Power emergency communication network resource allocation method and system based on genetic algorithm

Abstract

The invention discloses an electric power emergency communication network resource allocation method and system based on a genetic algorithm. The method comprises the following steps: acquiring a plurality of users and a plurality of subcarriers currently coexisting in an electric power emergency communication network; according to the plurality of users and the plurality of subcarriers, combining a preset resource allocation model, solving the resource allocation model by using a genetic algorithm, and determining a resource allocation scheme of the power emergency communication network; wherein the resource allocation model is provided with a dual-objective function and a constraint condition set of resource allocation; the dual-objective function is a resource allocation optimization function established by taking power emergency communication network capacity maximization and energy efficiency maximization as optimization objectives; the constraint condition set comprises a service quality constraint condition and a network resource limit constraint condition; and carrying out resource allocation on the power emergency communication network according to the resource allocation scheme. According to the invention, reasonable scheduling and dynamic allocation of resources in the power emergency communication network can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of network resource allocation and management, and particularly relates to a power emergency communication network resource allocation method and system based on a genetic algorithm. BACKGROUND

[0002] As an important part of the power system, the communication quality and reliability of the power communication system plays a vital role in the safe and stable operation of the entire power grid. In particular, after major natural disasters such as earthquakes and floods, it is urgent to build a power emergency communication network with high robustness and rapid deployment capability to ensure the efficient development of power grid fault repair and command and dispatch work.

[0003] However, after the initial construction of the power emergency communication network, a large number of network resources are demanded by various types of business terminals. Due to the diversity and suddenness of emergency services, each communication node often spontaneously applies for more communication bandwidth, frequency resources or access time slots to ensure the timely transmission of its business data. This resource request behavior can easily cause communication congestion, resource redundancy occupation and other problems in a resource-limited network environment, ultimately affecting the coordinated operation and communication quality of the overall network. Therefore, an efficient and reasonable resource allocation method is needed to orderly schedule and optimize the configuration of limited network resources to improve resource utilization and ensure the priority transmission of critical services.

[0004] At present, the common resource allocation method in the prior art mainly adopts traditional optimization algorithms such as linear programming, constraint programming and dynamic programming. These methods usually rely on the precise definition of the problem model and find the optimal solution in the solution space through analytical or enumeration search methods. However, with the continuous increase of resource types, business types and constraint conditions in the emergency communication network, the problem model presents highly nonlinear and high-dimensional complex characteristics, making the traditional optimization algorithm face problems such as huge search space, high computational complexity and easy to fall into local optimum in the solving process. In addition, most network resource allocation problems belong to NP-hard problems, and the traditional method is difficult to achieve fast and globally effective optimization solution when facing large-scale nodes or rapidly changing network environment. SUMMARY

[0005] The present application provides a power emergency communication network resource allocation method and system based on a genetic algorithm, which can efficiently and reasonably allocate power emergency communication network resources under the premise of meeting the quality of service and resource constraints, thereby improving network capacity and energy efficiency.

[0006] In a first aspect, the present application provides a power emergency communication network resource allocation method based on a genetic algorithm, comprising:

[0007] Obtain real-time state information of a plurality of users and a plurality of subcarriers currently coexisting in the power emergency communication network;

[0008] According to the real-time state information of the plurality of users and the plurality of subcarriers, a resource allocation model is solved by using a genetic algorithm in combination with a preset resource allocation model, and a resource allocation scheme of the power emergency communication network is determined through an allocation relationship corresponding to an optimal chromosome; wherein the resource allocation model is provided with a double-objective function and a constraint condition set of resource allocation; the double-objective function is a resource allocation optimization function established by taking maximization of power emergency communication network capacity and maximization of energy efficiency as optimization objectives; and the constraint condition set includes a quality of service constraint condition and a network resource limit constraint condition.

[0009] According to the resource allocation scheme, resource allocation is performed on the power emergency communication network.

[0010] The embodiment of the application starts from the actual demand of the power emergency communication network, and takes network capacity and energy efficiency as optimization objectives in view of the limited network resources and high demand characteristics of service terminals in an emergency scenario, fully considers the service characteristics of the power communication system, and improves the practicability of the method; by introducing the quality of service constraint condition (such as transmission rate, delay, packet loss rate, etc.) and the resource limit constraint condition (such as time slot, subcarrier, power, etc.), these constraint conditions are integrated, which can dynamically adapt to complex network environments and improve the accuracy and reliability of resource allocation; by using the genetic algorithm to search the complex solution space in combination with operations such as crossover and mutation, the local optimal solution can be effectively jumped out, so that the global optimal solution is solved, and when facing large-scale users and complex constraint conditions, the method still maintains high computational efficiency.

[0011] Further, the resource allocation model includes:

[0012] A double-objective function of resource allocation is established by taking joint optimization of network capacity and energy efficiency as an objective;

[0013] A constraint condition set of resource allocation is set, including a quality of service constraint condition and a network resource limit constraint condition;

[0014] The double-objective function and the constraint condition set are uniformly integrated to construct the resource allocation model.

[0015] The embodiment of the present application can balance and improve the resource utilization rate and network performance by considering the optimization goals of network capacity and energy efficiency in the resource allocation process, introduce the quality of service constraint condition and network resource limit constraint condition, and integrate them into the resource allocation model, effectively reflect the multi-dimensional limit requirements of the power emergency communication network in actual operation, avoid the allocation results that do not meet the business requirements or resource limits in the optimization solving process, improve the feasibility and reliability of the resource allocation scheme in the emergency scene, and then realize the efficient use of energy and the optimization of the overall performance of the system while ensuring the quality of key business transmission.

[0016] Further, the dual-objective function for resource allocation aims at the joint optimization of network capacity and energy efficiency, wherein the network capacity is the number of users served by the power emergency communication network, and the specific expression is:

[0017]

[0018] wherein k represents the number of users in the coverage range of the power emergency communication network, e k represents the utility of the user, r k represents the instantaneous signal-to-interference-and-noise ratio of the user, y k represents the actual transmission rate of the network, and I represents the maximum transmission rate that can be obtained.

[0019] The energy efficiency is the utility value of the power emergency communication network under the preset condition, and the specific expression is:

[0020]

[0021] wherein sigmoid represents the utility function based on the average energy efficiency, r min represents the threshold value of the utility function, and P k represents the transmission power of the kth user on the allocated resource block.

[0022] The embodiment of the application can simultaneously consider the network capacity and energy efficiency performance indexes in the resource allocation optimization process through the construction of the above-mentioned double-objective function, thereby effectively reducing the energy consumption while improving the network service capacity, wherein the network capacity optimization target can dynamically evaluate the serviceable capacity of the network according to the utility of the user, the instantaneous signal-to-noise ratio and the actual transmission rate and other factors, and ensure that the high-level service carrying capacity is maintained in the case of multi-user concurrent access; the energy efficiency optimization target can realize the fine control of the power allocation of different users by introducing the utility function and threshold value design based on the average energy efficiency, in combination with the user transmission power constraint, thereby effectively reducing the invalid energy consumption; the joint optimization of the two can make the obtained resource allocation scheme consider the business quality guarantee and the energy utilization efficiency maximization in the complex and changeable power emergency communication scene, and improve the overall operation economy and emergency response capability of the system.

[0023] Further, the resource allocation process needs to meet the user service quality constraint condition, and the specific expression of the service quality constraint condition is:

[0024]

[0025] Wherein, v represents the actual transmission rate of the network, v min represents the minimum transmission rate required by the user, t represents the actual delay of the network, t max represents the maximum tolerable delay of the user, s represents the actual packet loss rate of the network, and s max represents the maximum tolerable packet loss rate of the user.

[0026] The embodiment of the application can ensure that each user meets the business demand in the key performance indexes such as transmission rate, delay and packet loss rate in the resource allocation process by introducing the above-mentioned service quality constraint condition, thereby avoiding the allocation result that only starts from the optimization target but cannot meet the user experience in actual transmission; wherein the minimum transmission rate constraint can ensure that the user still obtains stable data transmission capacity in the case of high concurrency or channel condition fluctuation, the maximum delay constraint can guarantee that the real-time business (such as scheduling control, emergency instruction, etc.) in the emergency scene completes transmission within the specified time, and the maximum packet loss rate constraint can ensure the transmission reliability of important data; the introduction of the constraint condition set makes the resource allocation scheme not only have high optimization performance indexes, but also meet the actual operation demand of the power emergency communication network, thereby significantly improving the implementability and stability of the allocation scheme in the complex network environment.

[0027] Further, the resource allocation process also needs to meet the network available resource limit constraint condition, and the specific expression of the network resource limit constraint condition is:

[0028]

[0029] wherein, E represents a constraint condition of the power emergency communication network to available network resources, R represents actually used time slots, R * is an available time slot, L represents actually used subcarriers, L * is an available subcarrier, A represents actually consumed power, A max represents a maximum transmission power.

[0030] The embodiment of the present application can effectively limit the actual use range of the time slot quantity, the subcarrier quantity and the transmission power in the resource allocation process by introducing the above network resource limit constraint condition, prevent the resource allocation result from exceeding the available capacity or the power upper limit of the network, and thus avoid the problems of link congestion, system instability or device overload caused by resource overload; wherein, the time slot and subcarrier limit constraint can ensure fair and efficient resource utilization under limited frequency spectrum and time resources, and the maximum transmission power constraint can prevent the node from causing hardware damage or sharp rise in energy consumption due to excessively high power, especially in the power emergency communication scene, which is helpful to prolong the endurance time of the key node and reduce the system energy consumption risk; the introduction of the constraint condition makes the generated resource allocation scheme be able to fully utilize the efficiency of limited resources under the premise of ensuring the safe and stable operation of the system, and further improve the availability and reliability of the emergency communication network.

[0031] Further, according to the real-time state information of the plurality of users and the plurality of subcarriers, and in combination with a preset resource allocation model, a genetic algorithm is used to solve the resource allocation model, including:

[0032] A chromosome with a length corresponding to the number of subcarriers is set, and the chromosome is encoded in an integer coding mode, wherein each gene value in the chromosome represents that the corresponding subcarrier is allocated to a certain user;

[0033] Under the coding condition of meeting the corresponding relationship between each user and each subcarrier in the power emergency communication network, all subcarriers are randomly allocated to each user to generate an initial population, wherein the initial population represents a plurality of candidate resource allocation schemes;

[0034] When allocating subcarriers to users, the fitness value of each chromosome individual is calculated according to the double-objective function under the constraint condition set combining the service quality constraint condition and the network resource limit constraint condition;

[0035] Individuals with high fitness values are selected as parents according to the fitness values, and genetic operations are performed;

[0036] Self-adaptive crossover operation is performed on the selected parent individuals to generate new individuals;

[0037] Self-adaptive mutation operation is performed on the newly generated individuals;

[0038] updating the population individuals according to the fitness value calculation results until a termination condition is met, wherein each iteration comprises: first initializing the population and setting algorithm parameters including population size, crossover probability and mutation probability; then calculating the fitness value of each individual in the current population, and determining whether a preset termination condition is met, if yes, outputting the chromosome individual with the optimal current fitness as the optimal resource allocation scheme, if not, adaptively adjusting the crossover probability and the mutation probability according to the fitness distribution, and performing crossover and mutation operations on the parent individuals according to a selection strategy to generate a new generation of population, and taking the new generation of population as the current population to enter the next iteration until the end.

[0039] The embodiment of the application can efficiently find an optimal resource allocation scheme meeting the dual constraints in a huge search space by modeling the subcarrier allocation problem as a chromosome coding form, combining the quality of service constraint condition and the network resource limit constraint condition, and using the genetic algorithm to solve under the guidance of the dual objective function, wherein by selecting individuals with high fitness as parents and introducing adaptive crossover and adaptive mutation operations, the crossover probability and the mutation probability can be dynamically adjusted according to the current population fitness distribution, so as to effectively avoid the algorithm from falling into a local optimal solution, and improve the diversity and global search ability of the population; at the same time, the iterative updating mechanism can gradually improve the solution quality within limited computing resources, and finally obtain a resource allocation scheme considering network capacity and energy efficiency; the method is not only suitable for high-load and strict-constraint environments in the power emergency communication scene, but also can maintain high computing efficiency and allocation accuracy under large-scale user and complex network conditions, and significantly improves the service capability and operation stability of the network.

[0040] Further, the adaptive crossover operation and the adaptive mutation operation comprise:

[0041] adjusting the search strategy by the crossover probability P c and the mutation probability P m to realize adaptive adjustment of the crossover and the mutation, P c and P m The specific expressions of P

[0042]

[0043] wherein, g now represents the current iteration number, and g max represents the maximum iteration number.

[0044] The embodiments of the present application introduce a dynamic adjustment mechanism of adaptive crossover probability and adaptive mutation probability in the genetic algorithm, so that the algorithm can maintain a high crossover probability and a low mutation probability in the early iteration to improve the global optimization ability of the algorithm and expand the exploration range of the solution space. With the increase of the number of iterations, the crossover probability gradually decreases and the mutation probability gradually increases, thereby improving the local search accuracy and accelerating the convergence speed. This strategy can achieve a dynamic balance between search range and search accuracy at different stages of algorithm operation, effectively avoid the premature convergence problem, improve the population diversity and the probability of obtaining the global optimal solution. In the resource allocation problem of the power emergency communication network, this mechanism can maintain high solution efficiency and allocation accuracy under complex constraint conditions and large-scale search space, further improve the capacity utilization and energy efficiency of the network.

[0045] In a second aspect, the embodiments of the present application provide a power emergency communication network resource allocation system based on a genetic algorithm, comprising an acquisition module, a scheme generation module and a resource allocation module.

[0046] The acquisition module is configured to acquire real-time state information of a plurality of users and a plurality of subcarriers currently coexisting in the power emergency communication network.

[0047] The scheme generation module is configured to solve the resource allocation model by using the genetic algorithm according to the real-time state information of the plurality of users and the plurality of subcarriers in combination with a preset resource allocation model, and determine a resource allocation scheme of the power emergency communication network through an allocation relationship corresponding to an optimal chromosome. The resource allocation model is provided with a double-objective function and a constraint condition set of resource allocation. The double-objective function is a resource allocation optimization function established by taking the maximum capacity and the maximum energy efficiency of the power emergency communication network as optimization objectives. The constraint condition set includes a quality of service constraint condition and a network resource limit constraint condition.

[0048] The resource allocation module is configured to allocate resources to the power emergency communication network according to the resource allocation scheme.

[0049] The embodiment of the present application can realize full-process automatic processing from network state information acquisition, resource allocation scheme generation to actual resource allocation, reduce manual intervention, and improve system operation efficiency by modularizing the resource allocation function into an acquisition module, a scheme generation module and a resource allocation module. The scheme generation module uses a genetic algorithm to efficiently solve in a complex search space based on a dual-objective function and a constraint condition set, can guarantee joint optimization of network capacity and energy efficiency, and can meet multiple constraint requirements of quality of service and resource limits, thereby improving rationality and feasibility of resource allocation. Through the combination of systematic design and intelligent optimization method, the resource utilization rate, service quality guarantee capability and overall operation reliability of the power emergency communication network in a burst scenario can be significantly improved, thereby providing strong support for efficient and stable operation of emergency communication services.

[0050] In a third aspect, an embodiment of the present application provides a terminal device, comprising: a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus;

[0051] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operation of the power emergency communication network resource allocation method based on the genetic algorithm.

[0052] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, the computer readable storage medium comprises a stored computer program, wherein when the computer program runs, the computer readable storage medium controls the device or system where the computer readable storage medium is located to execute the power emergency communication network resource allocation method based on the genetic algorithm.

[0053] The above description is only a summary of the technical solutions of the embodiments of the present application, in order to more clearly understand the technical means of the embodiments of the present application, the embodiments of the present application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the embodiments of the present application more obvious and easy to understand, the specific embodiments of the present application are described below. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0055] Figure 1 is a flowchart of an embodiment of the power emergency communication network resource allocation method based on the genetic algorithm provided by the present application;

[0056] Figure 2 is a structural schematic diagram of an embodiment of a power emergency communication network resource allocation system based on a genetic algorithm provided by the present application. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the protection scope of the present application.

[0058] The power communication system is crucial to the safe and stable operation of the power grid, especially after major natural disasters such as earthquakes and floods, a power emergency communication network with high robustness and rapid deployment capability needs to be quickly built. However, the diversification and suddenness of emergency services can lead to frequent application of more bandwidth, frequency resources or access time slots by terminal nodes, which can easily cause communication congestion and resource waste under resource-limited conditions, affecting the overall coordinated operation and communication quality. Therefore, an efficient and reasonable resource allocation method is needed to improve resource utilization and ensure the priority transmission of key services. However, the existing resource allocation methods based on traditional optimization algorithms such as linear programming, constraint programming and dynamic programming have high computational complexity and are prone to local optimization in the solving process, and it is difficult to quickly obtain a global optimal solution in a large-scale or dynamic network environment due to the complex and variable resource types, service requirements and constraint conditions of the emergency communication network, and the highly nonlinear and high-dimensional problem model.

[0059] Referring to Figure 1 To realize the reasonable scheduling and dynamic allocation of resources in the power emergency communication network, an embodiment of the present application provides a power emergency communication network resource allocation method based on a genetic algorithm, which includes steps S101 to S103.

[0060] Step S101, obtaining real-time state information of a plurality of users and a plurality of subcarriers currently coexisting in the power emergency communication network;

[0061] In some embodiments, during the operation of the power emergency communication network, the real-time state information of the plurality of users currently coexisting is obtained through a network management system or a base station controller, wherein the user information includes user identification, user location, channel quality indicator (CQI), instantaneous signal-to-noise ratio (SINR), service type and its QoS requirement (minimum rate, maximum delay, maximum packet loss rate).

[0062] It should be noted that the user identification information is the unique identification information (such as IMSI or device MAC address) of each user obtained through the user access authentication process, which is used to accurately locate the resource demand object in the allocation process; the user location information is the geographical location and the corresponding service cell where the user is located determined by the base station positioning or the ranging function of the unmanned aerial node; the channel quality indicator (CQI) and the instantaneous signal-to-noise ratio (SINR) are periodically reported through physical layer measurement reporting, which reflects the instantaneous quality condition of the current channel of the user; the service type and its QoS demand include the user service type (such as voice communication, video conference, SCADA data transmission, etc.) and its corresponding QoS parameters, such as the minimum transmission rate v min , the maximum tolerable delay t max , and the maximum tolerable packet loss rate s max .

[0063] In some embodiments, during the operation of the power emergency communication network, the real-time state information of a plurality of subcarriers coexisting is obtained by the network management system or the base station controller, wherein the subcarrier information includes the total number of available subcarriers, the allocated state, the number of available time slots, the upper limit of transmission power, etc.

[0064] It should be noted that the total number of subcarriers is the total amount of available physical resource blocks determined by the system bandwidth and the subcarrier spacing (such as 15 kHz); the allocated state is the subcarrier occupation table maintained by the scheduler in real time, which is used to exclude the resources currently occupied by fixed tasks; the number of available time slots is determined by the frame structure configuration and the number of time slots that can be allocated in the current scheduling period; the upper limit of transmission power is determined by the base station power amplifier capability and the battery capacity (such as a portable base station).

[0065] It should be noted that the collection method of the plurality of user information and the plurality of subcarrier information is to collect user access information and channel measurement values by the base station control unit at regular intervals, and then the network management center communicates with the base station through the interface, and formats the data; for the air-ground ad hoc network node temporarily erected after the disaster, the node state is obtained by using link probe instruction (such as HELLO message) and link measurement feedback.

[0066] Step S102, according to the real-time state information of the plurality of users and the plurality of subcarriers, combining a preset resource allocation model, using a genetic algorithm to solve the resource allocation model, and determining the resource allocation scheme of the power emergency communication network through the allocation relationship corresponding to the optimal chromosome; wherein the resource allocation model is provided with a double objective function and a constraint condition set of resource allocation; the double objective function is a resource allocation optimization function established with the maximum capacity of the power emergency communication network and the maximum energy efficiency as optimization objectives; the constraint condition set includes a quality of service constraint condition and a network resource limit constraint condition;

[0067] In some embodiments, real-time state information of the several users and subcarriers is obtained, a resource allocation double-objective function is established aiming at joint optimization of network capacity and energy efficiency, a constraint condition set is set, and the resource allocation model is constructed; a chromosome (length = number of subcarriers) is established by using integer coding conditions, and each gene value in the chromosome indicates which user to which subcarrier is allocated, for example: assuming that there are N subcarriers and K users in the power emergency communication network, the power emergency communication network resource allocation is to allocate N subcarriers to K users, and the corresponding is to allocate the nth subcarrier to the kth user, a chromosome with a length of N is set, and any gene value in the chromosome represents allocation of the nth subcarrier to the kth user; an initial population (several chromosomes) is randomly generated, such as randomly allocating N subcarriers to K users; the fitness of each individual (chromosome) is calculated: when allocating subcarriers to users, the resource allocation double-objective function f(x) is calculated as the fitness calculation criterion in combination with the constraint condition set, where f(x) = max F + max η; the parent generation is selected according to the fitness (roulette or tournament), the offspring generation is generated according to the adaptive crossover probability P c and the adaptive mutation probability P m The elite individuals are retained, the population is updated until the termination condition (maximum iteration number or fitness convergence) is met; the optimal chromosome is output and decoded into a resource allocation table, and is issued for execution.

[0068] It should be noted that the resource allocation model is provided with a double-objective function and a constraint condition set of resource allocation; the double-objective function is a resource allocation optimization function established aiming at maximizing the capacity and energy efficiency of the power emergency communication network; the constraint condition set includes a quality of service constraint condition and a network resource limit constraint condition;

[0069] The network capacity is the number of users that can be served by the power emergency communication network, and the specific expression is:

[0070]

[0071] Wherein, k represents the number of users in the coverage range of the power emergency communication network, e k represents the utility of the user, r k represents the instantaneous signal-to-interference-and-noise ratio of the user, y k represents the actual transmission rate of the network, and I represents the maximum transmission rate that can be obtained.

[0072] The energy efficiency is the utility value of the power emergency communication network under given conditions, and the specific expression is:

[0073]

[0074] where sigmoid represents a utility function based on average energy efficiency, r min represents a utility function threshold value, P k represents the transmission power used by the kth user on the allocated resource block.

[0075] where the specific expression of the service quality constraint condition is:

[0076]

[0077] where v represents the actual transmission rate of the network, v min represents the minimum transmission rate required by the user, t represents the actual delay of the network, t max represents the maximum tolerable delay of the user, s represents the actual packet loss rate of the network, s max represents the maximum tolerable packet loss rate of the user.

[0078] The specific expression of the network resource limit constraint condition is:

[0079]

[0080] where E represents the constraint condition of the network available resources of the power emergency communication network, R represents the actually used time slots, R * available time slots, L represents the actually used subcarriers, L * available subcarriers, A represents the actually consumed power, A max represents the maximum transmission power.

[0081] By constructing a resource allocation model containing a double-objective function (network capacity maximization and energy efficiency maximization) and a constraint condition set (service quality constraint condition and network resource limit constraint condition), and solving the model by using a genetic algorithm, a resource allocation scheme close to the global optimum can be obtained under the premise of meeting the real-time, reliability and power consumption control requirements of the power emergency communication service, thereby improving the disaster resistance guarantee capability and operation stability of the power emergency communication network.

[0082] In some embodiments, the specific process of the fitness function calculation is as follows: taking the resource allocation double-objective function as the fitness calculation criterion, for each chromosome individual in the population, first calculating its network capacity F and energy efficiency η, and then normalizing and arranging according to the weighting coefficient to obtain the fitness value Fit, and the specific expression is:

[0083]

[0084] where w1+w2=1, and w1, w2∈[0,1], where w1 is a weighted coefficient of network capacity, used to represent the importance of the capacity indicator in the fitness calculation, in the scenario of network channel tension or the need to quickly restore communication capability, w1 should take a larger value, for example, 0.6-0.8, to preferentially guarantee the system throughput; w2 is a weighted coefficient of energy efficiency, used to represent the importance of the energy efficiency indicator in the fitness calculation, in the scenario of power limitation or device relying on battery power supply, w2 should take a larger value, for example, 0.6-0.8, to prolong the endurance time of the communication network; F max is the maximum reference value of network capacity, in engineering implementation, the maximum value of network capacity in the current generation population or in the history of several generations can be taken as the reference upper limit to ensure that the normalized indicator is between 0-1, and to improve the calculation stability; in theoretical analysis, the theoretical capacity upper limit based on the optimal channel allocation and power allocation strategy can be taken as the maximum value reference of capacity; η max is the maximum reference value of energy efficiency, in engineering implementation, the maximum value of the energy efficiency indicator in the current generation population or in the history of several generations can be taken as the reference upper limit; in theoretical analysis, the energy efficiency upper limit under the minimum power allocation condition or ideal transmission condition can be calculated.

[0085] In some embodiments, the fitness calculation can also combine a constraint penalty mechanism: when an individual violates the resource constraint (such as the total power constraint, the user minimum rate constraint or the delay constraint), the fitness value Fit is deducted or directly set to zero to ensure that the evolution process of the genetic algorithm converges to the feasible solution space.

[0086] In some embodiments, according to the fitness value, a roulette wheel selection method or a tournament selection method is used to select individuals with high fitness from the current population as parent individuals, and the crossover probability P c and the mutation probability P m are adaptively adjusted. c and P m The specific calculation formulas are as follows:

[0087]

[0088] where, g now represents the current iteration number, and g max represents the maximum iteration number. This adaptive adjustment mechanism can maintain a larger search space in the early stage and gradually improve the local exploration ability in the later stage, thereby improving the convergence speed and the quality of the solution.

[0089] In some embodiments, after each iteration ends, it is determined whether any of the following termination conditions is met: iteration number condition, the current iteration number g now ≥g maxconverge condition, the optimal fitness variation of continuous k generations (for example, k = 50) is less than a threshold value ∈ (for example, ∈ = 10 -5 ), and it is considered that the algorithm has converged; performance target condition, the optimal fitness value reaches or exceeds a preset performance index Fit target (for example, Fit target = 0.9, which means that the weighted comprehensive of network capacity and energy efficiency reaches 90% or above); if the termination condition is met, the iteration is stopped, otherwise the fitness function calculation step is returned to continue the calculation; when the termination condition is met, the chromosome individual with the highest fitness value in the current population is output, and the gene sequence corresponding to the "subcarrier-user" mapping relationship of the chromosome individual is the optimal resource allocation scheme of the power emergency communication network.

[0090] It should be noted that when the preset termination condition is met, the chromosome individual with the highest fitness value in the current population is obtained, since the gene position of the chromosome corresponds to the subcarrier one by one, the gene value corresponds to the user one by one, and the individual has passed the feasibility verification of the quality of service constraint condition and the network resource limit constraint condition, therefore, the "subcarrier-user" mapping relationship corresponding to the chromosome is the optimal resource allocation scheme of the power emergency communication network.

[0091] For example, it is assumed that the network has a total of 20 subcarriers, 10 users, the initial population size N = 100, the maximum number of iterations g max = 500, the weighting coefficients w1 = 0.6 and w2 = 0.4, the threshold value ∈ = 10 -5 , the continuous generation number k = 50, and the performance target Fit target = 0.9; during the running process, the optimal fitness value reaches 0.905 at the 320th generation, which exceeds the performance target, so the optimal resource allocation scheme is output in advance.

[0092] By introducing the genetic algorithm optimization mechanism based on the double-objective function (maximization of network capacity and maximization of energy efficiency) in the resource allocation process, and combining the integer coding, elite reservation, adaptive crossover and mutation probability adjustment strategies, the global optimal resource allocation scheme can be efficiently searched and approximated under the conditions of multiple users, multiple subcarriers and multiple constraints.

[0093] In step S103, the resource allocation scheme is used to allocate resources to the power emergency communication network.

[0094] In some embodiments, the power emergency communication network is allocated resources according to the optimal resource allocation scheme output, specifically including: first, the optimal resource allocation scheme output by the genetic algorithm is parsed, which is usually described in the form of a matrix or table to describe the resource occupation of each node, each link and each service in the network, and the system control module analyzes the scheme to extract the link bandwidth allocation ratio, spectrum block assignment result, transmission power allocation parameter and priority strategy of different services; second, the resource allocation result parsed is converted into control instructions recognizable by network equipment, specifically including: updating the bandwidth scheduling table of the base station or the relay node, issuing time slot and spectrum block allocation information to the link scheduling module, and setting the transmission power upper limit or distribution parameter of each node, the above control instructions are issued to each node in the emergency communication network through the network management system or the software defined network control plane; third, each network node configures its local scheduling module and transceiver module according to the received instructions, for example, the base station modifies the time-frequency resource block allocation table in the scheduler, the unmanned aerial vehicle relay node adjusts its forwarding bandwidth and power threshold, and the edge router updates the priority weight of the service queue, so as to ensure that high-priority services obtain priority transmission resources; then, different types of services are bound to corresponding network resources according to the QoS mapping relationship in the resource allocation scheme, high-priority and low-latency command communication services are preferentially allocated to stable links and large bandwidth resources, and low-priority data services are allocated to the remaining resources, so as to realize reasonable bearing of multiple services; finally, after the resource allocation is completed, the running monitoring module collects link utilization, delay, packet loss rate and other running indexes in real time, and compares them with the expected performance of the resource allocation scheme, when the monitoring result deviates greatly from the expectation, the system triggers the feedback mechanism, re-calls the genetic algorithm for iterative optimization, and issues the updated resource allocation scheme to each network node again, thereby forming a closed-loop optimization process.

[0095] Through the above process, it is ensured that the optimal resource allocation scheme output by the genetic algorithm can be effectively implemented in the actual power emergency communication network, and has dynamic adjustment and continuous optimization capability.

[0096] The beneficial effects of the present application are:

[0097] 1. The present application takes the maximization of power emergency communication network capacity and the maximization of energy efficiency as double optimization objectives, which can realize efficient allocation and utilization of network resources under the condition of limited spectrum and power, improve the overall carrying capacity of the network, and reduce the overall energy consumption, which is beneficial to guarantee the continuous and stable operation of the emergency communication network in disaster scenarios.

[0098] 2. When establishing the resource allocation model, this invention introduces service quality constraints (including minimum transmission rate, maximum tolerable delay, and maximum tolerable packet loss rate) and network resource limit constraints (including available time slots, available subcarriers, and maximum transmit power). This can meet user service needs while avoiding congestion and waste caused by improper resource allocation, thereby improving the accuracy and reliability of resource allocation.

[0099] 3. This invention employs a genetic algorithm to solve complex nonlinear, multi-constraint resource allocation optimization problems. By combining global search with adaptive adjustment of crossover and mutation operations, it effectively avoids getting trapped in local optima and can obtain globally optimal resource allocation schemes in complex scenarios involving multiple users and multiple subcarriers.

[0100] 4. This invention introduces an adaptive adjustment mechanism in the iterative process of the genetic algorithm, dynamically adjusting the crossover probability and mutation probability according to the number of iterations. This ensures the diversity of solutions and global exploration capability in the early stages of the search, while enhancing the local fine-grained search capability in the later stages, thereby improving the convergence speed and solution quality, and meeting the needs of power emergency communication networks for rapid optimization.

[0101] 5. The method of the present invention has good scalability and versatility, can adapt to large-scale network nodes, complex service types and rapidly changing network environments, and is suitable for deployment and resource scheduling scenarios of various emergency communication networks, and has high engineering application value.

[0102] like Figure 2 As shown, based on the above method embodiments, corresponding apparatus embodiments are provided;

[0103] An embodiment of the present invention provides a power emergency communication network resource allocation system based on a genetic algorithm, comprising: an acquisition module 100, a scheme generation module 200, and a resource allocation module 300;

[0104] The acquisition module 100 is used to acquire real-time status information of several users and several subcarriers currently coexisting in the power emergency communication network.

[0105] The scheme generation module 200 is used to solve the resource allocation model using a genetic algorithm based on the real-time status information of the plurality of users and the plurality of subcarriers, combined with a preset resource allocation model, and to determine the resource allocation scheme of the power emergency communication network through the allocation relationship corresponding to the optimal chromosomes; wherein, the resource allocation model is set with a dual objective function and a set of constraints for resource allocation; the dual objective function is a resource allocation optimization function established with the optimization objectives of maximizing the capacity and maximizing the energy efficiency of the power emergency communication network; the set of constraints includes service quality constraints and network resource limit constraints;

[0106] The resource allocation module 300 is configured to allocate resources to the power emergency communication network according to the resource allocation scheme.

[0107] It can be understood that the above-mentioned device embodiments are corresponding to the method embodiments of the present application, and can realize the power emergency communication network resource allocation method based on the genetic algorithm provided by any one of the above-mentioned method embodiments of the present application.

[0108] It should be noted that the above-mentioned device embodiments are only schematic, and part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. In addition, in the device embodiment provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which can be realized as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.

[0109] On the basis of the above-mentioned embodiments of the power emergency communication network resource allocation method based on the genetic algorithm, another embodiment of the present application provides a terminal device, which comprises 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, the power emergency communication network resource allocation method based on the genetic algorithm of any one embodiment of the present application is realized.

[0110] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present application. The one or more modules can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the terminal device.

[0111] The terminal device can be a desktop computer, a notebook computer, a palm computer and a cloud server, etc. The terminal device can include, but is not limited to, a processor and a memory.

[0112] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The processor is a control center of the terminal device, and connects all parts of the terminal device through various interfaces and lines.

[0113] On the basis of the above-mentioned method embodiment, another embodiment of the present application provides a computer readable storage medium, including a stored computer program, wherein when the computer program runs, the device where the computer readable storage medium is located executes the power emergency communication network resource allocation method based on the genetic algorithm in the above-mentioned method embodiment of the present application.

[0114] The modules / units integrated in the device / terminal equipment, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which 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, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0115] The above-described specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above-described specific embodiments are merely examples of the present application and are not intended to limit the protection scope of the present application. It is particularly pointed out that any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A power emergency communication network resource allocation method based on genetic algorithm, characterized in that, The method comprises the following steps: acquiring real-time state information of a plurality of users and a plurality of subcarriers currently coexisting in the power emergency communication network; solving the resource allocation model by using a genetic algorithm according to the real-time state information of the plurality of users and the plurality of subcarriers in combination with a preset resource allocation model, and determining a resource allocation scheme of the power emergency communication network through an allocation relationship corresponding to an optimal chromosome; wherein the resource allocation model is provided with a double-objective function and a constraint condition set of resource allocation; the double-objective function is a resource allocation optimization function established by taking maximization of network capacity and maximization of energy efficiency as optimization objectives; and the constraint condition set comprises a quality of service constraint condition and a network resource limit constraint condition; allocating resources to the power emergency communication network according to the resource allocation scheme.

2. The method of claim 1, wherein, In the method, the resource allocation model comprises the following steps: establishing a double-objective function of resource allocation by taking joint optimization of network capacity and energy efficiency as an objective; setting a constraint condition set of resource allocation, which comprises a quality of service constraint condition and a network resource limit constraint condition; integrating the double-objective function and the constraint condition set to construct the resource allocation model.

3. The method of claim 2, wherein, In the method, the network capacity is the number of users that can be served by the power emergency communication network, and the specific expression is: where k represents the number of users within the coverage of the power emergency communication network, e k represents the utility of the user, r k represents the instantaneous signal-to-interference-and-noise ratio of the user, y k represents the actual transmission rate of the network, and I represents the maximum transmission rate available; the energy efficiency is the utility value of the power emergency communication network under given conditions, and the specific expression is: where sigmoid denotes a utility function based on average energy efficiency, r min denotes a utility function threshold value, P k denotes the transmit power used by the kth user on the allocated resource block.

4. The genetic algorithm based power emergency communication network resource allocation method of claim 2, wherein, the specific expression of the quality of service constraint condition is: where v represents the actual transmission rate of the network, v min represents the minimum transmission rate required by the user, t represents the actual delay of the network, t max represents the maximum tolerable delay of the user, s represents the actual packet loss rate of the network, s max represents the maximum tolerable packet loss rate of the user.

5. The genetic algorithm based power emergency communication network resource allocation method of claim 2, wherein, the specific expression of the network resource limit constraint condition is: wherein E represents a constraint condition of the power emergency communication network on network available resources, R represents actually used time slots, R * is available time slots, L represents actually used subcarriers, L * is available subcarriers, A represents actually consumed power, A max represents the maximum transmission power.

6. The method of claim 1, wherein, In the method, solving the resource allocation model by using a genetic algorithm according to the real-time state information of the plurality of users and the plurality of subcarriers in combination with a preset resource allocation model comprises the following steps: setting a chromosome with a length corresponding to the number of subcarriers, and encoding the chromosome by using an integer coding mode, wherein each gene value in the chromosome represents that a corresponding subcarrier is allocated to a user; allocating all subcarriers to users randomly under the coding condition of corresponding relationships between users and subcarriers in the power emergency communication network to generate an initial population, wherein the initial population represents a plurality of candidate resource allocation schemes; calculating an adaptability value of each chromosome individual according to the double-objective function under the constraint condition set comprising the quality of service constraint condition and the network resource limit constraint condition when allocating subcarriers to users; selecting individuals with high adaptability as parents to perform genetic operations according to the adaptability values; performing self-adaptive crossover operations on the selected parent individuals to generate new individuals; performing self-adaptive mutation operations on the new individuals. The population individuals are iteratively updated according to the fitness value calculation results until a termination condition is met; wherein each iteration includes: first, initializing the population and setting algorithm parameters including population size, crossover probability, and mutation probability; then, calculating the fitness values of each individual in the current population, and determining whether a preset termination condition is met, if yes, outputting the chromosome individual with the optimal current fitness as the optimal resource allocation scheme, if not, adaptively adjusting the crossover probability and the mutation probability according to the fitness distribution, and performing crossover and mutation operations on the parent individuals according to a selection strategy to generate a new generation of population, and taking the new generation of population as the current population to enter the next iteration until the end.

7. The method of claim 6, wherein, Wherein, The adaptive crossover operation and the adaptive mutation operation include: By the cross probability P c With the mutation probability P m Adjustment of search strategy is completed, adaptive adjustment of cross and mutation is realized, P c And P m The specific expression is: wherein g now denotes the current iteration number, g max denotes the maximum iteration number.

8. A power emergency communication network resource allocation system based on genetic algorithm, characterized in that, Including: An acquisition module, a scheme generation module, and a resource allocation module; The acquisition module is configured to acquire real-time state information of a plurality of users and a plurality of subcarriers currently coexisting in the power emergency communication network; The scheme generation module is configured to solve the resource allocation model by using a genetic algorithm according to the real-time state information of the plurality of users and the plurality of subcarriers and in combination with a preset resource allocation model, and determine a resource allocation scheme of the power emergency communication network through an allocation relationship corresponding to an optimal chromosome; wherein the resource allocation model is provided with a double-objective function and a constraint condition set of resource allocation; the double-objective function is a resource allocation optimization function established by taking maximization of power emergency communication network capacity and maximization of energy efficiency as optimization objectives; and the constraint condition set includes a quality of service constraint condition and a network resource limit constraint condition; The resource allocation module is configured to allocate resources to the power emergency communication network according to the resource allocation scheme.

9. A terminal device, comprising: Including: A processor, a memory, a communication interface, and a communication bus, the processor, the memory, and the communication interface complete communication with each other through the communication bus; The memory is configured to store at least one executable instruction, and the executable instruction causes the processor to perform the operations of the power emergency communication network resource allocation method based on a genetic algorithm according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, the device or system where the computer-readable storage medium is located controls the execution of the power emergency communication network resource allocation method based on a genetic algorithm according to any one of claims 1 to 7.

Images