Identity authentication method for smart power distribution network and related device

Abstract

The application provides an identity authentication method for a smart power distribution network and related equipment. A plurality of auxiliary verifiers receives a feedback signal sent by a regional metering management terminal, performs identity authentication on at least one power consumption terminal based on power consumption request information, obtains and sends a plurality of first identity authentication results to the regional metering management terminal, and then the regional metering management terminal processes the obtained evaluation indexes through an entropy weight algorithm to obtain a first weight. By introducing the evaluation indexes affecting authentication, a weight setting matched with the current performance of each auxiliary verifier is obtained. Then, based on the obtained historical credit value and the first weight, the weight of each auxiliary verifier is updated to obtain a second weight corresponding to each auxiliary verifier, and identity authentication is performed on the at least one power consumption terminal to obtain and determine whether to pass the power consumption request according to the second identity authentication result. Thus, accurate and reliable identity authentication can be realized, thereby ensuring the safe and stable operation of the smart power distribution network.

Description

Technical Field

[0001] This application relates to the field of power distribution security technology, and in particular to an identity authentication method and related equipment for smart power distribution networks. Background Technology

[0002] To meet the demand for efficient information exchange, smart distribution networks often use wireless communication for flexible networking. However, due to the inherent broadcast characteristics of wireless communication links, smart distribution networks are highly vulnerable to potential attack threats, such as unauthorized access, data tampering, deception, and denial-of-service attacks, which can affect the safe and stable operation of the distribution network. Summary of the Invention

[0003] In view of this, the purpose of this application is to propose an identity authentication method and related equipment for smart distribution networks to solve the above-mentioned technical problems.

[0004] To achieve the above objectives, the first aspect of this application provides an identity authentication method for smart distribution networks, applied to an identity authentication system for smart distribution networks, the system comprising at least one electricity user terminal, multiple auxiliary authenticators, and a regional metering management terminal, the method comprising:

[0005] The plurality of auxiliary verifiers receive feedback signals sent by the regional metering management terminal, perform identity authentication on the at least one electricity terminal based on the feedback signals, obtain a plurality of first identity authentication results corresponding to the plurality of auxiliary verifiers, and send the plurality of first identity authentication results to the regional metering management terminal. The feedback signal is a signal generated by the regional metering management terminal based on the electricity request information sent by the at least one electricity terminal.

[0006] The regional metering management terminal receives the multiple first identity authentication results and obtains the evaluation indicators corresponding to the multiple auxiliary verifiers. Based on the evaluation indicators, it processes them through an entropy weight algorithm to obtain the first weight corresponding to each auxiliary verifier at the current time.

[0007] The regional metering management terminal obtains the historical reputation value corresponding to each auxiliary verifier, updates the weight of each auxiliary verifier based on the historical reputation value and the first weight, obtains the second weight corresponding to each auxiliary verifier, and performs identity authentication on the at least one electricity terminal based on the second weight and the plurality of first identity authentication results to obtain the second identity authentication result. Based on the second identity authentication result, it determines whether the electricity request information is approved.

[0008] Optionally, obtaining the historical reputation value corresponding to each auxiliary validator includes:

[0009] Obtain the quality inspection records corresponding to each auxiliary verifier;

[0010] Based on the reputation evaluation result corresponding to each auxiliary validator, the historical reputation value corresponding to each auxiliary validator is obtained through the Gompertz function.

[0011] Optionally, obtaining the quality inspection record corresponding to each auxiliary verifier includes:

[0012] Obtain the identity authentication accuracy rate for each auxiliary verifier, as well as the average identity authentication accuracy rate;

[0013] The identity authentication accuracy rate corresponding to each auxiliary verifier is compared with the average identity authentication accuracy rate to obtain the comparison results.

[0014] In response to determining that a comparison result corresponding to an auxiliary verifier indicates that the identity authentication accuracy rate is greater than the average identity authentication accuracy rate, the number of good performance records for the auxiliary verifier corresponding to the comparison result is increased; or,

[0015] In response to determining that there exists an auxiliary verifier whose comparison result is that the identity authentication accuracy is less than or equal to the average identity authentication accuracy, the number of records of poor performance of the auxiliary verifier corresponding to the comparison result is increased.

[0016] The quality inspection record is obtained by using a linear interpolation function to calculate the number of good performance records and the number of bad performance records of the auxiliary verifier corresponding to the comparison results.

[0017] Optionally, the feedback signal includes channel state information;

[0018] The step of authenticating the identity of the at least one power-consuming terminal based on the feedback signal to obtain multiple first identity authentication results corresponding to the multiple auxiliary verifiers includes:

[0019] The channel state information is input into a pre-trained identity authentication model, and the identity authentication model is used to authenticate the channel state information to obtain multiple first identity authentication results corresponding to the multiple auxiliary verifiers.

[0020] Optionally, the training process of the identity authentication model includes:

[0021] Acquire training data and build a pre-trained model;

[0022] The cross-entropy loss function is determined based on the training data, wherein the cross-entropy loss function is specifically:

[0023]

[0024] in, Represented as the cross-entropy loss function, Indicates the true label, This represents the prediction label, k represents the k-th power terminal, K represents the number of power terminals, and T k This indicates that the current prediction result is that the electricity request information belongs to electricity terminal k, and m represents the m-th auxiliary verifier;

[0025] The training data is input into the pre-trained model, and the cross-entropy loss function is minimized. The pre-trained model is continuously trained and adjusted to obtain a trained pre-trained model, which is then used as the identity authentication model.

[0026] Optionally, the step of processing the evaluation index using an entropy weight algorithm to obtain the first weight corresponding to each auxiliary validator at the current time includes:

[0027] Construct an indicator judgment matrix based on the evaluation indicators corresponding to each auxiliary validator;

[0028] Based on the index judgment matrix, the index entropy value is processed using the entropy weighting function to obtain the index entropy value corresponding to each auxiliary verifier.

[0029] The difference between the preset parameter values ​​and the entropy value of each indicator is calculated to obtain the difference result.

[0030] The difference result is summed to obtain the first summation result;

[0031] The first ratio processing result is obtained by comparing the difference processing result with the first sum processing result.

[0032] The first weight is obtained by weighting and summing the result of the first ratio processing with the evaluation index.

[0033] Optionally, the step of updating the weight of each auxiliary validator based on the historical reputation value and the first weight to obtain a second weight corresponding to each auxiliary validator includes:

[0034] Obtain the measurement parameter corresponding to the first weight, the second weight of the previous time at the current time, and the measurement parameter corresponding to the second weight of the previous time at the current time;

[0035] The first weighted sum is obtained by using the measurement parameters to perform a weighted summation on the second weight of the previous time and the first weight of the current time.

[0036] The historical reputation values ​​of each auxiliary validator are summed to obtain the second summation result.

[0037] The historical reputation value corresponding to each auxiliary validator is compared with the second summation result to obtain the second ratio processing result for each auxiliary validator.

[0038] The second ratio processing result corresponding to each auxiliary validator and the first weighted sum processing result are multiplied to obtain the second weight corresponding to each auxiliary validator.

[0039] Optionally, the second authentication result includes legitimate terminals and illegitimate terminals;

[0040] The step of authenticating the at least one power-consuming terminal based on the second weight and the plurality of first identity authentication results to obtain a second identity authentication result includes:

[0041] The second weight corresponding to each auxiliary validator is normalized to obtain the normalization result for each auxiliary validator.

[0042] The normalized result corresponding to each auxiliary verifier is used to perform a weighted summation with multiple first identity authentication results to obtain the second weighted summation result;

[0043] Retrieve the tag corresponding to the second weighted summation processing result, determine the at least one power terminal as the legitimate terminal or the illegitimate terminal based on the tag, and use the at least one power terminal as the legitimate terminal or the illegitimate terminal as the second identity authentication result.

[0044] Based on the same inventive concept, the second aspect of this application provides an identity authentication system for smart distribution networks, including at least one electricity terminal, multiple auxiliary verifiers and a regional metering management terminal.

[0045] The plurality of auxiliary verifiers are configured to receive feedback signals sent by the regional metering management terminal, perform identity authentication on the at least one electricity terminal based on the feedback signals, obtain a plurality of first identity authentication results corresponding to the plurality of auxiliary verifiers, and send the plurality of first identity authentication results to the regional metering management terminal. The feedback signals are signals generated by the regional metering management terminal based on the electricity request information sent by the at least one electricity terminal.

[0046] The regional metering management terminal is configured to receive the plurality of first identity authentication results and obtain evaluation indicators corresponding to the plurality of auxiliary verifiers. Based on the evaluation indicators, it processes them using an entropy weight algorithm to obtain a first weight corresponding to each auxiliary verifier at the current time. The regional metering management terminal obtains the historical reputation value corresponding to each auxiliary verifier and updates the weight of each auxiliary verifier based on the historical reputation value and the first weight to obtain a second weight corresponding to each auxiliary verifier. Based on the second weight and the plurality of first identity authentication results, it performs identity authentication on the at least one electricity terminal to obtain a second identity authentication result. Based on the second identity authentication result, it determines whether the electricity request information is approved.

[0047] Based on the same inventive concept, a third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in the first aspect.

[0048] As can be seen from the above, the identity authentication method and related equipment for smart distribution networks provided in this application involve multiple auxiliary verifiers receiving feedback signals from a regional metering management terminal, authenticating at least one electricity terminal based on electricity request information, obtaining multiple first identity verification results corresponding to the multiple auxiliary verifiers, and sending the multiple first identity verification results to the regional metering management terminal. By introducing multiple auxiliary verifiers as task-sharing entities for the regional metering management terminal, the processing pressure on the regional metering management terminal caused by a surge in electricity terminals can be avoided, and the situation of authentication failure due to relying solely on the regional metering management terminal for single-point authentication can be avoided. Then, the regional metering management terminal obtains the evaluation indicators corresponding to the multiple auxiliary verifiers, processes them based on the evaluation indicators using an entropy weight algorithm, obtains the first weight corresponding to each auxiliary verifier at the current moment, and obtains a weight setting that matches the current performance of each auxiliary verifier by introducing evaluation indicators that affect authentication. The system acquires the historical reputation value of each auxiliary verifier and updates the weight of each auxiliary verifier based on the historical reputation value and the first weight, resulting in a second weight corresponding to each auxiliary verifier. By reasonably and dynamically adjusting the importance of each auxiliary verifier in the final decision aggregation stage based on its historical performance and current performance, the system obtains the second weight corresponding to each auxiliary verifier. Based on the second weight and multiple first identity authentication results, at least one power terminal is authenticated to obtain a second identity authentication result. The system determines whether the power request is approved based on the second identity authentication result. Since the second weight can dynamically reflect its importance in the final decision aggregation stage and can adapt to changes or fluctuations caused by the instability of the propagation environment or propagation nodes in the smart distribution network, setting the second weight as the weight of the first identity authentication result to obtain the second identity authentication result can make the obtained second identity authentication result more accurate, thereby ensuring the safe and stable operation of the smart distribution network. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart of an identity authentication method for smart distribution networks according to an embodiment of this application;

[0051] Figure 2 This is a schematic diagram of an identity authentication scenario for a smart distribution network, as described in an embodiment of this application.

[0052] Figure 3This is a structural block diagram of an identity authentication system for smart power distribution networks according to an embodiment of this application;

[0053] Figure 4 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0055] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0056] It is understood that before using the technical solutions of the various embodiments in this application, users will be informed of the type, scope of use, and usage scenarios of the personal information involved in an appropriate manner, and user authorization will be obtained.

[0057] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media performing the operations described in this application.

[0058] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0059] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this application. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this application.

[0060] In related technologies, the legitimacy of power terminals is verified through upper-layer cryptographic mechanisms. However, with the improvement of advanced computing power, brute-force attacks have become possible. Moreover, the entities responsible for communication and authentication in smart distribution networks are often wireless sensor nodes or smart terminal devices with extremely limited computing power, energy, and storage. This can lead to situations where they cannot bear the high computational overhead and complexity of upper-layer authentication. At the same time, the additional processing delays caused by encryption and decryption operations further restrict the timeliness of authentication. Therefore, traditional cryptographic methods that rely on computational security are not suitable for the deployment and implementation of authentication in smart distribution networks.

[0061] The authentication of smart distribution networks relies on the extraction and rational utilization of channel characteristics. Strong electromagnetic noise and uncertain channel disturbances often occur, which can lead to the failure of centralized single-point authentication. Moreover, relying solely on the channel estimation results of a single node for authentication will not guarantee the accuracy of authentication. In addition, the surge in the number of connected power terminals will also increase the processing pressure of authentication, and may even create a bottleneck.

[0062] Furthermore, authentication methods for smart distribution networks can be divided into threshold-based authentication strategies and threshold-free authentication strategies based on machine learning. For large-scale power terminal access in smart distribution networks, threshold-based authentication strategies face the problem of difficulty in determining multiple decision boundaries. Moreover, the dynamic fluctuations of wireless channels and the additional impact of noise will exacerbate this problem to some extent. Existing machine learning-based authentication relies on a single isolated node for model training and classification. However, since all power terminals are connected to an authentication node and authentication is performed in a one-to-many mode, the authentication node must always remain available and highly reliable. However, this is difficult to guarantee in real smart distribution network scenarios. On the one hand, channel observation and analysis of multiple devices will cause a surge in processing pressure at the central node, leading to bottlenecks or unavoidable single-point failures.

[0063] This application provides an identity authentication method for smart distribution networks, applied to an identity authentication system for smart distribution networks. The system includes at least one electricity user terminal, multiple auxiliary verifiers, and a regional metering management terminal. By introducing multiple auxiliary verifiers as task-sharing entities for the regional metering management terminal, the method avoids the processing pressure on the regional metering management terminal caused by a surge in electricity user terminals, and avoids authentication failures due to relying solely on the regional metering management terminal for single-point authentication. Furthermore, by introducing evaluation indicators affecting authentication, a weight setting matching the current performance of each auxiliary verifier is obtained. Simultaneously, the historical reputation value corresponding to each auxiliary verifier is acquired, and the weight of each auxiliary verifier is updated based on the historical reputation value and a first weight, enabling authentication to be performed according to... Based on the historical performance and current performance of each auxiliary verifier, its importance in the final decision aggregation stage is reasonably and dynamically adjusted. This involves assigning a second weight to each auxiliary verifier and then using this second weight along with multiple first identity authentication results to authenticate at least one power terminal, obtaining a second identity authentication result. The power request is then approved based on this second identity authentication result. Since the second weight can dynamically reflect its importance in the final decision aggregation stage and can adapt to changes or fluctuations caused by the instability of the propagation environment or propagation nodes in the smart distribution network, setting the second weight as the weight of the first identity authentication result makes the obtained second identity authentication result more accurate, thereby ensuring the safe and stable operation of the smart distribution network.

[0064] like Figure 1 As shown, the method in this embodiment includes:

[0065] Step 101: The plurality of auxiliary verifiers receive feedback signals sent by the regional metering management terminal, perform identity authentication on the at least one electricity terminal based on the feedback signals, obtain a plurality of first identity authentication results corresponding to the plurality of auxiliary verifiers, and send the plurality of first identity authentication results to the regional metering management terminal. The feedback signal is a signal generated by the regional metering management terminal based on the electricity request information sent by the at least one electricity terminal.

[0066] In this step, the auxiliary verifier is an intelligent auxiliary device with low-power wireless communication and certain computing capabilities. The regional metering management terminal is a central connection point via a wireless link terminal, computer, or communication equipment. Typically, one regional metering management terminal is deployed within a region to perform electricity consumption data transmission and identity authentication for electricity-using terminals. The first identity authentication result represents the preliminary identity authentication result and serves as the data basis for subsequent further identity authentication.

[0067] By introducing multiple auxiliary verifiers within a region as task-sharing entities for regional metering management terminals to collaboratively execute the identity authentication process, the processing pressure on regional metering management terminals caused by the surge in the number of electricity terminals is alleviated. This avoids the occurrence of single-point collapse, single-point failure, or processing bottlenecks that may occur when relying solely on regional metering management terminals. Multiple auxiliary verifiers are deployed in different geographical locations within the same region to perform multi-directional channel parallel processing.

[0068] In addition, an auxiliary verifier is introduced, which no longer relies on the key distribution and encryption / decryption algorithms of a trusted third party (TTP), but directly uses the wireless channel fingerprint of the power terminal for identity authentication. The feedback signal includes the wireless channel fingerprint, thereby avoiding the additional processing delay caused by encryption and decryption operations and ensuring the timeliness of identity authentication.

[0069] like Figure 2 As shown, the system includes: smart meter 1 to be authenticated, smart meter k...smart meter K, illegal electricity thief i (i.e., electricity user), regional metering control and concentrator (i.e., regional metering management terminal), and a data processing center located at a remote power supplier. An additional M auxiliary authenticator nodes (auxiliary authenticator 1, auxiliary authenticator 2, auxiliary authenticator m...auxiliary authenticator M) are introduced as task-sharing entities for the regional metering control and concentrator to collaboratively complete the authentication of the same electricity user. Furthermore, instead of relying on a trusted third party for key distribution and encryption / decryption algorithms, the system directly utilizes the wireless channel fingerprints of each meter for identity verification.

[0070] Step 102: The regional metering management terminal receives the multiple first identity authentication results and obtains the evaluation indicators corresponding to the multiple auxiliary verifiers. Based on the evaluation indicators, it processes them using an entropy weight algorithm to obtain the first weight corresponding to each auxiliary verifier at the current time.

[0071] In this step, each auxiliary verifier will have a corresponding first identity authentication result for the power-consuming terminal. The first weight is used to measure the importance of the local decision opinion of the corresponding auxiliary verifier to the final decision aggregation. The evaluation index is the channel characteristics of the transmission link, which is used to evaluate the current performance of the auxiliary verifier in identity authentication judgment.

[0072] Therefore, by introducing evaluation metrics and using the entropy weight algorithm to obtain weight settings that match the current performance of each auxiliary validator, the entropy weight algorithm eliminates the need for subjective assignment of the importance of the evaluation metrics, thus reducing the influence of subjectivity on the obtained first weight.

[0073] Step 103: The regional metering management terminal obtains the historical reputation value corresponding to each auxiliary verifier, updates the weight of each auxiliary verifier based on the historical reputation value and the first weight, obtains the second weight corresponding to each auxiliary verifier, and performs identity authentication on the at least one electricity terminal based on the second weight and the plurality of first identity authentication results to obtain the second identity authentication result, and determines whether the electricity request information is approved based on the second identity authentication result.

[0074] In this step, considering the potential additional noise interference and instability of various device nodes in the smart distribution network, a dynamic update mechanism based on historical reputation value and first weight is introduced. This mechanism adjusts the weight allocation according to the adaptability of each auxiliary verifier to maximize the performance gain of collaborative decision-making under multiple consecutive authentication time slots.

[0075] Historical reputation values ​​indicate the long-term impression / trust level of regional metrology management terminals towards each auxiliary verifier. The accumulation of positive behaviors will lead to improved reputation, while the occurrence of negative behaviors will damage the previous impression.

[0076] Compared to traditional static weighted voting, a dynamic update mechanism based on historical reputation value and first weight is introduced. This allows for the reasonable and dynamic adjustment of the importance of each auxiliary verifier in the final decision aggregation stage based on its historical performance and current performance. It can adapt to changes or fluctuations caused by the propagation environment or node instability in the smart distribution network, thereby achieving accurate and reliable identity authentication and ensuring the safe and stable operation of the smart distribution network.

[0077] The second authentication result represents the final authentication result.

[0078] Through the above scheme, multiple auxiliary verifiers receive feedback signals from the regional metering management terminal, authenticate at least one electricity terminal based on the electricity request information, obtain multiple first authentication results corresponding to the multiple auxiliary verifiers, and send the multiple first authentication results to the regional metering management terminal. By introducing multiple auxiliary verifiers as task-sharing entities for the regional metering management terminal, the processing pressure on the regional metering management terminal due to a surge in electricity terminals can be avoided, and the authentication failure situation caused by relying solely on the regional metering management terminal for single-point authentication can be avoided. Then, the regional metering management terminal obtains the evaluation indicators corresponding to the multiple auxiliary verifiers, processes them based on the evaluation indicators using the entropy weight algorithm, obtains the first weight corresponding to each auxiliary verifier at the current time, and obtains the weight settings that match the current performance of each auxiliary verifier by introducing evaluation indicators that affect authentication. At the same time, the historical data corresponding to each auxiliary verifier is also obtained. The system uses a reputation value and updates the weights of each auxiliary verifier based on its historical reputation value and a first weight to obtain a second weight corresponding to each auxiliary verifier. This allows for a reasonable and dynamic adjustment of the importance of each auxiliary verifier in the final decision aggregation stage based on its historical performance and current performance. The second weight is then used to authenticate at least one power terminal based on the second weight and multiple first authentication results to obtain a second authentication result. The power request is then approved based on the second authentication result. Since the second weight dynamically reflects its importance in the final decision aggregation stage and can adapt to changes or fluctuations caused by the instability of the propagation environment or propagation nodes in the smart distribution network, using the second weight as the weight of the first authentication result to obtain the second authentication result makes the second authentication result more accurate, thereby ensuring the safe and stable operation of the smart distribution network.

[0079] In some embodiments, step 103, obtaining the historical reputation value corresponding to each auxiliary verifier, includes:

[0080] Step A1: Obtain the quality inspection record corresponding to each auxiliary verifier.

[0081] Step A2: Based on the reputation evaluation result corresponding to each auxiliary validator, the historical reputation value corresponding to each auxiliary validator is obtained through the Gompertz function.

[0082] In the above scheme, the following procedure is performed for each auxiliary verifier:

[0083] By inputting the reputation evaluation result corresponding to the auxiliary validator into the Gompertz function, the historical reputation value of the auxiliary validator under the first T authentication time slots can be obtained, which can be represented as follows:

[0084]

[0085] Where m represents the m-th auxiliary validator, Repu m This represents the historical reputation value of the m-th auxiliary validator. Let represent the quality detection record of the m-th auxiliary verifier, a represent the first parameter of the exponential function, e represent the constant of the exponential function, b represent the second parameter of the exponential function, and c represent the third parameter of the exponential function.

[0086] a, b, and c can be set according to specific circumstances. Here, a is preferably 1, b is preferably 2.5, and c is preferably 5.5.

[0087] The Gompertz function can be used to establish a trust model, and it has the characteristics of non-linear growth, clear upper and lower limits, and strong curve fitting ability, which makes the obtained historical reputation value more accurate.

[0088] In some embodiments, step A1 includes:

[0089] Step A11: Obtain the identity authentication accuracy rate for each auxiliary verifier, as well as the average identity authentication accuracy rate.

[0090] Step A12: Compare the identity authentication accuracy rate of each auxiliary verifier with the average identity authentication accuracy rate to obtain the comparison results.

[0091] Step A13: In response to determining that there exists an auxiliary verifier whose comparison result shows the identity authentication accuracy rate is greater than the average identity authentication accuracy rate, the number of good performance records for the auxiliary verifier corresponding to the comparison result is increased. Alternatively,

[0092] Step A14: In response to determining that there exists an auxiliary verifier whose comparison result is that the identity authentication accuracy is less than or equal to the average identity authentication accuracy, the number of bad performance records of the auxiliary verifier corresponding to the comparison result is increased.

[0093] Step A15: Based on the number of good performance records and the number of bad performance records of the auxiliary verifier corresponding to the comparison results, the quality inspection record is obtained through a linear interpolation function.

[0094] In the above scheme, in order to evaluate the long-term performance of each auxiliary verifier, a reputation accumulation based on quality detection is introduced. Authentication is performed in time slots, that is, in each time slot, the auxiliary verifier intercepts and identifies a fixed number of data packets. For each authentication time slot, only auxiliary verifiers whose identity authentication accuracy exceeds the average performance will bring positive benefits to the final decision and pass the quality detection, while auxiliary verifiers whose identity authentication accuracy does not reach the average accuracy cannot participate in the collaborative authentication in this time slot.

[0095] The identity authentication accuracy rate of each auxiliary verifier is compared with the average identity authentication accuracy rate. As authentication proceeds, each auxiliary verifier accumulates corresponding quality inspection records. If the identity authentication accuracy rate of an auxiliary verifier is greater than the average identity authentication accuracy rate, it means that the auxiliary verifier passes the quality inspection in the current time slot, and the number of good performance records for the auxiliary verifier is incremented by 1. If the identity authentication accuracy rate of an auxiliary verifier is less than or equal to the average identity authentication accuracy rate, it means that the auxiliary verifier fails the quality inspection in the current time slot, and the number of bad performance records for the auxiliary verifier is incremented by 1.

[0096] Based on the number of good performance records and the number of bad performance records, the inspection records are integrated using a linear interpolation function to obtain quality inspection records, which are used to represent long-term reputation evaluation results, as follows:

[0097]

[0098] Where m represents the m-th auxiliary verifier, This represents the quality inspection record corresponding to the m-th auxiliary validator, where γ represents the weight. This represents the number of good performance records for the m-th auxiliary validator. This represents the number of times the m-th auxiliary validator recorded poor performance.

[0099] The weight γ is set in the range of (0, 0.5).

[0100] By integrating the number of good performance records and the number of bad performance records corresponding to the same auxiliary validator through a linear interpolation function, the resulting quality inspection records can more accurately represent the long-term reputation evaluation results.

[0101] In some embodiments, the feedback signal includes channel state information.

[0102] In step 101, the step of authenticating the identity of the at least one power-consuming terminal based on the feedback signal to obtain multiple first identity authentication results corresponding to the multiple auxiliary verifiers includes:

[0103] The channel state information is input into a pre-trained identity authentication model, and the identity authentication model is used to authenticate the channel state information to obtain multiple first identity authentication results corresponding to the multiple auxiliary verifiers.

[0104] In the above scheme, the feedback signal includes Channel State Information (CSI). The Channel State Information is the channel attribute of the communication link between the power user terminal and the auxiliary verifier. It describes the signal attenuation factor on each transmission path, i.e., the channel response matrix, which can serve as a unique identifier for the power user terminal.

[0105] The channel response matrix (i.e., channel state information) extracted under Multiple Input Multiple (MIMO) conditions is mapped into a two-dimensional image in terms of data format. This image serves as the feature input for convolutional neural networks (CNNs) (i.e., the authentication model). The convolution operation in CNNs has the characteristic of "weight sharing," which can effectively reduce the number of network parameters, thereby reducing overfitting and risk. Through the stacking of multiple convolutional layers and nonlinear activation functions, CNNs can automatically extract more abstract and deeper features layer by layer, and ultimately establish a mapping function relationship between the location of the power terminal, the physical layer features of the channel (i.e., channel state information), and the identity identifier of the power terminal, thus making the obtained first authentication result more accurate.

[0106] In some embodiments, the training process of the identity authentication model includes:

[0107] Step B1: Obtain training data and build a pre-trained model.

[0108] Step B2, determine the cross-entropy loss function based on the training data, wherein the cross-entropy loss function is specifically:

[0109]

[0110] in, Represented as the cross-entropy loss function, Indicates the true label, This represents the prediction label, k represents the k-th power terminal, K represents the number of power terminals, and T k This indicates that the current prediction result is that the electricity request information belongs to the electricity terminal k, and m represents the m-th auxiliary verifier.

[0111] Step B3: Input the training data into the pre-trained model, and minimize the cross-entropy loss function. Continuously train and adjust the pre-trained model to obtain a trained pre-trained model, and use the trained pre-trained model as the identity authentication model.

[0112] In the above scheme, before training the pre-trained model, the original channel state information is preprocessed. First, normalization is performed using max-min normalization to map the input values ​​to the range [0, 1], thereby improving the learning efficiency of the convolutional neural network. Then, the features are labeled. Corresponding terminal identification tags are added to the instantaneous channel state information collected at multiple time points, and one-hot encoding is used to encode the tags, so that the input data meets the data input format requirements of the convolutional neural network.

[0113] The preprocessed channel state information is input into the pre-trained model for training. Forward propagation yields the corresponding predicted labels, which are compared with the true labels to calculate the model's cross-entropy loss function. With the goal of minimizing the cross-entropy loss function, backpropagation iteratively updates the network parameters of the pre-trained model, thereby learning the optimal network parameters and obtaining the final identity authentication model.

[0114] The identity authentication model corresponding to each auxiliary validator has a structure of 3 convolutional layers, 1 pooling layer, and 2 fully connected layers.

[0115] In addition, each convolutional layer is followed by a batch normalization (BN) layer and a rectified linear unit (Re-LU) activation layer. Each batch normalization layer normalizes the same-dimensional features of a batch of samples during network training, accelerating model training and improving accuracy. Since channel state information is non-linearly separable, the introduction of the activation function provides the network with additional non-linear modeling and learning capabilities. Pooling layers are mainly used to compress network parameters, maintaining scale invariance while removing irrelevant redundant information. The last fully connected layer uses a normalized exponential function (Soft-max) layer to map all predicted outputs of the network to probabilities in the range [0, 1], which facilitates the subsequent implementation of soft-weighted voting.

[0116] In some embodiments, step 102, which involves processing the evaluation index using an entropy weight algorithm to obtain the first weight corresponding to each auxiliary validator at the current time, includes:

[0117] Step 1021: Construct an indicator judgment matrix based on the evaluation indicators corresponding to each auxiliary validator.

[0118] Step 1022: Based on the index judgment matrix, the index entropy value is processed using the entropy weight function to obtain the index entropy value corresponding to each auxiliary verifier.

[0119] Step 1023: Calculate the difference between the preset parameter values ​​and the entropy value of each indicator to obtain the difference result.

[0120] Step 1024: Summation is performed on the difference result to obtain the first summation result;

[0121] Step 1025: The difference processing result is compared with the first summation processing result to obtain the first ratio processing result.

[0122] Step 1026: Use the first ratio processing result and the evaluation index to perform weighted summation to obtain the first weight.

[0123] In the above scheme, the evaluation indicators include channel quality indicators, perceived location indicators, and sample discrimination ability indicators. These indicators all affect the final identity authentication performance. Therefore, these evaluation indicators are introduced to assess the current performance of each auxiliary verifier, thereby making the assessment of the current performance of each auxiliary verifier more accurate.

[0124] Channel quality metrics are reflected by the received signal-to-noise ratio (SNR). A higher SNR indicates better channel quality and more accurate channel estimation, which can be expressed as follows:

[0125]

[0126] Where m represents the auxiliary verifier m, x1(m) represents the channel quality index of the auxiliary verifier m, u represents the power terminal u, and W u d represents the transmitted signal power of the power terminal u. m，u Let m represent the distance between the auxiliary verifier m and the power terminal u, α represent the free path loss, β0 represent the channel constant, and σ represent the distance between the auxiliary verifier m and the power terminal u. n This represents the noise figure.

[0127] The perceived location metric is represented by position perception sensitivity (PPS). The closer the auxiliary verifier is to the regional metering management terminal, the lower the probability of reporting errors when uploading local output. The closer the auxiliary verifier is to the power consumption terminal, the smaller the impact of noise uncertainty and fading. This can be expressed as follows:

[0128]

[0129] Where m represents the auxiliary verifier m, x2(m) represents the sensing location index of the auxiliary verifier m, and u represents the power consumption terminal u; d m，u This represents the distance between the auxiliary verifier m and the power terminal u; RC represents the area metering management terminal, and d... mRC represents the distance between the auxiliary verifier m and the regional metrology management terminal RC.

[0130] The sample discrimination capability index is reflected by the F1 score, which comprehensively considers recall (the ability to distinguish legitimate power-using terminals) and precision (the ability to distinguish illegitimate power-using terminals) to characterize the identity authentication model's ability to discriminate against the features of the collection channel (i.e., the identity authentication model). It can be expressed as follows:

[0131]

[0132] Where m represents the auxiliary validator m, x3(m) represents the sample discrimination ability index of the auxiliary validator m, Precision represents precision, and Recall represents recall.

[0133] The evaluation indicators are integrated using the entropy weight algorithm to obtain the first weight assigned to each auxiliary validator. The entropy weight algorithm evaluates the importance of each indicator in the overall evaluation based on its entropy value. That is, the smaller the entropy value of an indicator, the greater its dispersion, indicating a greater impact on the overall evaluation. The specific process can be represented as follows:

[0134] Establish an indicator judgment matrix based on the evaluation indicators corresponding to each auxiliary validator:

[0135]

[0136] Where X represents the indicator judgment matrix, N represents the evaluation indicator number, and M represents the auxiliary validator number.

[0137] Normalize the indicator judgment matrix:

[0138]

[0139] Where, ρ mn Let x represent the normalized evaluation metric, m represent the m-th auxiliary validator, n represent the n-th evaluation metric, and x represent the normalized evaluation metric. mn Let x represent the nth evaluation index of the mth auxiliary validator in the index judgment matrix, min{x n} represents the smallest evaluation index in the index judgment matrix, max{x n} represents the largest evaluation indicator.

[0140] Calculate the entropy values ​​of each indicator:

[0141]

[0142] Where, k n Let M represent the entropy value of the indicator, m represent the number of auxiliary validators, n represent the m-th auxiliary validator, n represent the n-th evaluation indicator, and N represent the number of evaluation indicators. ρmn This represents the evaluation index after normalization.

[0143] Based on the principle that the larger the difference coefficient, the higher the weight, the indicators are weighted accordingly:

[0144]

[0145] Where, ψ n k represents the weights corresponding to the evaluation indicators. n Let n represent the entropy value of the indicator, n represent the nth evaluation indicator, and N represent the number of evaluation indicators.

[0146] The current time slot weight (i.e., the first weight) assigned to the auxiliary validator is calculated based on the weighted sum of each indicator:

[0147]

[0148] Where t represents the current time slot (i.e., the current time), and ψ n x represents the weight corresponding to the evaluation index. mn This represents the nth evaluation indicator of the mth auxiliary validator in the indicator judgment matrix, where n represents the nth evaluation indicator and N represents the number of evaluation indicators.

[0149] In some embodiments, step 103, which involves updating the weight of each auxiliary validator based on the historical reputation value and the first weight to obtain a second weight corresponding to each auxiliary validator, includes:

[0150] Step C1: Obtain the measurement parameter corresponding to the first weight, the second weight of the previous time step, and the measurement parameter corresponding to the second weight of the previous time step.

[0151] Step C2: Using the measurement parameters, perform a weighted summation of the second weight and the first weight of the previous time step to obtain the first weighted summation result.

[0152] Step C3: Summing the historical reputation values ​​of each auxiliary validator to obtain the second summation result.

[0153] Step C4: Ratio processing is performed using the historical reputation value corresponding to each auxiliary validator and the second summation processing result to obtain the second ratio processing result corresponding to each auxiliary validator.

[0154] Step C5: Multiply the second ratio processing result corresponding to each auxiliary validator and the first weighted summation processing result to obtain the second weight corresponding to each auxiliary validator.

[0155] In the above scheme, by simultaneously referencing the current performance of historical reputation, we can achieve a more reasonable and fair dynamic weighted aggregation compared to traditional static weighted voting. Specifically, this update mechanism is determined by three parts: the historical reputation of the collaborative AVm (performance of participation), all historical weights over T time slots (historical performance of participation), and the current weight (performance in the current time slot). These are combined in a multiplicative manner to represent their interrelationships.

[0156]

[0157] in, This indicates the second weight, and m represents the m-th auxiliary validator. Indicates the first weight. The second weight represents the weight of the previous time step, t represents the current time slot (i.e., the current time step), i represents time slot i, T represents the total number of time slots, φ represents the magnitude of the impact of historical performance and current performance on weight updates, M represents the number of auxiliary validators, m represents the m-th auxiliary validator, and Repu m Z represents historical reputation value. T-i This represents the forgetting factor, used to decay the historical weights across multiple time slots one by one. It is believed that the closer to the current time slot t, the higher the reference value of the weight.

[0158] This achieves a more reasonable and fair dynamic weighted aggregation compared to traditional static weighted voting.

[0159] In some embodiments, the second authentication result includes legitimate terminals and illegitimate terminals.

[0160] In step 103, the step of authenticating the at least one power-consuming terminal based on the second weight and the plurality of first identity authentication results to obtain a second identity authentication result includes:

[0161] Step D1: Normalize the second weight corresponding to each auxiliary validator to obtain the normalization result for each auxiliary validator.

[0162] Step D2: Using the normalized processing result corresponding to each auxiliary verifier, perform a weighted summation with multiple first identity authentication results to obtain the second weighted summation result.

[0163] Step D3: Retrieve the tag corresponding to the second weighted summation processing result, determine the at least one power terminal as the legitimate terminal or the illegitimate terminal based on the tag, and use the at least one power terminal as the legitimate terminal or the illegitimate terminal as the second identity authentication result.

[0164] In the above scheme, the second weights of each auxiliary validator are normalized, and can be represented as follows:

[0165]

[0166] in, This represents the second weight after normalization. denoted as the second weight, t represents the current time slot (i.e., the current time), and m represents the m-th auxiliary validator.

[0167] This result is then weighted and summed with the corresponding first identity authentication result (using soft decision, i.e., feeding back the CNN's predicted probabilities for all possible categories). The label corresponding to the highest predicted probability is the final authentication result (i.e., the second identity authentication result) given by the collaborative authentication network, which can be represented as follows:

[0168]

[0169] Among them, Decison t+1 Indicates the maximum predicted probability. The second weight is the normalized weight, t represents the current time slot (i.e., the current time), m represents the m-th auxiliary validator, M represents the number of auxiliary validators, and Out represents the second weight. m This indicates the result of the first identity verification.

[0170] By introducing the first identity authentication result and dynamic weighted aggregation, i.e., the second weight, the obtained second identity authentication result is more accurate.

[0171] It should be noted that the method in this embodiment can be executed by a single device, such as a processor or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the process. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.

[0172] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0173] Based on the same inventive concept, and corresponding to any of the above embodiments, this application also provides an identity authentication system for smart distribution networks.

[0174] refer to Figure 3 The identity authentication system for smart distribution networks includes at least one electricity terminal, multiple auxiliary verifiers, and a regional metering management terminal.

[0175] The plurality of auxiliary verifiers 301 are configured to receive feedback signals sent by the regional metering management terminal, perform identity authentication on the at least one electricity terminal based on the feedback signals, obtain a plurality of first identity authentication results corresponding to the plurality of auxiliary verifiers, and send the plurality of first identity authentication results to the regional metering management terminal. The feedback signals are signals generated by the regional metering management terminal based on the electricity request information sent by the at least one electricity terminal.

[0176] The regional metering management terminal 302 is configured to receive the plurality of first identity authentication results and obtain evaluation indicators corresponding to the plurality of auxiliary verifiers. Based on the evaluation indicators, it processes them using an entropy weight algorithm to obtain a first weight corresponding to each auxiliary verifier at the current time. The regional metering management terminal obtains the historical reputation value corresponding to each auxiliary verifier and updates the weight of each auxiliary verifier based on the historical reputation value and the first weight to obtain a second weight corresponding to each auxiliary verifier. Based on the second weight and the plurality of first identity authentication results, it performs identity authentication on the at least one electricity terminal to obtain a second identity authentication result. Based on the second identity authentication result, it determines whether the electricity request information is approved.

[0177] In some embodiments, the regional metering management terminal 302 includes:

[0178] The quality inspection record acquisition unit is configured to acquire the quality inspection record corresponding to each auxiliary verifier.

[0179] The historical reputation value determination unit is configured to obtain the historical reputation value corresponding to each auxiliary validator through the Gompertz function based on the reputation evaluation result corresponding to each auxiliary validator.

[0180] In some embodiments, the quality inspection record acquisition unit is specifically configured as follows:

[0181] Obtain the identity authentication accuracy rate for each auxiliary verifier, as well as the average identity authentication accuracy rate;

[0182] The identity authentication accuracy rate corresponding to each auxiliary verifier is compared with the average identity authentication accuracy rate to obtain the comparison results.

[0183] In response to determining that a comparison result corresponding to an auxiliary verifier indicates that the identity authentication accuracy rate is greater than the average identity authentication accuracy rate, the number of good performance records for the auxiliary verifier corresponding to the comparison result is increased; or,

[0184] In response to determining that there exists an auxiliary verifier whose comparison result is that the identity authentication accuracy is less than or equal to the average identity authentication accuracy, the number of records of poor performance of the auxiliary verifier corresponding to the comparison result is increased.

[0185] The quality inspection record is obtained by using a linear interpolation function to calculate the number of good performance records and the number of bad performance records of the auxiliary verifier corresponding to the comparison results.

[0186] In some embodiments, the feedback signal includes channel state information;

[0187] The plurality of auxiliary verifiers 301 are specifically configured as follows:

[0188] The channel state information is input into a pre-trained identity authentication model, and the identity authentication model is used to authenticate the channel state information to obtain multiple first identity authentication results corresponding to the multiple auxiliary verifiers.

[0189] In some embodiments, the identity authentication system for smart distribution networks further includes a model training module, which is specifically configured as follows:

[0190] Acquire training data and build a pre-trained model;

[0191] The cross-entropy loss function is determined based on the training data, wherein the cross-entropy loss function is specifically:

[0192]

[0193] in, Represented as the cross-entropy loss function, Indicates the true label, This represents the prediction label, k represents the k-th power terminal, K represents the number of power terminals, and T k This indicates that the current prediction result is that the electricity request information belongs to electricity terminal k, and m represents the m-th auxiliary verifier;

[0194] The training data is input into the pre-trained model, and the cross-entropy loss function is minimized. The pre-trained model is continuously trained and adjusted to obtain a trained pre-trained model, which is then used as the identity authentication model.

[0195] In some embodiments, the regional metering management terminal is specifically configured as follows:

[0196] Construct an indicator judgment matrix based on the evaluation indicators corresponding to each auxiliary validator;

[0197] Based on the index judgment matrix, the index entropy value is processed using the entropy weighting function to obtain the index entropy value corresponding to each auxiliary verifier.

[0198] The difference between the preset parameter values ​​and the entropy value of each indicator is calculated to obtain the difference result.

[0199] The difference result is summed to obtain the first summation result;

[0200] The first ratio processing result is obtained by comparing the difference processing result with the first sum processing result.

[0201] The first weight is obtained by weighting and summing the result of the first ratio processing with the evaluation index.

[0202] In some embodiments, the regional metering management terminal is specifically configured as follows:

[0203] Obtain the measurement parameter corresponding to the first weight, the second weight of the previous time at the current time, and the measurement parameter corresponding to the second weight of the previous time at the current time;

[0204] The first weighted sum is obtained by using the measurement parameters to perform a weighted summation on the second weight of the previous time and the first weight of the current time.

[0205] The historical reputation values ​​of each auxiliary validator are summed to obtain the second summation result.

[0206] The historical reputation value corresponding to each auxiliary validator is compared with the second summation result to obtain the second ratio processing result for each auxiliary validator.

[0207] The second ratio processing result corresponding to each auxiliary validator and the first weighted sum processing result are multiplied to obtain the second weight corresponding to each auxiliary validator.

[0208] In some embodiments, the second authentication result includes a legitimate terminal and an illegitimate terminal;

[0209] The regional metering management terminal is specifically configured as follows:

[0210] The second weight corresponding to each auxiliary validator is normalized to obtain the normalization result for each auxiliary validator.

[0211] The normalized result corresponding to each auxiliary verifier is used to perform a weighted summation with multiple first identity authentication results to obtain the second weighted summation result;

[0212] Retrieve the tag corresponding to the second weighted summation processing result, determine the at least one power terminal as the legitimate terminal or the illegitimate terminal based on the tag, and use the at least one power terminal as the legitimate terminal or the illegitimate terminal as the second identity authentication result.

[0213] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.

[0214] The apparatus described above is used to implement the corresponding identity authentication method for smart distribution networks in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0215] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a processor program stored in the memory and executable on the processor, wherein the processor executes the program to implement the identity authentication method for smart distribution networks described in any of the above embodiments.

[0216] Figure 4 This illustration shows a more specific hardware structure diagram of an electronic device provided in this embodiment. The device may include: a processor 401, a memory 402, an input / output interface 403, a communication interface 404, and a bus 405. The processor 401, memory 402, input / output interface 403, and communication interface 404 are interconnected internally via the bus 405.

[0217] The processor 401 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0218] The memory 402 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 402 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 402 and is called and executed by the processor 401.

[0219] Input / output interface 403 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0220] Communication interface 404 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0221] Bus 405 includes a pathway for transmitting information between various components of the device (e.g., processor 401, memory 402, input / output interface 403, and communication interface 404).

[0222] It should be noted that although the above-described device only shows the processor 401, memory 402, input / output interface 403, communication interface 404, and bus 405, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0223] The electronic devices described above are used to implement the corresponding identity authentication methods for smart distribution networks in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0224] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory processor-readable storage medium, which stores processor instructions for causing the processor to execute the identity authentication method for smart distribution networks as described in any of the above embodiments.

[0225] The processor-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be processor-readable instructions, data structures, program modules, or other data. Examples of processor storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by the processing device.

[0226] The processor instructions stored in the storage medium of the above embodiments are used to cause the processor to execute the identity authentication method for smart distribution networks as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0227] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0228] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0229] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0230] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. An identity authentication method for smart distribution networks, characterized in that, An identity authentication system for smart distribution networks, the system comprising at least one electricity user terminal, multiple auxiliary authenticators, and a regional metering management terminal, the method comprising: The plurality of auxiliary verifiers receive feedback signals sent by the regional metering management terminal, perform identity authentication on the at least one electricity terminal based on the feedback signals, obtain a plurality of first identity authentication results corresponding to the plurality of auxiliary verifiers, and send the plurality of first identity authentication results to the regional metering management terminal. The feedback signal is a signal generated by the regional metering management terminal based on the electricity request information sent by the at least one electricity terminal. The regional metering management terminal receives the multiple first identity authentication results and obtains the evaluation indicators corresponding to the multiple auxiliary verifiers. Based on the evaluation indicators, it processes them through an entropy weight algorithm to obtain the first weight corresponding to each auxiliary verifier at the current time. The regional metering management terminal obtains the historical reputation value corresponding to each auxiliary verifier, updates the weight of each auxiliary verifier based on the historical reputation value and the first weight, obtains the second weight corresponding to each auxiliary verifier, and performs identity authentication on the at least one electricity terminal based on the second weight and the plurality of first identity authentication results to obtain the second identity authentication result, and determines whether the electricity request information is approved based on the second identity authentication result. The step of updating the weight of each auxiliary validator based on the historical reputation value and the first weight to obtain a second weight corresponding to each auxiliary validator includes: Obtain the measurement parameter corresponding to the first weight, the second weight of the previous time at the current time, and the measurement parameter corresponding to the second weight of the previous time at the current time; The first weighted sum is obtained by using the measurement parameters to perform a weighted summation on the second weight of the previous time and the first weight of the current time. The historical reputation values ​​of each auxiliary validator are summed to obtain the second summation result. The historical reputation value corresponding to each auxiliary validator is compared with the second summation result to obtain the second ratio processing result for each auxiliary validator. The second ratio processing result corresponding to each auxiliary validator and the first weighted sum processing result are multiplied to obtain the second weight corresponding to each auxiliary validator.

2. The method according to claim 1, characterized in that, The step of obtaining the historical reputation value corresponding to each auxiliary verifier includes: Obtain the quality inspection records corresponding to each auxiliary verifier; Based on the reputation evaluation result corresponding to each auxiliary validator, the historical reputation value corresponding to each auxiliary validator is obtained through the Gompertz function.

3. The method according to claim 2, characterized in that, The process of obtaining the quality inspection record corresponding to each auxiliary verifier includes: Obtain the identity authentication accuracy rate for each auxiliary verifier, as well as the average identity authentication accuracy rate; The identity authentication accuracy rate corresponding to each auxiliary verifier is compared with the average identity authentication accuracy rate to obtain the comparison results. In response to determining that a comparison result corresponding to an auxiliary verifier indicates that the identity authentication accuracy rate is greater than the average identity authentication accuracy rate, the number of good performance records for the auxiliary verifier corresponding to the comparison result is increased; or, In response to determining that there exists an auxiliary verifier whose comparison result is that the identity authentication accuracy is less than or equal to the average identity authentication accuracy, the number of records of poor performance of the auxiliary verifier corresponding to the comparison result is increased. The quality inspection record is obtained by using a linear interpolation function to calculate the number of good performance records and the number of bad performance records of the auxiliary verifier corresponding to the comparison results.

4. The method according to claim 1, characterized in that, The feedback signal includes channel state information; The step of authenticating the identity of the at least one power-consuming terminal based on the feedback signal to obtain multiple first identity authentication results corresponding to the multiple auxiliary verifiers includes: The channel state information is input into a pre-trained identity authentication model, and the identity authentication model is used to authenticate the channel state information to obtain multiple first identity authentication results corresponding to the multiple auxiliary verifiers.

5. The method according to claim 4, characterized in that, The training process of the identity authentication model includes: Acquire training data and build a pre-trained model; The cross-entropy loss function is determined based on the training data, wherein the cross-entropy loss function is specifically: in, Represented as the cross-entropy loss function, Indicates the true label, Indicates the predicted label, Indicates the first Individual power terminals, Indicates the number of power terminals. This indicates that the current forecast result is electricity demand information belonging to the electricity user terminal. , Indicates the first One auxiliary verifier; The training data is input into the pre-trained model, and the cross-entropy loss function is minimized. The pre-trained model is continuously trained and adjusted to obtain a trained pre-trained model, which is then used as the identity authentication model.

6. The method according to claim 1, characterized in that, The process of processing the evaluation index using the entropy weight algorithm to obtain the first weight corresponding to each auxiliary validator at the current time includes: Construct an indicator judgment matrix based on the evaluation indicators corresponding to each auxiliary validator; Based on the index judgment matrix, the index entropy value is processed using the entropy weighting function to obtain the index entropy value corresponding to each auxiliary verifier. The difference between the preset parameter values ​​and the entropy value of each indicator is calculated to obtain the difference result. The difference result is summed to obtain the first summation result; The first ratio processing result is obtained by comparing the difference processing result with the first sum processing result. The first weight is obtained by weighting and summing the result of the first ratio processing with the evaluation index.

7. The method according to claim 1, characterized in that, The second authentication result includes legitimate terminals and illegitimate terminals; The step of authenticating the at least one power-consuming terminal based on the second weight and the plurality of first identity authentication results to obtain a second identity authentication result includes: The second weight corresponding to each auxiliary validator is normalized to obtain the normalization result for each auxiliary validator. The normalized result corresponding to each auxiliary verifier is used to perform a weighted summation with multiple first identity authentication results to obtain the second weighted summation result; Retrieve the tag corresponding to the second weighted summation processing result, determine the at least one power terminal as the legitimate terminal or the illegitimate terminal based on the tag, and use the at least one power terminal as the legitimate terminal or the illegitimate terminal as the second identity authentication result.

8. An identity authentication system for smart distribution networks, characterized in that, It includes at least one electricity terminal, multiple auxiliary verifiers, and a regional metering management terminal; The plurality of auxiliary verifiers are configured to receive feedback signals sent by the regional metering management terminal, perform identity authentication on the at least one electricity terminal based on the feedback signals, obtain a plurality of first identity authentication results corresponding to the plurality of auxiliary verifiers, and send the plurality of first identity authentication results to the regional metering management terminal. The feedback signal is a signal generated by the regional metering management terminal based on the electricity request information sent by the at least one electricity terminal. The regional metering management terminal is configured to receive the multiple first identity authentication results, obtain the evaluation index corresponding to the multiple auxiliary verifiers, and process the evaluation index using an entropy weight algorithm to obtain the first weight corresponding to each auxiliary verifier at the current time. The regional metering management terminal obtains the historical reputation value corresponding to each auxiliary verifier, updates the weight of each auxiliary verifier based on the historical reputation value and the first weight, obtains the second weight corresponding to each auxiliary verifier, and performs identity authentication on the at least one electricity terminal based on the second weight and the plurality of first identity authentication results to obtain the second identity authentication result, and determines whether the electricity request information is approved based on the second identity authentication result. The step of updating the weight of each auxiliary validator based on the historical reputation value and the first weight to obtain a second weight corresponding to each auxiliary validator includes: Obtain the measurement parameter corresponding to the first weight, the second weight of the previous time at the current time, and the measurement parameter corresponding to the second weight of the previous time at the current time; The first weighted sum is obtained by using the measurement parameters to perform a weighted summation on the second weight of the previous time and the first weight of the current time. The historical reputation values ​​of each auxiliary validator are summed to obtain the second summation result. The historical reputation value corresponding to each auxiliary validator is compared with the second summation result to obtain the second ratio processing result for each auxiliary validator. The second ratio processing result corresponding to each auxiliary validator and the first weighted sum processing result are multiplied to obtain the second weight corresponding to each auxiliary validator.

9. An electronic device, comprising a memory, a processor, and a processor program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 7.

Images