Communication cabinet temperature adaptive control method and system

Abstract

The application discloses a communication cabinet temperature self-adaptive control method and system, and relates to the technical field of temperature control; a first environment parameter of a target communication cabinet is determined, the first environment parameter is adaptively optimized through an improved firefly algorithm to obtain a target environment parameter; a PID control parameter is obtained through simulation running of a target environment according to the target environment parameter; the PID control parameter is optimized through an improved sparrow algorithm to obtain a target control parameter, and the temperature control system is updated according to the target control parameter; the improved firefly algorithm optimizes the environment parameter, improves the accuracy and the anti-interference ability; the PID effect is verified based on the simulation environment of the accurate parameter, and dynamic optimization is realized; the improved sparrow algorithm is combined to optimize the control parameter, the temperature self-adaptive control precision and the response speed are enhanced, the communication cabinet is ensured to stably and efficiently run under different working conditions, and the equipment reliability is ensured.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of temperature control, and particularly relates to a communication cabinet temperature adaptive control method and system. BACKGROUND

[0002] With the rapid development of information technology and the increasing complexity of communication networks, the reliability and security of communication cabinets, as important components of communication systems, are particularly critical. A large number of high-performance communication devices and electronic components are integrated inside the communication cabinet. These devices generate a large amount of heat during operation. If heat dissipation is not timely and effective, the temperature inside the cabinet will quickly rise, which may cause the devices to overheat, affecting their normal operation, and even cause safety accidents such as failure, data loss, and fire.

[0003] Patent No. CN119493434A discloses a high-efficiency machine room approaching temperature control method, which combines historical data prediction with real-time sensor data to adaptively adjust the state of the refrigeration system. It uses thermal imaging technology to dynamically optimize cabinet layout and airflow path, adopts computational fluid dynamics to optimize airflow design, intelligently controls dampers and fans, implements heat recovery and renewable energy utilization to improve energy efficiency, establishes a multi-level redundant refrigeration system to predict and prevent failures, and uses the Internet of Things and AI to realize remote monitoring and automated operation and maintenance to ensure precise control of machine room temperature, reduce energy consumption, and improve operation efficiency.

[0004] The above technology has solved some problems, but still has some problems, for example: the existing communication cabinet temperature control has a response lag, the temperature control is not reasonable, resulting in high energy consumption, or the temperature control does not meet the expected result, resulting in a reduction in the frequency of communication equipment, and the traditional optimization method lacks precision and has low optimization efficiency. SUMMARY

[0005] The purpose of the present application is to solve the problems of existing communication cabinet temperature control, such as response lag, unreasonable temperature control leading to high energy consumption, or temperature control not meeting the expected result leading to a reduction in the frequency of communication equipment, and the traditional optimization method lacking precision and having low optimization efficiency, and to propose a communication cabinet temperature adaptive control method and system.

[0006] In the first aspect of the present application, a communication cabinet temperature adaptive control method is first proposed, which comprises:

[0007] determining a first environmental parameter of a target communication cabinet, and adaptively optimizing the first environmental parameter by improving the glowworm algorithm to obtain a target environmental parameter; the first environmental parameter includes: specific heat capacity of the communication cabinet, thermal resistance of the communication cabinet, heat generation rate of the communication cabinet, and system time lag of the communication cabinet;

[0008] The PID control parameter is obtained by simulating a target environment according to the target environment parameter, and the PID control parameter is optimized by improving the sparrow algorithm to obtain a target control parameter, and the temperature control system is updated according to the target control parameter.

[0009] The PID control parameter is obtained by simulating a target environment according to the target environment parameter, and the PID control parameter is optimized by improving the sparrow algorithm to obtain a target control parameter, and the temperature control system is updated according to the target control parameter.

[0010] Optionally, the target environment parameter is obtained by adaptively optimizing the first environment parameter by improving the firefly algorithm, comprising:

[0011] The first environment parameter is taken as a firefly, and a first preset parameter of the improved firefly algorithm is initialized; the first preset parameter comprises: population size, maximum iteration number, upper and lower bounds, dimension, light intensity absorption coefficient, maximum attraction and step factor;

[0012] The fitness is calculated according to the position of the target firefly in the population, the target distance between the target firefly and each firefly in the population is calculated, and the relative fluorescence brightness of the target firefly and each firefly in the population is calculated according to the target distance; the fitness represents the maximum fluorescence brightness of the firefly;

[0013] The attraction between the target firefly and each firefly is calculated according to the target distance, the position update formula is determined according to the iteration number and the attraction, and the position of the firefly is updated according to the position update formula and the relative fluorescence brightness;

[0014] The position update formula is: x i (t+1)=ω(t)*x i (t)+β(x j (t)-x i (t))

[0015] The adaptive weight formula is: ω(t)=sin(πt / 2t max +π)+1

[0016] Wherein, t is the current iteration number, t max is the maximum iteration number, ω(t) is the adaptive weight, x i (t+1) is the position of firefly i after updating in the t+1 iteration, β( ) is the attraction calculation formula, x j (t) is the firefly position of firefly j in t iteration, x i (t) is the firefly position of firefly i in t iteration.

[0017] The fitness is calculated according to the updated position of the target firefly in the population, and the optimal firefly is output if the maximum iteration number is reached; the best firefly is the target environment parameter.

[0018] Optionally, the PID control parameter is optimized to obtain a target control parameter by improving the sparrow algorithm, comprising:

[0019] Step one, the PID control parameter is taken as a sparrow, the second preset parameter of the improved sparrow algorithm is initialized, and the sparrow population position is initialized by tent chaos mapping; the second preset parameter includes: population size, maximum iteration number, upper limit and lower limit, dimension;

[0020] Step two, the fitness of the sparrow population individual is calculated, the fitness table is obtained by descending arrangement according to the fitness size, the corresponding sparrow in the fitness table is screened according to the preset rule to obtain a screening result, the screening result is taken as a discoverer, and the remaining sparrow is taken as a follower;

[0021] Step three, the discoverer position update strategy is optimized by the butterfly algorithm, and the discoverer is updated in position according to the discoverer position update strategy;

[0022] Step four, the follower position update strategy is optimized by the Cauchy distribution and Gaussian distribution, and the follower is updated according to the follower position update strategy;

[0023] Step five, the global fitness is updated, whether the maximum iteration number is reached is detected, if the maximum iteration number is reached, the optimal sparrow is output, otherwise, step three is returned.

[0024] Optionally, the fitness of the sparrow population individual is calculated, and the fitness formula includes: Wherein, SY is the fitness, wc(t) is the temperature error, e is a natural constant, P(t) is the air conditioning working energy consumption, and T is the total control process time.

[0025] Optionally, the target control parameter is used to update the temperature control system, comprising:

[0026] The target control parameter is sent to the temperature control system, and the temperature control system receives the target control parameter and controls the temperature according to the target control parameter;

[0027] After a preset time period, the second environment parameter in the target communication cabinet is obtained, and whether the target communication cabinet is in an abnormal overload state is judged, if it is in an abnormal overload state, the second environment parameter is updated; otherwise, the updating is stopped.

[0028] In the second aspect of the embodiment of the application, a communication cabinet temperature adaptive control system is provided, comprising: an environment determination module, a simulation simulation module and a control updating module:

[0029] The environment determining module is configured to determine a first environment parameter of the target communication cabinet, and to obtain a target environment parameter by adaptively optimizing the first environment parameter through the improved glowworm algorithm; the first environment parameter includes specific heat capacity of the communication cabinet, thermal resistance of the communication cabinet, heat production rate of the communication cabinet, and system time lag of the communication cabinet.

[0030] The simulation module is configured to simulate a target environment according to the target environment parameter, and to obtain a PID control parameter by running the simulation.

[0031] The control updating module is configured to obtain a target control parameter by optimizing the PID control parameter through the improved sparrow algorithm, and to update the temperature control system according to the target control parameter.

[0032] Optionally, the environment determining module includes an algorithm initialization module, a fitness calculation module, a glowworm calculation module, a glowworm updating module, and an iteration updating module.

[0033] The algorithm initialization module is configured to initialize a first preset parameter of the improved glowworm algorithm by taking the first environment parameter as a glowworm; the first preset parameter includes population size, maximum iteration number, upper and lower bounds, dimension, light intensity absorption coefficient, maximum attraction, and step factor.

[0034] The fitness calculation module is configured to calculate a fitness by a position of a target glowworm in a population, to calculate a target distance between the target glowworm and each glowworm in the population, and to calculate relative fluorescence brightness of the target glowworm and each glowworm in the population according to the target distance; the fitness represents maximum fluorescence brightness of the glowworm.

[0035] The glowworm updating module is configured to calculate attraction between the target glowworm and each glowworm according to the target distance, to determine a position updating formula according to the iteration number and the attraction, and to update the position of the glowworm according to the position updating formula and the relative fluorescence brightness; the position updating formula is as follows:

[0036] x i (t+1)=ω(t)*x i (t)+β(x j (t)-x i (t))

[0037] The adaptive weight formula is as follows:

[0038] ω(t)=sin(πt / 2t max +π)+1

[0039] wherein t is a current iteration number, t max is a maximum iteration number, ω(t) is an adaptive weight, and x i(t+1) is the position of the firefly i after updating at the (t+1)th iteration, β() is the attraction calculation formula, x j (t) is the firefly position of the firefly j at the tth iteration, i (t) is the firefly position of the firefly i at the tth iteration;

[0040] The iterative updating module is configured to calculate the fitness according to the updated position of the target firefly in the population, and output the optimal firefly if the maximum number of iterations is reached; the optimal firefly is the target environmental parameter.

[0041] Optionally, the control updating module comprises a first execution module, a second execution module, a third execution module, a fourth execution module and a fifth execution module:

[0042] The first execution module is configured to initialize the second preset parameter of the improved sparrow algorithm by taking the PID control parameter as a sparrow, and initialize the sparrow population position through tent chaotic mapping; the second preset parameter comprises a population size, a maximum number of iterations, an upper limit and a lower limit, and a dimension;

[0043] The second execution module is configured to calculate the fitness of the sparrow population individuals, arrange the sparrow population individuals in descending order according to the fitness to obtain a fitness table, screen the corresponding sparrow in the fitness table according to a preset rule to obtain a screening result, take the screening result as a discoverer, and take the remaining sparrows as followers;

[0044] The third execution module is configured to optimize the discoverer position updating strategy through a butterfly algorithm, and update the position of the discoverer according to the discoverer position updating strategy;

[0045] The fourth execution module is configured to optimize the follower position updating strategy through Cauchy distribution and Gaussian distribution, and update the follower according to the follower position updating strategy;

[0046] The fifth execution module is configured to update the global fitness, detect whether the maximum number of iterations is reached, and output the optimal sparrow if the maximum number of iterations is reached, or return to the third execution module otherwise. Optionally, the second execution module is further configured to: Wherein, SY is the fitness, wc(t) is the temperature error, e is a natural constant, P(t) is the air conditioning working energy consumption, and T is the total control process time.

[0047] Optionally, the control updating module further comprises a data transmission module and a data judgment module:

[0048] The data transmission module is configured to send the target control parameter to a temperature control system, and the temperature control system receives the target control parameter and performs temperature control according to the target control parameter.

[0049] The data judgment module is configured to acquire a second environment parameter in the target communication cabinet after a preset time period, and judge whether the target communication cabinet is in an abnormal overload state, if yes, update according to the second environment parameter, and if not, stop updating.

[0050] The present application has the following beneficial effects: the present application provides a communication cabinet temperature adaptive control method, by determining the first environment parameter of the target communication cabinet, the first environment parameter is adaptively optimized by improving the firefly algorithm to obtain the target environment parameter; the target environment is simulated according to the target environment parameter, and the PID control parameter is obtained by simulating operation according to the target environment; the target control parameter is obtained by optimizing the PID control parameter by improving the sparrow algorithm, and the temperature control system is updated according to the target control parameter; the environment parameter is optimized by improving the firefly algorithm, the accuracy and anti-interference ability are improved; the PID effect is verified by simulating the environment based on the accurate parameter, and dynamic optimization is realized; the control parameter is optimized by combining the improved sparrow algorithm, the temperature adaptive control precision and response speed are enhanced, the communication cabinet is stably and efficiently operated under different working conditions, and the equipment reliability is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0051] The present application will be further described below in combination with the drawings.

[0052] Figure 1 A flow chart of a communication cabinet temperature adaptive control method provided for the embodiment of the present application;

[0053] Figure 2 A frame diagram of a communication cabinet temperature adaptive control system provided for the embodiment of the present application. DETAILED DESCRIPTION

[0054] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. The term “and / or” in this document is only used to describe the association relationship of associated objects, and can represent three relationships, for example, A and B can represent three cases of existence of A alone, existence of A and B together, and existence of B alone. In addition, the description of “first”, “second” and the like in the present application is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features defined as “first”, “second” can explicitly or implicitly include at least one of the features. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the fact that a person skilled in the art can realize it. When the combination of technical solutions contradicts each other or cannot be realized, it should be considered that the combination of technical solutions does not exist, and is also not within the protection scope of the present application.

[0055] Based on the embodiments in the present application, all other embodiments obtained by a person skilled in the art without creative labor are within the protection scope of the present application.

[0056] The embodiment of the present application provides a communication cabinet temperature adaptive control method. Referring to Figure 1 , Figure 1 The embodiment of the present application provides a flow chart of a communication cabinet temperature adaptive control method. The method comprises the following steps:

[0057] S101, determining the first environment parameter of the target communication cabinet, and obtaining the target environment parameter by adaptively optimizing the first environment parameter through the improved firefly algorithm;

[0058] S102, simulating the target environment according to the target environment parameter, and obtaining the PID control parameter according to the simulation running of the target environment;

[0059] S103, obtaining the target control parameter by optimizing the PID control parameter through the improved sparrow algorithm, and updating the temperature control system according to the target control parameter.

[0060] The first environment parameter comprises: the specific heat capacity of the communication cabinet, the thermal resistance of the communication cabinet, the heat generation rate of the communication cabinet and the system time delay of the communication cabinet;

[0061] Based on the communication cabinet temperature adaptive control method provided by the embodiment of the application, the environmental parameters are optimized by improving the glowworm algorithm, the accuracy and anti-interference ability are improved, the PID effect is verified based on the precise parameter simulation environment, dynamic optimization is realized, the control parameters are optimized by combining the improved sparrow algorithm, the temperature adaptive control precision and response speed are enhanced, the communication cabinet is ensured to stably and efficiently operate under different working conditions, and the equipment reliability is ensured.

[0062] In an implementation manner, the first environmental parameters are for example: communication cabinet specific heat capacity (the ability of the communication cabinet to store heat energy as a whole), communication cabinet thermal resistance (heat dissipation resistance between the communication cabinet and the environment), communication cabinet heat generation rate (total heat generation power of the communication cabinet), and communication cabinet system time delay (system response delay including: sensor delay, actuator delay, heat propagation delay); the first environmental parameters are all acquired in the communication cabinet; the acquisition mode of the first environmental parameters is as follows: the communication cabinet specific heat capacity is regarded as the specific heat capacity of the air in the communication cabinet, the communication cabinet thermal resistance is measured by a thermocouple, a thermistor or an infrared temperature sensor (the temperature sensors need to be uniformly distributed), the communication cabinet heat generation rate is acquired by an intelligent electric meter and a Hall effect sensor (installed at the input end of the cabinet power supply, and real-time monitoring of equipment power consumption), and the communication cabinet system time delay is the delay between the control signal of the communication cabinet system and the actual response time of the corresponding module (for example, the time from when the control signal is sent to when the refrigeration system actually starts cooling after receiving the control signal).

[0063] In an implementation manner, a target environment is simulated according to a target environmental parameter, the target environment is a simulation environment (for example: Matlab) simulated by the target environmental parameter, the simulation environment is used for simulating the environment in the communication cabinet, and the purpose of simulation is to verify the effect of the PID control parameter; if the execution effect of the PID control parameter is not ideal, the PID control parameter is optimized again, and the temperature adaptive control is realized by continuously optimizing the PID control parameter.

[0064] In an implementation manner, a target environmental parameter is obtained by optimizing the first environmental parameter through a first preset algorithm, the first preset algorithm is an improved glowworm algorithm (1. adaptive inertia weight: dynamically balance global search and local development, and avoid premature convergence; 2. noise robustness enhancement: suppress noise interference through a Gaussian disturbance term); and a target control parameter is obtained by optimizing the PID control parameter through a second preset algorithm, the second preset algorithm is an improved sparrow algorithm (1. Tent chaotic mapping initialization: uniformly distribute initial population, and avoid local aggregation; 2. butterfly algorithm global search: the finder quickly moves to the optimal solution direction, and convergence is accelerated; 3. Cauchy-Gaussian variation: early Cauchy variation expands the search, and late Gaussian variation finely optimizes)

[0065] In an implementation, the first environmental parameter of the communication cabinet is optimized by the improved glowworm algorithm, which can dynamically balance global search and local development, avoid premature convergence, and enhance noise robustness by suppressing noise interference through a Gaussian disturbance term. This makes the obtained target environmental parameter more accurate and stable, providing a more reliable environmental basis for subsequent temperature control, thereby improving the adaptability and reliability of the communication cabinet temperature control system.

[0066] In an implementation, the simulation environment is simulated according to the optimized target environmental parameter, and the PID control parameter is obtained through simulation running. This process can effectively verify the effect of the PID control parameter, and if the execution effect is not ideal, optimization can be performed again, realizing accurate simulation and optimization of the communication cabinet temperature control, improving the adaptability and effectiveness of the control parameter, and thereby enhancing the self-adaptive ability of the temperature control system, ensuring that the communication cabinet can maintain a good temperature state under different environmental conditions.

[0067] In an implementation, the improved sparrow algorithm is used to optimize the PID control parameter (in addition to the sparrow algorithm, particle swarm optimization algorithm, grey wolf algorithm, etc.), including Tent chaotic mapping initialization, butterfly algorithm global search, and Cauchy-Gaussian mutation. These improvements can uniformly distribute the initial population, avoid local aggregation, accelerate convergence, and achieve early extensive search and late fine optimization during the optimization process. The final target control parameter can more accurately guide the update of the temperature control system, thereby improving the precision and response speed of the communication cabinet temperature control and effectively ensuring the stable operation of the communication equipment.

[0068] In an implementation, the target environmental parameter is obtained by adaptively optimizing the first environmental parameter through the improved glowworm algorithm, including:

[0069] The first environmental parameter is used as a glowworm to initialize the first preset parameter of the improved glowworm algorithm; the first preset parameter includes: population size, maximum iteration number, upper and lower bounds, dimension, light absorption coefficient, maximum attraction, and step factor;

[0070] The fitness is calculated based on the position of the target glowworm in the population, the target distance between the target glowworm and each glowworm in the population is calculated, and the relative fluorescence brightness of the target glowworm and each glowworm in the population is calculated based on the target distance; the fitness represents the maximum fluorescence brightness of the glowworm;

[0071] The attraction between the target glowworm and each glowworm is calculated based on the target distance, the position update formula is determined based on the iteration number and the attraction, and the position of the glowworm is updated based on the position update formula and the relative fluorescence brightness;

[0072] Position update formula:

[0073] x i (t+1)=ω(t)*x i (t)+β(x j (t)-x i (t))

[0074] Adaptive weight formula:

[0075] ω(t)=sin(πt / 2t max +π)+1

[0076] Where t is the current iteration number, t max is the maximum iteration number, ω(t) is the adaptive weight, x i (t+1) is the position of firefly i after updating in the t+1 iteration number, β() is the attraction calculation formula, x j (t) is the firefly position of firefly j in t iteration number, x i (t) is the firefly position of firefly i in t iteration number.

[0077] The fitness is calculated according to the updated position of the target firefly in the population, and if the maximum iteration number is reached, the optimal firefly is output; the best firefly is the target environmental parameter.

[0078] In one implementation, the first preset parameter is the population size, which refers to the number of fireflies in the algorithm, i.e., the number of individuals participating in the optimization process. The maximum number of iterations refers to the maximum number of loops the algorithm runs, i.e., the upper limit of the number of times the algorithm attempts to optimize the objective function. Setting the maximum number of iterations can prevent the algorithm from running indefinitely, while controlling the running time and computational resource consumption of the algorithm. A larger number of iterations may improve optimization accuracy, but it will also increase the calculation time. The upper and lower bounds refer to the value range of each firefly position variable, i.e., the minimum and maximum values of each dimension. The upper and lower bounds limit the search range of the firefly's position, preventing the search process from deviating from the feasible solution space of the actual problem, ensuring the stability and effectiveness of the algorithm. The dimension refers to the number of dimensions of each firefly position vector, i.e., the number of variables of the optimization problem. The dimension reflects the complexity of the optimization problem. For example, the position of a two-dimensional optimization problem can be represented by two variables, while a high-dimensional problem requires more variables. The light intensity absorption coefficient is a parameter used to describe the attenuation of light intensity, indicating the degree of light intensity absorbed during propagation. The light intensity absorption coefficient affects the calculation of the relative fluorescence intensity between fireflies. A larger light intensity absorption coefficient will cause the light intensity to decay faster, affecting the attraction and movement direction between fireflies. The maximum attraction refers to the maximum attraction value that fireflies can reach. The maximum attraction determines the maximum movement distance between fireflies, affecting the search ability and convergence speed of the algorithm. A larger maximum attraction can make fireflies move faster towards better solutions. The step factor is a parameter used to control the step size of firefly movement. The step factor affects the movement distance of fireflies in each iteration. A larger step factor can make fireflies move faster in the search space, but it may cause the search process to be unstable. A smaller step factor can make the search process more precise, but it may slow down the convergence speed.

[0079] In one implementation, the key factors to improve the firefly algorithm are brightness and attraction. Brightness reflects the quality of firefly position and determines its movement direction, while attraction determines the distance of firefly movement. Through the continuous updating of brightness and attraction, the algorithm achieves the optimization of the target. In one implementation, the relative fluorescence intensity of fireflies is defined as: I(r)=I0e -γr , where I0 is the maximum fluorescence intensity of fireflies, e is the natural constant, γ is the light intensity absorption coefficient, and r is the Cartesian distance between any two fireflies. The distance between fireflies is defined as: , where r ij is the Cartesian distance between any two fireflies i and j, d is the spatial dimension, and k is the kth component of firefly i in d-dimensional space coordinates. The attraction of fireflies is defined as: β(r)=β0e -γ(r×r), b0 is the maximum attraction; determine the position update formula according to the iteration number and the attraction: x i (t+1) = w(t) * x i (t) + b(x j (t) - x i (t)), w(t) = sin (pi t / 2t max +pi) +1, t is the current iteration number, t max is the maximum iteration number, w(t) is the adaptive weight, x i (t+1) is the position of the firefly i after updating (at the t+1 iteration number), x j (t) is the firefly position of the firefly j at the t iteration number, x i (t) is the firefly position of the firefly i at the t iteration number; when the adaptive weight is large, the motion step of the last generation of fireflies has a large influence on the current motion, and the attraction between the fireflies has a relatively small influence, thereby enhancing the global search ability of the algorithm. Conversely, when the adaptive weight is small, the local search ability of the algorithm is enhanced, and fine search can be performed near the optimal solution, and the convergence speed is accelerated. In one implementation, by initializing the first preset parameter of the firefly algorithm and dynamically adjusting the position of the firefly in the iteration process, the algorithm can effectively explore the solution space. The introduction of brightness and attraction enables the firefly to move towards a better solution, and the setting of the adaptive weight is large at the beginning of the iteration, which enhances the global search ability of the algorithm, so that the firefly can widely explore different regions and avoid falling into a local optimum. As the iteration number increases, the adaptive weight gradually decreases, and the local search ability of the algorithm is enhanced. At this time, the firefly can perform fine search near the optimal solution and quickly converge to the global optimal solution. This mechanism of dynamically balancing global search and local search significantly improves the convergence speed of the algorithm. By continuously updating the position and brightness of the firefly, the final output of the optimal firefly position is the target environmental parameter. This process can accurately optimize the first environmental parameter of the communication cabinet and provide high-quality input for subsequent temperature control, thereby improving the performance of the entire temperature control system.

[0080] In one embodiment, the target control parameter is obtained by optimizing the PID control parameter through the improved sparrow algorithm, including:

[0081] Step one, taking the PID control parameter as a sparrow, initializing the second preset parameter of the improved sparrow algorithm, and initializing the sparrow population position through tent chaos mapping; the second preset parameter includes: population size, maximum iteration number, upper limit and lower limit, dimension;

[0082] Step two, calculate the fitness of each sparrow individual, arrange the sparrow individuals in descending order according to the fitness to obtain a fitness table, screen the sparrow individuals corresponding to the fitness table according to a preset rule to obtain a screening result, take the screening result as a discoverer, and take the remaining sparrows as followers;

[0083] Step three, updating the position of the discoverer by using the butterfly algorithm to optimize the position updating strategy of the discoverer, and updating the position of the discoverer according to the position updating strategy of the discoverer;

[0084] Step four, updating the position of the follower by using the Cauchy distribution and Gaussian distribution to optimize the position updating strategy of the follower, and updating the position of the follower according to the position updating strategy of the follower;

[0085] Step five, updating the global fitness, detecting whether the maximum iteration number is reached, if yes, outputting the optimal sparrow, otherwise, returning to step three.

[0086] In an implementation manner, the second preset parameter, the population size refers to the number of individuals in the sparrow population; the maximum iteration number refers to the maximum number of iterations of the algorithm; the upper and lower limits refer to the value range of each sparrow position variable; and the dimension refers to the dimension number of each sparrow position vector, that is, the number of variables of the optimization problem. In a traditional sparrow algorithm, the random initialization of the population can cause a large number of sparrow individuals to gather together, thereby causing uneven distribution. In order to increase the complexity and diversity of the initial state of the sparrow population, improve the quality of the sparrow individuals, and prevent local optimization caused by premature convergence of the algorithm, a tent chaotic mapping function operator is introduced in the initialization stage of the sparrow population, so that the algorithm can generate different initial solutions in the search space. , z i is the i th population, LS is the number of particles in the chaotic sequence, and rand(0, 1) is a random number with a value between 0 and 1.

[0087] In an implementation, the sparrows in the fitness table are screened according to a preset rule to obtain a screening result according to the fitness size from large to small (in descending order), and the preset rule is that 20%-30% of the individuals are taken as discoverers (the discoverers are usually individuals with higher fitness values in the current population), and the remaining individuals are taken as followers (the remaining individuals are classified as followers, and the fitness values of the followers are relatively low), wherein the discoverers are responsible for extensive exploration of new areas in the search space to find potential optimal solutions; and the followers perform local search around the position of the discoverer to optimize the current found solution. In an implementation, in a traditional discoverer position update formula, as the number of iterations increases, the distribution of the population becomes more uniform, which improves the convergence speed of the algorithm to a certain extent, and as the dimension of the discoverer decreases and gradually converges to zero, the global search ability of the discoverer is reduced; the position update formula of the discoverer is optimized by the global strategy of the butterfly algorithm, the ability of the sparrow algorithm to identify the optimal region and escape the local optimum is enhanced, the convergence speed is improved, the search space is expanded, and the global search and optimization ability of the algorithm is enhanced. , f i is the fitness of the ith sparrow, g * is the optimal solution in the current iteration, and SJ is a random number between 0 and 1, is the position of the ith sparrow in the jth dimension, t represents the current iteration number, q is a random number following a normal distribution, p is a 1xd matrix, each element in the matrix is 1, YJ∈[0,1] represents a warning value, and AQ∈[0.5,1] represents a safety threshold. In an implementation, the Cauchy distribution is a continuous probability distribution that can bring greater disturbance to individuals in the early stages of iteration. The Cauchy mutation operator is introduced in the follower update formula to disturb the positions of individuals in the sparrow population, thereby expanding the search range of the algorithm, enhancing the global search function of the algorithm, and preventing premature convergence. The introduction of the Gaussian operator in the follower update formula helps to provide more targeted exploration in the later stages of iteration, enhances the local search ability of the algorithm, and improves the convergence accuracy. The combination of the two mutation strategies in the follower update process ensures the global search ability of the algorithm and the detailed search ability near the optimal region, for example: , is the position of the ith sparrow in the jth dimension in the t+1th iteration, KS(0,1) is the Cauchy distribution function, GS(0,1) is the Gaussian distribution function, and X best (t) is the global optimal position, and is the meaning of multiplication. In an embodiment, the fitness of the sparrow population individuals is calculated, and the fitness formula includes: wherein, SY is the fitness, wc(t) is the temperature error, e is a natural constant, P(t) is the air conditioning operating energy consumption, and T is the total control process time.

[0088] In an implementation, the smaller the fitness, the better the control performance, and the PID control parameters are obtained through simulation according to the target environment. The energy consumption (usually refrigeration) of the air conditioner during operation can also be obtained through simulation. -T As the time T increases or decreases, the system is more sensitive to early errors, so that the control system can respond to and compensate for errors in the time delay system more quickly, thereby reducing the adjustment time and control amplitude of the system.

[0089] In an implementation, the fitness of the sparrow is calculated by a fitness formula that takes into account both temperature error and air conditioner energy consumption. The smaller the fitness, the better the control performance. This fitness calculation method allows the system to consider both temperature control accuracy and energy optimization during optimization, and the PID control parameters obtained through simulation can respond to and compensate for errors in the time delay system more quickly, thereby reducing the adjustment time and control amplitude of the system and improving the overall performance and energy efficiency of the temperature control system.

[0090] In one embodiment, the temperature control system is updated according to the target control parameters, including:

[0091] The target control parameters are sent to the temperature control system, and the temperature control system receives the target control parameters and controls the temperature according to the target control parameters.

[0092] After a preset period of time, the second environmental parameters in the target communication cabinet are obtained, and it is determined whether the target communication cabinet is in an abnormal overload state. If it is in an abnormal overload state, the update is performed according to the second environmental parameters; otherwise, the update is stopped.

[0093] In an implementation, the optimized target control parameters are sent to the temperature control system, so that the temperature control system can adjust the temperature according to these accurate parameters. The control parameters obtained based on the optimization algorithm can effectively deal with the complex thermal environment in the communication cabinet, ensuring that the temperature in the cabinet is always within the appropriate range, thereby providing protection for the stable operation of communication equipment.

[0094] In an implementation, the second environmental parameter in the target communication cabinet is acquired after a preset time period, and it is determined whether an abnormal overload state exists (including device power consumption increase, device performance decline, such as data transmission delay increase, packet loss rate increase, and throughput decrease). This process enables the temperature control system to monitor the actual operation state of the cabinet in real time, and discover abnormal conditions in a timely manner. When in the abnormal overload state, the system can be updated according to the latest environmental parameter, and dynamically adjust the control strategy, thereby improving the adaptability of the system, and enabling it to better cope with various sudden situations and load changes.

[0095] In an implementation, through the precise control and adaptive updating mechanism, the temperature control system can avoid excessive refrigeration or heating under the premise of ensuring the normal operation of the communication device, thereby reducing the energy consumption of the system. Meanwhile, this optimized control mode reduces the possibility of device failure due to temperature abnormalities, reduces the maintenance cost of the device, prolongs the service life of the device, and improves the operation efficiency and economy of the entire communication system.

[0096] Based on the same inventive concept, the embodiments of the present application also provide a communication cabinet temperature adaptive control system. Referring to Figure 2 , Figure 2 A structural schematic diagram of a communication cabinet temperature adaptive control system provided by the embodiments of the present application includes an environment determination module, a simulation simulation module, and a control updating module:

[0097] The environment determination module is configured to determine a first environmental parameter of a target communication cabinet, and to obtain a target environmental parameter by adaptively optimizing the first environmental parameter through an improved firefly algorithm; the first environmental parameter includes a specific heat capacity of the communication cabinet, a thermal resistance of the communication cabinet, a heat generation rate of the communication cabinet, and a system time delay of the communication cabinet.

[0098] The simulation simulation module is configured to simulate a target environment according to the target environmental parameter, and to obtain a PID control parameter by simulating running of the target environment.

[0099] The control updating module is configured to obtain a target control parameter by optimizing the PID control parameter through an improved sparrow algorithm, and to update the temperature control system according to the target control parameter.

[0100] Based on the communication cabinet temperature adaptive control system provided by the embodiment of the application, the accuracy and anti-interference ability are improved by optimizing the environmental parameters based on the improved firefly algorithm; the PID effect is verified based on the precise parameter simulation environment, dynamic optimization is realized; the control parameters are optimized based on the improved sparrow algorithm, the temperature adaptive control precision and response speed are enhanced, the communication cabinet is ensured to stably and efficiently run under different working conditions, and the equipment reliability is ensured.

[0101] In one embodiment, the environment determination module comprises an algorithm initialization module, a fitness calculation module, a firefly updating module and an iteration updating module.

[0102] The algorithm initialization module is configured to initialize the first preset parameter of the improved firefly algorithm by taking the first environmental parameter as a firefly; the first preset parameter comprises a population size, a maximum iteration number, an upper and lower bound, a dimension, a light intensity absorption coefficient, a maximum attraction and a step factor.

[0103] The fitness calculation module is configured to calculate the fitness by the position of the target firefly in the population, calculate the target distance between the target firefly and each firefly in the population, and calculate the relative fluorescence brightness of the target firefly and each firefly in the population according to the target distance; the fitness represents the maximum fluorescence brightness of the firefly.

[0104] The firefly updating module is configured to calculate the attraction between the target firefly and each firefly according to the target distance, determine a position updating formula according to the iteration number and the attraction, and update the position of the firefly according to the position updating formula and the relative fluorescence brightness.

[0105] The position updating formula is x i (t+1)=ω(t)*x i (t)+β(x j (t)-x i (t))

[0106] The adaptive weight formula is ω(t)=sin(πt / 2t max +π)+1 where t is the current iteration number, t max is the maximum iteration number, ω(t) is the adaptive weight, x i (t+1) is the position of the firefly i after updating at the t+1 iteration number, β() is the attraction calculation formula, x j (t) is the firefly position of the firefly j at the t iteration number, and x i (t) is the firefly position of the firefly i at the t iteration number.

[0107] An iterative updating module is configured to calculate the fitness according to the updated position of the target firefly in the population, and output the optimal firefly if the maximum number of iterations is reached.

[0108] In one embodiment, the control updating module comprises a first execution module, a second execution module, a third execution module, a fourth execution module and a fifth execution module. The first execution module is configured to initialize the second preset parameter of the improved sparrow algorithm with the PID control parameter as the sparrow, and initialize the sparrow population position through the tent chaos mapping. The second preset parameter comprises the population size, the maximum number of iterations, the upper limit and the lower limit, and the dimension.

[0109] The second execution module is configured to calculate the fitness of the sparrow population individuals, arrange the sparrow population individuals in descending order according to the fitness to obtain a fitness table, screen the corresponding sparrow in the fitness table according to a preset rule to obtain a screening result, take the screening result as the discoverer, and take the remaining sparrow as the follower.

[0110] The third execution module is configured to optimize the discoverer position updating strategy through the butterfly algorithm, and update the position of the discoverer according to the discoverer position updating strategy.

[0111] The fourth execution module is configured to optimize the follower position updating strategy through the Cauchy distribution and the Gaussian distribution, and update the follower according to the follower position updating strategy.

[0112] The fifth execution module is configured to update the global fitness, detect whether the maximum number of iterations is reached, output the optimal sparrow if the maximum number of iterations is reached, and return to the third execution module if the maximum number of iterations is not reached. In one embodiment, the second execution module is further configured to: Wherein, SY is the fitness, wc(t) is the temperature error, e is a natural constant, P(t) is the air conditioning working energy consumption, and T is the total time of the control process.

[0113] In one embodiment, the control updating module further comprises a data transmission module and a data judgment module.

[0114] The data transmission module is configured to send the target control parameter to the temperature control system, and the temperature control system receives the target control parameter and performs temperature control according to the target control parameter.

[0115] The data judgment module is configured to obtain the second environmental parameter in the target communication cabinet after a preset time period, and judge whether the target communication cabinet is in an abnormal overload state. If the target communication cabinet is in the abnormal overload state, the target communication cabinet is updated according to the second environmental parameter. Otherwise, the updating is stopped.

[0116] The above has been described in detail one embodiment of the present application, but the content is only the preferred embodiment of the present application, cannot be considered for limiting the scope of the present application. Any equivalent changes and improvements made in the scope of the present application, should still belong to the scope of the present application.

Claims

1. A method for adaptive temperature control of a communication cabinet, characterized in that, The method includes: The first environmental parameters of the target communication cabinet are determined, and the target environmental parameters are obtained by adaptively optimizing the first environmental parameters through an improved firefly algorithm; the first environmental parameters include: specific heat capacity of the communication cabinet, thermal resistance of the communication cabinet, heat generation rate of the communication cabinet, and system time delay of the communication cabinet; The PID control parameters are obtained by simulating the target environment based on the target environment parameters. The target control parameters are obtained by optimizing the PID control parameters through an improved sparrow algorithm, and the temperature control system is updated based on the target control parameters. The target environmental parameters are obtained by adaptively optimizing the first environmental parameters using an improved firefly algorithm, including: The first environmental parameters are used as fireflies to initialize the first preset parameters of the improved firefly algorithm; the first preset parameters include: population size, maximum number of iterations, upper and lower bounds, dimension, light intensity absorption coefficient, maximum attraction and step size factor. Fitness is calculated by determining the position of the target firefly in the population, the target distance between the target firefly and other fireflies in the population is calculated, and the relative fluorescence intensity between the target firefly and other fireflies in the population is calculated based on the target distance; fitness represents the maximum fluorescence intensity of the firefly. The attraction between the target firefly and each other is calculated based on the target distance. A position update formula is determined based on the number of iterations and the attraction. The position of the firefly is updated based on the position update formula and the relative fluorescence brightness. Position update formula: x i (t+1)=ω(t)*x i (t)+β(x j (t)-x i (t)) Adaptive weighting formula: ω(t)=sin(πt / 2t) max +π)+1 Where t is the current iteration number, t max Let ω(t) be the maximum number of iterations, and x be the adaptive weight. i (t+1) represents the position of firefly i after the update at iteration number t+1, β() is the formula for calculating attraction, and x j (t) represents the position of firefly j at iteration number t, x i (t) represents the position of firefly i at iteration number t; the fitness is calculated based on the updated position of the target firefly in the population, and the optimal firefly is output if the maximum number of iterations is reached; the optimal firefly is the target environmental parameter; The target control parameters are obtained by optimizing the PID control parameters through the improved sparrow algorithm, including: Step 1, using the PID control parameters as sparrows, initializing the second preset parameters of the improved sparrow algorithm, and initializing the sparrow population position through tent chaotic mapping; the second preset parameters include: population size, maximum number of iterations, upper and lower limits, and dimension; Step 2: Calculate the fitness of individual sparrows in the population, sort them in descending order according to fitness to obtain a fitness table, and filter the sparrows corresponding to the fitness table according to preset rules to obtain the screening results. The screening results are used as discoverers, and the remaining sparrows are used as followers. Step 3: Optimize the discoverer's location update strategy using the butterfly algorithm, and update the discoverer's location according to the proposed strategy. Step 4: Optimize the follower position update strategy using Cauchy distribution and Gaussian distribution, and update the followers according to the follower position update strategy; Step 5: Update the global fitness and check if the maximum number of iterations has been reached. If it has, output the optimal sparrow; otherwise, return to step 3.

2. The adaptive temperature control method for a communication cabinet according to claim 1, characterized in that, The fitness of individuals in a sparrow population is calculated using the following formula: Where SY is the fitness, wc(t) is the temperature error, e is the natural constant, P(t) is the energy consumption of the air conditioner, and T is the total control time.

3. The adaptive temperature control method for a communication cabinet according to claim 1, characterized in that, The temperature control system is updated based on the target control parameters, including: The target control parameters are sent to the temperature control system, which receives the target control parameters and performs temperature control based on the target control parameters. After a preset time period, the second environmental parameters inside the target communication cabinet are obtained, and it is determined whether the target communication cabinet is in an abnormal overload state. If it is in an abnormal overload state, the second environmental parameters are updated; otherwise, the update is stopped.

4. A temperature adaptive control system for a communication cabinet, characterized in that, The system includes: an environment determination module, a simulation module, and a control update module. The environment determination module is used to determine the first environmental parameters of the target communication cabinet, and to obtain the target environmental parameters by adaptively optimizing the first environmental parameters through an improved firefly algorithm; the first environmental parameters include: specific heat capacity of the communication cabinet, thermal resistance of the communication cabinet, heat generation rate of the communication cabinet, and system time delay of the communication cabinet; The simulation module is used to simulate the target environment based on the target environment parameters to obtain PID control parameters. The control update module is used to optimize the PID control parameters by improving the sparrow algorithm to obtain target control parameters, and update the temperature control system according to the target control parameters; The environment determination module includes: an algorithm initialization module, a fitness calculation module, a firefly update module, and an iterative update module. The algorithm initialization module is used to initialize the first preset parameters of the improved firefly algorithm using the first environmental parameters as fireflies; the first preset parameters include: population size, maximum number of iterations, upper and lower bounds, dimension, light intensity absorption coefficient, maximum attraction force, and step size factor. The fitness calculation module is used to calculate the fitness of the target firefly based on its position in the population, calculate the target distance between the target firefly and other fireflies in the population, and calculate the relative fluorescence intensity between the target firefly and other fireflies in the population based on the target distance; fitness represents the maximum fluorescence intensity of the firefly. The firefly update module is used to calculate the attraction between the target firefly and each firefly based on the target distance, determine the position update formula based on the number of iterations and the attraction, and update the position of the firefly based on the position update formula and the relative fluorescence brightness. Position update formula: x i (t+1)=ω(t)*x i (t)+β(x j (t)-x i (t)) Adaptive weight formula: ω(t)=sin(πt / 2t max +π)+1 Where t is the current iteration number, t max Let ω(t) be the maximum number of iterations, and x be the adaptive weight. i (t+1) represents the position of firefly i after the update at the (t+1)th iteration, β() is the formula for calculating attraction, and x j (t) represents the position of firefly j at iteration number t, x i (t) represents the position of firefly i at iteration number t; the iterative update module is used to calculate the fitness based on the updated position of the target firefly in the population, and outputs the optimal firefly if the maximum number of iterations is reached; the optimal firefly is the target environmental parameter; The control update module includes: a first execution module, a second execution module, a third execution module, a fourth execution module, and a fifth execution module. The first execution module is used to initialize the second preset parameters of the improved sparrow algorithm using the PID control parameters as sparrows, and initialize the sparrow population position through tent chaotic mapping; the second preset parameters include: population size, maximum number of iterations, upper and lower limits, and dimension; the second execution module is used to calculate the fitness of individual sparrows in the population, sort them in descending order according to fitness to obtain a fitness table, filter the sparrows corresponding to the fitness table according to preset rules to obtain the filtering results, use the filtering results as discoverers, and use the remaining sparrows as followers; The third execution module is used to optimize the discoverer's location update strategy using the butterfly algorithm, and update the discoverer's location according to the discoverer's location update strategy. The fourth execution module is used to optimize the follower position update strategy through Cauchy distribution and Gaussian distribution, and update the followers according to the follower position update strategy. The fifth execution module is used to update the global fitness and detect whether the maximum number of iterations has been reached. If it has, the optimal sparrow is output; otherwise, the process returns to the third execution module.

5. The adaptive temperature control system for a communication cabinet according to claim 4, characterized in that, The second execution module is also used for: Where SY is the fitness, wc(t) is the temperature error, e is the natural constant, P(t) is the energy consumption of the air conditioner, and T is the total control time.

6. The adaptive temperature control system for a communication cabinet according to claim 4, characterized in that, The control update module further includes: a data transmission module and a data judgment module. The data transmission module is used to send the target control parameters to the temperature control system, and the temperature control system receives the target control parameters and performs temperature control according to the target control parameters; The data judgment module is used to acquire the second environmental parameters inside the target communication cabinet after a preset time period, and to determine whether the target communication cabinet is in an abnormal overload state. If it is in an abnormal overload state, it updates according to the second environmental parameters; otherwise, it stops updating.

Images