Method and device for optimizing substation trusted WLAN network coverage

Abstract

The application discloses a substation trusted WLAN network coverage optimization method and device, and belongs to the technical field of wireless communication of power systems. The method comprises the following steps: a three-dimensional trusted WLAN network node coverage rate model is constructed based on a ray tracing and machine learning fusion node coverage range prediction method; a Sobol sequence is used to initialize a COOT algorithm population, so that the population diversity is enhanced; a golden sine strategy is introduced in random motion position updating of the COOT algorithm, and a greedy strategy is introduced in random selection of individual motion modes; in the COOT algorithm optimization process, a disturbance strategy based on virtual force is introduced to disturb and update the leader position; and the optimized COOT algorithm is used to calculate and solve a target function of the three-dimensional trusted WLAN network node coverage rate model, so that the optimal node position is obtained. The application improves network coverage, reduces the number of communication node deployments, and saves network construction cost.

Description

TECHNICAL FIELD

[0001] The application relates to a substation trusted WLAN network coverage optimization method and device, and belongs to the technical field of wireless communication of a power system. BACKGROUND

[0002] With the continuous development of energy digitization and intelligentization, the digital and intelligent power grid supports the construction of a new power system, promotes the intelligent operation and inspection of substations and converter stations, the intelligent inspection of power transmission lines, the intelligent operation and maintenance system construction of power distribution, and the development of an intelligent power grid disaster sensing system. At present, the trusted WLAN network is being promoted in the application of intelligent inspection of power transmission and transformation, intelligent safety supervision, intelligent warehouse, remote operation and maintenance of secondary systems, and physical coding in substations. As many as possible businesses are connected to the trusted WLAN network. In order to better cope with new demands and challenges encountered in the application process of the trusted WLAN network, there is a strong demand for products, and efforts are made to realize the coordinated development of industry and application.

[0003] At present, the trusted WLAN is deployed on a large scale in the power system, provides wireless local area network authentication and security infrastructure interoperability, integrity and function testing, and provides wireless network security standard evaluation capability building services. However, in the current substation scene, the environment is complex, there are many devices, there are many non-line-of-sight transmission environments, and the communication system coverage performance is difficult to effectively guarantee. Therefore, the coverage depth of the trusted WLAN network in the complex scene of the substation needs to be improved, and the coverage performance of the trusted WLAN network still needs to be optimized. In the substation, coverage optimization is an important indicator reflecting the quality of monitoring work of the trusted WLAN network in the target area. Therefore, according to different application requirements, a suitable wireless network node deployment strategy and coverage optimization algorithm are designed to reduce the degree of node redundancy, supplement the blank area caused by the initial random deployment, and then improve the quality of network monitoring of the target area and ensure the accuracy of data.

[0004] In summary, in order to promote the construction of the trusted WLAN network in the substation, combined with the application scene of the power business, it is urgent to study a standard unified, coverage enhanced and economically efficient trusted WLAN network deployment scheme to provide a landing solution for digital communication and efficient operation and maintenance of equipment in the substation scene. SUMMARY

[0005] In order to solve the above problems, the application provides a substation trusted WLAN network coverage optimization method and device, which can determine the optimal node layout scheme of the wireless network in a complex environment, thereby improving the network coverage, reducing the coverage blind area, reducing the number of communication nodes, and saving the network construction cost.

[0006] The technical scheme adopted by the application to solve the technical problems is:

[0007] In a first aspect, the embodiments of the present application provide a method for optimizing substation trusted WLAN network coverage, comprising the following steps:

[0008] Step S1, constructing a three-dimensional trusted WLAN network node coverage model based on a ray tracing and machine learning fusion node coverage prediction method;

[0009] Step S2, initializing the COOT (Coot Bird Optimization Algorithm) algorithm population with Sobol sequence to enhance population diversity;

[0010] Step S3, introducing a golden sine strategy in the random motion position update of the COOT algorithm, and introducing a greedy strategy in the random selection of individual motion mode;

[0011] Step S4, introducing a disturbance strategy based on virtual force in the COOT algorithm optimization process to disturb and update the leader position;

[0012] Step S5, calculating and solving the objective function of the three-dimensional trusted WLAN network node coverage model using the optimized COOT algorithm to obtain the optimal node position, wherein the objective function is:

[0013]

[0014] In the formula, F cov is the total coverage rate of the trusted WLAN network to all the WLAN network communication nodes covered by the communication in the target area, m is the number of dividing the target area into small square regions, V k is the volume of the small square, V is the total volume of the target area, P(U, S j ) is the joint communication probability distribution of the trusted WLAN network communication nodes.

[0015] As a possible implementation manner of the embodiments, the step S1 comprises:

[0016] Obtaining channel measurement data based on the actual scene of the substation using a channel measurement system;

[0017] Constructing a three-dimensional scene simulation model of the substation based on the actual scene, and randomly arranging communication nodes in the target area;

[0018] Calculating the received power of the target node using the ray tracing method;

[0019] Calculating the road loss deviation value using the actual measured road loss value and the simulation road loss value obtained based on the ray tracing;

[0020] The DNN neural network is trained by using the road loss deviation values at different receiving end positions and 3D position information of the communication node and the target node, so as to realize accurate prediction of the road loss deviation value between any communication node and the target node in the target area.

[0021] The road loss deviation value predicted by the neural network is used to correct the simulation road loss value, so as to obtain an optimized road loss value and calculate the accurate receiving power at the corresponding target node.

[0022] The effective coverage range of the communication node is determined according to the receiving power of the target node and the set receiving power threshold, and a coverage rate model of the trusted WLAN network communication node is established.

[0023] As a possible implementation manner of the embodiment, the Sobol sequence is used to generate sample points in a multi-dimensional space with approximate uniform distribution, a low-bias sequence is generated by a quasi-Monte Carlo method, and a white-bone-top-bird population is initialized, and the position of the white-bone-top-bird population is:

[0024] X C (i)=S N (ub-lb)+lb

[0025] In the formula, [ub, lb] is a search range of a target space, a random number S N ∈[0,1],X C (i) is the position of the i th white-bone-top-bird, so as to enhance the diversity of the initialized population in the target space distribution.

[0026] As a possible implementation manner of the embodiment, the golden sine strategy is used to introduce a sine function to dynamically adjust a search step length in an algorithm iteration process, so as to improve the convergence speed and local search ability of the algorithm, and the greedy strategy is used to retain a current optimal solution in a local search stage, so as to reduce blindness in the movement process.

[0027] As a possible implementation manner of the embodiment, the disturbance strategy based on virtual force includes three virtual forces, and the position of the leader is disturbed and updated under the action of the three virtual forces, so as to balance the ability of local search and global optimization.

[0028] As a possible implementation manner of the embodiment, the greater the value of the target function is, the greater the coverage range of the node deployment is, and the more reasonable the node deployment position is.

[0029] As a possible implementation manner of the embodiment, the step S3 includes:

[0030] Randomly generate the positions of l white-bone-top-bird individuals, assume that each solution of the optimization problem corresponds to the position of the corresponding white-bone-top-bird in the search space, X i(t) represents the spatial position of the i-th individual of the Whitehead's bird in the d-dimensional individual space in the t-th iteration, i = 1, 2,..., l; Y i (t) is the optimal position of the i-th individual of the Whitehead's bird in the t-th iteration, and in the (t+1)-th iteration, the position updating formula of the i-th individual of the Whitehead's bird is as follows:

[0031] X i (t+1) = X i (t) x |sin(G1)| + G2 x sin(G1) x |μ x Y i (t) - ν x X i (t)|

[0032] In the formula, G1 is a random number in [0, 2π], which determines the moving distance of the i-th individual of the Whitehead's bird in the next iteration process; G2 is a random number in [0, π], which determines the position updating direction of the i-th individual of the Whitehead's bird in the next iteration process; μ and ν are coefficients obtained by introducing the golden section number, and the golden section number The values of μ and ν are calculated as follows:

[0033] μ = -π + (1-π) x 2π

[0034] ν = -π + λ x 2π

[0035] After introducing the golden sine strategy, in the random motion stage, the new position updating formula is as follows:

[0036] X C (i) = X i (t+1) = X i (t) x |sin(G1)| + G2 x sin(G1) x |μ x Y i (t) - ν x X i (t)|

[0037] First, it is determined whether the position after the movement of the previous iteration is improved, and then it is determined which moving way is selected in the current iteration. If the position after the movement of the previous individual of the Whitehead's bird is improved, the moving way of the movement process in the current iteration is selected to be the same as that of the previous iteration; if the position after the movement of the previous individual of the Whitehead's bird is not improved but worse, the moving way of the movement process in the current iteration is selected to be different from that of the previous iteration to obtain better moving effect; the rule formula is as follows:

[0038]

[0039] In the formula, Move(i) t is the moving way selected by the Whitehead's bird in the t-th movement; ~ represents the non-operation; random represents random selection; g(i) tThe fitness value of the tth movement of the white-bone top bird.

[0040] As a possible implementation manner of the embodiment, the step S4 comprises:

[0041] In the position updating process of the leader of the white-bone top bird group, a virtual force is added to change the search area of the leader, and the virtual force is generated by three parts of adjacent communication nodes, uncovered grid points and area boundaries; a disturbance factor of the virtual force is calculated by the following formula, and is used to disturb the position updating formula of the leader:

[0042]

[0043] In the formula, f i is the moving distance of the node under the action of the virtual force, F i is the resultant force of the virtual force applied on the communication node, F ij is the virtual force of the adjacent communication node, F ik is the virtual attractive force of the uncovered grid point, F ib is the boundary virtual repulsive force, and Step(t) is the single virtual moving step length of the node;

[0044] The virtual moving step length is set to gradually decrease with the increase of the iteration number, as follows:

[0045]

[0046] In the formula, Stepmax and Stepmin respectively represent the maximum and minimum moving step lengths, to ensure the stability of the algorithm and reduce the invalid movement of the node;

[0047] The leader position is updated by using the improved leader movement formula, as follows:

[0048]

[0049] In the formula, f i is the moving distance of the node under the action of the virtual force, X L (i) represents that the current leader positions B4 and B5 are random between the interval [0, 1]; B3 is a random number between the interval [-1, 1]; X best is the best position that can be found, max_Iter is the maximum iteration number, and t is the current iteration number.

[0050] In a second aspect, an optimization device for substation trusted WLAN network coverage is provided, comprising:

[0051] A model construction module is configured to construct a three-dimensional trusted WLAN network node coverage model based on a ray tracing and machine learning fusion node coverage range prediction method.

[0052] A population initialization module is configured to initialize a COOT algorithm population by using a Sobol sequence to enhance population diversity.

[0053] A strategy introduction module is configured to introduce a golden sine strategy in random motion position updating of the COOT algorithm and introduce a greedy strategy in random selection of individual motion modes.

[0054] A disturbance updating module is configured to introduce a disturbance strategy based on virtual force to disturb and update the leader position in the COOT algorithm optimization process.

[0055] A target function solving module is configured to calculate and solve a target function of the three-dimensional trusted WLAN network node coverage model by using the optimized COOT algorithm to obtain an optimal node position.

[0056] As a possible implementation manner of the embodiment, the target function is as follows:

[0057]

[0058] In the formula, F cov is the total coverage rate of all WLAN network communication nodes covered by the trusted WLAN network in the target area, m is the number of dividing the target area into small square regions, V k is the volume of the small square region, V is the total volume of the target area, and P(U, S j ) is the joint communication probability distribution of the trusted WLAN network communication nodes.

[0059] The technical scheme of the embodiment of the application has the following beneficial effects:

[0060] The application is based on a ray tracing and machine learning fusion node coverage range prediction method and constructs a node coverage range fusion prediction model suitable for a substation scene. Meanwhile, an optimized COOT algorithm is used to optimize the position of the trusted WLAN network node to determine an optimal node layout scheme of the wireless network in a complex environment. Compared with the traditional node coverage model and the traditional COOT algorithm, the coverage rate of the method of the application is improved, and the method has higher convergence speed, accuracy and convergence efficiency. The optimal coverage rate can be obtained without adding additional nodes. The application effectively improves the network coverage rate, reduces the coverage blind area, reduces the number of communication nodes to be deployed, saves the network construction cost, is suitable for WLAN network coverage optimization in a complex substation environment, and has strong practicability and promotional value. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1 is a flow chart of a substation trusted WLAN network coverage optimization method according to an example embodiment;

[0062] Figure 2 is a structure diagram of a substation trusted WLAN network coverage optimization device according to an example embodiment;

[0063] Figure 3 is a detailed implementation flow chart of a substation trusted WLAN network coverage optimization according to an example embodiment;

[0064] Figure 4 is a structure diagram of a white-headed bird algorithm according to an example embodiment. DETAILED DESCRIPTION

[0065] In order to more clearly illustrate the technical features of the scheme of the present application, the present application will be described in detail below with reference to specific embodiments and accompanying drawings.

[0066] As shown in Figure 1 , the substation trusted WLAN network coverage optimization method provided by the embodiment of the present application comprises the following steps:

[0067] Step S1, a three-dimensional trusted WLAN network node coverage rate model is constructed based on a ray tracing and machine learning fusion node coverage range prediction method;

[0068] Step S2, Sobol sequence is used to initialize the COOT algorithm population to enhance population diversity;

[0069] Step S3, a golden sine strategy is introduced in the random motion position update of the COOT algorithm, and a greedy strategy is introduced in the random selection of individual motion mode;

[0070] Step S4, in the optimization process of the COOT algorithm, a disturbance strategy based on virtual force is introduced to disturb and update the leader position;

[0071] Step S5, the optimized COOT algorithm is used to calculate and solve the objective function of the three-dimensional trusted WLAN network node coverage rate model to obtain the optimal node position, and the objective function is:

[0072]

[0073] In the formula, F cov is the total coverage rate of the trusted WLAN network to all the WLAN network communication nodes covered by communication in the target area, m is the number of dividing the target area into small square regions, V kV is the total volume of the target area, P(U, S j ) is the joint communication probability distribution of the trusted WLAN network communication nodes.

[0074] As a possible implementation manner of the embodiment, the step S1 comprises:

[0075] The channel measurement system is used to obtain channel measurement data based on the actual scene of the substation.

[0076] A three-dimensional scene simulation model of the substation is constructed based on the actual scene, and the communication nodes are randomly arranged in the target area.

[0077] The received power of the target node is calculated by using the ray tracing method.

[0078] The road loss deviation value is calculated by using the measured road loss value and the simulation road loss value obtained based on the ray tracing.

[0079] The DNN neural network is trained by using the road loss deviation values at different receiving end positions and the 3D position information of the communication nodes and the target node, so as to accurately predict the road loss deviation value between any communication node and the target node in the target area.

[0080] The simulation road loss value is corrected by using the road loss deviation value predicted by the neural network, to obtain an optimized road loss value, and the accurate received power at the corresponding target node is calculated.

[0081] The effective coverage range of the communication node is determined according to the received power of the target node and the set received power threshold, and a coverage rate model of the trusted WLAN network communication node is established.

[0082] As a possible implementation manner of the embodiment, the Sobol sequence is used to generate sample points in a multi-dimensional space with approximate uniform distribution, a low-bias sequence is generated by using the quasi-Monte Carlo method, and the white-bone top bird population is initialized, and the position of the white-bone top bird population is:

[0083] X C (i)=S N (ub-lb)+lb

[0084] In the formula, [ub, lb] is the search range of the target space, the random number S N ∈[0,1] and X C (i) is the position of the i-th white-bone top bird, so as to enhance the diversity of the initialized population in the target space distribution.

[0085] As a possible implementation manner of the embodiment, the golden sine strategy is used to introduce a sine function to dynamically adjust a search step length in an algorithm iteration process, so as to improve convergence speed and local search capability of the algorithm, and the greedy strategy is used to retain a current optimal solution in a local search stage, so as to reduce blindness in a movement process.

[0086] As a possible implementation manner of the embodiment, the disturbance strategy based on virtual force includes three virtual forces, and positions of the leader are disturbed and updated under the action of the three virtual forces, so as to balance local search capability and global optimization capability.

[0087] As a possible implementation manner of the embodiment, the greater the value of the target function is, the greater the coverage range of the node deployment is, and the more reasonable the node deployment position is.

[0088] As a possible implementation manner of the embodiment, the step S3 includes:

[0089] Randomly generating positions of l albatross individuals, assuming that each solution of the optimization problem corresponds to a position of a corresponding albatross in a search space, X i (t) represents a spatial position of an i th albatross individual in the d-dimensional individual space in the t th iteration, i = 1, 2,..., l; Y i (t) is an optimal position of the albatross individual i in the t th iteration, and in the (t+1) th iteration, a position updating formula of the i th albatross individual is as follows:

[0090] X i (t+1) = X i (t) × |sin(G1)| + G2 × sin(G1) × |μ × Y i (t) - v × X i (t)|

[0091] In the formula, G1 is a random number in [0, 2π], which determines a moving distance of the i th albatross individual in the next iteration process; G2 is a random number in [0, π], which determines a position updating direction of the i th albatross individual in the next iteration process; μ and v are coefficients obtained by introducing a golden section number, and the golden section number The values of μ and v are calculated as follows:

[0092] μ = -π + (1-π) × 2π

[0093] v = -π + λ × 2π

[0094] After introducing the golden sine strategy, in the random movement stage, a new position updating formula is as follows:

[0095] X C (i) = X i (t+1) = Xi (t)×|sin(G1)|+G2×sin(G1)×|μ×Y i (t)-ν×X i (t)|

[0096] First, the position is compared with that of the previous iteration to determine the movement method for the current iteration. If the position of the individual bird improved after the previous movement, the movement method for the current iteration is the same as the previous one. If the position of the individual bird did not improve after the previous movement and was even worse, the movement method for the current iteration is different from the previous one to achieve a better movement effect. The rule formula is as follows:

[0097]

[0098] In the formula, Move(i) t represents the movement chosen by the coot in its t-th movement; ~ indicates NOT operation; random indicates random selection; g(i) t Let be the fitness value of the Coot during its t-th movement.

[0099] This invention introduces a golden sine strategy, which makes the position update of individual white-crested birds more reasonable, enabling more effective exploration of the search space and improving solution efficiency. This invention also combines a greedy strategy to reduce the blindness in the movement of white-crested birds, thereby improving convergence speed and solution accuracy.

[0100] As one possible implementation of this embodiment, step S4 includes:

[0101] A virtual force is incorporated into the leader's position update process to alter the leader's search area. This virtual force is primarily generated by adjacent communication nodes, uncovered grid points, and the region boundary. The perturbation factor of the virtual force is calculated using the following formula to influence the leader's position update formula:

[0102]

[0103] In the formula, f i F is the distance a node moves under the influence of a virtual force. i It is the resultant force of virtual forces applied to the communication node. F ij It is the virtual force of adjacent communication nodes, F ik It is the virtual attraction of uncovered grid points, F ib It is the boundary virtual repulsion force, and Step(t) is the single virtual movement step size of the node;

[0104] The virtual moving step is gradually reduced with the increase of iteration times, as follows:

[0105]

[0106] In the formula, Stepmax and Stepmin represent the maximum and minimum moving steps respectively, to ensure the stability of the algorithm and reduce the invalid movement of the node.

[0107] The leader position is updated by using the improved leader movement formula as follows:

[0108]

[0109] In the formula, f i is the moving distance of the node under the action of the virtual force, X L (i) represents that the current leader positions B4 and B5 are random in the interval [0, 1], B3 is a random number in the interval [-1, 1], X best is the best position that can be found, max_Iter is the maximum iteration number, and t is the current iteration number.

[0110] The application effectively avoids the problem of falling into a local optimal solution in the leader position updating process, and improves the global optimization capability; the virtual moving step is gradually reduced with the increase of iteration times, which avoids the oscillation of coverage rate in the later iteration period and ensures the stability of the algorithm. The application is suitable for the position optimization problem of a mobile communication node, and can significantly improve the coverage rate and communication efficiency in a monitoring area.

[0111] As shown in Figure 2 The optimization device for the substation trusted WLAN network coverage provided by the embodiment of the application comprises:

[0112] A model construction module is configured to construct a three-dimensional trusted WLAN network node coverage rate model based on a ray tracing and machine learning fusion node coverage range prediction method.

[0113] A population initialization module is configured to initialize a COOT algorithm population by using a Sobol sequence to enhance population diversity.

[0114] A strategy introduction module is configured to introduce a golden sine strategy in random motion position updating of the COOT algorithm, and introduce a greedy strategy in random selection of individual motion modes.

[0115] A disturbance updating module is configured to introduce a disturbance strategy based on a virtual force to disturb and update the leader position in the COOT algorithm optimization process.

[0116] The objective function solving module is used to calculate and solve the objective function of the three-dimensional trusted WLAN network node coverage model using the optimized COOT algorithm, so as to obtain the optimal node location.

[0117] As one possible implementation of this embodiment, the objective function is:

[0118]

[0119] In the formula, F cov V represents the total coverage of the trusted WLAN network over all covered WLAN network communication nodes in the target area, m is the number of small square regions into which the target area is divided, and V is the total coverage of the trusted WLAN network over all covered WLAN network communication nodes in the target area. k Let V be the volume of the small cube, and V be the total volume of the target region. P(U,S) j ) represents the joint communication probability distribution of trusted WLAN network communication nodes.

[0120] like Figure 3 As shown, the specific implementation process of the present invention for optimizing the trusted WLAN network coverage in substations includes the following steps.

[0121] Step S101: Propose a node coverage prediction method based on the fusion of ray tracing and machine learning, and then establish a coverage model of three-dimensional trusted WLAN network nodes.

[0122] This invention proposes a node coverage prediction method based on the fusion of ray tracing and machine learning. First, channel measurement data is obtained using a channel measurement system based on the actual scenario of a substation. The measured path loss value PL can then be expressed as:

[0123]

[0124] Where d0 is the path loss reference distance; n PL X is the path loss exponent; σ The shadow fading follows a log-normal distribution.

[0125] Secondly, a 3D simulation model of a substation with an area of ​​M×N×L is constructed based on the actual scenario. It is assumed that n communication nodes are randomly arranged within the target area S, and the node set is represented as U={u1,u2,…,u…}. n}, where communication node u i The position is (x i ,y i ,z i Assume the transmit power of the communication nodes in the target area is P. i And the target node S within the target area j The position is (x j ,y j ,zj ), the received power P j of the target node is calculated by ray tracing method according to the position of the target node j is the superposition of all valid ray path powers, which is expressed as follows:

[0126]

[0127] where N is the number of all valid ray paths; P n is the received power of the nth valid ray path, and the corresponding path loss PL S is:

[0128] PL S (dB) = P i (dBm) - P j (dBm) + G i,Max (dBi) + G j,Max (dBi) - L S (dB) (3)

[0129] where P i is the transmitted power, P j is the received power of the target node, G i,Max and G j,Max are the maximum gains of the transmitting end antenna and the receiving end antenna, respectively, and L S is the preset loss in the communication system. Then, the path loss deviation value PL D is calculated by using the measured channel loss value at the same position in the target area and the simulated path loss value based on ray tracing, and is expressed as follows: PL D = PL - PL S (4)

[0130] Finally, the DNN neural network is trained by using the path loss deviation values PL D at different receiving end positions calculated above and the 3D position information of the communication node and the target node, so as to realize accurate prediction of the path loss deviation value between any communication node u i and the target node S j in the target area, which is expressed as follows:

[0131] PL E = f L (f L-1 (…f2(f1(u i ,s j ,PL D ;W (1) ,b (1) );W (2) ,b (2) );…W (L) ,b(L) )) (5)

[0132] where PL E is the predicted path loss bias value; f L is the transformation function of the Lth layer of the DNN neural network; W (L) and b (L) represent the weight and bias of the Lth layer, respectively; u i and S j represent the 3D positions of the communication node and the target node, respectively.

[0133] The path loss bias value accurately predicted by the above neural network is used to correct the simulation path loss value PL S obtained based on the ray tracing method to obtain an optimized path loss value, and the accurate received power P′ j at the corresponding target node is calculated, as shown below:

[0134] P′ j = P i + G i,Max + G j,Max - PL S + PL E - L S (6)

[0135] The receiving power threshold P i at which the target node u j can achieve reliable communication with the communication node S th is set. If the position of the communication node u i is fixed, the receiving power P′ j of the target node S j is updated by continuously adjusting the position of the target node S i , and the effective coverage range of the communication node u j can be obtained. That is, when the positions of the communication node u i and the target node S j change, if the receiving power P′ j of the target node S j is higher than the threshold P th , the target node can be effectively covered by the communication node u i , that is, the communication probability is 1; otherwise, the target node S j cannot be covered, that is, the communication probability is 0. The communication probability of the node u i to S j is represented by P(u i , S j ), and the mathematical expression is as follows:

[0136]

[0137] When the target is in the communication range of the node, the target can be successfully covered. The same target in the target area can be covered by multiple communication nodes at the same time, and the joint communication probability distribution of the nodes is:

[0138]

[0139] Assume that the target area is divided into m small square regions, and the volume of each small square is V k The overall coverage rate of the network is the ratio of the volume of the communication probability set of all sensor nodes to the total volume V of the target area, and the calculation formula is as follows:

[0140]

[0141] In the formula, F cov is the total coverage rate of the target area in the trusted WLAN network to all points covered by communication.

[0142] Step S102: introduce Sobol sequence to initialize the population to enrich the diversity of the population.

[0143] In the COOT algorithm, the population represents different communication nodes, and the original COOT algorithm uses a random initialization method to generate an initial solution. The random initialization method greatly reduces the uniformity of the population initialization distribution and hinders the optimization ability of the algorithm. Sobol sequence is a kind of high-efficiency and low-deviation sequence, which is used to generate sample points in a multi-dimensional space that are approximately uniformly distributed, so as to distribute the sample points in the target area as uniformly as possible. It can effectively enhance the diversity of the initialization population in the target space distribution. The COOT algorithm can realize high optimization in the global region, and avoid the situation of slow convergence speed or unsatisfactory convergence precision.

[0144] The present application uses the high-efficiency and low-deviation deterministic Sobol sequence S N to complete the initialization of the population, and the population position expression is as follows:

[0145] X C (i)=S N (ub-lb)+lb (10)

[0146] In the formula, [ub,lb] is the search range of the target space, random number S N ∈[0,1], X C (i) is the position of the i th white top bird.

[0147] Step S103: introduce golden sine strategy and greedy strategy to avoid the dilemma of falling into local optimal solution.

[0148] For example Figure 4As shown, the whole group is divided into leaders and followers during foraging, and the three kinds of motion of position update of followers are as follows:

[0149] 1) Random motion:

[0150] First, a position Q is randomly generated according to the following formula:

[0151] Q = S N (ub-lb)+lb (11)

[0152] Then, in order to prevent falling into local optimum, position update is performed:

[0153] X C (i) = X C (i)+A×B1×(Q-X C (i)) (12)

[0154] In the formula, B1 is a random number in the interval [0, 1]; A linearly decreases from 1 to 0 with the increase of iteration number, and its formula is as follows:

[0155]

[0156] Where, max_Iter is the maximum iteration number, and t is the current iteration number.

[0157] 2) Chain motion:

[0158] The chain motion is realized by the average position of two white-crowned sparrows, and one white-crowned sparrow moves to the other white-crowned sparrow with a moving distance being half of the distance vector, and the position update formula is as follows:

[0159]

[0160] In the formula, X C (i-1) is the position of the i-1th white-crowned sparrow.

[0161] 3) Follow the leader motion:

[0162] The individual white-crowned sparrow updates its own position according to the position of the leader in the group, and constantly moves towards the leader, and the leader is selected according to the following formula:

[0163] k = 1 + (i mod N L ) (15)

[0164] In the formula, k is the number of the leader; N L is the number of leaders; mod is the remainder function;

[0165] The position update formula of the follow-the-leader motion is as follows:

[0166] X C (i)=X L (k)+2×B2×cos(2πB3)×(X L (k)-X C (i)) (16)

[0167] In the formula, X L (k) represents the selected leader position; B2 is a random number in the interval [0,1]; B3 is a random number in the interval [-1,1].

[0168] In the traditional COOT algorithm, the follower's movement is randomly selected from the three methods mentioned above. This individual movement selection method is prone to problems such as slow convergence speed and getting trapped in local optima. This invention introduces a golden sine strategy into the position update of individual random movement. Iterative optimization using a sine function can traverse all points within the effective region, and this traversal behavior is similar to global search in optimization problems. At the same time, the introduction of the golden section coefficient in the position update process not only accelerates the convergence speed of the algorithm but also improves the local search capability.

[0169] The update process of the Golden Sine Strategy solution is its key core. First, the positions of l individual coots are randomly generated. It is assumed that each solution to the optimization problem corresponds to the position of the coot in the search space, X. i (t) represents the spatial position of the i-th Cootid individual in the t-th iteration of the d-dimensional individual space, i = 1, 2, ..., l; Y i (t) represents the optimal position of individual i of the white-crested eagles in the t-th iteration. In the (t+1)-th iteration, the position update formula for the i-th white-crested eagle individual is as follows:

[0170] X i (t+1)=X i (t)×|sin(G1)|+G2×sin(G1)×|μ×Y i (t)-ν×X i (t)| (17)

[0171] In the formula, G1 is a random number in the range [0, 2π], which determines the moving distance of the i-th coot individual in the next iteration; G2 is a random number in the range [0, π], which determines the position update direction of the i-th coot individual in the next iteration; μ and ν are coefficients obtained by introducing the golden ratio. The values ​​of μ and ν are calculated as follows:

[0172] μ=-π+(1-π)×2π (18)

[0173] ν=-π+λ×2π (19)

[0174] After introducing the golden sine strategy, in the random motion stage, the new position update formula is as follows:

[0175] X C (i)=X i (t+1)=X i (t)×|sin(G1)|+G2×sin(G1)×|μ×Y i (t)-ν×X i (t)| (20)

[0176] Secondly, the present application adds a greedy strategy in the movement mode selection process of the individual of the white-bone top bird group, so as to reduce the blindness in the movement process of the individual of the white-bone top bird. The main way of adding the greedy strategy to the movement selection process of the individual of the white-bone top bird group is: first, it is determined whether the position after the movement of the previous iteration is improved, and then it is determined which movement mode is selected in the present iteration. If the position after the movement of the individual of the white-bone top bird in the previous iteration is improved, the movement mode selection in the present movement process is the same as that in the previous iteration; if the position after the movement of the individual of the white-bone top bird in the previous iteration is not improved but is worse, the movement mode selection in the present movement process is different from that in the previous iteration, so as to obtain a better movement effect. The rule formula is as follows:

[0177]

[0178] In the formula, Move(i) t is the movement mode selected by the white-bone top bird in the tth movement; ~ represents the non-operation; random represents the random selection; g(i) t is the fitness value of the tth movement of the white-bone top bird.

[0179] Step S104: introducing a disturbance strategy based on virtual force to disturb and update the position of the leader, so as to coordinate the local search and global optimization ability.

[0180] In the whole optimization process, the position of the leader is related to the direction of the whole population. In order to find the optimal position, the leader must jump out of the existing local optimal position to find the optimal position, and the position update of the leader is completed by using the following formula.

[0181]

[0182] In the formula, X L (i) represents that the current leader position B4 and B5 are random between the interval [0, 1]; B3 is a random number between the interval [-1, 1]; X best is the best position that can be found; D is obtained by the following formula:

[0183]

[0184] The basic albatross optimization algorithm needs to select the optimal position by calculating the fitness after each iteration, and the algorithm is easy to fall into local optimum if the position update formula is not disturbed. The virtual force is added in the position update process of the albatross group leader in the application, which can change the search area of the leader, balance the ability of local search and global optimization, and thus obtain the optimal search result. The virtual force is mainly generated by three parts of adjacent communication nodes, uncovered grid points and regional boundaries. Under the influence of virtual force, the mobile communication nodes in the monitoring area may be repositioned. After each disturbance of virtual force, the communication node will finally move to the best position along the direction of the resultant force, and the disturbance factor of virtual force is calculated by the following formula:

[0185]

[0186] In the formula, f i is the moving distance of the node under the action of virtual force. F i is the virtual force of the communication node, F ij is the virtual force of adjacent communication nodes, F ik is the virtual attractive force of uncovered grid points, F ib is the boundary virtual repulsive force. Step(t) is the single virtual moving step length of the node.

[0187] In order to avoid the oscillation of coverage rate in the later iteration, the virtual moving step length is gradually reduced with the increase of iteration number t, as follows:

[0188]

[0189] This ensures the stability of the algorithm and reduces the invalid movement of the node. Stepmax and Stepmin represent the maximum and minimum moving step length.

[0190] The improved leader movement formula is as follows:

[0191]

[0192] In the formula, f i is the moving distance of the node under the action of virtual force.

[0193] Step S105: using COOT algorithm to optimize the position of the convergence node, and outputting the optimal node position.

[0194] After establishing the coverage rate model of three-dimensional trusted WLAN network nodes, taking F cov as the objective function, the improved albatross algorithm based on the optimization is used to calculate and solve the objective function. Taking F COVFor the target function, the greater the target function value, the greater the coverage range of the node deployment, and the more reasonable the node layout position.

[0195] For the coverage optimization problem of the three-dimensional trusted WLAN network communication node in the substation scene, the application proposes a node coverage range fusion prediction method based on ray tracing and machine learning, uses the 3D position information of the node and the road loss deviation value of the ray tracing simulation data and the measured channel data to train the DNN neural network, so as to accurately predict the path loss to calculate the receiving power of the target node, and then construct a node coverage range prediction model suitable for the substation scene; Meanwhile, the application also proposes an improved COOT algorithm (COOT) to guide the deployment scheme of the trusted WLAN network communication node in the substation with coverage rate as the optimization target. In view of the problems of low uniformity of initial population distribution in the traditional COOT algorithm, the application introduces Sobol sequence for population initialization to enrich the diversity of the population, and introduces golden sine strategy in individual random motion to speed up the convergence speed of the algorithm; Secondly, the greedy strategy is added in the movement mode selection of the follower to reduce the blindness of the moving process; Finally, the virtual force disturbance strategy is introduced in the iteration process of the algorithm to disturb and update the position of the leader, so as to coordinate the local search and global optimization ability, so as to obtain the optimal search result. The application can guarantee the full coverage of the trusted WLAN network communication node in the complex environment of the substation while reducing the repeated coverage rate of the node, effectively solving the problems of weak coverage and blind coverage of the node in the complex environment.

[0196] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application and not to limit it, although the present application has been described in detail with reference to the above examples, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced, without departing from the spirit and scope of the present application, any modification or equivalent replacement, which should be covered within the protection scope of the claims of the present application.

Claims

1. A method for optimization of substation trusted WLAN network coverage, characterized in that, The method comprises the following steps: Step S1, a three-dimensional trusted WLAN network node coverage rate model is constructed based on a ray tracing and machine learning combined node coverage prediction method; Step S2, Sobol sequence is used to initialize the COOT algorithm population to enhance population diversity; Step S3, a golden sine strategy is introduced in the random motion position update of the COOT algorithm, and a greedy strategy is introduced in the random selection of individual motion mode; Step S4, in the optimization process of the COOT algorithm, a disturbance strategy based on virtual force is introduced to disturb and update the position of the leader; Step S5, the optimized COOT algorithm is used to calculate and solve the objective function of the three-dimensional trusted WLAN network node coverage rate model, and the optimal node position is obtained, wherein the objective function is: wherein is the total coverage of the trusted WLAN network to all the trusted WLAN network communication nodes covered by the communication in the target area, is the number of small cuboid regions into which the target area is divided, is the volume of the small cuboid, is the total volume of the target area, is the joint communication probability distribution of the trusted WLAN network communication nodes.

2. The substation trusted WLAN network coverage optimization method of claim 1, wherein, The step S1 comprises: The channel measurement data is obtained based on the actual scene of the substation by using a channel measurement system; A three-dimensional scene simulation model of the substation is constructed based on the actual scene, and communication nodes are randomly arranged in the target area; The received power of the target node is calculated by using the ray tracing method; The road loss deviation value is calculated by using the actual measured road loss value and the simulation road loss value obtained based on the ray tracing; The DNN neural network is trained by using the road loss deviation value at different receiving end positions and the 3D position information of the communication node and the target node, so as to accurately predict the road loss deviation value between any communication node and the target node in the target area; The simulation road loss value is corrected by using the road loss deviation value predicted by the neural network, and the accurate received power at the corresponding target node is calculated; The effective coverage range of the communication node is determined according to the received power of the target node and the set received power threshold, and the coverage rate model of the trusted WLAN network communication node is established.

3. The substation trusted WLAN network coverage optimization method of claim 1, wherein, The Sobol sequence is used to generate sample points in a multi-dimensional space that are approximately uniformly distributed, and a low-bias sequence is generated by using a quasi-Monte Carlo method, and the albatross population is initialized, and the position of the albatross population is: In the formula, is the search range of the target space, and the random number , is the position of the first white-crowned sparrow, so as to enhance the diversity of the initialized population in the distribution of the target space.

4. The substation trusted WLAN network coverage optimization method of claim 1, wherein, The golden sine strategy is used to dynamically adjust the search step by introducing a sine function in the algorithm iteration process, so as to improve the convergence speed and local search ability of the algorithm, and the greedy strategy is used to retain the current optimal solution in the local search stage, so as to reduce the blindness in the movement process.

5. The substation trusted WLAN network coverage optimization method of claim 1, wherein, The disturbance strategy based on virtual force includes three virtual forces, and the position of the leader is disturbed and updated under the action of the three virtual forces, so as to balance the ability of local search and global optimization.

6. The substation trusted WLAN network coverage optimization method of claim 1, wherein, The greater the value of the objective function, the greater the coverage range of the node deployment, and the more reasonable the node deployment position.

7. The substation trusted WLAN network coverage optimization method of any of claims 1-6, wherein, The step S3 comprises: randomly generated the position of the ith individual of the ith iteration of the ith white- headed woodpecker, denotes the position of the ith individual of the ith iteration of the ith white- headed woodpecker, the position of the ith individual of the ith iteration of the ith white- headed woodpecker, the position of the ith individual of the ith iteration of the ith white- headed woodpecker, ; the optimal position of the ith individual of the ith iteration of the ith white- headed woodpecker, the optimal position of the ith individual of the ith iteration of the ith white- headed woodpecker, the optimal position of the ith individual of the ith iteration of the ith white- headed woodpecker, the optimal position of the ith individual of the ith iteration of the ith white- headed woodpecker, the optimal position of the ith individual of the ith iteration of the ith white- headed woodpecker, wherein, is a random number between 0 and 1, is a random number between 0 and 1, determines the moving distance of the i-th individual of the Ostrich population in the next iteration process, is a random number between 0 and 1, determines the moving direction of the i-th individual of the Ostrich population in the next iteration process, and are coefficients obtained by introducing the golden section number, the golden section number , and are calculated as follows:​ After introducing the golden sine strategy, the new position update formula in the random motion stage is as follows: First, it is compared whether the position after the movement of the previous iteration is improved, if the position after the movement of the previous albatross individual is improved, the movement mode selection of the current movement process is the same as the previous one; if the position after the movement of the previous albatross individual is not improved but worse, the movement mode selection of the current movement process is different from the previous one, so as to obtain better movement effect; the rule formula is as follows: wherein is the movement selected by the white-crowned sparrow at the th movement; is represented by a non-operation; is represented by a random selection; is the fitness value of the white-crowned sparrow at the th movement.

8. The substation trusted WLAN network coverage optimization method of any of claims 1-6, wherein, The step S4 comprises: Virtual forces are added in the position updating process of the leader of the flock of white-topped birds to change the search area of the leader, and the virtual forces are generated by three parts of adjacent communication nodes, uncovered grid points and area boundaries; A disturbance factor of the virtual force is calculated by the following formula to disturb the position updating formula of the leader: wherein, is the distance of movement of a node under the virtual force, is the resultant virtual force applied on a communication node, , is the virtual force of adjacent communication nodes, is the virtual attractive force of uncovered grid points, is the boundary virtual repulsive force, is the individual virtual movement step of a node; The virtual moving step size is set to gradually decrease with the increase of the iteration number, as follows: wherein, and respectively represent the maximum and minimum moving step size to ensure the stability of the algorithm and reduce the invalid movement of the nodes. The position of the leader is updated by using the improved leader movement formula as follows: wherein is the moving distance of the node under the virtual force, denotes the current leader position and is a random number between and is a random number between and is the best position that can be found, is the maximum number of iterations, is the current iteration number.

9. An optimization device for trusted WLAN network coverage in substations, characterized in that, The method comprises the following steps: A model construction module is configured to construct a three-dimensional credible WLAN network node coverage rate model based on a ray tracing and machine learning combined node coverage range prediction method; A population initialization module is configured to initialize a COOT algorithm population by using a Sobol sequence to enhance population diversity; A strategy introduction module is configured to introduce a golden sine strategy in random motion position updating of the COOT algorithm and introduce a greedy strategy in random selection of individual motion modes; A disturbance updating module is configured to introduce a disturbance strategy based on virtual forces to disturb and update the position of the leader in the optimization process of the COOT algorithm; A target function solving module is configured to calculate and solve a target function of the three-dimensional credible WLAN network node coverage rate model by using the optimized COOT algorithm to obtain an optimal node position.

10. The substation trusted WLAN network coverage optimization apparatus of claim 9, wherein, The target function is as follows: wherein is the total coverage of the trusted WLAN network to all the trusted WLAN network communication nodes being communicated to in the target area, is the number of small square areas into which the target area is divided, is the volume of the small square, is the total volume of the target area, is the joint communication probability distribution of the trusted WLAN network communication nodes.

Images