A method, device, terminal device and storage medium for optimizing network communication scheduling

Abstract

The present invention relates to the field of network communication technologies, and discloses a method, apparatus, device, and storage medium for optimizing network communication scheduling. The method includes obtaining network communication parameter information from a sending end to a receiving end, constructing a network communication scheduling model based on the network communication parameter information, obtaining an objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model, and using a reinforcement colugo algorithm to calculate an optimal solution of the objective function as the optimal scheduling of the network communication scheduling model, so that the sending end and the receiving end transmit information through the path of the optimal scheduling. The method, apparatus, device, and storage medium for optimizing network communication scheduling provided by the present invention can comprehensively consider the information transmission time and transmission power consumption, calculate the optimal scheduling of network communication, and solve the problem of optimizing network communication scheduling.

Description

Technical Field

[0001] The present invention relates to the field of network communication technologies, and in particular, to a method, apparatus, terminal device, and storage medium for optimizing network communication scheduling. Background Art

[0002] Infrastructure including communication facilities, transportation facilities, power facilities, etc. is completely destroyed, and it is easy to fall into network paralysis or network overload, unable to meet the exponentially growing burst communication service demands in emergency scenarios. Moreover, some dedicated networks are prone to service overload during emergency communication, have idle spectrum resources during non-emergency communication, and have vulnerability problems in resisting interference attacks.

[0003] And the information transmission time and transmission power consumption are important parameters for network information scheduling. Therefore, how to successfully transmit network information to the destination in the shortest possible time and with the smallest possible energy consumption has become the direction of network information scheduling optimization. Summary of the Invention

[0004] The present invention provides a method, apparatus, terminal device, and storage medium for optimizing network communication scheduling. Based on the enhanced colugo algorithm, it can comprehensively consider the information transmission time and transmission power consumption, calculate the optimal scheduling of network communication, and solve the problem of optimizing network communication scheduling.

[0005] To achieve the above object, in a first aspect, an embodiment of the present invention provides a method for optimizing network communication scheduling, including:

[0006] Obtain network communication parameter information from the sending end to the receiving end, where the network communication parameter information includes: the power required for signal transmission per unit distance, the signal transmission distance, the signal congestion coefficient, the maximum speed of information transmission, the signal transmission volume, the information congestion status coefficient, the information interference coefficient, the communication time, and the communication transmission power consumption;

[0007] Construct a network communication scheduling model based on the network communication parameter information, and obtain the objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model;

[0008] Use the enhanced colugo algorithm to calculate the optimal solution of the objective function as the optimal scheduling of the network communication scheduling model, so that the sending end and the receiving end transmit information through the path of the optimal scheduling; where the enhanced colugo algorithm is based on the colugo algorithm and introduces the A-L chaotic mapping, water wave adaptive factor, golden Lévy flight mechanism, and dimension crossover learning mechanism to expand the search range and enhance the global optimization ability.

[0009] Further, the step of using the enhanced colugo algorithm to calculate the optimal solution of the objective function specifically includes the following steps:

[0010] S31. Initialize the population parameters, set the maximum number of iterations T, and the population parameters include: the number of population individuals, the glide constant, the air density, the lift coefficient, the air resistance coefficient, the glide speed, and the surface area of the flying membrane of the colugo;

[0011] S32. Generate the initial population using the A-L chaotic map;

[0012] S33. Take the objective function as the fitness function, calculate the fitness values of the positions of the population individuals, sort the population individuals from largest to smallest according to the fitness values, take the first N positions with larger fitness values as the positions of the colugo group, take the N positions with smaller fitness values as the positions of the fruits, and the remaining N positions as the positions of the young leaves, where N is one-third of the number of population individuals, the positions of the fruits and young leaves are fixed, and the positions of the colugo individuals are movable;

[0013] S34. According to the four movement modes in the foraging process of the colugo individual, arrange one iteration in the order of from the roosting point to the fruit, from the roosting point to the young leaf, from the fruit to the young leaf, and from the young leaf to the fruit, and use one of the movement modes periodically to update the positions of the colugo individuals, including:

[0014] When the random number is greater than or equal to the probability of the predator appearing, take the position calculated by the movement expression as the updated position of the colugo individual;

[0015] When the random number is less than the probability of the predator appearing, take the randomly generated position as the updated position of the colugo individual;

[0016] The movement expression is:

[0017]

[0018] Where, is the updated position of the colugo individual; d is the glide distance of the colugo individual; C is the glide constant; is the current position of the colugo individual; is the target position of the colugo individual; X rand is the randomly generated position; rand is a random number in (0,1); P is the probability of the predator appearing; γ is the water wave adaptive factor, t is the current iteration number, and T is the maximum number of iterations;

[0019] S35. Repeat S33;

[0020] S36. If the rainfall random number p ≥ 0.5, update the position of the colugo individual as follows:

[0021]

[0022] Where, is the updated position of the colugo individual; s is the golden Levy step size; p is the rainfall random number; X i,L and X i,U are the lower and upper bounds of the i-th dimension respectively;

[0023] If the rainfall random number p < 0.5, do not update the position of the colugo individual;

[0024] S37. Take the objective function as the fitness function, calculate the fitness value of the position of the colugo individual, and take the position with the maximum fitness value of the current iteration number as the optimal solution of the objective function;

[0025] S38. Use the dimension crossover learning mechanism to generate a new optimal individual position, calculate the fitness value of the optimal individual position, compare the fitness value of the optimal individual position with the maximum fitness value of the current iteration number, and obtain the optimal solution of the objective function;

[0026] S39. If the current iteration number is less than the maximum iteration number, increment the current iteration number by one, and return to execute S33 - S38 until the current iteration number is equal to the maximum iteration number, and output the optimal solution of the objective function.

[0027] Furthermore, obtaining the objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model specifically includes:

[0028] Obtain the network communication time m1 of the network communication scheduling model,

[0029]

[0030] Where, L is the set of all paths from the sender to the receiver; l is a path in the set of all paths; K is the set of all signal nodes in the l-th path; k is a node in the set of all signal nodes; v is the maximum speed of information transmission; is the weight coefficient given priority; a l indicates whether the l-th path is selected; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; is the signal congestion coefficient of the k-th node in the l-th path;

[0031] Obtain the communication transmission power consumption m2 of the network communication scheduling model,

[0032]

[0033] where c is the power required for the signal to transmit per unit distance; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; a l indicates whether the l-th path is selected;

[0034] The constraint condition of the objective function is a l ,

[0035]

[0036] where z is a selected path from the set of all paths. If the l-th path is the selected z, then a l = 1, otherwise a l = 0;

[0037] Obtain the objective function min M of the network communication scheduling model,

[0038] min M = m1 + ωm2

[0039] where m1 is the network communication time of the network communication scheduling model; m2 is the communication transmission power consumption of the network communication scheduling model; ω is the weight coefficient.

[0040] Furthermore, generating a new optimal individual position by using the dimension crossover learning mechanism specifically includes:

[0041] Obtain the crossover probability of the current iteration number;

[0042] When the random number is greater than the crossover probability, take the position calculated by the formula of the optimal individual position as the optimal individual position;

[0043] When the random number is less than or equal to the crossover probability, take the individual position of the current iteration number as the optimal individual position;

[0044] The formula for the optimal individual position is:

[0045]

[0046] where Y d is the optimal individual position; y d is a parameter of a certain dimension in the search space; X dis the individual position at the current iteration; rand is a random number within (0, 1); cr is the crossover probability, t is the current iteration; T is the maximum number of iterations.

[0047] Furthermore, comparing the fitness value of the optimal individual position with the maximum fitness value at the current iteration to obtain the optimal solution of the objective function is specifically as follows:

[0048] If the fitness value of the optimal individual position is greater than or equal to the maximum fitness value at the current iteration, take the optimal individual position as the optimal solution of the objective function;

[0049] If the fitness value of the optimal individual position is less than the maximum fitness value at the current iteration, take the position of the maximum fitness value at the current iteration as the optimal solution of the objective function.

[0050] In a second aspect, an embodiment of the present invention provides a network communication scheduling optimization device, including:

[0051] An acquisition module, configured to acquire network communication parameter information from a sender to a receiver, where the network communication parameter information includes: the power required for signal transmission per unit distance, the signal transmission distance, the signal congestion coefficient, the maximum speed of information transmission, the signal transmission volume, the information congestion condition coefficient, the information interference coefficient, the communication time, and the communication transmission power consumption;

[0052] A modeling module, configured to construct a network communication scheduling model based on the network communication parameter information, and obtain the objective function of the network communication scheduling model according to the communication time and the communication transmission power consumption of the network communication scheduling model;

[0053] A calculation module, configured to calculate the optimal solution of the objective function by using the enhanced colugo algorithm as the optimal scheduling of the network communication scheduling model, so that the sender and the receiver transmit information through the path of the optimal scheduling; where the enhanced colugo algorithm is based on the colugo algorithm, and introduces an A-L chaotic mapping, a water wave adaptive factor, a golden Lévy flight mechanism, and a dimension crossover learning mechanism to expand the search range and enhance the global optimization ability.

[0054] Further, calculating the optimal solution of the objective function by using the enhanced colugo algorithm specifically includes:

[0055] S31. Initialize the population parameters, set the maximum number of iterations T, and the population parameters include: the number of population individuals, the glide constant, the air density, the lift coefficient, the air resistance coefficient, the glide speed, and the surface area of the colugo flying membrane;

[0056] S32. Generate an initial population using the A-L chaotic mapping;

[0057] S33. Use the objective function as the fitness function, calculate the fitness values of the positions of the population individuals, sort the population individuals from largest to smallest according to the fitness values, take the first N positions with larger fitness values as the positions of the colugo group, take the N positions with smaller fitness values as the positions of the fruits, and take the remaining N positions as the positions of the young leaves, where N is one-third of the number of population individuals, the positions of the fruits and young leaves are fixed, and the positions of the colugo individuals are movable;

[0058] S34. According to the four movement modes in the foraging process of the colugo individuals, arrange them in the order of from the roosting point to the fruit, from the roosting point to the young leaf, from the fruit to the young leaf, and from the young leaf to the fruit, and use one of the movement modes for one iteration. Periodically update the positions of the colugo individuals, including:

[0059] When the random number is greater than or equal to the probability of the predator appearing, take the position calculated by the movement expression as the updated position of the colugo individual;

[0060] When the random number is less than the probability of the predator appearing, take the randomly generated position as the updated position of the colugo individual;

[0061] The movement expression is:

[0062]

[0063] Among them, is the updated position of the colugo individual; d is the gliding distance of the colugo individual; C is the gliding constant; is the current position of the colugo individual; is the target position of the colugo individual; X rand is the randomly generated position; rand is a random number in (0, 1); P is the probability of the predator appearing; γ is the water wave adaptive factor, t is the current iteration number, and T is the maximum iteration number;

[0064] S35. Repeat S33;

[0065] S36. If the rainfall random number p ≥ 0.5, then update the position of the colugo individual to:

[0066]

[0067] Among them, The updated position of the colugo individual; s is the golden Levy step size; p is the rainfall random number; X i,L and X i,U are the lower and upper bounds of the i-th dimension respectively;

[0068] If the rainfall random number p < 0.5, the position of the colugo individual is not updated;

[0069] S37. Take the objective function as the fitness function, calculate the fitness value of the position of the colugo individual, and take the position with the maximum fitness value of the current iteration as the optimal solution of the objective function;

[0070] S38. Use the dimension crossover learning mechanism to generate a new optimal individual position, calculate the fitness value of the optimal individual position, compare the fitness value of the optimal individual position with the maximum fitness value of the current iteration, and obtain the optimal solution of the objective function;

[0071] S39. If the current iteration number is less than the maximum iteration number, increment the current iteration number by one, and return to execute S33 - S38 until the current iteration number is equal to the maximum iteration number, and output the optimal solution of the objective function.

[0072] Furthermore, obtaining the objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model specifically includes:

[0073] Obtain the network communication time m1 of the network communication scheduling model,

[0074]

[0075] where L is the set of all paths from the sender to the receiver; l is a path in the set of all paths; K is the set of all signal nodes in the l-th path; k is a node in the set of all signal nodes; v is the maximum speed of information transmission; is the weight coefficient for priority consideration; a l indicates whether the l-th path is selected; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; is the signal congestion coefficient of the k-th node in the l-th path;

[0076] Obtain the communication transmission power consumption m2 of the network communication scheduling model,

[0077]

[0078] where c is the power required for signal transmission per unit distance; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; a l indicates whether the l-th path is selected;

[0079] The constraint conditions of the objective function are a l ,

[0080]

[0081] where z is a selected path in the set of all paths. If the l-th path is the selected z, then a l = 1, otherwise a l = 0;

[0082] Obtain the objective function min M of the network communication scheduling model,

[0083] min M = m1 + ωm2

[0084] where m1 is the network communication time of the network communication scheduling model; m2 is the communication transmission power consumption of the network communication scheduling model; ω is a weight coefficient.

[0085] In a third aspect, an embodiment of the present invention correspondingly provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the network communication scheduling optimization method as described in any one of the above.

[0086] In addition, an embodiment of the present invention further provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the network communication scheduling optimization method as described in any one of the above.

[0087] Compared with the prior art, a network communication scheduling optimization method, device, equipment and storage medium disclosed by the present invention obtain network communication parameter information from a sending end to a receiving end, construct a network communication scheduling model based on the network communication parameter information, obtain an objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model, and use a reinforcement colugo algorithm to calculate an optimal solution of the objective function as the optimal scheduling of the network communication scheduling model, so that the sending end and the receiving end transmit information through the path of the optimal scheduling. The network communication scheduling optimization method, device, equipment and storage medium provided by the present invention can comprehensively consider the information transmission time and transmission power consumption, calculate the optimal scheduling of network communication, enable network information to be successfully transmitted to the destination in as short a time as possible and with as little energy consumption as possible, improve the lifespan of the network communication path, and solve the problem of network communication scheduling optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Figure 1 is a schematic flowchart of a network communication scheduling optimization method provided by an embodiment of the present invention;

[0089] Figure 2 is a schematic structural diagram of a network communication scheduling optimization device provided by an embodiment of the present invention;

[0090] Figure 3 is a schematic structural diagram of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0091] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0092] It should be noted that the terms "including" and "specific" in the present invention and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or devices.

[0093] Please refer to Figure 1 , Figure 1 is a schematic flowchart of a network communication scheduling optimization method provided by an embodiment of the present invention. The network communication scheduling optimization method includes steps S1 to S3:

[0094] S1: Obtain the network communication parameter information from the sender to the receiver. Among them, the network communication parameter information includes: the power required for signal transmission per unit distance, signal transmission distance, signal congestion coefficient, maximum speed of information transmission, signal transmission volume, information congestion status coefficient, information interference coefficient, communication time, and communication transmission power consumption.

[0095] S2: Construct a network communication scheduling model based on the network communication parameter information. According to the communication time and communication transmission power consumption of the network communication scheduling model, obtain the objective function of the network communication scheduling model.

[0096] S3: Use the enhanced colugo algorithm to calculate the optimal solution of the objective function as the optimal scheduling of the network communication scheduling model, so that the sender and the receiver transmit information through the path of the optimal scheduling. Among them, the enhanced colugo algorithm is based on the colugo algorithm, and introduces the A-L chaotic mapping, water wave adaptive factor, golden Lévy flight mechanism, and dimension crossover learning mechanism to expand the search range and enhance the global optimization ability.

[0097] It should be noted that in network communication scheduling, network communication time is given priority. The shorter the signal successful transmission time is, the more important it is for network communication scheduling optimization. On the premise of ensuring that communication information is successfully transmitted to the destination in the shortest possible time, fully reducing information transmission power consumption, reducing node burden, and improving the path life are also the key points of network communication scheduling optimization. The colugo algorithm is a bionic algorithm developed based on the behavior of colugos gliding and foraging in the forest. The position of the colugo is the solution of the objective function, and the position of the fruit is the optimal solution of the objective function. The process of the colugo moving from the roosting point to the food is the optimization process of the emergency network communication scheduling optimization model. The main food sources of colugos are fruits and young leaves.

[0098] A network communication scheduling optimization method provided by an embodiment of the present invention obtains network communication parameter information from a sender to a receiver. Among them, the network communication parameter information includes: the power required for signal transmission per unit distance, signal transmission distance, signal congestion coefficient, maximum speed of information transmission, signal transmission volume, information congestion status coefficient, information interference coefficient, communication time, and communication transmission power consumption. Then, a network communication scheduling model is constructed based on the network communication parameter information. According to the communication time and communication transmission power consumption of the network communication scheduling model, the objective function of the network communication scheduling model is obtained. Finally, the enhanced colugo algorithm is used to calculate the optimal solution of the objective function as the optimal scheduling of the network communication scheduling model, so that the sender and the receiver transmit information through the path of the optimal scheduling. Among them, the enhanced colugo algorithm introduces the A-L chaotic mapping, water wave adaptive factor, golden Lévy flight mechanism, and dimension crossover learning mechanism on the basis of the colugo algorithm to expand the search range and enhance the global optimization ability. It can fully consider network communication time and network communication power consumption, establish a network communication scheduling optimization model, and then integrate the enhanced colugo algorithm to efficiently solve the network communication scheduling optimization problem.

[0099] In specific implementation, the sender can be a computer or a mobile phone, and the receiver can be a computer or a mobile phone. The sender has a sending module supporting the WIFI6 protocol, and the receiver has a receiving module supporting the WIFI6 protocol. The sender and the receiver are wirelessly connected based on the WIFI6 protocol and are not limited by cables.

[0100] In a preferred embodiment, in step S3: the step of using the enhanced colugo algorithm to calculate the optimal solution of the objective function specifically includes the following steps:

[0101] S31. Initialize the population parameters, set the maximum number of iterations T. The population parameters include: the number of population individuals, glide constant, air density, lift coefficient, air resistance coefficient, glide speed, and the surface area of the colugo flying membrane;

[0102] S32. Use the A-L chaotic mapping to generate the initial population;

[0103] S33. Take the objective function as the fitness function, calculate the fitness values of the positions of the population individuals, sort the population individuals from largest to smallest according to the fitness values, take the first N positions with larger fitness values as the positions of the colugo group, take the N positions with smaller fitness values as the positions of the fruits, and the remaining N positions as the positions of the young leaves. Among them, N is one-third of the number of population individuals. The positions of the fruits and young leaves are fixed, and the positions of the colugo individuals are movable;

[0104] S34. According to the four movement modes in the foraging process of the colugo individual, one of the movement modes is adopted in sequence for one iteration in the order from the roosting point to the fruit, from the roosting point to the young leaves, from the fruit to the young leaves, and from the young leaves to the fruit, and the position of the colugo individual is updated periodically, including:

[0105] When the random number is greater than or equal to the probability of the predator appearing, the position calculated by the movement expression is used as the updated position of the colugo individual;

[0106] When the random number is less than the probability of the predator appearing, a randomly generated position is used as the updated position of the colugo individual;

[0107] The movement expression is:

[0108]

[0109] Among them, is the updated position of the colugo individual; d is the gliding distance of the colugo individual; C is the gliding constant; is the current position of the colugo individual; is the target position of the colugo individual; X rand is the randomly generated position; rand is a random number within (0, 1); P is the probability of the predator appearing; γ is the water wave adaptive factor, t is the current iteration number, and T is the maximum iteration number;

[0110] S35. Repeat S33;

[0111] S36. If the rainfall random number p ≥ 0.5, then update the position of the colugo individual as:

[0112]

[0113] Among them, is the updated position of the colugo individual; s is the golden Levy step size; p is the rainfall random number; X i,L 、X i,U are the lower bound and upper bound of the i-th dimension respectively;

[0114] If the rainfall random number p < 0.5, then do not update the position of the colugo individual;

[0115] S37. Take the objective function as the fitness function, calculate the fitness value of the position of the colugo individual, and take the position with the maximum fitness value at the current iteration number as the optimal solution of the objective function;

[0116] S38. Generate a new optimal individual position by using the dimension crossover learning mechanism, calculate the fitness value of the optimal individual position, compare the fitness value of the optimal individual position with the maximum fitness value of the current iteration, and obtain the optimal solution of the objective function;

[0117] S39. If the current iteration number is less than the maximum iteration number, increment the current iteration number by one, and return to execute S33 - S38 until the current iteration number is equal to the maximum iteration number, and output the optimal solution of the objective function.

[0118] It should be noted that using the A - L chaotic mapping to generate the initial population can not only increase the uniformity of the initial solution distribution, but also improve the optimization efficiency and traversal uniformity, and can also improve the group search ability. During the foraging process of the colugo, there are four moving situations in total. Update the individual position of the colugo according to the four moving methods of the colugo. Taking 4 iteration numbers as a cycle, within one cycle, in the first iteration, update according to the colugo moving from the roosting point to the fruit, in the second iteration, update according to the colugo moving from the roosting point to the young leaves, in the third iteration, update according to the colugo moving from the fruit to the young leaves, and in the fourth iteration, update according to the colugo moving from the young leaves to the fruit, and so on in a continuous cycle. The colugo is very vigilant when foraging, and its moving path will be affected by predators. In order to make the colugo individuals show a convergence phenomenon during movement, a water wave adaptive factor is added on the basis of the colugo's movement. In order to avoid the algorithm falling into local optimum, increase the population diversity, and improve the global optimization ability of the algorithm, a dimension crossover learning mechanism is introduced to generate a new optimal individual and compare it with the individual with the optimal fitness value of the current iteration to obtain the optimal solution of the objective function.

[0119] The colugo moves between different trees by gliding. When gliding, the sum of the lift force L and the drag force D acting on the colugo generates a resultant force R, and this resultant force is equal in magnitude and opposite in direction to the gravity of the colugo. Therefore, the colugo can glide down at a certain angle φ with the horizontal plane in a straight line. Among them, the formula for the lift force is expressed as L = 0.5ρC L V 2 S, where: ρ is the air density; C L is the lift coefficient; V is the gliding speed; S is the surface area of the colugo's flight membrane. The formula for the drag force is expressed as D = 0.5ρC D V 2 S, where: C D is the air drag coefficient; the formula for the descent angle is expressed as: Thus, the gliding distance d of the colugo can be obtained as: where: h is the amount of descent of the colugo's gliding height.

[0120] Preferably, in S38, the generating a new optimal individual position by using the dimension crossover learning mechanism specifically includes:

[0121] Obtain the crossover probability of the current iteration number;

[0122] When the random number is greater than the crossover probability, take the position calculated by the formula of the optimal individual position as the optimal individual position;

[0123] When the random number is less than or equal to the crossover probability, take the individual position of the current iteration number as the optimal individual position;

[0124] The formula for the optimal individual position is:

[0125]

[0126] where Y d is the optimal individual position; y d is a parameter of a certain dimension in the search space; X d is the individual position of the current iteration number; rand is a random number in (0, 1); cr is the crossover probability, t is the current iteration number; T is the maximum iteration number.

[0127] Preferably, in S38, the comparing the fitness value of the optimal individual position with the maximum fitness value of the current iteration number to obtain the optimal solution of the objective function is specifically:

[0128] If the fitness value of the optimal individual position is greater than or equal to the maximum fitness value of the current iteration number, take the optimal individual position as the optimal solution of the objective function;

[0129] If the fitness value of the optimal individual position is less than the maximum fitness value of the current iteration number, take the position of the maximum fitness value of the current iteration number as the optimal solution of the objective function.

[0130] It should be noted that by comparing the magnitudes of the fitness values of the current optimal value and the new solution obtained by dimensional crossover learning, the optimal solution among them is selected for retention. The formula is:

[0131]

[0132] where Y is the optimal individual position; is the optimal individual position of the current iteration.

[0133] In another preferred embodiment, in step S2: the obtaining the objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model specifically includes:

[0134] Obtain the network communication time m1 of the network communication scheduling model,

[0135]

[0136] Among them, L is the set of all paths from the sending end to the receiving end; l is a path in the set of all paths; K is the set of all signal nodes in the l-th path; k is a node in the set of all signal nodes; v is the maximum speed of information transmission; is the weight coefficient given priority; a l indicates whether the l-th path is selected; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; is the signal congestion coefficient of the k-th node in the l-th path;

[0137] Obtain the communication transmission power consumption m2 of the network communication scheduling model,

[0138]

[0139] Among them, c is the power required for unit distance of signal transmission; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; a l indicates whether the l-th path is selected;

[0140] The constraint condition of the objective function is a l ,

[0141]

[0142] Among them, z is a selected path in the set of all paths. If the l-th path is the selected z, then a l = 1, otherwise a l = 0;

[0143] Obtain the objective function min M of the network communication scheduling model,

[0144] min M = m1 + ωm2

[0145] Among them, m1 is the network communication time of the network communication scheduling model; m2 is the communication transmission power consumption of the network communication scheduling model; ω is the weight coefficient.

[0146] It should be noted that the signal congestion coefficient of the k-th node in the l-th path

[0147]

[0148]

[0149] In the formula: TV k is the signal transmission volume of the k-th node in the l-th path; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; TD k The information congestion status coefficient of the k-th node in the l-th path, where the congestion status is determined by the signal transmission volume of this node. The greater the signal transmission volume, the more congested the information; TD max and TD min are respectively the maximum and minimum information congestion coefficients among all nodes; ε is the information interference coefficient.

[0150] Correspondingly, the present invention also provides a network communication scheduling optimization device, which can implement all processes of the above network communication scheduling optimization method.

[0151] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a network communication scheduling optimization device provided by an embodiment of the present invention. The network communication scheduling optimization device includes:

[0152] An acquisition module 21, configured to acquire network communication parameter information from a sending end to a receiving end. Among them, the network communication parameter information includes: the power required for signal transmission per unit distance, signal transmission distance, signal congestion coefficient, maximum speed of information transmission, signal transmission volume, information congestion status coefficient, information interference coefficient, communication time, and communication transmission power consumption;

[0153] A modeling module 22, configured to construct a network communication scheduling model based on the network communication parameter information, and obtain an objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model;

[0154] A calculation module 23, configured to calculate an optimal solution of the objective function by using a reinforced colugo algorithm as the optimal scheduling of the network communication scheduling model, so that the sending end and the receiving end transmit information through the path of the optimal scheduling; among them, the reinforced colugo algorithm introduces an A-L chaotic mapping, a water wave adaptive factor, a golden Lévy flight mechanism, and a dimension crossover learning mechanism on the basis of the colugo algorithm to expand the search range and enhance the global optimization ability.

[0155] In a preferred embodiment, in the calculation module 23, the specific content of calculating the optimal solution of the objective function by using the reinforced colugo algorithm has been described in the above method embodiment and will not be elaborated here.

[0156] In another preferred embodiment, in the modeling module 22, the content specifically included in obtaining the objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model has been described in the above method embodiment and will not be elaborated here.

[0157] The network communication scheduling optimization device provided by the embodiments of the present invention can implement all the processes of the network communication scheduling optimization method in any of the above embodiments. The functions of each module in the device and the achieved technical effects respectively correspond to the functions and achieved technical effects of the network communication scheduling optimization method in the above embodiments and will not be elaborated here.

[0158] Please refer to Figure 3 , which is a schematic structural diagram of a terminal device provided by an embodiment of the present invention. The terminal device 3 in this embodiment includes: a processor 31, a memory 32, and a computer program stored in the memory 32 and executable on the processor 31. When the processor 31 executes the computer program, it implements the steps in the above embodiment of the network communication scheduling optimization method. Alternatively, when the processor 31 executes the computer program, it implements the functions of each module in the above embodiment of the network communication scheduling optimization device.

[0159] Exemplarily, the computer program can be divided into one or more modules. The one or more modules are stored in the memory 32 and executed by the processor 31 to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of completing specific functions, and these instruction segments are used to describe the execution process of the computer program in the terminal device 3.

[0160] The terminal device 3 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device 3 may include, but is not limited to, a processor 31 and a memory 32. Those skilled in the art can understand that the schematic diagram is only an example of the terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the terminal device 3 may further include input / output devices, network access devices, a bus, etc.

[0161] The so-called processor 31 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor 31 is the control center of the terminal device 3, and connects various parts of the entire terminal device 3 through various interfaces and lines.

[0162] The memory 32 can be used to store the computer programs and / or modules. The processor 31 realizes various functions of the terminal device 3 by running or executing the computer programs and / or modules stored in the memory 32, and by calling the data stored in the memory 32. The memory 32 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory 32 may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0163] Among them, if the modules integrated in the terminal device 3 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 31, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0164] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. 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. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative work.

[0165] The embodiment of the present invention also provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. Among them, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the network communication scheduling optimization method as described above.

[0166] In summary, the embodiments of the present invention disclose a method, apparatus, device, and storage medium for optimizing network communication scheduling. By obtaining the network communication parameter information from the sender to the receiver, constructing a network communication scheduling model based on the network communication parameter information, obtaining the objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model, and using the enhanced colugo algorithm to calculate the optimal solution of the objective function as the optimal scheduling of the network communication scheduling model, so that the sender and the receiver transmit information through the path of the optimal scheduling. The method, apparatus, device, and storage medium for optimizing network communication scheduling provided by the present invention can comprehensively consider the information transmission time and transmission power consumption, calculate the optimal scheduling of network communication, enable network information to be successfully transmitted to the destination in the shortest possible time and with the smallest possible energy consumption, improve the lifespan of the network communication path, and solve the problem of optimizing network communication scheduling.

[0167] The foregoing is the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A method for optimizing network communication scheduling, characterized in that, It includes the following steps: Obtain the network communication parameter information from the sender to the receiver. The network communication parameter information includes: the power required for signal transmission per unit distance, the signal transmission distance, the signal congestion coefficient, the maximum speed of information transmission, the signal transmission volume, the information congestion status coefficient, the information interference coefficient, the communication time, and the communication transmission power consumption; Construct a network communication scheduling model based on the network communication parameter information, and obtain the objective function of the network communication scheduling model according to the communication time and the communication transmission power consumption of the network communication scheduling model; Use the enhanced colugo algorithm to calculate the optimal solution of the objective function as the optimal scheduling of the network communication scheduling model, so that the sender and the receiver transmit information through the path of the optimal scheduling; wherein, the enhanced colugo algorithm introduces the A-L chaotic mapping, the water wave adaptive factor, the golden Lévy flight mechanism, and the dimension crossover learning mechanism on the basis of the colugo algorithm to expand the search range and enhance the global optimization ability; The step of using the enhanced colugo algorithm to calculate the optimal solution of the objective function specifically includes the following steps: S31. Initialize the population parameters, set the maximum number of iterations T. The population parameters include: the number of population individuals, the glide constant, the air density, the lift coefficient, the air resistance coefficient, the glide speed, and the surface area of the colugo flying membrane; S32. Generate the initial population using the A-L chaotic mapping; S33. Take the objective function as the fitness function, calculate the fitness values of the positions of the population individuals, sort the population individuals from largest to smallest according to the fitness values, take the first N positions with larger fitness values as the positions of the colugo group, take the N positions with smaller fitness values as the positions of the fruits, and the remaining N positions as the positions of the young leaves. Here, N is one-third of the number of population individuals. The positions of the fruits and young leaves are fixed, and the positions of the colugo individuals are movable; S34. According to the four movement modes in the foraging process of the colugo individuals, arrange to use one of the movement modes in one iteration in the order from the roosting point to the fruits, from the roosting point to the young leaves, from the fruits to the young leaves, and from the young leaves to the fruits, and periodically update the positions of the colugo individuals, including: When the random number is greater than or equal to the probability of the appearance of the predator, take the position calculated by the movement expression as the updated position of the colugo individual; When the random number is less than the probability of the appearance of the predator, take the randomly generated position as the updated position of the colugo individual; The movement expression is: Among them, is the updated position of the colugo individual; d is the gliding distance of the colugo individual; C is the gliding constant; is the current position of the colugo individual; is the target position of the colugo individual; X rand is the randomly generated position; rand is a random number within (0, 1); P is the predator appearance probability; γ is the water wave adaptive factor, t is the current iteration number, and T is the maximum iteration number; S35. Repeat S33; S36. If the rainfall random number p≥0.5, update the position of the colugo individual as: Among them, is the updated position of the colugo individual; s is the golden Lévy step size; p is the rainfall random number; X i,L and X i,U are the lower and upper bounds of the i-th dimension respectively; If the rainfall random number p<0.5, do not update the position of the colugo individual; S37. Take the objective function as the fitness function, calculate the fitness value of the position of the colugo individual, and take the position with the maximum fitness value in the current iteration as the optimal solution of the objective function; S38. Generate a new optimal individual position by using the dimension crossover learning mechanism, calculate the fitness value of the optimal individual position, compare the fitness value of the optimal individual position with the maximum fitness value of the current iteration number, and obtain the optimal solution of the objective function; S39. If the current iteration number is less than the maximum iteration number, increment the current iteration number by one, and return to execute S33 - S38 until the current iteration number is equal to the maximum iteration number, and output the optimal solution of the objective function.

2. The method for optimizing network communication scheduling according to claim 1, characterized in that, The method for obtaining the objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model specifically includes: Obtain the network communication time m1 of the network communication scheduling model; Among them, L is the set of all paths from the sending end to the receiving end; l is a path in the set of all paths; K is the set of all signal nodes in the l-th path; k is a node in the set of all signal nodes; v is the maximum speed of information transmission; is the weight coefficient to be prioritized; a l indicates whether the l-th path is selected; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; is the signal congestion coefficient of the k-th node in the l-th path; Obtain the communication transmission power consumption m2 of the network communication scheduling model; where c is the power required for the signal to be transmitted per unit distance; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; a l indicates whether the l-th path is selected; The constraint condition of the objective function is a l , Among them, z is a selected path from the set of all the paths. If the l-th path is the selected z, then a l = 1; otherwise a l = 0; Obtain the objective function min M of the network communication scheduling model; min M = m1 + ωm2 where m1 is the network communication time of the network communication scheduling model; m2 is the communication transmission power consumption of the network communication scheduling model; ω is the weight coefficient.

3. The method for optimizing network communication scheduling according to claim 1, characterized in that, The method for generating a new optimal individual position by using the dimension crossover learning mechanism specifically includes: Obtain the crossover probability of the current iteration number; When the random number is greater than the crossover probability, use the position calculated by the formula of the optimal individual position as the optimal individual position; When the random number is less than or equal to the crossover probability, use the individual position of the current iteration number as the optimal individual position; The formula of the optimal individual position is: Among them, Y d is the optimal individual position; y d is a parameter of a certain dimension in the search space; X d is the individual position at the current iteration; rand is a random number within (0, 1); cr is the crossover probability, t is the current iteration number; T is the maximum iteration number.

4. The network communication scheduling optimization method according to claim 1, characterized in that, The method for comparing the fitness value of the optimal individual position with the maximum fitness value of the current iteration number and obtaining the optimal solution of the objective function is specifically: If the fitness value of the optimal individual position is greater than or equal to the maximum fitness value of the current iteration number, use the optimal individual position as the optimal solution of the objective function; If the fitness value of the optimal individual position is less than the maximum fitness value of the current iteration number, use the position of the maximum fitness value of the current iteration number as the optimal solution of the objective function.

5. A network communication scheduling optimization device, characterized in that, It includes: An acquisition module, configured to acquire the network communication parameter information from the sender to the receiver, where the network communication parameter information includes: the power required for signal transmission per unit distance, the signal transmission distance, the signal congestion coefficient, the maximum speed of information transmission, the signal transmission volume, the information congestion condition coefficient, the information interference coefficient, the communication time, and the communication transmission power consumption; A modeling module, configured to construct a network communication scheduling model based on the network communication parameter information, and obtain the objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model; A calculation module, which is used to calculate the optimal solution of the target function by using the enhanced colugo algorithm as the optimal scheduling of the network communication scheduling model, so that the sender and the receiver transmit information through the path of the optimal scheduling; wherein, the enhanced colugo algorithm is based on the colugo algorithm, and introduces the A-L chaotic mapping, the water wave adaptive factor, the golden Lévy flight mechanism and the dimension crossover learning mechanism to expand the search range and enhance the global optimization ability; The calculation of the optimal solution of the target function by using the enhanced colugo algorithm specifically includes the following steps: S31. Initialize the population parameters, set the maximum number of iterations T, and the population parameters include: the number of population individuals, the glide constant, the air density, the lift coefficient, the air resistance coefficient, the glide speed, and the surface area of the colugo flying membrane; S32. Generate the initial population by using the A-L chaotic mapping; S33. Use the target function as the fitness function, calculate the fitness values of the positions of the population individuals, sort the population individuals from largest to smallest according to the fitness values, take the first N positions with larger fitness values as the positions of the colugo group, take the N positions with smaller fitness values as the positions of the fruits, and the remaining N positions as the positions of the young leaves, where N is one-third of the number of population individuals, and the positions of the fruits and young leaves are fixed, and the positions of the colugo individuals are movable; S34. According to the four movement modes in the foraging process of the colugo individuals, arrange one iteration in the order from the roosting point to the fruit, from the roosting point to the young leaf, from the fruit to the young leaf, and from the young leaf to the fruit, and use one of the movement modes periodically to update the positions of the colugo individuals, including: When the random number is greater than or equal to the probability of the appearance of the predator, take the position calculated by the movement expression as the updated position of the colugo individual; When the random number is less than the probability of the appearance of the predator, take the randomly generated position as the updated position of the colugo individual; The movement expression is: Among them, is the updated position of the colugo individual; d is the gliding distance of the colugo individual; C is the gliding constant; is the current position of the colugo individual; is the target position of the colugo individual; X rand is the randomly generated position; rand is a random number within (0, 1); P is the predator appearance probability; γ is the water wave adaptation factor, t is the current iteration number, and T is the maximum iteration number; S35. Repeat S33; S36. If the rainfall random number p≥0.5, update the position of the colugo individual as: Among them, is the updated position of the colugo individual; s is the golden Lévy step size; p is the rainfall random number; X i,L , X i,U are the lower and upper bounds of the i-th dimension respectively; If the rainfall random number p<0.5, do not update the position of the colugo individual; S37. Use the target function as the fitness function, calculate the fitness value of the position of the colugo individual, and take the position with the maximum fitness value of the current iteration as the optimal solution of the target function; S38. Use the dimension crossover learning mechanism to generate a new optimal individual position, calculate the fitness value of the optimal individual position, compare the fitness value of the optimal individual position with the maximum fitness value of the current iteration, and obtain the optimal solution of the target function; S39. If the current iteration number is less than the maximum iteration number, increment the current iteration number by one, and return to execute S33~S38 until the current iteration number is equal to the maximum iteration number, and output the optimal solution of the target function.

6. The network communication scheduling optimization device according to claim 5, characterized in that, Obtaining the objective function of the network communication scheduling model according to the communication time and communication transmission power consumption of the network communication scheduling model specifically includes: Obtaining the network communication time m1 of the network communication scheduling model, Among them, L is the set of all paths from the sending end to the receiving end; l is a path in the set of all paths; K is the set of all signal nodes in the l-th path; k is a node in the set of all signal nodes; v is the maximum speed of information transmission; is the weight coefficient to be given priority; a l indicates whether the l-th path is selected; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; is the signal congestion coefficient of the k-th node in the l-th path; Obtaining the communication transmission power consumption m2 of the network communication scheduling model, Among them, c is the power required for the signal to transmit a unit distance; is the signal transmission distance from the (k - 1)-th node to the k-th node in the l-th path; a l indicates whether the l-th path is selected; The constraint condition of the objective function is a l , Among them, z is a selected path from the set of all the paths. If the l-th path is the selected z, then a l = 1; otherwise a l = 0; Obtaining the objective function min M of the network communication scheduling model, min M = m1 + ωm2 where m1 is the network communication time of the network communication scheduling model; m2 is the communication transmission power consumption of the network communication scheduling model; ω is the weight coefficient.

7. A terminal device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the network communication scheduling optimization method according to any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the network communication scheduling optimization method according to any one of claims 1 to 4.

Images