Power business access routing method and device based on full-time and global terminal access network

Abstract

The present invention provides a method and device for access routing of electric power services based on a full-time and full-domain terminal access network, which can be applied to the field of communication technology. The method includes: obtaining the communication requirements of the target electric power communication service, the first attribute information of the access device, the second attribute information of each communication device deployed in the terminal access network, and the current network resource status of the terminal access network; generating the importance of the target electric power communication service by analyzing the importance of the communication requirements; inputting the importance, the first attribute information, and the second attribute information into a decision tree model, and outputting the target communication type that matches the target electric power communication service; and using the routing decision model corresponding to the target communication type, based on the current network resource status of the terminal access network and the predetermined link selection weight, obtaining the target communication path corresponding to the target electric power communication service.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and more specifically, to a method and device for accessing and routing electric power services based on a full-time and global terminal access network. Background Art

[0002] With the development of energy Internet and the construction of new distribution networks, large-scale decentralized access of distributed new energy in new power systems, the emergence of new ecosystems such as load aggregators, integrated energy systems, and virtual power plants have made the communication boundaries of the power communication network more complex, the coverage more extensive, and the terminal equipment more abundant.

[0003] Based on this, the power terminal access network must make comprehensive use of multiple communication methods such as fiber-optic private networks, wireless public networks, wireless private networks, power line carriers, etc. to support the transmission of power distribution and utilization business information, thereby meeting various application requirements.

[0004] In the process of implementing the concept of the present invention, the inventors discovered that there is at least a technical problem of low communication resource utilization in the related technology. Summary of the invention

[0005] In view of this, the present invention provides a method and device for access routing of electric power services based on a full-time and global terminal access network.

[0006] One aspect of the present invention provides a method for accessing and routing electric power services based on a full-time and global terminal access network, comprising:

[0007] Acquire the communication requirements of the target power communication service, the first attribute information of the access device, the second attribute information of each communication device deployed in the terminal access network and the current network resource status of the terminal access network; wherein the access device represents the equipment used to access the target power communication service to the terminal access network; generate the importance of the target power communication service by performing importance analysis on the communication requirements; input the importance, the first attribute information and the second attribute information into a decision tree model, and output a target communication type that matches the target power communication service; and utilize a routing decision model corresponding to the target communication type, based on the current network resource status of the terminal access network and a predetermined link selection weight, obtain a target communication path corresponding to the target power communication service, wherein the target communication path indicates the communication routing link of the target power communication service in the terminal access network.

[0008] According to an embodiment of the present invention, the second attribute information includes: the signal strength received by each communication device and the spatial distance between each communication device and the access device; the importance, the first attribute information and the second attribute information are input into a decision tree model, and a target communication type matching the target power communication service is output, including: in response to the first attribute information being a movable attribute, the target communication type is determined according to the spatial distance, importance and the signal strength received by each communication device; and in response to the first attribute information being a non-mobile attribute, the target communication type is determined according to the importance.

[0009] According to an embodiment of the present invention, the target communication type is determined based on the spatial distance, importance and the signal strength received by each communication device, including: in response to the spatial distance being less than a first predetermined threshold, the target communication type is determined based on the importance; and in response to the spatial distance being greater than or equal to the first predetermined threshold, the target communication type is determined based on the importance and the signal strength received by each communication device.

[0010] According to an embodiment of the present invention, the target communication type is determined based on the importance, including: in response to the importance being less than a second predetermined threshold, determining the target communication type to be power line carrier communication; and in response to the importance being greater than or equal to the second predetermined threshold, determining the target communication type to be optical fiber communication.

[0011] According to an embodiment of the present invention, the target communication type is determined based on the importance and the signal strength received by each communication device, including: in response to the signal strength received by each communication device being less than a third predetermined threshold and the importance being less than a second predetermined threshold, determining the target communication type to be power line carrier communication; in response to the signal strength received by each communication device being less than the third predetermined threshold and the importance being greater than or equal to the second predetermined threshold, determining the target communication type to be optical fiber communication; in response to the signal strength received by each communication device being greater than or equal to the third predetermined threshold and the importance being less than the second predetermined threshold, determining the target communication type to be wireless public network communication; and in response to the signal strength received by each communication device being greater than or equal to the third predetermined threshold and the importance being greater than or equal to the second predetermined threshold, determining the target communication type to be wireless private network communication.

[0012] According to an embodiment of the present invention, a routing decision model corresponding to a target communication type is used, based on a current network resource state of a terminal access network and a predetermined link selection weight, to obtain a target communication path corresponding to a target electric power communication service, including: constructing a state space corresponding to the target communication type based on the current network resource state of the terminal access network; constructing an action space based on a predetermined link selection weight; based on the state space and the action space, determining a target communication path from the terminal access network based on the Dykstra algorithm using a routing decision model; wherein the routing decision model is obtained through reinforcement learning training using a reward function constructed based on performance parameters of the terminal access network; the performance parameters include: network delay, packet loss rate, network node idle rate, load balancing entropy, and a matching degree between electric power communication services and network resources.

[0013] According to an embodiment of the present invention, based on the current network resource status of the terminal access network, a state space corresponding to the target communication type is constructed, including: in response to the target communication type being a wired communication type, based on the wired communication network delay, the current available bandwidth of the wired communication link, the packet loss rate of the wired communication link, the node idle rate of the wired communication network and the remaining amount of wired bandwidth resources, a state space corresponding to the wired communication type is constructed.

[0014] According to an embodiment of the present invention, based on the current network resource status of the terminal access network, a state space corresponding to the target communication type is constructed, including: in response to the target communication type being a wireless communication type, based on the wireless communication network delay, the current available bandwidth of the wireless communication link, the wireless communication link packet loss rate, the node idle rate of the wireless communication network and the remaining amount of wireless spectrum resources, a state space corresponding to the wireless communication type is constructed.

[0015] According to an embodiment of the present invention, the importance of the target power communication service is generated by performing importance analysis on the communication demand, including: using a characteristic indicator evaluation method to perform importance analysis on the communication demand to generate the importance; wherein the characteristic indicators of the communication demand include: communication type, communication delay level, single service communication bandwidth, communication redundancy coefficient, minimum concurrency ratio and aggregate bandwidth estimation value.

[0016] Another aspect of the present invention provides a power service access routing device based on a full-time global terminal access network, comprising:

[0017] An acquisition module, used to acquire the name of the target power communication service, the first attribute information of the access device, the second attribute information of each communication device deployed in the terminal access network, and the current network resource status of the terminal access network; wherein the access device represents the device used to access the target power communication service to the terminal access network;

[0018] A first determination module is used to determine the importance of the target power communication service according to the name;

[0019] a communication type decision module, configured to input the importance, the first attribute information, and the second attribute information into a decision tree model, and output a target communication type that matches the target power communication service; and

[0020] The communication routing decision module is used to obtain a target communication path corresponding to a target power communication service based on a current network resource status of a terminal access network and a predetermined link selection weight by using a routing decision model corresponding to a target communication type, wherein the target communication path indicates a communication routing link of the target power communication service in the terminal access network.

[0021] According to an embodiment of the present invention, an importance analysis is performed according to the communication requirements of the target power communication service, and the importance, attribute information of the access device, and attribute information of each communication device of the access network are input into a decision tree model to obtain a communication type matching the target power communication service, and a routing decision model corresponding to the communication type is used to determine the target communication path corresponding to the target power communication service according to the current network resource status and the predetermined link selection weight. Since the communication routing link is selected according to the importance of the target power communication service and the network resource status, a mapping relationship between the service and the communication application requirements can be established for power communication services of different communication types and different importance, thereby dynamically allocating access routes. Since the network resources are reasonably allocated, the abundant terminal communication resources are fully utilized to ensure that data can be transmitted in a timely and accurate manner, thereby improving the resource utilization efficiency and the overall utilization and performance of the network. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0023] Figure 1 A schematic diagram of an application scenario of a power service access routing method based on a full-time global terminal access network according to an embodiment of the present invention is shown;

[0024] Figure 2 A flowchart of a method for accessing and routing electric power services based on a full-time and global terminal access network according to an embodiment of the present invention is schematically shown;

[0025] Figure 3 A schematic diagram of a decision process of a target communication type according to an embodiment of the present invention is schematically shown;

[0026] Figure 4 A schematic diagram of training a decision tree model according to an embodiment of the present invention is shown;

[0027] Figure 5A schematic diagram schematically shows a comparison of service quality satisfaction rates of a routing decision algorithm according to an embodiment of the present invention and a traditional technology algorithm;

[0028] Figure 6 A schematic diagram showing a comparison of load balancing entropy under different traffic emphasis according to an embodiment of the present invention is shown;

[0029] Figure 7 A schematic diagram schematically shows a comparison of wired network load balancing entropy according to an embodiment of the present invention and a conventional technology; and

[0030] Figure 8 A block diagram of a power service access routing device based on a full-time global terminal access network according to an embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0031] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0032] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0033] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0034] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0035] In the embodiments of the present invention, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage and other aspects of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information and network security.

[0036] In the embodiment of the present invention, before obtaining or collecting the user's personal information, the user's authorization or consent is obtained.

[0037] In modern power communication networks, the widespread application of various communication technologies such as fiber-optic private networks, wireless public networks, wireless private networks, and power line carriers provides a variety of options for access to power services. However, the diversity of technologies also brings some challenges, such as the following problems in resource utilization:

[0038] The coverage of various communication technologies overlaps, which increases the range of communication options for business terminals. This can easily lead to a waste of resources because the selection is not optimized based on actual communication needs.

[0039] Based on this, it is difficult for traditional technologies to improve service routing methods to optimize network performance from the perspective of traffic load and communication quality, and therefore it is difficult to select appropriate communication methods for a variety of new power services such as distributed energy, source-grid-load-storage, etc.

[0040] In order to at least partially solve the technical problems existing in the related art, an embodiment of the present invention provides an electric power service access routing method based on a full-time and full-domain terminal access network, including: obtaining the communication requirements of the target electric power communication service, the first attribute information of the access device, the second attribute information of each communication device deployed in the terminal access network, and the current network resource status of the terminal access network; wherein the access device represents the equipment used to access the target electric power communication service to the terminal access network; by performing an importance analysis on the communication requirements, the importance of the target electric power communication service is generated; the importance, the first attribute information and the second attribute information are input into a decision tree model, and a target communication type matching the target electric power communication service is output; and using a routing decision model corresponding to the target communication type, based on the current network resource status of the terminal access network and a predetermined link selection weight, a target communication path corresponding to the target electric power communication service is obtained, wherein the target communication path indicates the communication routing link of the target electric power communication service in the terminal access network.

[0041] Figure 1 The application scenario diagram of the power service access routing method based on the full-time and global terminal access network according to an embodiment of the present invention is schematically shown.

[0042] It should be noted that Figure 1 The examples shown are merely application scenarios to which the embodiments of the present invention can be applied, in order to help those skilled in the art understand the technical content of the present invention, but do not mean that the embodiments of the present invention cannot be used in other devices, systems, environments or scenarios.

[0043] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a terminal device 101, a network 102 and a server 103. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0044] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0045] The terminal device 101 may be any electronic device having a display screen and supporting web browsing, including but not limited to a smart phone, a tablet computer, a laptop computer, a desktop computer, and the like.

[0046] The server 103 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the terminal device 101. The background management server may analyze and process received data such as user requests, and feed back processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0047] For example: the server 103 is used to receive the power communication service 104, and obtain the communication requirements of the power communication service 104, the first attribute information of the access device, the second attribute information of each communication device deployed in the terminal access network and the current network resource status of the terminal access network; according to the communication requirements, the importance 105 of the power communication service is generated; the importance, the first attribute information and the second attribute information are input into the decision tree model, and the communication type 106 matching the power communication service is output; using the routing decision model corresponding to the communication type, based on the current network resource status of the terminal access network and the predetermined link selection weight, the communication path 107 corresponding to the power communication service is obtained.

[0048] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0049] The following will be based on Figure 1 The scene described by Figure 2~Figure 7 The power service access routing method based on the full-time and global terminal access network of an embodiment of the invention is described in detail.

[0050] Figure 2 The flowchart of the power service access routing method based on the full-time and global terminal access network according to an embodiment of the present invention is schematically shown.

[0051] like Figure 2 As shown, the method 200 includes operations S210 to S240.

[0052] In operation S210, communication requirements of a target power communication service, first attribute information of an access device, second attribute information of each communication device deployed in a terminal access network, and a current network resource status of the terminal access network are obtained.

[0053] According to an embodiment of the present invention, in order to promote the development of the power system in a direction that is observable in all time and all domains and to improve the flexibility and interactivity of the power system, the target power communication service and the corresponding communication demand are modeled. The target power communication service may include electric vehicle services, source-grid-load-storage collaborative interaction, new energy cloud, etc. The communication demand may characterize the performance indicators and functional characteristics required for the application scenarios based on the target power communication service, such as communication access mode, communication delay level, single service communication bandwidth, redundancy coefficient, minimum concurrency ratio, and aggregation bandwidth estimation. The correspondence between the target power communication service and the communication demand is shown in Table 1 below.

[0054] Table 1

[0055]

[0056] According to an embodiment of the present invention, an access device may represent a device used to access a target electric power communication service to a terminal access network; the first attribute information may represent relevant information that affects the communication quality of the access device, such as the device type, device parameters, device location and other information corresponding to the access device; the second attribute information may represent relevant information that affects the communication quality of each communication device in the terminal access network.

[0057] According to an embodiment of the present invention, the current network resource status may include network delay, packet loss rate, network idle rate, etc.

[0058] In operation S220 , importance of the target power communication service is generated by performing importance analysis on the communication demand.

[0059] According to an embodiment of the present invention, the importance of the target power communication service may represent the importance level of the target power communication service in the power system, and is an indicator for evaluating the impact of the service on the operation, control and safety of the power system.

[0060] According to the embodiments of the present invention, the terminal access network in the conventional technology can select wired communication or wireless communication. Compared with the wireless path, the wired path is not affected by electromagnetic signal interference, obstacles and transmission distance, and generally has the advantages of stability, high bandwidth, low latency and stronger penetration ability in long-distance transmission scenarios, so it is more suitable for services with high business importance and services with high requirements on the current network resource status.

[0061] According to an embodiment of the present invention, the importance analysis of communication needs can be performed using methods such as the analytic hierarchy process and the characteristic index evaluation method. The analytic hierarchy process can decompose complex problems into multiple components by establishing a hierarchical model, and compare the factors one by one to determine the relative importance of each factor. The characteristic index evaluation method focuses on identifying and quantifying the key performance indicators of a business or system. It can collect relevant data and then evaluate the indicators according to preset evaluation criteria or thresholds. By sorting out the existing research based on the characteristic index evaluation method, the importance values ​​of the target power communication business in each safety area can be obtained as shown in Table 2 below.

[0062] Table 2

[0063]

[0064] In operation S230, the importance, the first attribute information, and the second attribute information are input into a decision tree model, and a target communication type matching the target power communication service is output.

[0065] According to an embodiment of the present invention, when network communication resources are limited, the selection of the best target communication type by the power communication service can be modeled as a multi-classification problem with continuous eigenvalues. When solving classification problems, the random forest algorithm is a simple and effective method that can handle high-dimensional data and missing values, has high classification accuracy, low computational complexity, high computational efficiency and strong robustness, and solves the problem of easy overfitting of the decision tree model to a certain extent, which is conducive to improving the accuracy of the model.

[0066] According to an embodiment of the present invention, the construction and optimization of the decision tree model can use a random forest-based communication mode selection algorithm (RF-CMS, Random Forest-Concurrent Mark Sweep) to select a matching target communication type for the power communication service, achieve loose coupling of the power communication service to the communication type, ensure full-time and full-domain stable communication connection of the service, and improve the overall resource utilization efficiency of the network.

[0067] According to an embodiment of the present invention, the target communication type may include power line carrier communication, optical fiber communication, wireless public network and wireless private network.

[0068] In operation S240, a target communication path corresponding to the target power communication service is obtained based on the current network resource status of the terminal access network and a predetermined link selection weight using a routing decision model corresponding to the target communication type.

[0069] According to an embodiment of the present invention, the target communication path indicates a communication routing link of the target power communication service in the terminal access network.

[0070] According to an embodiment of the present invention, the routing decision model corresponding to the target communication type can be regarded as a multi-constraint routing model based on a multi-agent reinforcement learning algorithm (MAPPO, Multi-Agent Proximal Policy Optimization), and the optimization of the routing decision model can be regarded as a Markov decision process. Therefore, the RF-CMS algorithm and the MAPPO algorithm are combined to determine the target communication type and target communication path of the target power communication service.

[0071] According to an embodiment of the present invention, Markov decision making includes state, action, transition probability and learning reward, and can interact with the environment. i , and for S i Continuously update to determine the current learning strategy and select the best behavior based on the learning strategy i , when the state of the routing decision entity is changed from S i Transform to S i+1 After that, you get the learning reward r i , the routing decision entity continuously updates and determines the best behavior in the cyclic learning to optimize the reward function.

[0072] According to the embodiment of the present invention, routing decisions are made for wired communication services and wireless communication services respectively, so two types of routing decision entities A and B are defined. When it arrives, the routing decision entity starts making routing decisions, where is the source node, is the target node.

[0073] According to an embodiment of the present invention, an importance analysis is performed according to the communication requirements of the target power communication service, and the importance, attribute information of the access device, and attribute information of each communication device of the access network are input into a decision tree model to obtain a communication type matching the target power communication service, and a routing decision model corresponding to the communication type is used to determine the target communication path corresponding to the target power communication service according to the current network resource status and the predetermined link selection weight. Since the communication routing link is selected according to the importance of the target power communication service and the network resource status, a mapping relationship between the service and the communication application requirements can be established for power communication services of different communication types and different importance, thereby dynamically allocating access routes. Since the network resources are reasonably allocated, the abundant terminal communication resources are fully utilized to ensure that data can be transmitted in a timely and accurate manner, thereby improving the resource utilization efficiency and the overall utilization and performance of the network.

[0074] According to an embodiment of the present invention, the importance of the target power communication service is generated by performing importance analysis on the communication demand, including: using a characteristic indicator evaluation method to perform importance analysis on the communication demand to generate the importance; wherein the characteristic indicators of the communication demand include: communication type, communication delay level, single service communication bandwidth, communication redundancy coefficient, minimum concurrency ratio and aggregate bandwidth estimation value.

[0075] According to an embodiment of the present invention, the communication delay level can be the delay time requirement for data transmission, such as seconds (s) and milliseconds (ms); the single-service communication bandwidth is used to represent the minimum bandwidth required for a single target power communication service, usually measured in kbps; the communication redundancy coefficient can characterize the redundant communication requirements set to ensure communication reliability; the minimum concurrency ratio can characterize the minimum ratio of concurrent connections, which can affect the concurrent processing capability of the network; the aggregate bandwidth estimate can be an estimate of the total bandwidth required after multiple target power communication services are aggregated.

[0076] According to an embodiment of the present invention, the importance can be calculated by the feature index evaluation method by multiplying each feature index by the corresponding index weight and then adding them together.

[0077] According to an embodiment of the present invention, the indicator weights are dynamically adjusted according to different communication requirements so as to be able to flexibly adapt to different communication requirements and network resource states. Therefore, different target power communication services can be processed more intelligently, making full use of abundant terminal communication resources.

[0078] According to an embodiment of the present invention, the second attribute information includes: the signal strength received by each communication device and the spatial distance between each communication device and the access device; the importance, the first attribute information and the second attribute information are input into a decision tree model, and a target communication type matching the target power communication service is output, including: in response to the first attribute information being a movable attribute, the target communication type is determined according to the spatial distance, importance and the signal strength received by each communication device; and in response to the first attribute information being a non-mobile attribute, the target communication type is determined according to the importance.

[0079] According to an embodiment of the present invention, the severity of signal shielding and interference at the geographical location of each communication device can be evaluated based on the signal strength received by each communication device. When the signal strength RSSI received by the communication device is lower than -90dBm, the signal quality is poor, which may cause packet loss, data transmission errors and other problems, and is usually not suitable for transmission using wireless communication.

[0080] According to an embodiment of the present invention, the spatial distance ED between each communication device and the access device can be calculated based on the coordinates of each node in the SDN (Software Defined Network) perception network topology. The spatial distance ED can affect the attenuation of the signal in the route. The longer the spatial distance, the greater the signal attenuation, and thus a stronger signal or relay device is required to ensure the communication quality.

[0081] According to an embodiment of the present invention, the first attribute information is used to characterize the mobility Mod of the communication device, where Mod is a Boolean type data stored in the form of an 8-bit numerical value in a variable. When the communication device is a mobile device, the first attribute information is a movable attribute, Mod=1; when the communication device is a non-mobile device, the first attribute information is a non-mobile attribute, Mod=0.

[0082] According to an embodiment of the present invention, the decision tree model evaluates the applicability of different communication types based on the second attribute information, combined with the spatial distance, importance and signal strength. In the case where the communication device is a mobile device with a large range of movement, wireless communication with good coverage and high signal strength can be preferred. In the case where the communication device is a non-mobile device with low mobility or fixed, wired communication can be considered to ensure the stability of the route and bandwidth requirements.

[0083] According to the embodiment of the present invention, the communication type is determined based on the second attribute information, the communication demand of the target power communication service is met, and the network resources are optimized.

[0084] According to an embodiment of the present invention, the target communication type is determined based on the spatial distance, importance and the signal strength received by each communication device, including: in response to the spatial distance being less than a first predetermined threshold, the target communication type is determined based on the importance; and in response to the spatial distance being greater than or equal to the first predetermined threshold, the target communication type is determined based on the importance and the signal strength received by each communication device.

[0085] According to an embodiment of the present invention, the decision tree model inputs different parameters to determine the target communication type according to the magnitude relationship between the spatial distance and the first predetermined threshold.

[0086] According to an embodiment of the present invention, when the spatial distance exceeds the first predetermined threshold, the importance and signal strength jointly determine the target communication type. Conversely, when the spatial distance is less than the first predetermined threshold, the importance becomes a decisive factor in selecting the target communication type.

[0087] For example, the first predetermined threshold can be set to 50m according to demand. When the spatial distance of the mobile communication devices does not exceed 50m, wired communication can be selected; conversely, when the spatial distance of the mobile communication devices exceeds 50m, wireless communication can be selected.

[0088] According to an embodiment of the present invention, by judging the decisive factors of the spatial distance and the first predetermined threshold for the target communication type, the decision tree model is dynamically adjusted to select the optimal communication type according to business needs, which is conducive to the reasonable allocation of network resources.

[0089] According to an embodiment of the present invention, the target communication type is determined based on the importance, including: in response to the importance being less than a second predetermined threshold, determining the target communication type to be power line carrier communication; and in response to the importance being greater than or equal to the second predetermined threshold, determining the target communication type to be optical fiber communication.

[0090] According to the embodiments of the present invention, for wired communication types, optical fiber communication has the characteristics of high speed, large bandwidth, strong stability, etc., and is more suitable for services with high business importance than power line carrier communication.

[0091] For example, the second predetermined threshold may be set to 0.5 according to demand. When the importance Imp is less than 0.5, power line carrier communication may be used; conversely, when the importance Imp is less than 0.5, optical fiber communication may be used.

[0092] According to an embodiment of the present invention, the target communication type is determined based on the importance and the signal strength received by each communication device, including: in response to the signal strength received by each communication device being less than a third predetermined threshold and the importance being less than a second predetermined threshold, determining the target communication type to be power line carrier communication; in response to the signal strength received by each communication device being less than the third predetermined threshold and the importance being greater than or equal to the second predetermined threshold, determining the target communication type to be optical fiber communication; in response to the signal strength received by each communication device being greater than or equal to the third predetermined threshold and the importance being less than the second predetermined threshold, determining the target communication type to be wireless public network communication; and in response to the signal strength received by each communication device being greater than or equal to the third predetermined threshold and the importance being greater than or equal to the second predetermined threshold, determining the target communication type to be wireless private network communication.

[0093] According to an embodiment of the present invention, when the spatial distance is greater than or equal to the first predetermined threshold, the target communication type can be determined based on the magnitude relationship between the importance and the second predetermined threshold and the magnitude relationship between the signal strength and the third predetermined threshold.

[0094] For example, the third predetermined threshold corresponding to the signal strength may be set to -90 dBm according to requirements.

[0095] In order to better understand the decision process of the target communication type in the embodiment of the present invention, the following first predetermined threshold is set to 50m, the second predetermined threshold is set to 0.5, and the third predetermined threshold is set to -90dBm as an example. Figure 3 The decision process of the target communication type is illustrated.

[0096] Figure 3 The following is a schematic diagram of a target communication type decision process according to an embodiment of the present invention.

[0097] like Figure 3As shown, for the target power communication service, it is first determined whether Mod is a mobile attribute: when Mod is a non-mobile attribute, the target communication type is determined according to Imp, and when Imp is less than the second predetermined threshold, it is determined to be power line carrier communication, and when Imp is greater than or equal to the second predetermined threshold, it is determined to be optical fiber communication; when Mod is a mobile attribute, it is determined whether ED is less than the first predetermined threshold, and when ED is less than the first predetermined threshold, the target communication type is determined according to Imp, and when Imp is less than the second predetermined threshold, it is determined to be power line carrier communication, and when Imp is greater than or equal to the second predetermined threshold, it is determined to be optical fiber communication; when ED is greater than or equal to the first predetermined threshold, it is determined whether RSSI is less than the third predetermined threshold, and when RSSI is less than the third predetermined threshold, the target communication type is determined according to Imp, and when Imp is less than the second predetermined threshold, it is determined to be power line carrier communication, and when Imp is greater than or equal to the second predetermined threshold, it is determined to be optical fiber communication; when RSSI is greater than or equal to the third predetermined threshold and Imp is greater than or equal to the second predetermined threshold, it is determined to be a wireless private network, and when RSSI is greater than or equal to the third predetermined threshold and Imp is less than the second predetermined threshold, it is determined to be a wireless public network.

[0098] According to the embodiment of the present invention, for communication devices with lower importance and lower signal strength, power line carrier communication is selected as the target communication type, thereby solving the cost problem.

[0099] According to an embodiment of the present invention, for communication equipment with high importance and low signal strength, optical fiber communication is selected as the target communication type, which is conducive to providing high speed and high stability.

[0100] According to the embodiment of the present invention, for communication devices with lower importance and higher signal strength, wireless public network communication is selected as the target communication type, making the communication process more flexible and convenient.

[0101] According to an embodiment of the present invention, for communication equipment with higher importance and higher signal strength, wireless private network communication is selected as the target communication type. Since the wireless private network can allocate network resources according to the needs and importance of different services, it ensures the real-time and stability of key services and provides a communication type with better signal coverage and stronger security.

[0102] According to an embodiment of the present invention, by comprehensively considering signal strength, importance and spatial distance, it can be ensured that under different network environments and communication service requirements, a more matching target communication type can be selected for the target power communication service according to the decision tree model, so as to optimize network performance and improve communication efficiency and reliability.

[0103] As mentioned above, the target communication type can be determined according to a decision tree model, wherein the decision tree model can be constructed after reinforcement training through a random forest algorithm.

[0104] In order to better understand the training process of the decision tree model in the embodiment of the present invention, Figure 4 The decision tree model is explained in detail.

[0105] Figure 4 The diagram schematically shows a training diagram of a decision tree model according to an embodiment of the present invention.

[0106] like Figure 4 As shown, the embodiment 400 includes a training data set 410, a sample set 420, a random forest 430, a prediction result set 440, and a target communication type 450. The sample set includes w sample sets S1, S2, ..., S w , the random forest 430 includes a decision tree 431, and the prediction result set 440 includes prediction results f1, f2, ..., f corresponding to each decision tree in the random forest 430. w .

[0107] According to an embodiment of the present invention, a feature set X as shown in the following formula (1) can be obtained according to the importance Imp, the signal strength RSSI, the spatial distance ED and the mobility Mod of the communication device.

[0108] X={Imp, RSSI, ED, Mod} (1)

[0109] According to an embodiment of the present invention, the feature set X can be used as the input of the decision tree model. According to the features extracted from the feature set, a plurality of decision tree models are trained using the random forest algorithm. The training data set D is sampled with replacement using the front-end development framework (Bootstrap) method to generate w sample sets S1, S2, ... S w , and generate w decision trees based on the sample set to form a random forest.

[0110] According to an embodiment of the present disclosure, a training data set D is input, and a bootstrap method is used to perform a sampling with replacement on the training data set D to generate w sample sets S1, S2, ..., S w , and generate w decision trees based on the sample set to form a random forest.

[0111] According to an embodiment of the present invention, each initial decision tree model uses a CART (Classification and Regression Trees) algorithm to classify a single sample in a sample set.

[0112] According to an embodiment of the present invention, the training of the decision tree model starts from the root node, and each node is processed until the current node meets the termination condition of node splitting, thereby completing the training of the decision tree model that can obtain the target communication type.

[0113] According to an embodiment of the present invention, the training data set corresponding to the current node is , randomly select a subset of feature set X as the sub-feature set , calculate the sub-feature set The feature value pairs in the training data set The Gini coefficient is also called Gini Impurity, which is a metric used in decision tree algorithms to select split nodes. It is used to quantify the uncertainty or impurity in a dataset, that is, the degree of mixing of categories in a dataset. The value of the Gini coefficient ranges between 0 and 1. When the Gini coefficient is 0, all samples belong to the same category and there is no uncertainty. When the Gini coefficient is 1, the samples of each category in the dataset are evenly distributed and the uncertainty is the highest. Training dataset The Gini coefficient Gini( The calculation process of ) is shown in the following formula (2).

[0114] (2)

[0115] Among them, K is used to represent the training data set The total number of categories in the k-th category is C. k .

[0116] According to an embodiment of the present invention, the sub-feature set The characteristic value x in has the case of taking the value a and the case of not taking the value a, so the training data set D' can be divided into the first branch D1 and the second branch D2. The Gini coefficient Gini(D1) corresponding to the first branch D1 and the Gini coefficient Gini(D2) corresponding to the second branch D2 can be obtained according to the above formula (2), which will not be repeated here. The branch division of the training data set is based on the first predetermined threshold, the second predetermined threshold and the third predetermined threshold.

[0117] According to an embodiment of the present invention, the training data set can be calculated using the following formula (3): The conditional Gini index .

[0118] (3)

[0119] Among them, | | can represent the training data set The total number of samples in D1 is represented by |D1|, and the number of samples included in the first branch D1 is represented by |D2|.

[0120] According to an embodiment of the present invention, the training data set Substitute all the eigenvalues ​​into the above formula (3) and obtain the feature x with the smallest Gini index as the optimal feature.

[0121] According to an embodiment of the present invention, when x is a discrete feature, the feature value corresponding to x is the optimal feature value. According to the optimal feature and the corresponding optimal feature value, the left and right nodes of the current node are established based on the first branch D1 and the second branch D2, and the used features are deleted from the sub-feature set X'.

[0122] According to an embodiment of the present invention, when x is a continuous feature, the Gini index of the left and right nodes of the current node is recursively operated until the Gini index is less than the Gini index threshold or the sub-feature set When it is an empty set and the samples belong to the same category, the recursive operation is completed to generate a decision tree model.

[0123] According to an embodiment of the present invention, some features are randomly selected during the training of the decision tree model to increase the differences between the decision trees, thereby achieving independent training and prediction.

[0124] According to an embodiment of the present invention, after each decision tree in the random forest gives a prediction result, the final classification decision can be determined by voting, thereby obtaining a target communication type that matches the target power communication service. The formula of the combined classification model H(x) can be obtained as follows: Formula (4).

[0125] (4)

[0126] Among them, argmax() is the maximum index function, h i (x) represents the classification model of the i-th decision tree, Y can represent the output target communication type, and I() represents the indicative function.

[0127] According to an embodiment of the present invention, a routing decision model corresponding to a target communication type is used, based on a current network resource state of a terminal access network and a predetermined link selection weight, to obtain a target communication path corresponding to a target electric power communication service, including: constructing a state space corresponding to the target communication type based on the current network resource state of the terminal access network; constructing an action space based on a predetermined link selection weight; based on the state space and the action space, determining a target communication path from the terminal access network based on the Dykstra algorithm using a routing decision model; wherein the routing decision model is obtained through reinforcement learning training using a reward function constructed based on performance parameters of the terminal access network; the performance parameters include: network delay, packet loss rate, network node idle rate, load balancing entropy, and a matching degree between electric power communication services and network resources.

[0128] According to an embodiment of the present invention, the state space may be a collection of all network resource states considered in the routing decision process. The current network resource state and the predetermined link selection weight determine the target communication path.

[0129] According to an embodiment of the present invention, the action space may be all communication paths that the communication device may select in each state. Due to the different characteristics of network resources for wired communication and wireless communication, the action spaces of the two types of routing decision entities are the same, but the state spaces are different.

[0130] According to an embodiment of the present invention, the predetermined link selection weight may be an action in the action space, and a target communication path corresponding to the target power communication service may be obtained by solving the predetermined link selection weight using a Dijikstra algorithm.

[0131] According to an embodiment of the present invention, the network delay D is used to characterize the delay time of data transmission, which affects the real-time performance of the target power communication service; the packet loss rate L is used to characterize the proportion of data packets lost during data transmission, which affects the reliability of communication.

[0132] According to an embodiment of the present invention, the network node idle rate NIR is used to characterize the proportion of idle nodes in the network, which can reflect the degree of congestion of the network. From the overall perspective of the network structure, in the process of network data transmission, the more idle nodes there are under the same network load, the lower the degree of congestion. Therefore, the node idle rate NIR is included in the evaluation index of network balance. When the target power communication service arrives at the node, if the node is busy, the target power communication service enters the queue, and the target power communication service is forwarded immediately when the queue is empty. Therefore, the probability of the node queue being empty is used to describe the node idle rate.

[0133] According to an embodiment of the present invention, the load balancing entropy L E It can be used to represent an indicator to measure the degree of network traffic balance. The larger the load balancing entropy, the more uniform the traffic distribution.

[0134] For example, for a network topology G(V, E), V is used to represent a set of vertices. A vertex can represent a node in a network, such as a router, a switch, a communication base station, or a terminal device. Each node is a connection point in the network and can send or receive data. E represents a set of edges. An edge can represent a communication link or path connecting two nodes, so that data can be transmitted between different nodes in the network. In the network topology G(V, E), a predetermined link (x, y) is included, where x is used to represent a first node and y is used to represent a second node. The percentage of the load flow of the predetermined link (x, y) to the total capacity η(x, y) can be obtained according to the following formula (5).

[0135] (5)

[0136] Where C(x, y) represents the total capacity of the communication link (x, y), and l(x, y) represents the remaining capacity of the communication link. Normalizing η(x, y) yields , then the load balancing entropy L E It can be obtained using the following formula (6).

[0137] (6)

[0138] According to an embodiment of the present invention, in order to verify the effectiveness of the RF-CMS algorithm, the matching degree Mr of the power communication service and the network resources can be used to reflect the matching degree of the target power communication service and the network resource status, thereby measuring the load balancing situation of each communication path and the network resource utilization rate. Therefore, the matching degree Mr of the power communication service and the network resources can be obtained according to the cross entropy of the load balancing entropy of the wired network and the load balancing entropy of the wireless network using the following formula (7).

[0139] (7)

[0140] Among them, CE() is used to represent cross entropy, LB w Used to represent the load balancing entropy of the wired network, LB wl Used to represent the load balancing entropy of a wireless network.

[0141] According to an embodiment of the present invention, the reward function R i The reward function R can be constructed based on the performance parameters mentioned above. i It can be expressed as the following formula (8).

[0142] (8)

[0143] Among them, α+β+θ+ε+δ=1.

[0144] According to an embodiment of the present invention, the reward function can be reinforced trained according to the performance parameters to obtain an optimal routing decision model.

[0145] According to the embodiment of the present invention, in order to better verify the effectiveness of the routing decision model constructed based on the RF-CMS algorithm and the MAPPO algorithm in the embodiment of the present invention, the MAPPO framework can be constructed using simulation software, and a communication network of 100 nodes can be built in a corresponding simulation environment for simulation operation. The routing decision model constructed based on the RF-CMS algorithm and the MAPPO algorithm in the embodiment of the present invention is compared and evaluated with the routing decision model in the related art, and the superiority of the combined algorithm in the embodiment of the present invention is verified from the two aspects of service satisfaction rate and network load balancing.

[0146] Figure 5 The diagram schematically shows a comparison of the service quality satisfaction rate between the routing decision algorithm according to the embodiment of the present invention and the traditional technical algorithm.

[0147] like Figure 5 As shown, the service quality satisfaction rates of network delay, bandwidth and packet loss rate of the embodiments of the present invention are higher than those of the traditional technology, and therefore, the service quality requirements of the target power communication business can be better met.

[0148] Figure 6 A schematic diagram schematically shows a comparison of load balancing entropies under different traffic emphasis according to an embodiment of the present invention.

[0149] like Figure 6 As shown, with the increase of traffic intensity, the wireless network load balancing entropy of the embodiment of the present invention shows a small fluctuation downward trend, while the wired network load balancing entropy increases significantly. It can be seen that in the actual terminal access network, the wireless network resources are abundant, and accordingly, the load balancing entropy changes less. The supplementation of wireless network resources alleviates the business bearing pressure of the wired network and can help the wired network achieve a better network load balancing state.

[0150] Figure 7 The schematic diagram schematically shows a comparison of wired network load balancing entropy according to an embodiment of the present invention and that of a conventional technology.

[0151] like Figure 7 As shown, under different traffic intensities, the routing decision algorithm of the embodiment of the present invention can effectively improve resource utilization efficiency and achieve better network load balancing compared to traditional technologies.

[0152] According to an embodiment of the present invention, a routing decision model is used based on the Dykstra algorithm to determine the target communication path from the terminal access network. On the premise of determining the target communication type, the abundant terminal communication resources are fully utilized, the problem of redundant resource configuration of the terminal access network in the related technology is overcome, and the full-time and full-domain observability of the power communication network is achieved. The RF-CMS algorithm is used to comprehensively consider the requirements of the target power communication service such as latency, bandwidth, and packet loss rate, and the MAPPO algorithm is used to dynamically allocate routes for the target power communication service to ensure that the target power communication service data, such as measurement information and control information, can be transmitted on the network in a timely and accurate manner to achieve network load balancing.

[0153] According to an embodiment of the present invention, based on the current network resource status of the terminal access network, a state space corresponding to the target communication type is constructed, including: in response to the target communication type being a wired communication type, based on the wired communication network delay, the current available bandwidth of the wired communication link, the packet loss rate of the wired communication link, the node idle rate of the wired communication network and the remaining amount of wired bandwidth resources, a state space corresponding to the wired communication type is constructed.

[0154] According to an embodiment of the present invention, the state space S corresponding to the wired communication type A It can be expressed as the following formula (9).

[0155] S A ={D, B w , L, NIR, W} (9)

[0156] Among them, B w S represents the remaining available bandwidth of the wired communication link, and W can represent the remaining available resources of the wired communication bandwidth. A Represents the routing decision entity state S in the routing decision model corresponding to the wired communication type i .

[0157] Based on the needs of application scenarios, the wired communication type can also be specifically divided into power line carrier communication and optical fiber communication. Therefore, based on the method described above, a state space corresponding to the power line carrier communication can be constructed according to the network resources of the power line carrier communication, and a state space corresponding to the optical fiber communication can be constructed according to the network resources of the optical fiber communication.

[0158] According to an embodiment of the present invention, wired communication can optimize route selection based on network latency, current available bandwidth of the wired communication link, packet loss rate of the wired communication link, node idle rate of the wired communication network, and remaining amount of wired bandwidth resources, thereby avoiding link or node overload, achieving efficient utilization of wired communication resources, and meeting the communication needs of different power communication services.

[0159] According to an embodiment of the present invention, based on the current network resource status of the terminal access network, a state space corresponding to the target communication type is constructed, including: in response to the target communication type being a wireless communication type, based on the wireless communication network delay, the current available bandwidth of the wireless communication link, the wireless communication link packet loss rate, the node idle rate of the wireless communication network and the remaining amount of wireless spectrum resources, a state space corresponding to the wireless communication type is constructed.

[0160] According to an embodiment of the present invention, the state space S corresponding to the wireless communication type B It can be expressed as the following formula (10).

[0161] S B ={D, B w , L, NIR, W l} (10)

[0162] Among them, W l Indicates the remaining amount of wireless spectrum resources. B Represents the routing decision entity state S in the routing decision model corresponding to the wireless communication type i .

[0163] Based on the needs of application scenarios, wireless communication types can be specifically divided into wireless public network communication and wireless private network communication. Therefore, based on the method described above, a state space corresponding to wireless public network communication can be constructed according to the network resources of wireless public network communication, or a state space corresponding to wireless public network communication can be constructed according to the network resources of wireless private network communication.

[0164] According to the embodiment of the present invention, as the network status changes, the information in the status space will be continuously updated, and therefore, it is necessary to perform routing optimization according to the latest status space.

[0165] According to the embodiments of the present invention, by means of dynamic routing allocation and load balancing, wireless network resources can be more effectively utilized and resource waste can be reduced. Routing strategies can be flexibly adjusted according to changes in state space to cope with different communication requirements.

[0166] Figure 8 A block diagram of a power service access routing device based on a full-time global terminal access network according to an embodiment of the present invention is schematically shown.

[0167] like Figure 8 As shown, the apparatus 800 includes an acquisition module 810 , a first determination module 820 , a communication type decision module 830 , and a communication route decision module 840 .

[0168] The acquisition module 810 is used to obtain the name of the target power communication service, the first attribute information of the access device, the second attribute information of each communication device deployed in the terminal access network, and the current network resource status of the terminal access network; wherein the access device represents the device used to access the target power communication service to the terminal access network.

[0169] A first determination module 820 is used to determine the importance of the target power communication service according to the name;

[0170] The communication type decision module 830 is used to input the importance, the first attribute information and the second attribute information into a decision tree model, and output a target communication type that matches the target power communication service.

[0171] The communication routing decision module 840 is used to obtain a target communication path corresponding to the target power communication service based on the current network resource status of the terminal access network and a predetermined link selection weight using a routing decision model corresponding to the target communication type, wherein the target communication path indicates the communication routing link of the target power communication service in the terminal access network.

[0172] According to an embodiment of the present invention, the communication type decision module 830 includes a first determination submodule and a second determination submodule.

[0173] The first determination submodule is used to determine the target communication type according to the spatial distance, importance and signal strength received by each communication device in response to the first attribute information being a movable attribute.

[0174] The second determination submodule is configured to determine the target communication type according to the importance in response to the first attribute information being a non-mobile attribute.

[0175] According to an embodiment of the present invention, the first determining submodule includes a first determining unit and a second determining unit.

[0176] The first determining unit is configured to determine the target communication type according to the importance in response to the spatial distance being less than a first predetermined threshold.

[0177] The second determination unit is configured to determine the target communication type according to the importance and the signal strength received by each communication device in response to the spatial distance being greater than or equal to the first predetermined threshold.

[0178] According to an embodiment of the present invention, the first determining unit includes a first determining subunit and a second determining subunit.

[0179] The first determining subunit is configured to determine that the target communication type is power line carrier communication in response to the importance being less than a second predetermined threshold.

[0180] The second determining subunit is configured to determine that the target communication type is optical fiber communication in response to the importance being greater than or equal to a second predetermined threshold.

[0181] According to an embodiment of the present invention, the second determining unit includes a first determining subunit, a second determining subunit, a third determining subunit and a fourth determining subunit.

[0182] The first determination subunit is used to determine that the target communication type is power line carrier communication in response to the signal strength received by each communication device being less than a third predetermined threshold and the importance being less than a second predetermined threshold.

[0183] The second determining subunit is used to determine that the target communication type is optical fiber communication in response to the signal strength received by each communication device being less than a third predetermined threshold and the importance being greater than or equal to a second predetermined threshold.

[0184] The third determining subunit is used to determine that the target communication type is wireless public network communication in response to the signal strength received by each communication device being greater than or equal to a third predetermined threshold and the importance being less than a second predetermined threshold.

[0185] The fourth determination subunit is used to determine that the target communication type is wireless private network communication in response to the signal strength received by each communication device being greater than or equal to a third predetermined threshold and the importance being greater than or equal to a second predetermined threshold.

[0186] According to an embodiment of the present invention, the communication route decision module includes a first construction submodule, a second construction submodule and a determination submodule.

[0187] The first construction submodule is used to construct a state space corresponding to the target communication type based on the current network resource state of the terminal access network.

[0188] The second construction submodule is used to construct an action space based on a predetermined link selection weight.

[0189] The determination submodule is used to determine the target communication path from the terminal access network based on the state space and the action space and the routing decision model based on the Dykstra algorithm.

[0190] According to an embodiment of the present invention, the first building submodule includes a first building unit and a second building unit.

[0191] The first construction unit is used to construct a state space corresponding to the wired communication type in response to the target communication type being a wired communication type, based on the wired communication network delay, the currently available bandwidth of the wired communication link, the packet loss rate of the wired communication link, the node idle rate of the wired communication network, and the remaining amount of wired bandwidth resources.

[0192] The second construction unit is used to construct a state space corresponding to the wireless communication type in response to the target communication type being the wireless communication type, based on the wireless communication network delay, the currently available bandwidth of the wireless communication link, the packet loss rate of the wireless communication link, the node idle rate of the wireless communication network and the remaining amount of wireless spectrum resources.

[0193] According to an embodiment of the present invention, the first determining module includes a generating submodule.

[0194] The generation submodule is used to analyze the importance of communication requirements using the characteristic index evaluation method and generate the importance.

[0195] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware, and firmware, or by a proper combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be executed.

[0196] For example, any multiple of the acquisition module 810, the first determination module 820, the communication type decision module 830, and the communication route decision module 840 can be combined in one module / unit / sub-unit for implementation, or any one of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to an embodiment of the present invention, at least one of the acquisition module 810, the first determination module 820, the communication type decision module 830, and the communication route decision module 840 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware, and firmware, or by a suitable combination of any of them. Alternatively, at least one of the acquisition module 810, the first determination module 820, the communication type decision module 830, and the communication route decision module 840 may be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function may be executed.

[0197] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments of the present invention can be combined and / or combined in various ways, even if such a combination or combination is not explicitly recorded in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features recorded in the various embodiments of the present invention can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present invention.

[0198] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination advantageously. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A method for accessing and routing electric power services based on a full-time and global terminal access network, characterized in that: include: Acquire the communication requirements of the target power communication service, the first attribute information of the access device, the second attribute information of each communication device deployed in the terminal access network, and the current network resource status of the terminal access network; wherein the access device represents the device used to access the target power communication service to the terminal access network; By performing importance analysis on the communication demand, the importance of the target power communication service is generated; inputting the importance, the first attribute information, and the second attribute information into a decision tree model, and outputting a target communication type that matches the target power communication service; and Using a routing decision model corresponding to the target communication type, based on the current network resource state of the terminal access network and a predetermined link selection weight, a target communication path corresponding to the target power communication service is obtained, wherein the target communication path indicates a communication routing link of the target power communication service in the terminal access network; The method of obtaining a target communication path corresponding to the target power communication service by using a routing decision model corresponding to the target communication type based on a current network resource state of the terminal access network and a predetermined link selection weight includes: Based on the current network resource state of the terminal access network, constructing a state space corresponding to the target communication type; constructing an action space based on the predetermined link selection weights; Based on the state space and the action space, the target communication path is determined from the terminal access network using the routing decision model based on the Dykstra algorithm; wherein the routing decision model is obtained through reinforcement learning training based on a reward function constructed based on performance parameters of the terminal access network; the performance parameters include: network delay, packet loss rate, network node idle rate, load balancing entropy, and the matching degree between power communication services and network resources.

2. The method according to claim 1, characterized in that: The second attribute information includes: the signal strength received by each communication device and the spatial distance between each communication device and the access device; The step of inputting the importance, the first attribute information, and the second attribute information into a decision tree model and outputting a target communication type matching the target power communication service includes: In response to the first attribute information being a movable attribute, determining the target communication type according to the spatial distance, the importance, and the signal strength received by each communication device; and In response to the first attribute information being a non-mobile attribute, the target communication type is determined according to the importance.

3. The method according to claim 2, characterized in that The determining the target communication type according to the spatial distance, the importance, and the signal strength received by each communication device includes: In response to the spatial distance being less than a first predetermined threshold, determining the target communication type according to the importance; and In response to the spatial distance being greater than or equal to a first predetermined threshold, the target communication type is determined according to the importance and the signal strength received by each communication device.

4. The method according to claim 2 or 3, characterized in that: The step of determining the target communication type according to the importance includes: In response to the importance being less than a second predetermined threshold, determining that the target communication type is power line carrier communication; and In response to the importance being greater than or equal to the second predetermined threshold, the target communication type is determined to be optical fiber communication.

5. The method according to claim 4, characterized in that The determining the target communication type according to the importance and the signal strength received by each communication device includes: In response to the signal strength received by each communication device being less than a third predetermined threshold, and the importance being less than the second predetermined threshold, determining that the target communication type is power line carrier communication; In response to the signal strength received by each communication device being less than the third predetermined threshold, and the importance being greater than or equal to the second predetermined threshold, determining that the target communication type is optical fiber communication; In response to the signal strength received by each communication device being greater than or equal to the third predetermined threshold, and the importance being less than the second predetermined threshold, determining that the target communication type is wireless public network communication; and In response to the signal strength received by each communication device being greater than or equal to the third predetermined threshold, and the importance being greater than or equal to the second predetermined threshold, the target communication type is determined to be wireless private network communication.

6. The method according to claim 1, characterized in that The constructing a state space corresponding to the target communication type based on the current network resource state of the terminal access network includes: In response to the target communication type being a wired communication type, a state space corresponding to the wired communication type is constructed based on the wired communication network delay, the currently available bandwidth of the wired communication link, the packet loss rate of the wired communication link, the node idle rate of the wired communication network, and the remaining amount of wired bandwidth resources.

7. The method according to claim 1, characterized in that The constructing a state space corresponding to the target communication type based on the current network resource state of the terminal access network includes: In response to the target communication type being a wireless communication type, a state space corresponding to the wireless communication type is constructed based on the wireless communication network delay, the currently available bandwidth of the wireless communication link, the packet loss rate of the wireless communication link, the node idle rate of the wireless communication network and the remaining amount of wireless spectrum resources.

8. The method according to claim 1, characterized in that The generating the importance of the target power communication service by analyzing the importance of the communication demand includes: The importance of the communication demand is analyzed by using a characteristic index evaluation method to generate the importance; wherein the characteristic indexes of the communication demand include: communication type, communication delay level, single-service communication bandwidth, communication redundancy coefficient, minimum concurrency ratio and aggregate bandwidth estimation value.

9. A power service access routing device based on a full-time and global terminal access network, characterized in that: include: An acquisition module, used to acquire the name of the target power communication service, the first attribute information of the access device, the second attribute information of each communication device deployed in the terminal access network, and the current network resource status of the terminal access network; wherein the access device represents the device used to access the target power communication service to the terminal access network; A first determination module, configured to determine the importance of the target power communication service according to the name; a communication type decision module, configured to input the importance, the first attribute information, and the second attribute information into a decision tree model, and output a target communication type that matches the target power communication service; and a communication routing decision module, configured to obtain a target communication path corresponding to the target power communication service by using a routing decision model corresponding to the target communication type, based on a current network resource state of the terminal access network and a predetermined link selection weight, wherein the target communication path indicates a communication routing link of the target power communication service in the terminal access network; The communication routing decision module comprises: A first construction submodule is used to construct a state space corresponding to a target communication type based on a current network resource state of a terminal access network; A second construction submodule is used to construct an action space based on a predetermined link selection weight; A determination submodule is used to determine a target communication path from a terminal access network based on a state space and an action space, using a routing decision model based on the Dykstra algorithm; wherein the routing decision model is obtained through reinforcement learning training based on a reward function constructed based on performance parameters of the terminal access network; the performance parameters include: network delay, packet loss rate, network node idle rate, load balancing entropy, and matching degree between power communication services and network resources.

Images