Position Determination Method for Converged Terminal

Abstract

The present invention provides a method for determining the position of a fusion terminal. The method includes: initializing multiple artificial fish; determining multiple target indicators of a 5G integrated power network based on the initial positions of the fusion terminals in the multiple artificial fish, the positions of the service terminals accessing the fusion terminals, the construction indicators of the communication links in the 5G integrated power network, the preset fusion terminal deployment indicators, and the total number of fusion terminals; performing iterative processing on the multiple artificial fish based on the multiple target indicators, the preset visible range, and the preset artificial fish movement step size to obtain multiple target artificial fish; and determining the positions included in the target artificial fish corresponding to the maximum target indicator among the multiple target artificial fish as the target positions of the respective fusion terminals. The present invention provides a method for determining the position of a fusion terminal to improve the coverage ability for service terminals.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular, to a method for determining the position of a fusion terminal. Background Art

[0002] Currently, with the deep integration of 5G technology and the power industry, a 5G integrated power network that combines 5G technology as the main body and multiple wireless communication systems has emerged. The 5G integrated power network can effectively improve the informatization, digitization, and intelligent level of power grid services.

[0003] In the related art, the deployment quality of the fusion terminals in the 5G integrated power network affects the coverage ability of service terminals and so on.

[0004] Therefore, how to deploy the fusion terminals to improve the coverage ability of service terminals has become a technical problem to be solved urgently. Summary of the Invention

[0005] The present invention provides a method for determining the position of a fusion terminal to solve the problem of the deployment of fusion terminals in the prior art and achieve the purpose of improving the coverage ability of service terminals.

[0006] In a first aspect, the present invention provides a method for determining the position of a fusion terminal, including:

[0007] Initializing multiple artificial fish, where each artificial fish includes the initial positions of the fusion terminals in the 5G integrated power network;

[0008] Based on the multiple artificial fish, the positions of the service terminals accessing the fusion terminals, the construction indexes of the communication links in the 5G integrated power network, the preset fusion terminal deployment indexes, and the total number of the fusion terminals, determining multiple target indexes of the 5G integrated power network; wherein, each service terminal accessing the fusion terminal is located in the 5G integrated power network;

[0009] Performing iterative processing on the multiple artificial fish based on the multiple target indexes and a preset visible range to obtain multiple target artificial fish;

[0010] Determining the positions included in the target artificial fish corresponding to the maximum target index among the multiple target artificial fish as the target positions of the fusion terminals.

[0011] In a second aspect, the present invention further provides a device for determining the position of a fusion terminal, including:

[0012] An initialization module, configured to initialize multiple artificial fish, where each artificial fish includes the initial positions of the fusion terminals in the 5G integrated power network;

[0013] The first determination module is configured to determine multiple target metrics of the 5G converged power network based on the multiple artificial fish, the positions of the service terminals accessing the converged terminal, the construction metrics of the communication links in the 5G converged power network, the preset converged terminal deployment metrics, and the total number of the converged terminals; wherein, each service terminal accessing the converged terminal is located in the 5G converged power network;

[0014] The iteration module is configured to perform iterative processing on the multiple artificial fish based on the multiple target metrics and a preset visual range to obtain multiple target artificial fish;

[0015] The second determination module is configured to determine the target positions of the respective converged terminals as the positions included in the target artificial fish corresponding to the maximum target metric among the multiple target artificial fish.

[0016] In a third aspect, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the program, the method for determining the position of the converged terminal as described in any one of the above is implemented.

[0017] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for determining the position of the converged terminal as described in any one of the above is implemented.

[0018] In a fifth aspect, the present invention further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method for determining the position of the converged terminal as described in any one of the above is implemented.

[0019] The method for determining the position of the converged terminal provided by the present invention initializes multiple artificial fish; determines the coverage rate, QoS metrics, and deployment metrics based on the initial positions of the respective converged terminals in the multiple artificial fish, the positions of the service terminals accessing the converged terminal, the construction metrics of the communication links in the 5G converged power network, the preset converged terminal deployment metrics, and the total number of the converged terminals, determines multiple target metrics of the 5G converged power network based on the coverage rate, QoS metrics, and deployment metrics; performs iterative processing on the multiple artificial fish based on the multiple target metrics and a preset visual range to obtain multiple target artificial fish; determines the target positions of the respective converged terminals as the positions included in the target artificial fish corresponding to the maximum target metric among the multiple target artificial fish, so that the target positions of the converged terminals are obtained, comprehensively considering the influences of the coverage rate, QoS metrics, and deployment metrics, and improving the performance of the 5G converged power network and the coverage ability for the service terminals. Description of the Drawings

[0020] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 It is a schematic diagram of an application scenario provided by the present invention;

[0022] Figure 2 It is a schematic flowchart of the method for determining the position of the fusion terminal provided by the present invention;

[0023] Figure 3 It is a schematic flowchart of the method for determining a target index of the 5G integrated power network provided by the present invention;

[0024] Figure 4 It is a schematic flowchart of the method for determining the coverage rate of the 5G integrated power network provided by the present invention;

[0025] Figure 5 It is a schematic flowchart of the method for determining the QoS index of the 5G integrated power network provided by the present invention;

[0026] Figure 6 It is a schematic flowchart of the method for determining the position of the fusion terminal based on the improved AFSA provided by the present invention;

[0027] Figure 7 It is one of the schematic diagrams of the simulation experiment of the method for determining the position of the fusion terminal provided by the present invention;

[0028] Figure 8 It is another schematic diagram of the simulation experiment of the method for determining the position of the fusion terminal provided by the present invention;

[0029] Figure 9 It is yet another schematic diagram of the simulation experiment of the method for determining the position of the fusion terminal provided by the present invention;

[0030] Figure 10 It is still another schematic diagram of the simulation experiment of the method for determining the position of the fusion terminal provided by the present invention;

[0031] Figure 11 It is a schematic structural diagram of the device for determining the position of the fusion terminal provided by the present invention;

[0032] Figure 12 It is a schematic physical structure diagram of an electronic device provided by the present invention. Detailed implementation manners

[0033] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts shall fall within the protection scope of the present invention.

[0034] In the present invention, the term "including" and its variations may refer to non-limiting inclusion; the term "or" and its variations may refer to "and / or". In the present invention, terms such as "first" and "second" are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence. In the present invention, "at least one" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0035] In the prior art, the deployment advantages and disadvantages of the convergence terminals in the 5G converged power network affect the coverage ability of service terminals. To improve the coverage ability of the convergence terminals for service terminals, the present invention provides a method for determining the positions of convergence terminals. In this method, multiple artificial fish are initialized, and each artificial fish includes the initial positions of the convergence terminals in the 5G converged power network. Based on the Artificial Fish School (AFS) algorithm, iterative processing is performed on the multiple artificial fish to obtain the target positions of the convergence terminals, solving the deployment problem of the convergence terminals in the prior art and improving the coverage ability of service terminals in the 5G converged power network.

[0036] Next, in combination with Figure 1 , the application scenarios of the technical solutions shown in the present invention will be described.

[0037] Figure 1 is a schematic diagram of an application scenario provided by the present invention. As Figure 1 shown, this application scenario includes: a service layer, a cloud transmission network, a base station layer, and a terminal layer.

[0038] Optionally, the service layer may include different types of power services, and different types include at least one of control types, small particle collection types, large bandwidth transmission types, etc. Among them, control types such as intelligent distributed distribution automation and distributed energy regulation; small particle collection types such as power distribution and utilization information collection and power quality monitoring; large bandwidth transmission types such as distribution comprehensive monitoring.

[0039] Optionally, the base station layer may include 5G base stations, 5G NR-U base stations, and satellites.

[0040] Optionally, the terminal layer includes: a fusion terminal and a service terminal accessing the fusion terminal.

[0041] Optionally, the number of fusion terminals can be at least one, and the number of service terminals accessing one fusion terminal can be at least one.

[0042] Optionally, the service terminal can access the fusion terminal by different communication methods. Optionally, the fusion terminal has different communication methods, and at least one service terminal corresponding to each power service can be specified to access the fusion terminal by a unique communication method.

[0043] Optionally, the communication method can be Wi-Fi, Lora (Long Range Radio), Bluetooth, PLC (Programmable Logic Controller), or RS-485, etc.

[0044] Optionally, the fusion terminal can communicate with the cloud transmission network through the base station layer, and the fusion terminal can also directly communicate with the cloud transmission network.

[0045] Optionally, the fusion terminal can also have multi-hop networking capabilities. In the case where the fusion terminal has multi-hop networking capabilities, if the fusion terminal and the service terminal accessing the fusion terminal form a Mesh network, the fusion terminal at the last hop in the Mesh network can communicate with the cloud transmission network through the base station layer or directly communicate with the cloud transmission network; or, if the fusion terminal and the service terminal accessing the fusion terminal form an Integrated Access Backhaul (IAB), the fusion terminal at the last hop in the IAB can communicate with the cloud transmission network through the base station layer.

[0046] Next, in combination with Figure 2 specific embodiments, the method for determining the position of the fusion terminal provided by the present invention will be described.

[0047] Figure 2 is a schematic flowchart of the method for determining the position of the fusion terminal provided by the present invention. As Figure 2 shown, the method for determining the position of the fusion terminal provided in this embodiment includes:

[0048] Step 201, initialize multiple artificial fish, and each artificial fish includes the initial positions of each fusion terminal in the 5G integrated power network.

[0049] Optionally, multiple artificial fish are randomly generated.

[0050] Step 202: Determine multiple target metrics of the 5G integrated power network based on multiple artificial fish, the locations of each service terminal accessing the integrated terminal, the construction metrics of each communication link in the 5G integrated power network, the preset integrated terminal deployment metrics, and the total number of integrated terminals; wherein, each service terminal accessing the integrated terminal is located in the 5G integrated power network.

[0051] For each artificial fish, determine the target metrics of the 5G integrated power network based on the initial locations of each integrated terminal in the artificial fish, the locations of each service terminal accessing the integrated terminal, the construction metrics of each communication link in the 5G integrated power network, the preset integrated terminal deployment metrics, and the total number of integrated terminals.

[0052] Optionally, the construction metrics of each communication link in the 5G integrated power network can be the construction cost per unit length of each communication link.

[0053] Optionally, the preset integrated terminal deployment metrics can be the deployment cost of the integrated terminal.

[0054] Specifically, for a detailed description of determining one target metric of the 5G integrated power network, please refer to Figure 3 the embodiments.

[0055] Step 203: Based on the multiple target metrics and the preset visual range, perform iterative processing on the multiple artificial fish to obtain multiple target artificial fish.

[0056] The preset visual range can be the initialized visual range.

[0057] Optionally, a preset artificial fish movement step size can also be initialized.

[0058] In the case where the preset visual range and the preset artificial fish movement step size are pre-set, the artificial fish school algorithm (AFSA) can be used to perform iterative processing on the multiple artificial fish based on the multiple target metrics, the preset visual range, and the preset artificial fish movement step size to obtain multiple target artificial fish.

[0059] Optionally, when the number of iterations reaches the preset number of iterations, or when other termination conditions are met, end the AFS algorithm to obtain multiple target artificial fish.

[0060] Other termination conditions include that the mean square error of the target metrics obtained continuously for multiple times is less than the preset error threshold, the ratio of the number of artificial fish aggregated in a certain area to the total number of multiple artificial fish is greater than or equal to the preset ratio, reaching a certain ratio, or the mean value obtained continuously for multiple times does not exceed the maximum target metric that has been found, etc.

[0061] Optionally, the preset number of iterations can be, for example, 500, 1000, or 2000, etc.

[0062] In the present invention, the AFSA in the related art can also be improved to obtain the improved AFSA provided by the present invention. By means of the improved AFSA, based on multiple target metrics and a preset visual range, iterative processing is performed on multiple artificial fish to obtain multiple target artificial fish. For a detailed description of the improved AFSA, please refer to Figure 6 the embodiments.

[0063] Step 204: Determine the positions included in the target artificial fish corresponding to the maximum target metric among the multiple target artificial fish as the target positions of each fusion terminal.

[0064] In the present invention, based on multiple target metrics, a preset visual range, and a preset artificial fish movement step size, iterative processing is performed on multiple artificial fish to obtain multiple target artificial fish; the positions included in the target artificial fish corresponding to the maximum target metric among the multiple target artificial fish are determined as the target positions of each fusion terminal, solving the deployment problem of the fusion terminal, thereby improving the coverage ability for service terminals.

[0065] Figure 3 It is a schematic flowchart of a method for determining a target metric of a 5G converged power network provided by the present invention. It should be noted that Figure 3 it is described with the initial positions of each fusion terminal in an artificial fish. As Figure 3 shown, the method includes:

[0066] Step 301: For each fusion terminal, determine the distance between the fusion terminal and each service terminal based on the initial position of the fusion terminal and the positions of each service terminal accessing the fusion terminal.

[0067] For example, when the initial position of the fusion terminal is (x1, x2) and the position of the service terminal accessing the fusion terminal is (y1, y2), the distance between the fusion terminal and the service terminal is

[0068] Step 302: Based on the transmission parameter sets of each service terminal accessing the fusion terminal and the distances between each fusion terminal and each service terminal accessing the fusion terminal, determine the coverage rate of the 5G converged power network.

[0069] Optionally, each transmission parameter set of the service terminal includes: the signal transmission power of the service terminal, the receiving gain of the fusion terminal, the system processing gain between the service terminal and the fusion terminal, a preset propagation loss, a preset signal wavelength, the antenna height of the service terminal, and the antenna height of the fusion terminal.

[0070] Specifically, for the detailed description of determining the coverage rate of the 5G converged power network, please refer to Figure 4 the embodiment.

[0071] Step 303: Determine the QoS indicators of the 5G converged power network based on the distances between each converged terminal and each service terminal accessing the converged terminal, as well as the signal delay and bit error rate of each service terminal accessing the converged terminal.

[0072] Specifically, for the detailed description of determining the QoS indicators of the 5G converged power network, please refer to Figure 5 the embodiment.

[0073] Step 304: Determine the deployment indicators of the 5G converged power network based on the construction indicators of each communication link, the lengths of each communication link, the preset converged terminal deployment indicators, and the total number of converged terminals in the 5G converged power network.

[0074] Specifically, for the detailed description of determining the deployment indicators of the 5G converged power network, please refer to Figure 6 the embodiment.

[0075] Step 305: Determine the target indicators of the 5G converged power network by summing the product of the coverage rate and the first weight, the product of the QoS indicators and the second weight, and the product of the deployment indicators and the third weight.

[0076] Optionally, the target indicators of the 5G converged power network can also be obtained by processing the coverage rate, QoS indicators, and deployment indicators through a first preset model.

[0077] The first preset model is:

[0078] where f(x) represents the target indicators of the 5G converged power network, α1 represents the first weight, f1(x) represents the coverage rate of the 5G converged power network, α2 represents the second weight, f2(x) represents the QoS indicators of the 5G converged power network, α3 represents the third weight, f3(x) represents the deployment indicators of the 5G converged power network, R cov (rh b ) represents the coverage rate of the b-th converged terminal, rh b represents the set of each service terminal accessing the b-th converged terminal, b = 1......B, B represents the total number of converged terminals in the 5G converged power network, R comin represents the coverage rate threshold, R QoS (rh b ) represents the QoS indicators of the b-th converged terminal, R QoSmmin represents the QoS indicator threshold.

[0079] Optionally, the first weight, the second weight, and the third weight are determined by the judgment matrix in the analytic hierarchy process.

[0080] Optionally, the judgment matrix is: It should be noted that the values of the elements in the judgment matrix are different preset values set according to requirements.

[0081] According to the judgment matrix, the weight matrix corresponding to the first weight, the second weight, and the third weight is determined as: [α1, α2, α3].

[0082] In the present invention, based on the coverage rate, QoS index, and deployment index of the 5G integrated power network, the target index of the 5G integrated power network is determined, so that the target position of the integrated terminal determined based on the target index can comprehensively consider the influence of the coverage rate, QoS index, and deployment index of the 5G integrated power network on the 5G integrated power network, improving the reliability of the 5G integrated power network.

[0083] Figure 4 It is a schematic flow chart of the method for determining the coverage rate of the 5G integrated power network provided by the present invention. As Figure 4 shown, the method includes:

[0084] It should be noted that steps 401 to 403 are executed for each service terminal accessing the integrated terminal.

[0085] Step 401: Based on the antenna height of the service terminal, the antenna height of the integrated terminal, and the preset signal wavelength, determine the diameter length of the Fresnel zone.

[0086] Optionally, the diameter length of the Fresnel zone is determined by a second preset model.

[0087] The second preset model is:

[0088] where D f represents the diameter length of the Fresnel zone, h t represents the antenna height of the service terminal, h r represents the antenna height of the integrated terminal, and λ represents the preset signal wavelength.

[0089] Optionally, the preset signal wavelength can be equal to the speed of light.

[0090] Step 402: Based on the preset signal wavelength, the distance between the integrated terminal and the service terminal, and the diameter length of the Fresnel zone, determine the direct wave path loss.

[0091] Optionally, the direct wave path loss is determined by a third preset model.

[0092] The third preset model is:

[0093]

[0094] Among them, L Los (d k ) represents the direct wave path loss of the k-th service terminal, π represents the pi, d k represents the distance between the fusion terminal and the k-th service terminal, λ represents the preset signal wavelength, D f represents the diameter length of the Fresnel region, and γ represents the distance attenuation factor.

[0095] Step 403: Through the signal strength value determination model, process the signal transmission power, direct wave path loss, preset propagation loss, receiving gain of the fusion terminal, and system processing gain of the service terminal to obtain the signal strength value of the service terminal.

[0096] Optionally, the signal strength value determination model is:

[0097] P RSSI (d k ) = P Tx -L Los (d k ) - L0 + G Rx +G System ;

[0098] Among them, P RSSI (d k ) represents the signal strength value of the k-th service terminal, P Tx represents the signal transmission power of the service terminal, L Los (d k ) represents the direct wave path loss of the k-th service terminal, L0 represents the preset propagation loss, G Rx represents the receiving gain of the fusion terminal, G System represents the system processing gain.

[0099] Optionally, the preset propagation loss can be the loss generated by the signal being affected by buildings in the propagation path.

[0100] Step 404: Determine the ratio of the total number of service terminals with signal strength values greater than the preset strength threshold among all service terminals to the total number of all service terminals as the coverage rate of the fusion terminal.

[0101] Optionally, through the fourth preset model, determine the coverage rate of the fusion terminal.

[0102] The fourth preset model is:

[0103] Among them, R cov (rh b) represents the coverage rate of the b-th fusion terminal, rh b represents the set composed of each service terminal accessing the b-th fusion terminal, b = 1......B, B represents the total number of fusion terminals in the 5G integrated power network, N cov (rh b ) represents rh b the total number of service terminals in rh Total (rh b ) represents rh b the total number of service terminals in rh

[0104] Step 405: Determine the average value of the coverage rates of each fusion terminal as the coverage rate of the 5G integrated power network.

[0105] Optionally, determine the coverage rate of the 5G integrated power network through the fifth preset model.

[0106] The fifth preset model is:

[0107] Among them, R cov represents the coverage rate of the 5G integrated power network, B represents the total number of fusion terminals in the 5G integrated power network, R cov (rh b ) represents the coverage rate of the b-th fusion terminal.

[0108] In the present invention, based on the set of transmission parameters of each service terminal accessing the fusion terminal and the distances between each fusion terminal and each service terminal accessing the fusion terminal, the signal strength value of the service terminal is determined. Considering the requirements of different service terminals and different communication methods for the signal strength value, the ratio of the total number of service terminals with a signal strength value greater than the preset strength threshold among each service terminal to the total number of each service terminal is determined as the coverage rate of the fusion terminal, and the average value of the coverage rates of each fusion terminal is determined as the coverage rate of the 5G integrated power network, so that the obtained coverage rate of the 5G integrated power network has higher accuracy.

[0109] Figure 5 is the schematic diagram of the method flow for determining the QoS index of the 5G integrated power network provided by the present invention. As Figure 5 shown, the method includes:

[0110] For each service terminal accessing the fusion terminal, perform the following steps 501 and 502.

[0111] Step 501: Based on the distance between the fusion terminal and the service terminal, determine the signal transmission rate of the service terminal.

[0112] The model of the network where the fusion terminal and the service terminal are located can be a direct connection network model or a multi-hop network model.

[0113] In the direct connection network model, the fusion terminal is the target fusion terminal directly connected to the service terminal by the above communication method, and the target fusion terminal is the fusion terminal closest to the service terminal in the 5G integrated power network.

[0114] In the multi-hop network model, the fusion terminal is the last-hop fusion terminal in Mesh networking or IAB.

[0115] When the model of the network where the fusion terminal and the service terminal are located is a direct connection network model, the signal transmission rate of the service terminal is determined by Method 11.

[0116] When the model of the network where the fusion terminal and the service terminal are located is a multi-hop network model, the signal transmission rate of the service terminal is determined by Method 12.

[0117] Method 11 processes the distance between the fusion terminal and the service terminal, the bandwidth of the communication channel between the fusion terminal and the service terminal, and the noise power of the communication channel through the first signal transmission rate determination model of the service terminal to obtain the signal transmission rate of the service terminal;

[0118] The first signal transmission rate determination model of the service terminal is:

[0119]

[0120] where λ k represents the signal transmission rate of the k-th service terminal, W represents the bandwidth of the communication channel, p k represents the signal transmission power of the k-th service terminal, d k represents the distance between the fusion terminal and the k-th service terminal, h(d k ) represents the gain of the communication channel determined based on d k , σ 2 represents the noise power of the communication channel, and log represents the logarithm operation.

[0121] The channel gain calculation model based on Rayleigh fading is:

[0122] where A d represents the antenna gain, f c is the carrier frequency, d e represents the path loss exponent, represents following the Rayleigh distribution.

[0123] Method 12: Through the signal transmission rate second determination model of the service terminal, process the distance between the fusion terminal and the service terminal, the bandwidth of the communication channel between the fusion terminal and the service terminal, the noise power of the communication channel, the preset attenuation factor, and the total number of hops between the service terminal and the fusion terminal, to obtain the signal transmission rate of the service terminal;

[0124] The second determination model of the signal transmission rate of the service terminal is:

[0125]

[0126] where λ k represents the signal transmission rate of the k-th service terminal, α represents the preset attenuation factor, N represents the total number of hops between the service terminal and the fusion terminal, W represents the bandwidth of the communication channel, p k represents the signal transmission power of the k-th service terminal, d k represents the distance between the fusion terminal and the k-th service terminal, h(d k ) represents the gain of the communication channel determined based on d k σ represents the noise power of the communication channel. 2

[0127] Step 502: Through the QoS index determination model, process the signal transmission rate, signal delay, and bit error rate of the service terminal, to obtain the QoS index of the service terminal.

[0128] Optionally, in the case of determining the signal transmission rate of the service terminal by using Method 11, determine the signal delay of the service terminal by using Method 21; in the case of determining the signal transmission rate of the service terminal by using Method 12, determine the signal delay of the service terminal by using Method 22.

[0129] Method 21: Based on the distance between the fusion terminal and the service terminal, determine the signal propagation delay; determine the sum of the signal transmission delay and the signal propagation delay of the service terminal as the signal delay of the service terminal.

[0130] Specifically, T c (d k ) represents the signal propagation delay of the k-th service terminal, d k represents the distance between the fusion terminal and the k-th service terminal, and V represents the signal propagation speed.

[0131] Optionally, determine the signal delay of the service terminal through the sixth preset model.

[0132] The sixth preset model is: T k = T Tx，k + T​c (d k );

[0133] Among them, T k represents the signal delay of the k-th service terminal, and T Tx，k represents the signal transmission delay of the k-th service terminal.

[0134] Method 22: For each hop link between the service terminal and the fusion terminal, based on the distance between the two terminals in the link, determine the signal propagation delay; the sum of the signal processing delay, the preset signal retransmission delay, and the signal propagation delay of the fusion terminal among the two terminals is determined as the total delay of the link; the sum of the total delays of each hop link is determined as the signal delay of the service terminal.

[0135] Optionally, the total delay of the link is determined through the seventh preset model.

[0136] The seventh preset model is: t n，k =t o +t r +t c (d k );

[0137] Among them, t n，k represents the total delay of the n-th hop link of the k-th service terminal, t o represents the processing delay, t r represents the preset signal retransmission delay, t c (d k ) represents the signal propagation delay, and d k represents the distance between the two terminals in the link.

[0138] Optionally, in some application scenarios, the preset signal retransmission delay t r (d k ) can also be determined based on the distance between the two terminals in the link.

[0139] Optionally, the signal delay of the service terminal is determined through the eighth preset model.

[0140] The eighth preset model is:

[0141] Among them, T k represents the signal delay of the k-th service terminal, N represents the total number of hops between the service terminal and the fusion terminal, and t n，k represents the total delay of the n-th hop link of the k-th service terminal.

[0142] Optionally, the QoS index of the service terminal is determined through the ninth preset model.

[0143] The ninth preset model is:

[0144] Among them, QoS k represents the QoS index of the kth service terminal, ε k represents the bit error rate of the kth service terminal, W represents the bandwidth of the communication channel, and p k represents the signal transmission power of the kth service terminal, h(d k ) indicates that based on d k Determine the gain of the communication channel, σ 2 represents the noise power of the communication channel, T k Represents the signal delay of the kth service terminal.

[0145] Step 503: Determine the ratio of the total number of service terminals whose QoS indicators are greater than a preset QoS indicator threshold value to the total number of service terminals as the QoS indicator of the converged terminal.

[0146] Optionally, the QoS indicator of the converged terminal is determined through a tenth preset model.

[0147] The tenth preset model is:

[0148] Among them, R QoS (rh b ) represents the QoS index of the converged terminal, N QoS (rh b ) indicates rh b The total number of service terminals whose QoS index is greater than the preset QoS index threshold, N Total (rh b ) indicates rh b The total number of business terminals in the

[0149] Optionally, for each service of the service terminal, there is a preset QoS indicator threshold, and the preset QoS indicator threshold can be determined through an eleventh preset model.

[0150] The eleventh preset model is:

[0151] Among them, QoS min，k represents the preset QoS indicator threshold of the kth service terminal, ε max，k represents the preset bit error rate of the kth service, V max，k represents the service demand transmission rate of the kth service terminal, T max，k Indicates the preset delay threshold of the kth service terminal.

[0152] Step 504: Determine the average value of the QoS indicators of each integrated terminal as the initial QoS indicator of the 5G integrated power network.

[0153] Optionally, an initial QoS metric of the 5G converged power network is determined by a twelfth preset model.

[0154] The twelfth preset model is:

[0155] Wherein, R QoS represents the initial QoS metric of the 5G converged power network, B represents the total number of converged terminals in the 5G converged power network, and R QoS (rh b ) represents the QoS metric of the b-th converged terminal.

[0156] In the present invention, based on the signal transmission rate, signal delay, and bit error rate of the service terminal, the QoS metric of the service terminal is obtained. Based on the QoS metric of the service terminal and the preset QoS metric threshold, the QoS metric of the converged terminal is determined, so that the determined QoS metric of the converged terminal meets the requirements of different services processed by different service terminals for communication quality, and finally the service quality of the 5G converged power network for different services is improved.

[0157] In some embodiments, determining the deployment metrics of the 5G converged power network includes:

[0158] Through a deployment metric determination model, the construction metrics of each communication link, the length of each communication link, each preset converged terminal deployment metric, and the total number of converged terminals in the 5G converged power network are processed to obtain the deployment metrics of the 5G converged power network;

[0159] The deployment metric determination model is:

[0160] Wherein, f3 represents the deployment metrics of the 5G converged power network, L represents the total number of each communication link, represents the construction metric of the communication link , represents the length of the communication link , r_cost represents the preset converged terminal deployment metric, and B represents the total number of converged terminals.

[0161] Optionally, the construction metric of the communication link can be the construction cost per unit length of different types of communication links.

[0162] Optionally, the preset converged terminal deployment metric can be the construction cost of the converged terminal.

[0163] Figure 6 is a schematic flow diagram of the method for determining the location of the converged terminal based on the improved AFSA provided by the present invention. As Figure 6 shown, the method includes:

[0164] Step 601: Set initial parameters, where the initial parameters include parameters such as a preset visual range and a preset number of iterations.

[0165] Step 602: Generate multiple artificial fish.

[0166] Optionally, randomly generate multiple artificial fish.

[0167] Step 603: Based on the multiple artificial fish, the positions of each service terminal connected to the convergence terminal, the construction metrics of each communication link in the 5G converged power network, the preset convergence terminal deployment metrics, and the total number of convergence terminals, determine multiple target metrics of the 5G converged power network.

[0168] Step 604: When the maximum value among the multiple target metrics is greater than the value currently recorded in the bulletin board, update the bulletin board.

[0169] Optionally, the bulletin board also includes the number and position of the convergence terminals corresponding to the value currently recorded.

[0170] Step 605: Evaluate each artificial fish, update the preset visual range, process the updated visual range to obtain an updated artificial fish movement step size, select the behavior to be executed next based on the updated visual range and the updated artificial fish movement step size, execute the selected behavior, and update each artificial fish to obtain a new set of multiple artificial fish.

[0171] Optionally, update the preset visual range through a first update model to obtain an updated visual range; process the updated visual range through a second update model to obtain an updated artificial fish movement step size; wherein, the updated visual range and the updated artificial fish movement step size are used for iterative processing.

[0172] The first update model is:

[0173] wherein, Visual i+1 represents the visual range after the (i + 1)-th update, Visual i represents the visual range after the i-th update, Visual min represents the preset minimum visual range, in the case where i is equal to 0, Visual0 represents the preset visual range, μ represents the preset weight threshold, and μ ∈ (0, 1).

[0174] The second update model is: step i+1 = v * Visual i+1 ;

[0175] wherein, step i+1$step_{i + 1}$ represents the moving step of the artificial fish after the $(i + 1)$-th update, $v$ represents the preset control coefficient, and $\beta\in(0, 1)$. $step_0 = v * Visual_0$. $step_0$ represents the preset moving step of the artificial fish.

[0176] Among them, the behaviors to be executed next may include at least one of the following: foraging behavior, schooling behavior, and following behavior.

[0177] Optionally, the foraging behavior includes the following first to third steps:

[0178] First step, each artificial fish randomly selects a point $(X, Y)$ within the visual range v .

[0179] Second step, when the food concentration at the point $(X, Y)$ (i.e., the value currently recorded in the bulletin board) is higher than the food concentration at the current location of the artificial fish, the artificial fish moves in the direction of the point $(X, Y)$ v by $step$ v . If the food concentration at the point $(X, Y)$ i+1 is lower than or equal to the food concentration at the current location of the artificial fish, the first to second steps are repeated. v

[0180] Third step, within the preset number of selections, if the randomly selected point by the artificial fish does not meet the moving conditions, the artificial fish moves randomly by one step.

[0181] Optionally, the schooling behavior includes:

[0182] Each artificial fish first searches for the positions of other artificial fish within the visual range, calculates the center position of other artificial fish, the food concentration at this center position, and the food concentration at the current location of the artificial fish;

[0183] When the food concentration at the center position is higher than the food concentration at the current location of the artificial fish and the density of artificial fish at the center position is low, move towards this center position;

[0184] When the food concentration at the center position is lower than or equal to the food concentration at the current location of the artificial fish, execute the foraging behavior.

[0185] Optionally, the following behavior includes:

[0186] Each artificial fish searches for the positions of adjacent artificial fish within the visual range;

[0187] When the food concentration at the position of the optimal adjacent artificial fish is higher than the food concentration at the current location of the artificial fish and the density of artificial fish is low, then move towards the position of the optimal adjacent artificial fish;

[0188] ​​Forage behavior is executed when the food concentration at the position of the optimal adjacent artificial fish is lower than or equal to the food concentration at the current position of the artificial fish.

[0189] Step 606: Based on the new multiple artificial fish, repeat steps 603 to 604. When the number of iterations is greater than or equal to the preset number of iterations or other termination conditions are met, end the iteration to obtain multiple target artificial fish.

[0190] Step 607: Determine the positions included in the target artificial fish corresponding to the maximum target index among the multiple target artificial fish as the target positions of the respective fusion terminals.

[0191] Specifically, after obtaining the multiple target artificial fish, repeat step 603 based on the multiple target artificial fish to obtain multiple target indexes of the 5G integrated power network (i.e., the target indexes corresponding to the respective target artificial fish);

[0192] Determine the positions included in the target artificial fish corresponding to the maximum target index as the target positions of the respective fusion terminals.

[0193] In the present invention, based on the AFS algorithm to determine the positions of the fusion terminals, using the coverage rate, QoS index, and deployment index as the target indexes, and determining the positions included in the target artificial fish corresponding to the maximum target index as the target positions of the respective fusion terminals, improves the accuracy of the obtained target positions, enabling an optimal fusion terminal deployment plan to be finally obtained.

[0194] Figure 7 It is one of the schematic diagrams of the simulation experiment of the method for determining the positions of the fusion terminals provided by the present invention. As Figure 7 shown, it includes: Result 1 of the comparison of the algorithm performances of the improved AFSA, genetic algorithm (GA), and Greedy Algorithm (Greedy).

[0195] The simulation conditions for obtaining Result 1 are: the number of types of communication methods of the service terminals is 4, the positions of the service terminals are randomly generated, the communication methods of each service terminal are randomly specified, the number of base stations is 3, the construction cost of each fusion terminal is 10, the preset attenuation factor is 0.8, the first weight is 0.680, the second weight is 0.319, the third weight is 0.001, the preset number of iterations is 2000, the number of fusion terminals is 20, the number of artificial fish is 70, and the network scale is 100×100.

[0196] Figure 8 It is the second schematic diagram of the simulation experiment of the method for determining the positions of the fusion terminals provided by the present invention. As Figure 8As shown, it includes: the second comparison result of the algorithm performance of the improved AFSA, GA, and Greedy algorithm (Greedy).

[0197] The simulation conditions for obtaining the second result are as follows: the number of types of communication methods of service terminals is 4, the positions of service terminals are randomly generated, the communication method of each service terminal is randomly specified, the number of base stations is 3, the construction cost of each fusion terminal is 10, the preset attenuation factor is 0.8, the first weight is 0.680, the second weight is 0.319, the third weight is 0.001, the preset number of iterations is 2000, the number of fusion terminals is 20, the number of artificial fish is 70, and the network scale is 120×120.

[0198] Figure 9 It is the third schematic diagram of the simulation experiment of the method for determining the position of the fusion terminal provided by the present invention. As Figure 9 shown, it includes: the third comparison result of the algorithm performance of the improved AFSA, GA, and Greedy.

[0199] The simulation conditions for obtaining the third result are as follows: the number of types of communication methods of service terminals is 4, the positions of service terminals are randomly generated, the communication method of each service terminal is randomly specified, the number of base stations is 3, the construction cost of each fusion terminal is 10, the preset attenuation factor is 0.8, the first weight is 0.680, the second weight is 0.319, the third weight is 0.001, the preset number of iterations is 2000, the number of fusion terminals is 20, the number of artificial fish is 70, and the network scale is 150×150.

[0200] Figure 10 It is the fourth schematic diagram of the simulation experiment of the method for determining the position of the fusion terminal provided by the present invention. As Figure 10 shown, it includes: the fourth comparison result of the algorithm performance of the improved AFSA, GA, and Greedy.

[0201] The simulation conditions for obtaining the fourth result are as follows: the number of types of communication methods of service terminals is 4, the positions of service terminals are randomly generated, the communication method of each service terminal is randomly specified, the number of base stations is 3, the construction cost of each fusion terminal is 10, the preset attenuation factor is 0.8, the first weight is 0.680, the second weight is 0.319, the third weight is 0.001, the preset number of iterations is 2000, the number of fusion terminals is 20, the number of artificial fish is 70, and the network scale is 170×170.

[0202] Figures 7 to 10 The processing platform involved includes Python 3.10 and Visual Studio Code.

[0203] From Figures 7 to 10It can be seen that under four different network scales, the performance of the improved AFSA method proposed by the present invention is superior to that of the genetic algorithm and the greedy algorithm. Among them, the genetic algorithm and the greedy algorithm enter the algorithm bottleneck and fall into the local optimal solution when the number of iterations is about 300 rounds. However, for the improved AFSA method of the present invention, the Visual and Step step sizes are adjusted as the number of iterations increases, making the later search more refined, increasing the ability and stability to search for the optimal value, enabling the method to search for a better objective function value and having better optimization performance.

[0204] Meanwhile, as the network scale increases, the number of service terminals in the 5G converged power network increases, and the optimization target space expands. The number of iterations at which the comparison algorithms fall into the local optimal solution becomes smaller and smaller. When the network scale is 150×150 and 170×170, the comparison algorithms fall into the local extreme value when the number of iterations is nearly 200 rounds. However, when the search space is large, the improved AFSA method of the present invention still performs well, and the artificial fish swarm can fully search the area. The method proposed by the present invention can more easily find the optimal multi-link fusion communication terminal deployment scheme within the area.

[0205] Next, the position determination device for the fusion terminal provided by the present invention will be described. The position determination device for the fusion terminal described below can be mutually corresponded and referred to the position determination method for the fusion terminal described above.

[0206] Figure 11 is a schematic structural diagram of the position determination device for the fusion terminal provided by the present invention. As Figure 11 shown, the position determination device for the fusion terminal includes:

[0207] An initialization module 1110, configured to initialize multiple artificial fish, and each artificial fish includes the initial positions of each fusion terminal in the 5G converged power network;

[0208] A first determination module 1120, configured to determine multiple target indicators of the 5G converged power network based on the multiple artificial fish, the positions of each service terminal accessing the fusion terminal, the construction indicators of each communication link in the 5G converged power network, a preset fusion terminal deployment indicator, and the total number of the fusion terminals; wherein, each service terminal accessing the fusion terminal is located in the 5G converged power network;

[0209] An iteration module 1130, configured to perform iterative processing on the multiple artificial fish based on the multiple target indicators and a preset visual range to obtain multiple target artificial fish;

[0210] A second determination module 1140, configured to determine the positions included in the target artificial fish corresponding to the maximum target indicator among the multiple target artificial fish as the target positions of each fusion terminal.

[0211] A training device for a cloud detection model provided by the present invention, the first determination module 1120 is specifically configured to:

[0212] For the initial positions of each fusion terminal in the artificial fish, based on the initial positions of the fusion terminals and the positions of each service terminal accessing the fusion terminals, determine the distances between the fusion terminals and each service terminal;

[0213] Based on the transmission parameter sets of each service terminal accessing the fusion terminals and the distances between each fusion terminal and each service terminal accessing the fusion terminals, determine the coverage rate of the 5G fusion power network;

[0214] Based on the distances between each fusion terminal and each service terminal accessing the fusion terminals, as well as the signal delay and bit error rate of each service terminal accessing the fusion terminals, determine the QoS index of the 5G fusion power network;

[0215] Based on the construction indexes of each communication link in the 5G fusion power network, the lengths of each communication link, the preset fusion terminal deployment index, and the total number of fusion terminals, determine the deployment index of the 5G fusion power network;

[0216] Determine the sum of the product of the coverage rate and the first weight, the product of the QoS index and the second weight, and the product of the deployment index and the third weight as the target index of the 5G fusion power network.

[0217] A training device for a cloud detection model provided by the present invention, the first determination module 1120 is specifically configured to:

[0218] Based on the transmission parameter sets of each service terminal accessing the fusion terminals and the distances between each fusion terminal and each service terminal accessing the fusion terminals, determining the coverage rate of the 5G fusion power network includes:

[0219] For each service terminal accessing the fusion terminal, based on the antenna height of the service terminal, the antenna height of the fusion terminal, and the preset signal wavelength, determine the diameter length of the Fresnel region; based on the preset signal wavelength, the distance between the fusion terminal and the service terminal, and the diameter length, determine the direct wave path loss; through the signal strength value determination model, process the signal transmission power of the service terminal, the direct wave path loss, the preset propagation loss, the receiving gain of the fusion terminal, and the system processing gain to obtain the signal strength value of the service terminal;

[0220] Determine the ratio of the total number of service terminals with signal strength values greater than a preset strength threshold among the service terminals to the total number of the service terminals as the coverage rate of the fusion terminal;

[0221] Determine the average value of the coverage rates of the fusion terminals as the coverage rate of the 5G integrated power network.

[0222] According to a training device for a cloud detection model provided by the present invention, the first determination module 1120 is specifically configured to:

[0223] Perform the following operations on each service terminal accessing the fusion terminal:

[0224] Based on the distance between the fusion terminal and the service terminal, determine the signal transmission rate of the service terminal;

[0225] Through a QoS metric determination model, process the signal transmission rate, signal delay, and bit error rate of the service terminal to obtain the QoS metric of the service terminal;

[0226] Determine the ratio of the total number of service terminals with QoS metrics greater than a preset QoS metric threshold among the service terminals to the total number of the service terminals as the QoS metric of the fusion terminal;

[0227] Determine the average value of the QoS metrics of the fusion terminals as the initial QoS metric of the 5G integrated power network.

[0228] According to a training device for a cloud detection model provided by the present invention, the first determination module 1120 is specifically configured to:

[0229] Through a first signal transmission rate determination model of the service terminal, process the distance between the fusion terminal and the service terminal, the bandwidth of the communication channel between the fusion terminal and the service terminal, and the noise power of the communication channel to obtain the signal transmission rate of the service terminal;

[0230] The first signal transmission rate determination model of the service terminal is:

[0231]

[0232] where λ k represents the signal transmission rate of the service terminal, W represents the bandwidth of the communication channel, p k represents the signal transmission power of the service terminal, d k represents the distance between the fusion terminal and the service terminal, h(d k ) represents based on d kThe gain of the determined communication channel, σ 2 Represents the noise power of the communication channel.

[0233] A training device for a cloud detection model provided by the present invention, the first determination module 1120 is specifically configured to:

[0234] Based on the distance between the fusion terminal and the service terminal, determine the signal propagation delay;

[0235] Determine the sum of the signal transmission delay of the service terminal and the signal propagation delay as the signal delay of the service terminal.

[0236] A training device for a cloud detection model provided by the present invention, the first determination module 1120 is specifically configured to:

[0237] Through the signal transmission rate second determination model of the service terminal, process the distance between the fusion terminal and the service terminal, the bandwidth of the communication channel between the fusion terminal and the service terminal, the noise power of the communication channel, the preset attenuation factor, and the total number of hops between the service terminal and the fusion terminal, to obtain the signal transmission rate of the service terminal;

[0238] The signal transmission rate second determination model of the service terminal is:

[0239]

[0240] Where λ k Represents the signal transmission rate of the service terminal, α represents the preset attenuation factor, N represents the total number of hops between the service terminal and the fusion terminal, W represents the bandwidth of the communication channel, p k Represents the signal transmission power of the service terminal, d k Represents the distance between the fusion terminal and the service terminal, h(d k ) Represents the gain of the determined communication channel based on d k

[0241] A training device for a cloud detection model provided by the present invention, the first determination module 1120 is specifically configured to:

[0242] For each hop link between the service terminal and the fusion terminal, based on the distance between the two terminals in the link, respectively determine the preset signal retransmission delay and the signal propagation delay;

[0243] Determine the sum of the signal processing delay of the fusion terminal in the two terminals, the preset signal retransmission delay, and the signal propagation delay as the total delay of the link; ​

[0244] Determine the sum of the total delays of each hop link as the signal delay of the service terminal.

[0245] According to a training device for a cloud detection model provided by the present invention, the first determination module 1120 is specifically configured to:

[0246] Process the construction metrics of each communication link, the length of each communication link, the deployment metrics of each preset fusion terminal, and the total number of fusion terminals in the 5G converged power network through a deployment metric determination model to obtain the deployment metrics of the 5G converged power network;

[0247] The deployment metric determination model is:

[0248]

[0249] where f3 represents the deployment metrics of the 5G converged power network, L represents the total number of each communication link, represents the construction metrics of communication link , represents the length of communication link , r_cost represents the deployment metrics of the preset fusion terminal, and B represents the total number of fusion terminals.

[0250] According to a training device for a cloud detection model provided by the present invention, the iteration module 1130 is specifically configured to:

[0251] Update the preset visual range through a first update model to obtain an updated visual range; process the updated visual range through a second update model to obtain an updated artificial fish movement step; wherein, the updated visual range and the updated artificial fish movement step are used for the iterative process;

[0252] The first update model is:

[0253]

[0254] where Visual i+1 represents the visual range after the (i + 1)-th update, Visual i represents the visual range after the i-th update, Visual min represents the preset minimum visual range. When i is equal to 0, Visual0 represents the preset visual range, and μ represents the preset weight threshold;

[0255] The second update model is: step i+1 = v * Visual i+1 ;

[0256] where step i+1 represents the moving step of the artificial fish after the (i + 1)-th update, and v represents a preset control coefficient.

[0257] Figure 12 FIG. shows a schematic physical structure diagram of an electronic device, as Figure 8 shown, the electronic device may include: a processor 1210, a communications interface 1220, a memory 1230, and a communication bus 1240. Among them, the processor 1210, the communications interface 1220, and the memory 1230 communicate with each other through the communication bus 1240. The processor 1210 may call logic instructions in the memory 1230 to execute a method for determining the position of a convergence terminal. The method includes:

[0258] Initializing multiple artificial fish, where each artificial fish includes the initial positions of each convergence terminal in the 5G converged power network; determining multiple target metrics of the 5G converged power network based on the multiple artificial fish, the positions of each service terminal accessing the convergence terminal, the construction metrics of each communication link in the 5G converged power network, a preset convergence terminal deployment metric, and the total number of the convergence terminals; where each service terminal accessing the convergence terminal is located in the 5G converged power network; performing iterative processing on the multiple artificial fish based on the multiple target metrics and a preset visual range to obtain multiple target artificial fish; and determining the target positions of each convergence terminal as the positions included in the target artificial fish corresponding to the maximum target metric among the multiple target artificial fish.

[0259] In addition, when the logic instructions in the above-mentioned memory 1230 are implemented in the form of software functional units and sold or used as an independent product, they may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0260] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the location determination method of the fusion terminal provided by the above-mentioned various methods. The method includes: initializing multiple artificial fish, where each artificial fish includes the initial positions of the fusion terminals in the 5G fusion power network; based on the multiple artificial fish, the positions of the service terminals accessing the fusion terminals, the construction indicators of the communication links in the 5G fusion power network, the preset fusion terminal deployment indicators, and the total number of the fusion terminals, determining multiple target indicators of the 5G fusion power network; where each service terminal accessing the fusion terminal is located in the 5G fusion power network; based on the multiple target indicators and the preset visual range, performing iterative processing on the multiple artificial fish to obtain multiple target artificial fish; and determining the positions included in the target artificial fish corresponding to the maximum target indicator among the multiple target artificial fish as the target positions of the respective fusion terminals.

[0261] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the location determination method of the fusion terminal provided by the above-mentioned various methods. The method includes: initializing multiple artificial fish, where each artificial fish includes the initial positions of the fusion terminals in the 5G fusion power network; based on the multiple artificial fish, the positions of the service terminals accessing the fusion terminals, the construction indicators of the communication links in the 5G fusion power network, the preset fusion terminal deployment indicators, and the total number of the fusion terminals, determining multiple target indicators of the 5G fusion power network; where each service terminal accessing the fusion terminal is located in the 5G fusion power network; based on the multiple target indicators and the preset visual range, performing iterative processing on the multiple artificial fish to obtain multiple target artificial fish; and determining the positions included in the target artificial fish corresponding to the maximum target indicator among the multiple target artificial fish as the target positions of the respective fusion terminals.

[0262] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.

[0263] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0264] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining the position of a fusion terminal, characterized in that The method includes: Initializing multiple artificial fish, where each artificial fish includes the initial positions of each fusion terminal in the 5G converged power network; For the initial positions of each fusion terminal in the artificial fish, based on the initial positions of the fusion terminals and the positions of each service terminal accessing the fusion terminals, determining the distances between the fusion terminals and each service terminal; wherein, each service terminal accessing the fusion terminals is located in the 5G converged power network; Based on the set of transmission parameters of each service terminal accessing the fusion terminals, the distances between each fusion terminal and each service terminal accessing the fusion terminal, determining the coverage rate of the 5G converged power network; Based on the distances between each fusion terminal and each service terminal accessing the fusion terminal, as well as the signal delay and bit error rate of each service terminal accessing the fusion terminal, determining the QoS index of the 5G converged power network; Based on the construction indexes of each communication link in the 5G converged power network, the lengths of each communication link, the preset fusion terminal deployment index, and the total number of fusion terminals, determining the deployment index of the 5G converged power network; the construction index of each communication link in the 5G converged power network is the construction cost per unit length of each communication link; the preset fusion terminal deployment index is the deployment cost of the fusion terminal; Determining the sum of the product of the coverage rate and the first weight, the product of the QoS index and the second weight, and the product of the deployment index and the third weight as the target index of the 5G converged power network; Based on the multiple target indexes and the preset visual range, performing iterative processing on the multiple artificial fish to obtain multiple target artificial fish; Determining the positions included in the target artificial fish corresponding to the maximum target index among the multiple target artificial fish as the target positions of each fusion terminal; The determining the deployment index of the 5G converged power network based on the construction indexes of each communication link in the 5G converged power network, the lengths of each communication link, the preset fusion terminal deployment index, and the total number of fusion terminals includes: Processing the construction indexes of each communication link in the 5G converged power network, the lengths of each communication link, the preset fusion terminal deployment indexes, and the total number of fusion terminals through a deployment index determination model to obtain the deployment index of the 5G converged power network; The deployment index determination model is: Among them, f3 represents the deployment index of the 5G converged power network, L represents the total number of the communication links, represents the construction index of the communication link , represents the length of the communication link , r_cost represents the preset deployment index of the converged terminal, and B represents the total number of the converged terminals.

2. The method according to claim 1, wherein The set of transmission parameters of the service terminal includes: the signal transmission power of the service terminal, the receiving gain of the fusion terminal, the system processing gain between the service terminal and the fusion terminal, the preset propagation loss, the preset signal wavelength, the antenna height of the service terminal, the antenna height of the fusion terminal; Based on the set of transmission parameters of each service terminal accessing the fusion terminals, the distances between each fusion terminal and each service terminal accessing the fusion terminal, determining the coverage rate of the 5G converged power network includes: For each service terminal accessing the integrated terminal, based on the antenna height of the service terminal, the antenna height of the integrated terminal, and the preset signal wavelength, determine the diameter length of the Fresnel region; based on the preset signal wavelength, the distance between the integrated terminal and the service terminal, and the diameter length, determine the direct wave path loss; through a signal strength value determination model, process the signal transmission power of the service terminal, the direct wave path loss, the preset propagation loss, the receiving gain of the integrated terminal, and the system processing gain to obtain the signal strength value of the service terminal; Determine the ratio of the total number of service terminals with signal strength values greater than a preset strength threshold among the service terminals to the total number of the service terminals as the coverage rate of the integrated terminal; Determine the average value of the coverage rates of the integrated terminals as the coverage rate of the 5G integrated power network.

3. The method according to claim 1, wherein Based on the distances between the integrated terminals and the service terminals accessing the integrated terminals, as well as the signal delay and error rate of the service terminals accessing the integrated terminals, determine the QoS indicators of the 5G integrated power network, including: Perform the following operations for each service terminal accessing the integrated terminal: Based on the distance between the integrated terminal and the service terminal, determine the signal transmission rate of the service terminal; Through a QoS indicator determination model, process the signal transmission rate of the service terminal, the signal delay of the service terminal, and the error rate to obtain the QoS indicator of the service terminal; Determine the ratio of the total number of service terminals with QoS indicators greater than a preset QoS indicator threshold among the service terminals to the total number of the service terminals as the QoS indicator of the integrated terminal; Determine the average value of the QoS indicators of the integrated terminals as the initial QoS indicator of the 5G integrated power network.

4. The method according to claim 3, wherein The determining the signal transmission rate of the service terminal based on the distance between the integrated terminal and the service terminal includes: Through a first signal transmission rate determination model of the service terminal, process the distance between the integrated terminal and the service terminal, the bandwidth of the communication channel between the integrated terminal and the service terminal, and the noise power of the communication channel to obtain the signal transmission rate of the service terminal; The first signal transmission rate determination model of the service terminal is: Among them, λ k represents the signal transmission rate of the service terminal, W represents the bandwidth of the communication channel, p k represents the signal transmission power of the service terminal, d k represents the distance between the fusion terminal and the service terminal, h(d k ) represents the gain of the communication channel determined based on d k , and σ 2 represents the noise power of the communication channel.

5. The method according to claim 4, wherein The method further includes: Based on the distance between the integrated terminal and the service terminal, determine the signal propagation delay; Determine the sum of the signal transmission delay of the service terminal and the signal propagation delay as the signal delay of the service terminal.

6. The method according to claim 3, wherein The determining the signal transmission rate of the service terminal based on the distance between the integrated terminal and the service terminal includes: Through the second signal transmission rate determination model of the service terminal, process the distance between the fusion terminal and the service terminal, the bandwidth of the communication channel between the fusion terminal and the service terminal, the noise power of the communication channel, the preset attenuation factor, and the total number of hops between the service terminal and the fusion terminal, to obtain the signal transmission rate of the service terminal; The second signal transmission rate determination model of the service terminal is: Among them, λ k represents the signal transmission rate of the service terminal, α represents the preset attenuation factor, N represents the total number of hops between the service terminal and the fusion terminal, W represents the bandwidth of the communication channel, p k represents the signal transmission power of the service terminal, d k represents the distance between the fusion terminal and the service terminal, h(d k ) represents the gain of the communication channel determined based on d k .

7. The method according to claim 6, wherein The method further includes: For each hop link between the service terminal and the fusion terminal, based on the distance between the two terminals in the link, determine the signal propagation delay and the preset signal retransmission delay; Determine the sum of the signal processing delay of the fusion terminal in the two terminals, the preset signal retransmission delay, and the signal propagation delay as the total delay of the link; Determine the sum of the total delays of each hop link as the signal delay of the service terminal.

8. The method according to any one of claims 1 to 7, characterized in that During the iterative processing of the multiple artificial fish, the method further includes: Update the preset visual range through the first update model to obtain the updated visual range; process the updated visual range through the second update model to obtain the updated artificial fish movement step size; wherein, the updated visual range and the updated artificial fish movement step size are used for the iterative processing; The first update model is: Among them, Visual i+1 represents the visible range after the (i + 1)-th update, and Visual i represents the visible range after the i-th update, and Visual min represents the preset minimum visible range. When i is equal to 0, Visual0 represents the preset visible range, and μ represents the preset weight threshold; The second update model is: step i+1 = v * Visual i+1 ; where step i+1 represents the moving step length of the artificial fish after the (i + 1)-th update, and v represents the preset control coefficient.

Images