Edge calculation method and system of multimode communication technology

Abstract

The invention discloses an edge calculation method and system of a multimode communication technology. The method comprises the following steps: acquiring parameter information transmitted by a multimode communication network; power values of all power generation key nodes, all power utilization key nodes and all energy storage key nodes in the parameter information are obtained, the power generation key nodes are nodes with influence factors larger than a first threshold value after a node fault occurs, and the power utilization key nodes are nodes with influence factors larger than a second threshold value after the node fault occurs; the energy storage key nodes are nodes of which the influence factors are greater than a third threshold value after node faults; and based on the power values of the power generation key nodes, the power utilization key nodes and the energy storage key nodes, whether the micro-grid system of the power distribution area is unbalanced is judged, and edge calculation of the multimode communication technology is realized. And the goals of power grid safety, new energy consumption, resource optimization configuration, operation efficiency improvement and the like are realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent multi-mode communication technology, and in particular to an edge computing method and system for multi-mode communication technology. BACKGROUND

[0002] As of the end of February 2023, the total installed capacity of power generation in Yunnan Province was 113,567,200 kilowatts, of which: hydropower 81,935,800 kilowatts, thermal power 15,351,000 kilowatts, and new energy 16,280,400 kilowatts. Among them, the total installed capacity of power generation was 97,624,800 kilowatts, of which: hydropower 69,899,200 kilowatts, thermal power 1,255,900 kilowatts, wind power 9,570,600 kilowatts, and solar power 5,596,100 kilowatts. In January and February, the total power generation in the province was 55,082,000 kilowatt-hours, an increase of 16.4% over the same period last year. The power generation of large-scale power generation enterprises in the province was 48,802,000 kilowatt-hours, an increase of 8.4% over the same period last year, ranking third in the country. Among them: hydropower 33,268,000 kilowatt-hours, an increase of 11.2%; thermal power 91,930,000 kilowatt-hours, an increase of 3.1%; wind power 55,640,000 kilowatt-hours, an increase of 0.5%; and solar power 7,780,000 kilowatt-hours, an increase of 19.9%. It can be seen that the installed capacity of photovoltaic power generation accounts for 34.4% of the total installed capacity of new energy power generation in the province, but only accounts for 5% of the total installed capacity of power generation in the province. The development of distributed photovoltaic resources still has great space, and relevant work is in the important stage of advance planning and layout.

[0003] In view of the demand for county-wide photovoltaic construction, for county-level distribution networks, efforts should be made to overcome the actual pain points of local layer control difficulty, substation-level control difficulty, and distribution network-level control difficulty. The distributed and random access of distributed photovoltaic power to the power system brings major challenges to the safe and stable operation of the power system. The low-voltage distribution network is at the end of the power system, with characteristics such as wide distribution, complex power supply and use environment, and great difficulty in operation and maintenance. For a long time, there has been a lack of intelligent and efficient operation monitoring and operation and maintenance management means. After the addition of distributed photovoltaic power to the substation, it changes from passive to active, which will affect the safe and stable operation of the substation in terms of billing method, power quality, and operation management. At the same time, with the access of massive power and environmental related big data, the computing power and real-time performance of the monitoring platform are challenged, especially for integrated photovoltaic and storage projects, which have higher requirements for real-time local control. SUMMARY

[0004] This section is intended to summarize some aspects of the embodiments of the present application and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of the specification to avoid obscuring the purpose of this section, the abstract and the title, and such simplifications or omissions cannot be used to limit the scope of the present application.

[0005] In view of the above-mentioned existing problems, the present application is proposed.

[0006] Therefore, the application provides a multi-mode communication technology edge computing method and system, which can solve the problems mentioned in the background art.

[0007] To solve the above technical problems, the application provides the following technical scheme, a multi-mode communication technology edge computing method, comprising:

[0008] Obtain parameter information transmitted by a multi-mode communication network;

[0009] Obtain power values of each power generation key node, each power consumption key node and each energy storage key node in the parameter information, the power generation key node is a node whose influence factor after node failure is greater than a first threshold value, the power consumption key node is a node whose influence factor after node failure is greater than a second threshold value, and the energy storage key node is a node whose influence factor after node failure is greater than a third threshold value;

[0010] Based on the power values of the each power generation key node, the each power consumption key node and the each energy storage key node, it is judged whether the micro-grid system of a power distribution area is unbalanced, and the multi-mode communication technology edge computing is realized.

[0011] As a preferred scheme of the multi-mode communication technology edge computing method, the influence factor after node failure includes,

[0012] The power generation key node is calculated in the following manner:

[0013] η1=α1·S Q +α2·S C +α3·W Z +α4·B Y

[0014] Wherein, η1 represents the influence factor of the power generation key node after node failure, α1, α2, α3 and α4 represent the influence coefficients of the power generation key node after node failure, S Q represents the number of complete communities affected by the power key node after node failure, S C represents the number of complete shopping malls affected by the power key node after node failure, W Z represents the number of other complete buildings affected by the power key node after node failure, and B Y represents the number of transformers affected by the power key node after node failure.

[0015] The power consumption key node is calculated in the following manner:

[0016] η2=β1·S M +β2·M D +β3·MX

[0017] wherein, η2 represents the influence factor of the power consumption critical node after node failure, β1, β2, β3 represent the influence coefficient of the power consumption critical node when the node fails, S M represents the number of small power consumption equipment, M D represents the number of medium power consumption equipment, M X represents the number of large power consumption equipment;

[0018] The calculation method of the influence factor of the energy storage critical node after node failure is as follows:

[0019] η3 = δ1·S Y + δ2·M Y

[0020] wherein, η3 represents the influence factor of the energy storage critical node after node failure, δ1, δ2 represent the influence coefficient of the energy storage critical node when the node fails, S Y represents the number of commercial energy storage equipment, M Y represents the number of civil energy storage equipment.

[0021] An edge computing system of a multi-mode communication technology, characterized by comprising a communication unit and an edge computing unit,

[0022] The communication unit is used for receiving the power values of each power generation critical node, each power consumption critical node and each energy storage critical node transmitted by the multi-mode communication network.

[0023] The edge computing unit is used for judging whether the micro-grid system of the distribution area is unbalanced based on the power values of the each power generation critical node, each power consumption critical node and each energy storage critical node.

[0024] As a preferred scheme of the edge computing system of the multi-mode communication technology, the edge computing unit comprises a vector arrangement module, a vector extraction module, a vector fusion module and a micro-grid system judgment module,

[0025] The vector arrangement module, the vector extraction module, the vector fusion module and the micro-grid system judgment module are sequentially and unidirectionally connected, and the vector arrangement module is used for arranging the power values of the each power generation critical node, each power consumption critical node and each energy storage critical node into a power generation critical node power time sequence input vector, a power consumption critical node power time sequence input feature vector and an energy storage critical node power time sequence input vector according to the sample dimension respectively, and inputting the arranged results into the vector extraction module.

[0026] the vector extraction module is configured to extract power time sequence feature vectors of power generation key nodes, power time sequence feature vectors of power consumption key nodes, and power time sequence feature vectors of energy storage key nodes from the power time sequence input vectors of power generation key nodes, the power time sequence input feature vectors of power consumption key nodes, and the power time sequence input vectors of energy storage key nodes, and transmit the extracted feature vectors to the vector fusion module;

[0027] the vector fusion module is configured to fuse the power time sequence feature vectors of power generation key nodes, the power time sequence feature vectors of power consumption key nodes, and the power time sequence feature vectors of energy storage key nodes based on a Bayesian probability model to obtain a system posterior feature vector, and transmit the verified feature vector to the microgrid system judgment module;

[0028] the microgrid system judgment module is configured to judge whether the microgrid system of the power distribution area is unbalanced based on the system posterior feature vector.

[0029] As a preferred scheme of the edge computing system of the multi-mode communication technology, the vector extraction module includes a time sequence feature extractor based on a one-dimensional convolutional neural network model, which is configured to obtain the power time sequence feature vectors of power generation key nodes, the power time sequence feature vectors of power consumption key nodes, and the power time sequence feature vectors of energy storage key nodes from the power time sequence input vectors of power generation key nodes, the power time sequence input feature vectors of power consumption key nodes, and the power time sequence input vectors of energy storage key nodes, respectively.

[0030] As a preferred scheme of the edge computing system of the multi-mode communication technology, the vector fusion module includes an initial system posterior feature vector calculation unit, a perception factor calculation unit, a weighting unit, and a system posterior feature vector calculation unit,

[0031] the initial system posterior feature vector calculation unit is unidirectionally connected to the vector extraction module, and the vector extraction module sends the power time sequence feature vectors of power generation key nodes, the power time sequence feature vectors of power consumption key nodes, and the power time sequence feature vectors of energy storage key nodes to the initial system posterior feature vector calculation unit;

[0032] the initial system posterior feature vector calculation unit is configured to calculate an initial system posterior feature vector by taking the power time sequence feature vectors of power generation key nodes, the power time sequence feature vectors of power consumption key nodes, and the power time sequence feature vectors of energy storage key nodes as prior probability feature vectors, conditional probability feature vectors, and evidence probability feature vectors;

[0033] The perception factor calculation unit, the weighting unit and the system posterior feature vector calculation unit are sequentially connected, and the perception factor calculation unit is configured to calculate the transferable perception factors of the power time sequence feature vector of the power generation key node, the power time sequence feature vector of the power consumption key node and the power time sequence feature vector of the energy storage key node relative to the initial system posterior feature vector to obtain a first transferable perception factor, a second transferable perception factor and a third transferable perception factor.

[0034] The weighting unit is configured to weight the power time sequence feature vector of the power generation key node, the power time sequence feature vector of the power consumption key node and the power time sequence feature vector of the energy storage key node by using the first transferable perception factor, the second transferable perception factor and the third transferable perception factor as weights respectively to obtain a weighted power time sequence feature vector of the power generation key node, a weighted power time sequence feature vector of the power consumption key node and a weighted power time sequence feature vector of the energy storage key node.

[0035] The system posterior feature vector calculation unit is configured to calculate the system posterior feature vector by using the weighted power time sequence feature vector of the power generation key node, the weighted power time sequence feature vector of the power consumption key node and the weighted power time sequence feature vector of the energy storage key node as a prior probability feature vector, a conditional probability feature vector and an evidence probability feature vector.

[0036] As a preferred scheme of the edge computing system of the multi-mode communication technology, the perception factor calculation unit comprises,

[0037] The transferable perception factors of the power time sequence feature vector of the power generation key node, the power time sequence feature vector of the power consumption key node and the power time sequence feature vector of the energy storage key node relative to the initial system posterior feature vector are calculated by using the following optimization formula to obtain a first transferable perception factor, a second transferable perception factor and a third transferable perception factor.

[0038] The optimization formula is:

[0039]

[0040]

[0041]

[0042] V1 represents the power time sequence feature vector of the power generation key node, V represents the feature value of the i-th position of the power time sequence feature vector of the power generation key node, c represents the initial system posterior feature vector, an eigenvalue representing an i-th position of the initial system posterior eigenvector, V2 represents an eigenvalue representing an i-th position of the power time series eigenvector of the power consumption critical node, an eigenvalue representing an i-th position of the power time series eigenvector of the power consumption critical node, V3 represents an eigenvalue representing an i-th position of the power time series eigenvector of the energy storage critical node, an eigenvalue representing an i-th position of the power time series eigenvector of the energy storage critical node, log is a logarithmic function with 2 as a base, and a is a weighted hyperparameter, w1 represents the first transferability perception factor, w2 represents the second transferability perception factor, and w3 represents the third transferability perception factor.

[0043] As a preferred scheme of the edge computing system of the multi-mode communication technology, the micro-grid system judgment module is connected with the system posterior eigenvector calculation unit in a one-way manner, the micro-grid system judgment module obtains a classification result by using a classifier on the system posterior eigenvector, and the classification result is used to indicate whether the system is unbalanced.

[0044] A computer device comprises a memory and a processor, and the memory stores a computer program.

[0045] A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method.

[0046] The edge computing method and system of the multi-mode communication technology are provided, parameter information transmitted by a multi-mode communication network is acquired, power values of each power generation critical node, each power consumption critical node and each energy storage critical node in the parameter information are acquired, the power generation critical node is a node whose influence factor is greater than a first threshold value after a node failure, the power consumption critical node is a node whose influence factor is greater than a second threshold value after a node failure, and the energy storage critical node is a node whose influence factor is greater than a third threshold value after a node failure, whether a micro-grid system of a distribution area is unbalanced is judged based on the power values of the each power generation critical node, the each power consumption critical node and the each energy storage critical node, and edge computing of the multi-mode communication technology is implemented. The edge computing device is used to take a plurality of operation modes such as photovoltaic energy storage intelligent linkage in a new distribution area as a target, research wide-area source-grid-load-storage collaborative optimization operation technology, enrich functions such as source-source complementation, source-grid coordination, grid-load interaction and source-load interaction which are lacked in traditional source-load-storage control technology, and achieve goals such as power grid safety, new energy consumption, resource optimization allocation and improvement of operation efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments description will be briefly introduced as follows. Obviously, the drawings in the following description only represent some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings. Among them:

[0048] Figure 1 The method flow chart of the edge computing method and system of the multi-mode communication technology provided by one embodiment of the present application;

[0049] Figure 2 The system structure schematic diagram of the edge computing method and system of the multi-mode communication technology provided by one embodiment of the present application;

[0050] Figure 3 The internal structure diagram of the computer device of the edge computing method and system of the multi-mode communication technology provided by one embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the above objectives, features and advantages of the present application more apparent, the specific embodiments of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the protection scope of the present application.

[0052] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced without the specific details that are set forth in the description, and it is understood that persons having ordinary skill in the art can make and use other implementations of the present application according to the description herein without modifying the central idea of the present application. Accordingly, the present application is not intended to be limited by the description set forth and is intended to cover all alternatives consistent with the principles of the present application.

[0053] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. The "in one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0054] The present application is described in detail in combination with the schematic diagram. In the detailed description of the embodiments of the present application, the cross-sectional view of the device structure will be partially enlarged without the general proportion for the convenience of description, and the schematic diagram is only an example, which should not limit the protection scope of the present application herein. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in the actual manufacture.

[0055] Meanwhile, in the description of the present application, it should be noted that the terms "upper, lower, inner and outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first, second or third" are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0056] Unless otherwise expressly specified and limited, the terms "mounting, connecting, connecting" in the present application should be understood broadly, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through intermediate medium, or it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0057] Embodiment 1

[0058] Reference Figures 1-3 For the first embodiment of the present application, the embodiment provides a multi-mode communication technology edge computing system, comprising:

[0059] In a preferred embodiment, a multi-mode communication technology edge computing system comprises a communication unit 100 and an edge computing unit 200,

[0060] The communication unit 100 is used to receive the power values of each power generation key node, each power consumption key node and each energy storage key node transmitted by the multi-mode communication network;

[0061] The edge computing unit 200 is used to judge whether the micro-grid system of the power distribution area is unbalanced based on the power values of each power generation key node, each power consumption key node and each energy storage key node.

[0062] It should be noted that the communication unit 100 is a key component in the multi-mode communication technology edge computing gateway, and its main function is to receive the power values of each power generation key node, power consumption key node and energy storage key node transmitted by the multi-mode communication network.

[0063] Furthermore, the communication unit 100 needs to support multiple communication protocols to adapt to different types of power generation, power consumption and energy storage nodes, to ensure accurate transmission and reception of data; the communication unit 100 needs to take security measures such as data encryption and identity verification to protect the transmitted power value data from being illegally obtained or tampered with; the communication unit 100 needs to have high reliability to ensure stable data transmission and avoid data loss or transmission delay.

[0064] It should be noted that the communication unit 100 can receive the power value data of the power generation, power consumption and energy storage nodes in time, realize the real-time monitoring and management of the distribution area, integrate and analyze the received power value data, provide accurate data basis for the edge computing unit 200, and support the judgment and decision of the system. Through the reception of the power value data of the nodes, the communication unit 100 can timely detect the imbalance of the microgrid system of the distribution area, and provide basis for subsequent fault diagnosis and processing.

[0065] It should be noted that the edge computing unit 200 is another important component in the edge computing gateway of the multi-mode communication technology, and its main function is to judge whether the microgrid system of the distribution area is imbalanced based on the power values of the key nodes of power generation, power consumption and energy storage. Further, the edge computing unit 200 needs to use an efficient algorithm to accurately judge the imbalance of the microgrid system, including power imbalance, voltage instability and other problems. The edge computing unit 200 needs to have high real-time performance, and can timely respond to the change of the node power value and judge and adjust the system state.

[0066] Among them, the edge computing unit 200 includes a vector arrangement module 201, a vector extraction module 202, a vector fusion module 203 and a microgrid system judgment module 204, and the vector arrangement module 201, the vector extraction module 202, the vector fusion module 203 and the microgrid system judgment module 204 are sequentially and unidirectionally connected. The vector arrangement module 201 is used for arranging the power values of the key nodes of power generation, the key nodes of power consumption and the key nodes of energy storage into power generation key node power time sequence input vector, power consumption key node power time sequence input feature vector and energy storage key node power time sequence input vector respectively according to sample dimension, and inputting the arranged results into the vector extraction module 202;

[0067] In the embodiment of the present application, the power values are arranged according to the sample dimension, which can arrange the data into a structured vector form, which is helpful for data organization and management, and makes the data processing more convenient and efficient. By arranging the power values according to the sample dimension, the power time sequence features of the key nodes of power generation, the key nodes of power consumption and the key nodes of energy storage can be easily extracted, which can be used for subsequent data analysis, modeling and prediction, and help to understand the running state and trend of the system.

[0068] Among them, the vector extraction module 202 is used for extracting the power generation key node power time sequence feature vector, the power consumption key node power time sequence feature vector and the energy storage key node power time sequence feature vector from the power generation key node power time sequence input vector, the power consumption key node power time sequence input feature vector and the energy storage key node power time sequence input vector, and transmitting the extracted feature vectors to the vector fusion module 203;

[0069] The vector fusion module 203 is used to combine the Bayesian probability model to fuse the power time series feature vectors of key power generation nodes, key power consumption nodes, and key power storage nodes to obtain the system posterior feature vector, and then transmit the verified feature vector to the microgrid system judgment module 204.

[0070] The microgrid system judgment module 204 is used to determine whether the microgrid system of the distribution radio area is unbalanced based on the system posterior feature vector.

[0071] Furthermore, based on a Bayesian probability model, the power time-series feature vectors of key power generation nodes, key power consumption nodes, and key energy storage nodes are fused to obtain the system's posterior feature vector.

[0072] Specifically, in the technical solution of this application, the power time-series feature vectors of key power generation nodes, key power consumption nodes, and key energy storage nodes are used as prior probability feature vectors, conditional probability feature vectors, and evidential probability feature vectors to calculate the system's posterior feature vector. It should be understood that in the technical solution of this application, if the microgrid system is stable, there is a predetermined correlation pattern between the power values ​​of each power generation node, each power consumption node, and each energy storage node. Although the predetermined correlation pattern is complex and nonlinear, it can be fitted using a feature extractor based on a deep neural network model and the information exchange in the feature space can be performed using a Bayesian network model to obtain the system's posterior feature vector.

[0073] It should be noted that the Bayesian probabilistic model is a statistical model based on Bayes' theorem, used to infer relationships between variables and to make probabilistic inferences. When integrating the power time-series feature vectors of key nodes in power generation, consumption, and storage to obtain the system's posterior feature vector, the Bayesian probabilistic model can be used to establish probabilistic relationships between different nodes and infer the overall state of the system.

[0074] It should be noted that the core idea of ​​the Bayesian probabilistic model is to calculate the posterior probability based on known prior probabilities and new observation data using Bayes' theorem. Specifically, given the power time-series feature vectors of key nodes in power generation, consumption, and storage, the Bayesian probabilistic model can calculate the posterior feature vector of the system, that is, the probability distribution considering prior information and observation data.

[0075] It should be noted that the Bayesian probability model can be used to fuse the feature vectors of different nodes by establishing the conditional probability distribution between the nodes to describe the relationship between them. In this way, the information of each node can be fused to obtain the posterior feature vector of the whole system. Through the Bayesian probability model, the state of the system can be inferred and predicted to provide a basis for subsequent decision-making and control.

[0076] It should be noted that the advantage of the Bayesian probability model is that it can handle uncertainty and noise, and can be dynamically updated according to new observation data. It can use existing knowledge and data to infer unknown variables, thereby improving the prediction accuracy and robustness of the system. In the energy system, the Bayesian probability model can be used to establish a relationship model between nodes for system state estimation, anomaly detection, fault diagnosis and other tasks, thereby improving the operation efficiency and safety of the energy system.

[0077] In the technical solution of the present application, the power time sequence feature vector of the power generation key node, the power time sequence feature vector of the power consumption key node and the power time sequence feature vector of the energy storage key node respectively express the one-dimensional local correlation characteristics of the power value of each power generation key node, each power consumption key node and each energy storage key node in the sample direction. Therefore, considering the differences between different nodes, the feature fusion is expected to be based on the feature domain transition differences of the system posterior feature vectors finally obtained by them when calculating the posterior distribution of the correlation characteristics of the heterogeneous nodes based on the Bayesian probability, thereby improving the expression effect of the system posterior feature vector.

[0078] Further, the vector extraction module 202 includes a power generation key node power time sequence input vector, a power consumption key node power time sequence input feature vector and an energy storage key node power time sequence input vector, which are respectively input into a time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain a power generation key node power time sequence feature vector, a power consumption key node power time sequence feature vector and an energy storage key node power time sequence feature vector.

[0079] It should be noted that the one-dimensional convolutional neural network model can effectively extract the key features of time sequence data. By extracting the power time sequence data of power generation, power consumption and energy storage nodes, important patterns and trends in the data can be captured to provide useful information for subsequent analysis and control. Through the time sequence feature extractor, the original power time sequence data can be converted into a more compact feature vector. This can reduce the dimensionality of the data, reduce the storage and computing overhead, and filter out some noise and redundant information, improving the expressiveness and efficiency of the data.

[0080] It should be noted that the one-dimensional convolutional neural network model has good pattern recognition ability in time series data. By analyzing the power time series characteristics of power generation, power consumption and energy storage nodes, the correlation, periodicity and abnormality between different nodes can be identified. This helps to find potential problems and optimize control strategies. The one-dimensional convolutional neural network model can be processed in real time on edge computing devices. This means that the time series feature extractor can be deployed close to the data source, reducing data transmission delay and network load, and improving real-time performance and response capability.

[0081] It should be noted that the time series feature extractor based on the one-dimensional convolutional neural network model can help extract important features of power generation, power consumption and energy storage nodes, reduce data dimensionality, identify patterns and abnormal situations, and implement real-time processing on edge computing devices, thereby providing beneficial effects for monitoring and control of photovoltaic construction.

[0082] Further, the vector fusion module 203 includes an initial system posterior feature vector calculation unit 203a, a perception factor calculation unit 203b, a weighting unit 203c, and a system posterior feature vector calculation unit 203d. The vector extraction module 202 is unidirectionally connected to the initial system posterior feature vector calculation unit 203a. The vector extraction module 202 sends the power time series feature vector of the power generation key node, the power time series feature vector of the power consumption key node, and the power time series feature vector of the energy storage key node to the initial system posterior feature vector calculation unit 203a.

[0083] Further, the initial system posterior feature vector calculation unit 203a is configured to calculate the initial system posterior feature vector by taking the power time series feature vector of the power generation key node, the power time series feature vector of the power consumption key node, and the power time series feature vector of the energy storage key node as the prior probability feature vector, the conditional probability feature vector, and the evidence probability feature vector.

[0084] Further, the perception factor calculation unit 203b, the weighting unit 203c, and the system posterior feature vector calculation unit 203d are sequentially connected. The perception factor calculation unit 203b is configured to calculate the transferability perception factor of the power time series feature vector of the power generation key node, the power time series feature vector of the power consumption key node, and the power time series feature vector of the energy storage key node with respect to the initial system posterior feature vector to obtain the first transferability perception factor, the second transferability perception factor, and the third transferability perception factor.

[0085] Furthermore, the weighting unit 203c is used to weight the power time-series feature vectors of key power generation nodes, key power consumption nodes, and key energy storage nodes using the first transferability sensing factor, the second transferability sensing factor, and the third transferability sensing factor as weights, respectively, to obtain the weighted power time-series feature vectors of key power generation nodes, key power consumption nodes, and key energy storage nodes.

[0086] Furthermore, the system posterior feature vector calculation unit 203d is used to calculate the system posterior feature vector by using the weighted power generation key node power time series feature vector, the weighted power consumption key node power time series feature vector, and the weighted energy storage key node power time series feature vector as prior probability feature vector, conditional probability feature vector, and evidence probability feature vector.

[0087] It should be noted that the sensing factor calculation unit 203b includes calculating the transferability sensing factors of the power time-series feature vector of the power generation key node, the power time-series feature vector of the power consumption key node, and the power time-series feature vector of the energy storage key node relative to the initial system posterior feature vector using the following optimization formula to obtain a first transferable sensing factor, a second transferable sensing factor, and a third transferable sensing factor.

[0088] The optimized formula is:

[0089]

[0090]

[0091]

[0092] Where V1 represents the power time-series feature vector of key power generation nodes. V represents the eigenvalue at the i-th position of the power time-series eigenvector of key power generation nodes. c This represents the posterior feature vector of the initial system. V1 represents the eigenvalue at the i-th position of the initial system posterior feature vector, and V2 represents the power time-series feature vector of key power consumption nodes. V1 represents the eigenvalue at the i-th position of the power time-series feature vector of key electricity consumption nodes, and V2 represents the power time-series feature vector of key energy storage nodes. Let w1 represent the eigenvalue at the i-th position of the power time-series eigenvector of key energy storage nodes, log is a logarithmic function to the base 2, and α is a weighted hyperparameter. w1 represents the first transferability sensing factor, w2 represents the second transferability sensing factor, and w3 represents the third transferability sensing factor.

[0093] In the embodiments of the present application, the transferable quantification transferable perceptual factor of the features is estimated by the uncertainty metric under domain transfer to estimate the domain uncertainty of the feature space domain to the classification target domain, and since the domain uncertainty estimation can be used to identify the feature representation that has been transferred between domains, therefore by weighting the power time sequence feature vector of the power generation key node, the power time sequence feature vector of the power consumption key node and the power time sequence feature vector of the energy storage key node respectively with the factor as the weight, it can be identified by the cross-domain alignment of the feature space domain to the classification target domain whether the feature mapping is effectively transferred between domains, thereby quantitatively perceiving the transferability of the transferable features in different feature vectors, to realize the inter-domain adaptive feature fusion, to improve the accuracy of the posterior probability distribution calculation of the system posterior feature vector.

[0094] Further, the micro-grid system judgment module 204 includes a one-way connection between the micro-grid system judgment module 204 and the system posterior feature vector calculation unit 203d. The micro-grid system judgment module 204 obtains the classification result by classifying the system posterior feature vector through the classifier. The classification result is used to indicate whether the system is unbalanced.

[0095] It should be noted that in the technical solution of the present application, the process of using an algorithm to determine whether the system is unbalanced includes: first obtaining the power values of each power generation key node, each power consumption key node and each energy storage key node transmitted by the multi-mode communication network, wherein the multi-mode communication network includes communication technologies such as 5G, HPLC, LORA and Ethernet.

[0096] By receiving the power value of the power generation node, the actual power generation capacity of photovoltaic power generation can be understood. At the same time, the power value of the power consumption node can be received to understand the actual power consumption demand. The power value of the energy storage node can be received to understand the charging and discharging situation of the energy storage system. Through real-time monitoring and analysis of these data, the supply and demand balance of the micro-grid system can be determined. If the power generation power is greater than the power consumption power, it means that there is excess power in the system, which can be stored or processed in other ways; if the power consumption power is greater than the power generation power, it may be necessary to supplement the power supply from other power sources or make adjustments.

[0097] The above-mentioned unit modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to call and execute the operations corresponding to the above-mentioned modules by the processor.

[0098] In summary, the application provides an edge computing system of multi-mode communication technology, which obtains parameter information transmitted by a multi-mode communication network; obtains power values of each power generation key node, each power consumption key node and each energy storage key node in the parameter information, the power generation key node is a node whose influence factor after node failure is greater than a first threshold value, the power consumption key node is a node whose influence factor after node failure is greater than a second threshold value, and the energy storage key node is a node whose influence factor after node failure is greater than a third threshold value; judges whether the micro-grid system of a distribution area is unbalanced based on the power values of each power generation key node, each power consumption key node and each energy storage key node, and realizes edge computing of multi-mode communication technology. The edge computing device is used to take various operation modes such as photovoltaic energy storage intelligent linkage in a new distribution area as the target, research wide-area source-grid-load-storage collaborative optimization operation technology, enrich functions such as source-source complementation, source-grid coordination, grid-load interaction and source-load interaction which are lacked in traditional source-load-storage control technology, and realize goals such as power grid safety, new energy consumption, resource optimization allocation and improvement of operation efficiency.

[0099] Embodiment 2

[0100] Reference Figures 1-3 For an embodiment of the application, a multi-mode communication technology edge computing method is provided, which includes:

[0101] Obtain parameter information transmitted by a multi-mode communication network;

[0102] Obtain power values of each power generation key node, each power consumption key node and each energy storage key node in the parameter information, the power generation key node is a node whose influence factor after node failure is greater than a first threshold value, the power consumption key node is a node whose influence factor after node failure is greater than a second threshold value, and the energy storage key node is a node whose influence factor after node failure is greater than a third threshold value;

[0103] The influence factor after node failure includes,

[0104] The power generation key node is calculated in the following manner:

[0105] η1=α1·S Q +α2·S C +α3·W Z +α4·B Y

[0106] Wherein, η1 represents the influence factor of the power generation key node after node failure, α1, α2, α3 and α4 represent influence coefficients of the power generation key node after node failure, S Q represents the number of complete communities affected by the power key node after node failure, S C represents the number of complete shopping malls affected by the power key node after node failure, W ZB represents the number of other complete buildings affected by the node failure of the power key node Y B represents the number of transformers affected by the node failure of the power key node

[0107] The influence factor calculation method of the power key node after the node failure is as follows:

[0108] η2 = β1·S + β2·M + β3·M M D X

[0109] Wherein, η2 represents the influence factor of the power key node after the node failure, β1, β2, β3 represent the influence coefficient of the power key node after the node failure, S M represents the number of small power equipment, M D represents the number of medium power equipment, M X represents the number of large power equipment;

[0110] The influence factor calculation method of the energy storage key node after the node failure is as follows:

[0111] η3 = δ1·S + δ2·M Y Y

[0112] Wherein, η3 represents the influence factor of the energy storage key node after the node failure, δ1, δ2 represent the influence coefficient of the energy storage key node after the node failure, S Y represents the number of commercial energy storage equipment, M Y represents the number of civil energy storage equipment.

[0113] In this embodiment, the influence coefficient of the power generation key node after the node failure is set to 0.25, the influence coefficient of the power key node after the node failure is set to 0.3, and the influence coefficient of the energy storage key node after the node failure is set to 0.5, but this is not limited, the coefficient value can be changed according to the demand of the technician.

[0114] In this embodiment, the first threshold is set to 55, the second threshold is set to 216, and the third threshold is set to 40, but this is not limited, the coefficient value can be changed according to the demand of the technician, the greater the threshold, the lower the precision, and the smaller the threshold, the higher the precision.

[0115] Based on the power values of each power generation key node, each power key node and each energy storage key node, it is judged whether the microgrid system of the power distribution area is unbalanced, and the edge computing of the multi-mode communication technology is realized.

[0116] ​​​In summary, the application provides an edge computing method of multi-mode communication technology, parameter information transmitted by a multi-mode communication network is acquired, power values of each power generation key node, each power consumption key node and each energy storage key node in the parameter information are acquired, the power generation key node is a node whose influence factor after node failure is greater than a first threshold value, the power consumption key node is a node whose influence factor after node failure is greater than a second threshold value, and the energy storage key node is a node whose influence factor after node failure is greater than a third threshold value, whether the micro-grid system of a distribution area is unbalanced is judged based on the power values of each power generation key node, each power consumption key node and each energy storage key node, and edge computing of multi-mode communication technology is realized. The edge computing device is used to take various operation modes such as photovoltaic energy storage intelligent linkage in a new distribution area as the target, to research wide-area source-grid-load-storage collaborative optimization operation technology, to enrich functions such as source-source complementation, source-grid coordination, grid-load interaction and source-load interaction which are lacked in traditional source-load-storage control technology, and to realize goals such as power grid safety, new energy consumption, resource optimization allocation and improvement of operation efficiency.

[0117] In one embodiment, a computer device, which can be a terminal, is provided, and an internal structure diagram of the computer device can be as shown in Figure 3 The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement an edge computing method of multi-mode communication technology. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or can be a key, trackball or touchpad arranged on the shell of the computer device, or can be an external keyboard, touchpad or mouse, etc.

[0118] In one embodiment, a computer readable storage medium having a computer program stored thereon is provided, and the computer program is executed by a processor to implement the following steps:

[0119] Acquiring parameter information transmitted by a multi-mode communication network;

[0120] The power values of the power generation key nodes, the power consumption key nodes and the energy storage key nodes are obtained in the parameter information, the power generation key node is a node whose influence factor after node failure is greater than a first threshold value, the power consumption key node is a node whose influence factor after node failure is greater than a second threshold value, and the energy storage key node is a node whose influence factor after node failure is greater than a third threshold value;

[0121] Based on the power values of the power generation key nodes, the power consumption key nodes and the energy storage key nodes, it is determined whether the micro-grid system of the power distribution area is unbalanced, and edge computing of the multi-mode communication technology is realized.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

[0123] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages, such as object-oriented programming language Java and interpreted scripting language JavaScript.

[0124] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems) and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The functions specified in one flow or multiple flows and / or blocks

[0125] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The flow or flows and / or blocks Figure 1 The flow or flows and / or blocks

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 The flow or flows and / or blocks Figure 1 The flow or flows and / or blocks

[0127] Although preferred embodiments of the application have been described, those skilled in the art will recognize that additional modifications and variations can be made thereto without departing from the spirit and scope of the application. It is therefore intended that the appended claims cover all such modifications and variations as fall within the scope of the application.

[0128] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore intended that the present application be construed as including all such modifications and variations as fall within the scope of the applicant's contribution to the art.

Claims

1. A method for edge computing of multi-modal communication technology, characterized in that: The application relates to a multi-mode communication network edge computing method and device. Parameter information transmitted by a multi-mode communication network is acquired; Power values of each power generation key node, each power consumption key node and each energy storage key node in the parameter information are acquired, the power generation key node is a node whose influence factor after node failure is greater than a first threshold value, the power consumption key node is a node whose influence factor after node failure is greater than a second threshold value, and the energy storage key node is a node whose influence factor after node failure is greater than a third threshold value; Based on the power values of the power generation key node, the power consumption key node and the energy storage key node, whether a micro-grid system of a power distribution area is unbalanced is judged, and edge computing of the multi-mode communication technology is realized.

2. The edge computing method of multi-modal communication technology of claim 1, wherein: The influence factor after node failure includes The power generation key node is calculated in the following manner: η1 = α1 · S Q + α2 · S C + α3 · W Z + α4 · B Y Wherein, η1 represents the influence factor of the power key node after the node failure, α1, α2, α3, α4 represent the influence coefficient of the power key node when the node fails, S Q represents the number of complete communities affected by the power key node after the node failure, C represents the number of complete markets affected by the power key node after the node failure, Z represents the number of other complete buildings affected by the power key node after the node failure, and Y represents the number of transformers affected by the power key node after the node failure. The power consumption key node is calculated in the following manner: η2 = β1 · S M + β2 · M D + β3 · M X Wherein, η2 represents the influence factor of the power key node after the node failure, β1, β2, β3 represent the influence coefficient of the power key node when the node fails, S M represents the number of small power equipment, M D represents the number of medium-sized power equipment, M X represents the number of large power equipment; The energy storage key node is calculated in the following manner: η3 = δ1 • S Y + δ2 • M Y Wherein, η3 represents the energy storage key node as the node failure impact factor, δ1, δ2 represents the influence coefficient of the energy storage key node as the node failure, S Y represents the number of commercial energy storage devices, M Y represents the number of civil energy storage devices.

3. An edge computing system for multi-modal communication technology, characterized by: The device comprises a communication unit (100) and an edge computing unit (200), The communication unit (100) is used for receiving power values of each power generation key node, each power consumption key node and each energy storage key node transmitted by a multi-mode communication network; The edge computing unit (200) is used for judging whether a micro-grid system of a power distribution area is unbalanced based on the power values of the power generation key node, the power consumption key node and the energy storage key node.

4. The multi-modal communication technology edge computing system of claim 3, wherein: The edge computing unit (200) comprises a vector arrangement module (201), a vector extraction module (202), a vector fusion module (203) and a micro-grid system judgment module (204), The vector arrangement module (201), the vector extraction module (202), the vector fusion module (203) and the micro-grid system judgment module (204) are sequentially and unidirectionally connected, the vector arrangement module (201) is used for arranging the power values of each power generation key node, each power consumption key node and each energy storage key node into a power generation key node power time sequence input vector, a power consumption key node power time sequence input feature vector and an energy storage key node power time sequence input vector according to a sample dimension, and inputting the arranged results into the vector extraction module (202); The vector extraction module (202) is used for extracting a power generation key node power time sequence feature vector, a power consumption key node power time sequence feature vector and an energy storage key node power time sequence feature vector from the power generation key node power time sequence input vector, the power consumption key node power time sequence input feature vector and the energy storage key node power time sequence input vector, and transmitting the extracted feature vectors into the vector fusion module (203); The vector fusion module (203) is used for combining a Bayesian probability model to fuse the power generation key node power time sequence feature vector, the power consumption key node power time sequence feature vector and the energy storage key node power time sequence feature vector to obtain a system posterior feature vector, and transmitting the verified feature vector into the micro-grid system judgment module (204); The micro-grid system judgment module (204) is used for judging whether the micro-grid system of the power distribution area is unbalanced based on the system posterior feature vector.

5. The edge computing system of multi-modal communication technology of claim 4, wherein: The vector extraction module (202) comprises a time sequence feature extractor based on a one-dimensional convolutional neural network model, which is used for respectively extracting the power time sequence input vector of the power generation key node, the power time sequence input feature vector of the power consumption key node and the power time sequence input vector of the energy storage key node to obtain a power time sequence feature vector of the power generation key node, a power time sequence feature vector of the power consumption key node and a power time sequence feature vector of the energy storage key node.

6. The edge computing system of multi-modal communication technology of claim 5, wherein: The vector fusion module (203) comprises an initial system posterior feature vector calculation unit (203a), a perception factor calculation unit (203b), a weighting unit (203c) and a system posterior feature vector calculation unit (203d), The initial system posterior feature vector calculation unit (203a) is unidirectionally connected with the vector extraction module (202), and the vector extraction module (202) sends the power time sequence feature vector of the power generation key node, the power time sequence feature vector of the power consumption key node and the power time sequence feature vector of the energy storage key node to the initial system posterior feature vector calculation unit (203a). The initial system posterior feature vector calculation unit (203a) is used for taking the power time sequence feature vector of the power generation key node, the power time sequence feature vector of the power consumption key node and the power time sequence feature vector of the energy storage key node as a prior probability feature vector, a conditional probability feature vector and an evidence probability feature vector to calculate an initial system posterior feature vector. The perception factor calculation unit (203b), the weighting unit (203c) and the system posterior feature vector calculation unit (203d) are sequentially connected, the perception factor calculation unit (203b) is used for calculating the transferability perception factors of the power time sequence feature vector of the power generation key node, the power time sequence feature vector of the power consumption key node and the power time sequence feature vector of the energy storage key node relative to the initial system posterior feature vector to obtain a first transferability perception factor, a second transferability perception factor and a third transferability perception factor. The weighting unit (203c) is used for weighting the power time sequence feature vector of the power generation key node, the power time sequence feature vector of the power consumption key node and the power time sequence feature vector of the energy storage key node by taking the first transferability perception factor, the second transferability perception factor and the third transferability perception factor as weights to obtain a weighted power time sequence feature vector of the power generation key node, a weighted power time sequence feature vector of the power consumption key node and a weighted power time sequence feature vector of the energy storage key node. The system posterior feature vector calculation unit (203d) is used for taking the weighted power time sequence feature vector of the power generation key node, the weighted power time sequence feature vector of the power consumption key node and the weighted power time sequence feature vector of the energy storage key node as a prior probability feature vector, a conditional probability feature vector and an evidence probability feature vector to calculate the system posterior feature vector.

7. The edge computing system of multi-modal communication technology of claim 6, wherein: The perception factor calculation unit (203b) comprises, The transferability perception factors of the power time sequence feature vectors of the power generation key nodes, the power time sequence feature vectors of the power consumption key nodes and the power time sequence feature vectors of the energy storage key nodes relative to the initial system posterior feature vector are calculated by using an optimization formula to obtain a first transferability perception factor, a second transferability perception factor and a third transferability perception factor. The optimization formula is as follows: wherein V1 represents the power time series feature vector of the generation critical node, represents the feature value of the i-th position of the power time series feature vector of the generation critical node, c represents the initial system posterior feature vector, represents the feature value of the i-th position of the initial system posterior feature vector, V2 represents the power time series feature vector of the consumption critical node, represents the feature value of the i-th position of the power time series feature vector of the consumption critical node, V3 represents the power time series feature vector of the energy storage critical node, represents the feature value of the i-th position of the power time series feature vector of the energy storage critical node, log is a logarithmic function with base 2, and a is a weighting hyperparameter, w1 represents the first transferability perception factor, w2 represents the second transferability perception factor, and w3 represents the third transferability perception factor.

8. The edge computing system of multi-modal communication technology of claim 7, wherein: The microgrid system judgment module (204) is unidirectionally connected with the system posterior feature vector calculation unit (203d), and the microgrid system judgment module (204) classifies the system posterior feature vector by using a classifier to obtain a classification result, wherein the classification result is used to indicate whether the system is unbalanced. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method in any one of claims 1-2.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1-2.

Images