system state, the fault event, and the fault location to generate a fault-tolerant strategy;

[0152] A repair result acquisition module 205 is used to perform a repair operation according to the fault tolerance strategy to obtain a repair result;

[0153] A backup system startup module 206 is used to enable a backup system for the faulty part if the repair result is a repair failure;

[0154] The fault-tolerant strategy optimization module 207 is used to optimize the fault-tolerant strategy according to the repair result.

[0155] In one embodiment of the present invention, the fault prediction module 202 includes:

[0156] A model loading module, used to load a preset fault detection model; the fault detection model includes a first long short-term memory network, a second long short-term memory network, a first fully connected layer and a second fully connected layer;

[0157] A target sequence data acquisition module, used for performing a preprocessing operation on the system operation data and the historical fault data to obtain target sequence data;

[0158] A first time series feature extraction module, used for inputting the target sequence data into the first long short-term memory network to extract a first time series feature;

[0159] A second time series feature extraction module, used for inputting the first time series feature into the second long short-term memory network to extract a second time series feature;

[0160] A first fault feature mapping module, configured to input the second time series feature into the first fully connected layer and map it into a first fault feature;

[0161] A first probability prediction module is used to activate the first fault feature to predict a first probability of each fault location when a potential fault occurs in the electric power Internet of Things in the future;

[0162] A second fault feature mapping module, used for inputting the second time series feature into the second fully connected layer and mapping it into a second fault feature;

[0163] The second probability prediction module is used to activate the second fault feature to predict the second probability of each fault event when the electric power Internet of Things potentially fails in the future.

[0164] In one embodiment of the present invention, the fault prediction module 202 further includes:

[0165] A model training module, used for training the fault detection model according to the total loss function;

[0166] Wherein, the total loss function is expressed as:

[0167]

[0168] Fault Tolerance Loss=γ·(1-η);

[0169] Final Loss=α×Location Loss+β×Event Loss+Fault Tolerance Loss;

[0170] Among them, Final Loss is the total loss function, Location Loss is the location loss function, Event Loss is the event loss function, Fault Tolerance Loss is the fault tolerance loss function, and w i is the part weight of the i-th fault part, y location,i represents the i-th real fault location, represents the first probability of predicting the i-th fault location, t j represents the time to actually handle the jth fault event, T represents the time scale, and y event,j represents the jth real fault event, represents the second probability of predicting the jth fault event, γ is the fault tolerance loss coefficient, η represents the success rate of executing the fault tolerance strategy, α and β both represent adjustment coefficients, i∈num_locations, num_locations is the number of fault locations, j∈num_event_types, num_event_types is the number of fault events.

[0171] In one embodiment of the present invention, the preventive strategy report generation module 203 includes:

[0172] A candidate part determination module is used to determine the fault part as a candidate part if the first probability is greater than or equal to a preset first fault threshold; each of the fault parts has a part weight configured;

[0173] A target part determination module, used for screening out a plurality of candidate parts with the highest part weights as target parts;

[0174] a target time determination module, configured to determine the fault event as a target event if the second probability is greater than or equal to a preset second fault threshold;

[0175] A loss information calculation module, used to calculate the loss information caused by the target part and the target event in the power Internet of Things;

[0176] The preventive strategy report formulation module is used to formulate a preventive strategy report based on the loss information.

[0177] In one embodiment of the present invention, the fault-tolerant strategy generation module 204 includes:

[0178] A risk level calculation module, used to calculate the risk level when a fault occurs in the power Internet of Things according to the system state, the fault event, and the fault location;

[0179] A function and condition generation module, used for generating an objective function and constraint conditions for the preventive strategy report according to the risk level;

[0180] A fault-tolerant strategy correction module is used to correct the preventive strategy report into a fault-tolerant strategy with the goal of optimizing the objective function and subject to the constraints.

[0181] In one embodiment of the present invention, the risk level is:

[0182] R i =P i ×I i ×S i ;

[0183]

[0184] Where: R i Indicates the risk level of the failure, P i is the average value between the first probability of the fault location and the second probability of the fault event, I i Indicates the impact of the fault on the power Internet of Things, S i Indicates the sensitivity of the system state, L i is the load level of the power Internet of Things, L max is the maximum load capacity of the power Internet of Things, O norm is the standard operating status value of the power Internet of Things, O i is the real-time operating status value of the electric power Internet of Things under the system state, M i is the redundancy of the power Internet of Things, M max is the maximum redundancy of the power Internet of Things, and α, β, and γ are adjustment coefficients.

[0185] In one embodiment of the present invention, the objective function is:

[0186]

[0187] Where: C is the objective function, Minimize is the goal of optimizing the objective function to minimize the value output by the objective function, T i is the fault-tolerant time consumed by the power Internet of Things to perform the i-th fault-tolerant operation, D i is the delay event of the power Internet of Things switching to the backup resource, and λ represents the weight coefficient;

[0188] The constraints include at least one of the following:

[0189] Time constraints, resource constraints, and operation order constraints;

[0190] Wherein, the time constraint condition indicates that the fault tolerance time is less than or equal to the maximum time for processing a fault in the power Internet of Things;

[0191] The resource constraint condition indicates that the amount of resources consumed in executing the fault-tolerant operation is less than or equal to the amount of resources available to the power Internet of Things;

[0192] The operation order constraint condition indicates that the execution order between the plurality of fault-tolerant operations complies with a preset standard order.

[0193] In one embodiment of the present invention, the fault-tolerant strategy optimization module 207 includes:

[0194] An effect evaluation index calculation module is used to calculate multiple effect evaluation indicators according to the repair effect; the effect evaluation indicators include actual repair time, repair success rate and actual stability;

[0195] A repair effect value calculation module, used to add the product between the time difference and the first repair weight, the product between the repair success rate and the preset second repair weight, and the product between the stability difference and the preset third repair weight to obtain a repair effect value; the time difference is the difference between the preset standard repair time and the actual repair time, and the stability difference is the ratio between the actual stability and the preset standard stability;

[0196] A target evaluation index acquisition module is used to select the worst one from the multiple effect evaluation indicators as the target evaluation indicator if the repair effect value is less than or equal to a preset repair threshold value;

[0197] The parameter adjustment module is used to adjust the parameters in the fault-tolerant strategy with the goal of optimizing the target evaluation index.

[0198] The device for preventing faults in the electric power Internet of Things provided in the embodiment of the present invention can execute the method for preventing faults in the electric power Internet of Things provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method for preventing faults in the electric power Internet of Things.

[0199] Embodiment 3

[0200] See also Figure 3 , showing a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. The computer device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The computer device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0201] like Figure 3As shown, the computer device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the computer device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0202] A number of components in the computer device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the computer device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0203] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for preventing faults in the power Internet of Things.

[0204] In some embodiments, the method for preventing faults in the electric power Internet of Things may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the computer device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for preventing faults in the electric power Internet of Things described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the method for preventing faults in the electric power Internet of Things in any other appropriate manner (e.g., by means of firmware).

[0205] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0206] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0207] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0208] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0209] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0210] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0211] Embodiment 4

[0212] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the method for preventing faults in the power Internet of Things as provided in any embodiment of the present invention.

[0213] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "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 separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0214] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0215] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for preventing faults in an electric power Internet of Things, characterized in that: include: Collect system status, system operation data and historical fault data of the power Internet of Things; Input the system operation data and the historical fault data into a preset fault detection model to predict the fault events and fault locations of the power Internet of Things when a potential fault occurs in the future; Generate a preventive strategy report based on the fault event and the fault location; Optimizing the preventive strategy report according to the system state, the fault event, and the fault location to generate a fault-tolerant strategy; Performing a repair operation according to the fault-tolerant strategy to obtain a repair result; If the repair result is a repair failure, activating a backup system for the faulty part; The fault-tolerance strategy is optimized according to the repair result.

2. The method according to claim 1, characterized in that The inputting of the system operation data and the historical fault data into a preset fault detection model to predict the fault events and fault locations of the electric power Internet of Things when a potential fault occurs in the future includes: Loading a preset fault detection model; the fault detection model includes a first long short-term memory network, a second long short-term memory network, a first fully connected layer and a second fully connected layer; Performing a preprocessing operation on the system operation data and the historical fault data to obtain target sequence data; Inputting the target sequence data into the first long short-term memory network to extract a first time series feature; Inputting the first time series feature into the second long short-term memory network to extract a second time series feature; Inputting the second time series feature into the first fully connected layer and mapping it into a first fault feature; Activating the first fault feature to predict first probabilities of various fault locations when a potential fault occurs in the electric power Internet of Things in the future; Inputting the second time series feature into the second fully connected layer and mapping it into a second fault feature; The second fault feature is activated to predict the second probability of each fault event when the electric power Internet of Things potentially fails in the future.

3. The method according to claim 2, characterized in that Also includes: Training the fault detection model according to the total loss function; Wherein, the total loss function is expressed as: Fault Tolerance Loss=γ·(1-η); Final Loss=α×Location Loss+β×Event Loss+Fault Tolerance Loss; Among them, Final Loss is the total loss function, Location Loss is the location loss function, Event Loss is the event loss function, Fault Tolerance Loss is the fault tolerance loss function, and w i is the part weight of the i-th fault part, y location,i represents the i-th real fault location, represents the first probability of predicting the i-th fault location, t j represents the time to actually handle the jth fault event, T represents the time scale, and y event,j represents the jth real fault event, represents the second probability of predicting the jth fault event, γ is the fault tolerance loss coefficient, η represents the success rate of executing the fault tolerance strategy, α and β both represent adjustment coefficients, i∈num_locations, num_locations is the number of fault locations, j∈num_event_types, num_event_types is the number of fault events.

4. The method according to claim 2, characterized in that: The generating of a preventive strategy report according to the fault event and the fault location includes: If the first probability is greater than or equal to a preset first fault threshold, the fault location is determined to be a candidate location; each of the fault locations has a location weight configured; Screening out a plurality of candidate parts with the highest part weights as target parts; If the second probability is greater than or equal to a preset second fault threshold, determining the fault event as a target event; Calculating loss information caused by the target part and the target event in the electric power Internet of Things; Develop a preventive strategy report based on the loss information.

5. The method according to any one of claims 1 to 4, characterized in that The optimizing the preventive strategy report according to the system state, the fault event, and the fault location to generate a fault-tolerant strategy includes: Calculate the risk level when the power Internet of Things fails according to the system status, the fault event, and the fault location; generating an objective function and constraints for the preventive strategy report according to the risk level; With the goal of optimizing the objective function, the preventive strategy report is modified into a fault-tolerant strategy under the constraints of the constraints.

6. The method according to claim 5, characterized in that The risk levels are: R i =P i ×I i ×S i ; Where: R i Indicates the risk level of the failure, P i is the average value between the first probability of the fault location and the second probability of the fault event, I i Indicates the impact of the fault on the power Internet of Things, S i Indicates the sensitivity of the system state, L i is the load level of the power Internet of Things, L max is the maximum load capacity of the power Internet of Things, O norm is the standard operating status value of the power Internet of Things, O i is the real-time operating status value of the electric power Internet of Things under the system state, M i is the redundancy of the power Internet of Things, M max is the maximum redundancy of the power Internet of Things, and α, β, and γ are adjustment coefficients.

7. The method according to claim 5, characterized in that The objective function is: Where: C is the objective function, Minimize is the goal of optimizing the objective function to minimize the value output by the objective function, T i is the fault-tolerant time consumed by the power Internet of Things to perform the i-th fault-tolerant operation, D i is the delay event of the power Internet of Things switching to the backup resource, and λ represents the weight coefficient; The constraints include at least one of the following: Time constraints, resource constraints, and operation order constraints; Wherein, the time constraint condition indicates that the fault tolerance time is less than or equal to the maximum time for processing a fault in the power Internet of Things; The resource constraint condition indicates that the amount of resources consumed in executing the fault-tolerant operation is less than or equal to the amount of resources available to the power Internet of Things; The operation order constraint condition indicates that the execution order between the plurality of fault-tolerant operations complies with a preset standard order.

8. The method according to any one of claims 1-4, 6-7, characterized in that: Optimizing the fault tolerance strategy according to the repair result includes: Calculating multiple effect evaluation indicators based on the repair effect; the effect evaluation indicators include actual repair time, repair success rate and actual stability; The product of the time difference and the first repair weight, the product of the repair success rate and the preset second repair weight, and the product of the stability difference and the preset third repair weight are added together to obtain a repair effect value; the time difference is the difference between the preset standard repair time and the actual repair time, and the stability difference is the ratio between the actual stability and the preset standard stability; If the repair effect value is less than or equal to the preset repair threshold, the worst one is selected from the multiple effect evaluation indicators as the target evaluation indicator; The parameters in the fault-tolerant strategy are adjusted with the goal of optimizing the target evaluation index.

9. A computer device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for preventing faults in the electric power Internet of Things as described in any one of claims 1-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for preventing faults in the electric power Internet of Things as described in any one of claims 1 to 8 is implemented.

Images