10kV power distribution network safe operation management system based on intelligent monitoring

Abstract

The invention relates to the technical field of power distribution network intelligent management systems, in particular to a 10kV power distribution network safe operation management system based on intelligent monitoring, which realizes real-time state monitoring, risk prediction and dynamic protection strategy generation of a power distribution network through multi-modal data fusion, edge computing and cloud federated decision technologies.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network management systems, and more specifically, to a 10kV distribution network safe operation management system based on intelligent monitoring. Background Art

[0002] With the advancement of the construction of smart grids, the safe operation management technology of 10kV distribution networks has been continuously developing. The existing management systems have the following deficiencies. Most traditional systems adopt SCADA systems. Such systems only rely on electrical quantity monitoring (such as voltage and current), and cannot perceive the coupling risks of equipment physical states (such as temperature and deformation) and environmental factors (such as SF6 concentration). The monitoring dimension is single. At the same time, centralized data processing results in a fault prediction delay > 200ms, which cannot meet the rapid response requirements for transient faults (such as arc flash). The data in each area is stored independently, and the accuracy of global risk assessment is limited, and the misjudgment rate is relatively high. Therefore, a 10kV distribution network safe operation management system based on intelligent monitoring is provided. Through multi-modal data fusion, edge computing and cloud federated decision-making technology, real-time status monitoring, risk prediction and dynamic protection strategy generation of the distribution network are realized. Summary of the Invention

[0003] Aiming at the deficiencies existing in the prior art, the purpose of the present invention is to provide a 10kV distribution network safe operation management system based on intelligent monitoring to solve the problems existing in the above background art.

[0004] The above technical purpose of the present invention is achieved through the following technical solutions: A 10kV distribution network safe operation management system based on intelligent monitoring, including: a plurality of intelligent monitoring sub-terminals arranged on each distribution network node and a cloud decision-making platform arranged on the system terminal; a plurality of the intelligent monitoring sub-terminals are respectively in communication connection with the cloud decision-making platform; the intelligent monitoring sub-terminal includes: a data acquisition module for acquiring multi-modal data on the distribution network node and an edge computing cluster for extracting features from the acquired multi-modal data and then transmitting them; the cloud decision-making platform includes: a global risk prediction module for receiving the feature vectors transmitted by the edge computing cluster and performing risk prediction, and a dynamic protection strategy generation module for generating corresponding protection adjustment plans according to the calculation results of the global risk prediction module.

[0005] Optionally, the multi-modal data includes: electrical parameters: three-phase current signals, three-phase voltage signals, fundamental wave components of three-phase voltages, fundamental wave components of three-phase currents, harmonic effective values, total harmonic distortion rates and harmonic inter-phase coupling relationships of the nodes of the distribution network; thermal imaging parameters: visible light images of equipment, infrared images of equipment, highest surface temperature of equipment, temperature gradient, proportion of hot spot area and standard deviation of temperature distribution.

[0006] Optionally, the edge computing cluster includes: a harmonic depth analysis unit for extracting the harmonic distortion features and temporal correlation of the multimodal data, and a thermal image feature modeling unit for identifying the hot spots of the device based on image segmentation technology, quantifying the temperature gradient distribution, and then extracting the thermal image features; the harmonic depth analysis unit includes: an optimized window function processing unit for suppressing spectral leakage by using an optimized window function with fourth-order cosine components, and a harmonic inter-correlation analysis unit for performing harmonic inter-correlation feature extraction based on time series.

[0007] Optionally, the feature extraction of the harmonic depth analysis unit includes: the optimized window function processing unit performs windowed Fourier transform on the voltage signal by using an optimized window function to suppress spectral leakage; the harmonic inter-correlation analysis unit calculates the skewness of odd harmonics and the Pearson correlation coefficient matrix of adjacent harmonics, extracts the distribution characteristics of harmonic energy in the frequency band of 30 - 1500 Hz, and then calculates and obtains the harmonic distortion features.

[0008] Optionally, the feature extraction of the thermal image feature modeling module includes: the thermal image feature modeling module identifies the key areas of the device based on the image segmentation algorithm, delimits the ROI of the thermal temperature area for temperature analysis, calculates the maximum value of the temperature gradient and the radial attenuation coefficient within the ROI, and statistically calculates the proportion of pixel points exceeding the preset temperature threshold and the spatial distribution dispersion, and then calculates and obtains the thermal image features.

[0009] Optionally, the intelligent monitoring sub-terminal further includes: a gas detection module for detecting the change in SF6 concentration and triggering a gas insulation deterioration warning, a temperature and humidity sensing module for detecting the temperature and humidity, and an environmental compensation module for dynamically calibrating the electrical quantity measurement value according to the detection data of the humidity sensing module.

[0010] Optionally, the global risk prediction module includes: a federated feature fusion engine for receiving the feature vectors transmitted by a plurality of the intelligent monitoring sub-terminals, generating a multi-dimensional joint representation vector by using feature fusion and then transmitting it; a federated learning aggregator for receiving a plurality of the transmitted multi-dimensional joint representation vectors, aggregating a plurality of the multi-dimensional joint representation vectors every certain time period, and outputting a global risk prediction model; a risk assessment output layer for predicting and generating a three-dimensional risk situation map through the global risk prediction model, and synchronously outputting the risk level and the confidence interval.

[0011] Optionally, the dynamic protection policy generation module includes: a digital twin engine that generates a dynamic adjustment policy through the three-dimensional risk situation map; a blockchain consensus executor that receives the generated dynamic adjustment policy and uses an improved practical Byzantine fault tolerance algorithm to generate a dynamic adjustment policy instruction, and the dynamic adjustment policy instruction needs to be verified by more than 2 / 3 nodes before execution; a policy feedback optimizer that dynamically optimizes policy parameters according to the execution effect and synchronously generates an operation and maintenance recommendation policy.

[0012] In summary, the present invention has the following beneficial effects: 1. Starting from the perspective of multi-modal data determination, the system can synchronously analyze the correlation between electrical quantities, equipment temperatures, and environmental parameters, significantly improving the fault recognition rate of the system's determination and reducing the possibility of misjudgment.

[0013] 2. At the same time, intelligent monitoring sub-terminals are set at each configuration node, which speeds up feature extraction, optimizes data response speed, avoids data delay caused by centralized data processing in traditional systems, meets the transient fault response requirements, and further improves the system's reaction speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the system operation logic of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0015] In order to make the objectives, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be given with reference to the accompanying drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein.

[0016] In the present invention, unless otherwise clearly defined and limited, terms such as "installation", "connection", "connection", "fixation", etc. shall be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations. The terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0017] In the present invention, unless otherwise clearly specified and defined, the first feature being "on" or "under" the second feature may include direct contact between the first and second features, or may include the situation where the first and second features are not in direct contact but in contact through additional features therebetween. Moreover, the first feature being "above", "over" and "on top of" the second feature includes the first feature being directly above and obliquely above the second feature, or simply indicating that the horizontal height of the first feature is higher than that of the second feature. The first feature being "under", "beneath" and "underneath" the second feature includes the first feature being directly below and obliquely below the second feature, or simply indicating that the horizontal height of the first feature is less than that of the second feature. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions are only for the purpose of illustration, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation on the present invention.

[0018] The present invention will be described in detail below with reference to the accompanying drawings and embodiments.

[0019] The present invention provides a 10 kV distribution network safe operation management system based on intelligent monitoring, as Figure 1 shown, including: a plurality of intelligent monitoring sub - terminals arranged on each distribution network node and a cloud - based decision - making platform arranged on the system terminal; a plurality of the intelligent monitoring sub - terminals are respectively communicatively connected with the cloud - based decision - making platform; the intelligent monitoring sub - terminal includes: a data acquisition module for acquiring multi - modal data on the distribution network node and an edge computing cluster for extracting features from the acquired multi - modal data and then transmitting them; the cloud - based decision - making platform includes: a global risk prediction module for performing risk prediction after receiving the feature vectors transmitted by the edge computing cluster and a dynamic protection strategy generation module for generating a corresponding protection adjustment plan according to the calculation result of the global risk prediction module; thereby realizing the fault judgment logic of end - edge - cloud, and further increasing the scene adaptability.

[0020] In the specific implementation process, intelligent monitoring sub - terminals are installed on each node of the distribution network (which can be a power transmission node, a transfer node, etc.). Through the data acquisition module, multi - modal data on the node is obtained, and after feature extraction by the edge computing cluster of the intelligent monitoring sub - terminal, the feature vectors are transmitted to the cloud - based decision - making platform. After the global risk prediction module calculates and predicts the transmitted feature vectors, the danger level is predicted and calculated, and a dynamic protection strategy is generated through the dynamic protection strategy generation module, thereby ensuring the normal operation of the distribution network and avoiding serious property losses.

[0021] Further, the multimodal data includes: electrical parameters: three-phase current signals, three-phase voltage signals, fundamental wave components of three-phase voltages, fundamental wave components of three-phase currents, harmonic effective values, total harmonic distortion rates, and harmonic inter-phase coupling relationships of nodes in the distribution network; thermal imaging parameters: visible light images of equipment, infrared images of equipment, maximum surface temperature of equipment, temperature gradient, proportion of hot spot area, and standard deviation of temperature distribution.

[0022] In the first embodiment, through the broadband voltage sensing unit on the data acquisition module, three-phase voltage / current signals in the frequency band of 0.1 Hz - 10 MHz are collected, fundamental wave and harmonic components are synchronously extracted, and then the electrical parameters in the multimodal data are obtained; through the multispectral imaging unit on the data acquisition module, visible light images and infrared thermal images of the equipment are captured at a frame rate of 25 Hz, and then the thermal imaging parameters in the multimodal data are obtained.

[0023] Further, the edge computing cluster includes: a harmonic depth analysis unit for extracting harmonic distortion characteristics and temporal correlation of the multimodal data, and a thermal imaging feature modeling unit for identifying hot spot areas of equipment and quantifying temperature gradient distribution based on image segmentation technology, and then extracting thermal imaging features; the harmonic depth analysis unit includes: an optimized window function processing unit for suppressing spectral leakage by using an optimized window function with a fourth-order cosine component, and a harmonic inter-correlation analysis unit for performing harmonic inter-correlation feature extraction based on time series.

[0024] Further, the feature extraction of the harmonic depth analysis unit includes: the optimized window function processing unit performs windowed Fourier transform on the voltage signal using the optimized window function to suppress spectral leakage; the harmonic inter-correlation analysis unit calculates the skewness of odd harmonics and the Pearson correlation coefficient matrix of adjacent harmonics, extracts the distribution characteristics of harmonic energy in the frequency band of 30 - 1500 Hz, and then calculates and obtains the harmonic distortion characteristics.

[0025] Further, the feature extraction of the thermal imaging feature modeling module includes: the thermal imaging feature modeling module identifies key areas of the equipment based on the image segmentation algorithm, delimits the ROI of the thermal temperature analysis area, calculates the maximum temperature gradient and radial attenuation coefficient within the ROI, and counts the proportion and spatial distribution dispersion of pixel points exceeding the preset temperature threshold, and then calculates and obtains the thermal imaging features.

[0026] In the specific implementation process, the maximum temperature gradient and radial attenuation coefficient within the ROI are calculated, and the proportion and spatial distribution dispersion of pixel points exceeding the preset temperature threshold are counted, and then the thermal imaging features are calculated. The infrared thermal imaging temperature modeling formula is expressed as: , represents the true temperature of the equipment surface coordinates (x, y), Represents the radiant energy received by the infrared sensor, Represents the emissivity of the device surface, Represents the Stefan-Boltzmann constant, Represents the ambient temperature; calculate the temperature gradient within the ROI according to the modeling result, expressed as , where Represents the highest temperature within the ROI area, Represents the average temperature within the ROI area, Represents the radial distance from the center to the edge of the hot spot, and then obtains the thermal image feature.

[0027] Furthermore, the intelligent monitoring sub-terminal further includes: a gas detection module for detecting changes in SF6 concentration and triggering a gas insulation deterioration warning, a temperature and humidity sensing module for detecting temperature and humidity, and an environmental compensation module for dynamically calibrating the electrical quantity measurement value according to the detection data of the humidity sensing module.

[0028] In the second embodiment, to cope with the measurement deviation caused by environmental factors at the distribution network node, a data environmental compensation formula is adopted, expressed as , where Represents the effective value of the compensated voltage, Represents the original voltage value, Represents the temperature compensation coefficient, Represents the ambient temperature, Represents the temperature compensation coefficient, [[ID=3,4]]Represents the ambient relative humidity.

[0029] Furthermore, the global risk prediction module includes: a federated feature fusion engine for receiving the feature vectors transmitted by several of the intelligent monitoring sub-terminals, generating a multi-dimensional joint representation vector by feature fusion and then transmitting it; a federated learning aggregator for receiving several of the transmitted multi-dimensional joint representation vectors, aggregating several of the multi-dimensional joint representation vectors every certain time period, and outputting a global risk prediction model; a risk assessment output layer for predicting and generating a three-dimensional risk situation map through the global risk prediction model, and synchronously outputting the risk level and confidence interval.

[0030] In the third embodiment, the federated feature fusion engine consists of a cross-modal attention layer and a spatio-temporal convolutional network. Among them, the cross-modal attention layer adopts a multi-head attention mechanism, and the weight allocation formula is , where Represents the trainable parameter matrix, q represents the query vector, Represented as a key vector, the spatio-temporal convolutional network contains 3 layers of dilated convolutions with dilation factors d = 1, 2, 4 to capture harmonic temporal features, and can receive 18-dimensional feature vectors (harmonic distortion rate, temperature gradient) from each edge computing cluster, and then generate a 128-dimensional joint representation vector through feature fusion. The federated learning aggregator consists of a dynamic weighting unit and a differential injection unit. The dynamic weighting unit calculates the aggregation weight according to the node data quality (data loss rate) and model accuracy, represented as where represents the aggregation weight of the k-th edge node, represents the prediction accuracy of the k-th local node model, is the data missing rate of the k-th node, and K represents the total number of edge nodes participating in federated learning. The differential injection unit is used to add Laplace noise, represented as where represents the Laplace distribution, and it can aggregate the edge node model parameters every certain time period to output a high-precision global risk prediction model. The risk assessment output layer consists of a Softmax classifier and an interpretability analysis unit. The Softmax classifier is used to compare the prediction results of the global risk prediction model with the preset warning thresholds (warning ≥ 0.7, fault ≥ 0.9) and then output the three-level probabilities of normal / warning / fault. The interpretability analysis unit quantifies the contribution degree of each feature based on SHAP values, and can generate a three-dimensional risk situation map (spatial resolution 0.5m, time granularity 50ms), and synchronously output the risk level and confidence interval. For example, the fault probability of cable joint T23 is 92% ± 3%.

[0031] Furthermore, the dynamic protection strategy generation module includes: a digital twin engine that generates a dynamic adjustment strategy through the three-dimensional risk situation map; a blockchain consensus executor that receives the generated dynamic adjustment strategy and uses an improved practical Byzantine fault tolerance algorithm to generate a dynamic adjustment strategy instruction, and the dynamic adjustment strategy instruction needs to be verified by more than 2 / 3 nodes before execution; a strategy feedback optimizer that dynamically optimizes the strategy parameters according to the execution effect and synchronously generates an operation and maintenance recommendation strategy.

[0032] In the fourth embodiment, the digital twin engine consists of a real-time state mapping unit, and the real-time state mapping unit generates a dynamic adjustment strategy through the three-dimensional risk situation map generated in real time. The blockchain consensus executor consists of a PBFT consensus network and a smart contract library. The PBFT consensus network contains several verification nodes, where the number of verification nodes N ≥ 4 and the fault tolerance number f = 1 (satisfying N ≥ 3f + 1); the smart contract library contains 12 preset policy instructions such as overcurrent protection and arc isolation to extract the preset policy instructions for the corresponding dynamic adjustment policy, so as to generate dynamic adjustment policy instructions. During the implementation of the dynamic policy instructions, the verification nodes of the PBFT consensus network need to verify, and then verify the legality of the protection instructions (2 / 3 nodes need to confirm). After verification, the operation hash value is recorded for subsequent traceability operations; The policy feedback optimizer consists of a reinforcement learning agent processor and a historical case library. The reinforcement learning uses the DQN algorithm, and the reward function is designed as The historical case library is used to store historical fault handling records; the policy parameters are dynamically optimized according to the execution effect to generate operation and maintenance suggestions (such as "Line L12 needs to be inspected first").

[0033] In other embodiments, to ensure an effective response to transient faults, the digital twin engine can also receive real-time parameters to make a corresponding protection setting adjustment coefficient policy, expressed as where k represents the protection setting adjustment coefficient, represents the maximum operating temperature allowed for the device, represents the real-time monitored temperature, represents the change rate of the total harmonic distortion rate over time. The protection setting adjustment coefficient policy is obtained through rapid response, so as to achieve the response to transient faults.

[0034] In one specific embodiment, for example, if the cable joint in any distribution network has overheating, during the data collection process, the broadband sensor detects a sudden increase in the current harmonic distortion rate, and at the same time the infrared thermal image shows that the joint temperature rises from 45°C to 82°C, and the temperature gradient reaches 15°C / cm; Edge computing: The harmonic correlation analysis unit identifies the abnormal amplitude of the 3rd harmonic, and the thermal image feature modeling unit calculates that the hot spot area ratio reaches 12%; on the cloud decision-making platform, the federated feature fusion engine synthesizes the data of 10 edge nodes, and the federated learning aggregator aggregates the data and outputs it to the risk assessment output layer, and the output risk value is 0.93. The digital twin engine generates a dynamic adjustment policy: dynamically adjust the overcurrent protection threshold of this line from 120% of the rated value to 95%. The blockchain consensus executor triggers the circuit breaker to trip, avoiding the melting of the cable insulation layer. The whole process of the event (including multi-modal data) is chained and stored for evidence, and a unique hash identifier is generated.

[0035] In one embodiment, if a lightning strike fault occurs at any distribution network node, during data acquisition, the broadband sensor captures a 10 MHz high-frequency transient current, the multi-spectral imaging unit records the arc light trajectory, the harmonic inter-correlation analysis unit processes the signal using the Nuttall window function, extracts a wavefront time ≤ 1 μs, the thermal image feature modeling unit locates the arc spot coordinates, the federated feature fusion engine aggregates meteorological radar data, corrects the lightning strike point to pole tower T23 (error ±0.3 m), and the digital twin engine generates an inspection work order and pushes it to the operation and maintenance terminal.

[0036] A 10 kV distribution network safety operation management system based on intelligent monitoring according to the present invention determines from the perspective of multi-modal data, can synchronously analyze the correlation between electrical quantities, equipment temperatures and environmental parameters, significantly improves the fault recognition rate determined by the system, and reduces the possibility of misjudgment; at the same time, the intelligent monitoring sub-terminals set at each configuration node accelerate the feature extraction speed, optimize the data response speed, avoid data delay caused by centralized data processing in traditional systems, meet the transient fault response requirements, and further improve the system response speed.

[0037] The above are only the preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the idea of the present invention belong to the protection scope of the present invention. It should be noted that for those of ordinary skill in the art in this technical field, several improvements and refinements made without departing from the principle of the present invention should also be regarded as within the protection scope of the present invention.

Claims

1. A 10kV distribution network safety operation management system based on intelligent monitoring, characterized in that, Including: A number of intelligent monitoring sub - terminals set on each distribution network node and a cloud - based decision - making platform set on the system terminal; A number of the intelligent monitoring sub - terminals are respectively communicatively connected to the cloud - based decision - making platform; The intelligent monitoring sub - terminal includes: a data acquisition module for collecting multi - modal data on the distribution network node and an edge computing cluster for extracting features from the collected multi - modal data and then transmitting them; The cloud - based decision - making platform includes: a global risk prediction module for performing risk prediction after receiving the feature vectors transmitted by the edge computing cluster and a dynamic protection strategy generation module for generating corresponding protection adjustment plans according to the calculation results of the global risk prediction module.

2. The 10kV distribution network safety operation management system based on intelligent monitoring according to claim 1, wherein, The multi - modal data includes: Electrical parameters: three - phase current signals, three - phase voltage signals, fundamental wave components of three - phase voltage, fundamental wave components of three - phase current, harmonic effective values, total harmonic distortion rates, and harmonic - to - harmonic phase coupling relationships of the nodes of the distribution network; Thermal imaging parameters: visible light images of equipment, infrared images of equipment, highest surface temperature of equipment, temperature gradient, proportion of hot - spot area, and standard deviation of temperature distribution.

3. The 10kV distribution network safety operation management system based on intelligent monitoring according to claim 2, characterized in that, The edge computing cluster includes: a harmonic depth analysis unit for extracting harmonic distortion features and time - series correlation of the multi - modal data and a thermal imaging feature modeling unit for identifying the hot - spot area of the equipment based on image segmentation technology, quantifying the temperature gradient distribution, and then extracting thermal imaging features; The harmonic depth analysis unit includes: an optimized window function processing unit for suppressing spectral leakage by using an optimized window function with fourth - order cosine components and a harmonic - to - harmonic correlation analysis unit for performing harmonic - to - harmonic correlation feature extraction based on time series.

4. An intelligent monitoring-based 10kV distribution network safe operation management system according to claim 3, characterized in that, The feature extraction of the harmonic depth analysis unit includes: The optimized window function processing unit performs windowed Fourier transform on the voltage signal using the optimized window function to suppress spectral leakage; The harmonic - to - harmonic correlation analysis unit calculates the skewness of odd - order harmonics and the Pearson correlation coefficient matrix of adjacent harmonics, extracts the distribution characteristics of harmonic energy in the 30 - 1500 Hz frequency band, and then calculates and obtains the harmonic distortion features.

5. The 10kV distribution network safety operation management system based on intelligent monitoring according to claim 1, characterized in that, The feature extraction of the thermal imaging feature modeling module includes: The thermal imaging feature modeling module identifies the key area of the equipment based on the image segmentation algorithm, demarcates the region of interest (ROI) for temperature analysis, calculates the maximum value of the temperature gradient and the radial attenuation coefficient within the ROI, and statistically calculates the proportion of pixel points exceeding the preset temperature threshold and the spatial distribution dispersion to calculate the thermal imaging features.

6. The 10kV distribution network safe operation management system based on intelligent monitoring according to claim 1, characterized in that The intelligent monitoring sub - terminal further includes: a gas detection module for detecting changes in SF6 concentration and triggering gas insulation deterioration warnings, a temperature and humidity sensing module for detecting temperature and humidity, and an environmental compensation module for dynamically calibrating the electrical quantity measurement values according to the detection data of the humidity sensing module.

7. The 10kV distribution network safe operation management system based on intelligent monitoring according to claim 1, characterized in that, The global risk prediction module includes: A federated feature fusion engine for receiving the feature vectors transmitted by a number of the intelligent monitoring sub - terminals, generating a multi - dimensional joint representation vector by feature fusion and then transmitting it; A federated learning aggregator for receiving a number of the transmitted multi - dimensional joint representation vectors, aggregating a number of the multi - dimensional joint representation vectors every certain time period, and outputting a global risk prediction model; A risk assessment output layer, which is used to predict and generate a three-dimensional risk situation map through the global risk prediction model, and synchronously output the risk level and confidence interval.

8. An operation management system for the safe operation of a 10kV distribution network based on intelligent monitoring according to claim 7, characterized in that, The dynamic protection policy generation module includes: A digital twin engine, which generates a dynamic adjustment policy through the three-dimensional risk situation map; A blockchain consensus executor, which receives the generated dynamic adjustment policy, adopts an improved practical Byzantine fault tolerance algorithm to generate a dynamic adjustment policy instruction, and the dynamic adjustment policy instruction needs to be verified by more than 2 / 3 nodes before execution; A policy feedback optimizer, which dynamically optimizes policy parameters according to the execution effect and synchronously generates an operation and maintenance recommendation policy.

Images