Communication power supply and battery remote core capacity integrated control method and related device based on improved fish school algorithm

Abstract

The present invention provides a method and related device for remote core capacity integrated control of a communication power supply and a storage battery based on an improved fish school algorithm, belonging to the field of core capacity control of communication power supplies and batteries. The method includes obtaining operating status parameters of the communication power supply and the storage battery; using the parameters of the core capacity control strategy as the fish individuals of the improved fish school algorithm, iteratively solving the algorithm to obtain the optimal solution and form a parameter set of the core capacity integrated control strategy; performing remote core capacity integrated control of the communication power supply and the storage battery based on the parameter set; wherein the improved fish school algorithm uses a differential evolution algorithm to perform a mutation operation of the fish school, and at the same time adjusts the field of view of each fish according to the difference between the current optimal solution and the average solution, thereby achieving improvement. By improving the fish school algorithm, the present invention dynamically adjusts the core capacity control strategy parameters, and combines the differential evolution mutation operation with dynamic field of view adjustment, thereby reducing computing resource consumption and achieving remote core capacity control with a response in seconds.

Description

Technical Field

[0001] The present invention belongs to the technical field of core capacity control of communication power supplies and batteries, and particularly relates to a remote core capacity integrated control method and related devices for communication power supplies and batteries based on an improved fish school algorithm. Background Art

[0002] In the communications sector, the stable operation of communications power supplies and batteries is crucial, as their performance directly impacts the reliability and stability of communications systems. With the continuous advancement of communications technology, the demand for core capacity control of communications power supplies and batteries is increasing to ensure they maintain optimal operating conditions in a variety of complex environments.

[0003] Currently, researchers have carried out a series of work on the capacity control of communication power supplies and batteries, and have developed a variety of technical solutions, such as PI / PID-based control methods, capacity verification based on load discharge, deep learning-driven capacity prediction, and remote monitoring and safety protection systems.

[0004] However, existing technologies have numerous drawbacks. Traditional control methods, such as PI control, rely on fixed parameters and are unable to adapt to factors such as battery aging and ambient temperature fluctuations, resulting in poor voltage stability and fluctuations exceeding ±5%. While deep learning models can predict capacity, they require significant computing resources and suffer from poor real-time performance, making them unable to meet the second-level response requirements of remote capacity estimation. Most existing methods rely on regular manual calibration, making fully automated optimization difficult to achieve, resulting in high maintenance costs and low operational efficiency. Furthermore, existing technologies fail to fully account for differences in internal resistance and capacity decay among individual cells, leading to significant deviations in overall capacity estimation results. Summary of the Invention

[0005] In view of this, the present invention provides a communication power supply and battery remote core capacity integrated control method and related devices based on an improved fish school algorithm, aiming to solve one of the many defects in the existing technology.

[0006] In order to achieve the above object, the technical solution provided by the present invention is as follows:

[0007] In a first aspect, the present invention provides a method for controlling a communication power supply and a remote core capacity integrated battery based on an improved fish school algorithm, comprising the following steps:

[0008] Obtain operating status parameters of communication power supply and battery;

[0009] The parameters of the core-capacity control strategy are used as the fish individuals of the improved fish school algorithm. The improved fish school algorithm is iteratively solved based on the operating state parameters until the termination condition is met to obtain the final optimal solution. Based on the optimal solution, the parameter set of the core-capacity integrated control strategy is obtained.

[0010] Integrated control of communication power supply and battery remote core capacity based on parameter set;

[0011] Among them, the fish school algorithm is improved, and the differential evolution algorithm is used to perform the mutation operation of the fish school. At the same time, the field of view of each fish is adjusted according to the gap between the current optimal solution and the average solution, thereby achieving improvement.

[0012] Furthermore, in the fish swarm mutation operation using the differential evolution algorithm, the optimal solution in the swarm obtained by the differential evolution mutation operation is replaced with the worst solution in the swarm of fish obtained by the improved fish swarm algorithm. The differential evolution mutation operation expression is as follows:

[0013]

[0014] Where, New candidate solutions generated by the mutation operation, is the optimal solution for the current population, is the variation factor, and are two different individuals randomly selected from the population, is the number of iterations of the differential evolution algorithm.

[0015] Furthermore, the field of view of each fish is adjusted according to the difference between the current optimal solution and the average solution. The adjustment expression of the field of view is as follows:

[0016]

[0017] Where, is the visual field of the i-th fish after adjustment; is the initial field of view of each fish; For the core capacity control strategy parameter set Next, the current individual fish fitness; is the average fitness of the current fish population, corresponding to the fitness value of the average solution; is the current optimal fitness, corresponding to the fitness value of the optimal solution; Indicates the core capacity control policy parameter set.

[0018] Furthermore, the objective function and constraints of the improved fish swarm algorithm are as follows:

[0019] Objective function:

[0020]

[0021] Where, is the core capacity control strategy parameter set, is the current individual fish fitness, and the optimal solution is defined as the improved fish swarm algorithm when the iteration terminates. Get the minimum value , N is the number of communication power supplies and batteries or the number of subsystems, is the health index of the i-th object, is the running cost of the i-th object, is the maintenance efficiency of the i-th object, 、 、 Respectively represent 、 、 The weight coefficient of

[0022] Constraints:

[0023]

[0024]

[0025]

[0026] Where, and Representing the The minimum and maximum current allowed for each object, and Represents the control strategy parameter set Next The charging and discharging current of each object; and Representing the objects at time The charging and discharging energies under Represents the length of the time period considered.

[0027] Furthermore, the health index is determined based on the health status reliability assessment system, including:

[0028] Determine the values of each indicator in the health status reliability assessment system based on the operating status parameters;

[0029] Determine the weight of each indicator;

[0030] Based on the values and weights of each indicator, the health status score of the communication power supply and battery is obtained, and the health status score is used as the health index.

[0031] Furthermore, the parameters of the core capacity control strategy are used as the fish individuals of the improved fish school algorithm, and the algorithm is iteratively solved based on the operating state parameters, including:

[0032] Filter and normalize the operating status parameters;

[0033] Calculate the health status score based on the normalized operating status parameters and issue an early warning when the health status score falls below the set value;

[0034] The improved fish swarm algorithm is iteratively solved based on the normalized operating state parameters, and the iteration is terminated when the iteration number condition or the fitness change rate condition is met.

[0035] Furthermore, in the remote core-capacity integrated control of the communication power supply and the battery based on the core-capacity integrated control strategy, the parameter set of the core-capacity integrated control strategy is converted into a Modbus RTU protocol instruction and sent to the power controller through the RS485 bus.

[0036] In a second aspect, the present invention provides a communication power supply and battery remote core capacity integrated control device based on an improved fish school algorithm, comprising:

[0037] Parameter acquisition module, used to obtain the operating status parameters of the communication power supply and battery;

[0038] The strategy solving module is used to use the parameters of the core-capacity control strategy as the fish individuals of the improved fish school algorithm, iteratively solve the improved fish school algorithm based on the operating state parameters until the termination condition is met to obtain the final optimal solution, and then obtain the parameter set of the core-capacity integrated control strategy based on the optimal solution;

[0039] Control module, used for integrated control of communication power supply and battery remote capacity based on parameter set;

[0040] Among them, the fish school algorithm is improved, and the differential evolution algorithm is used to perform the mutation operation of the fish school. At the same time, the field of view of each fish is adjusted according to the gap between the current optimal solution and the average solution, thereby achieving improvement.

[0041] In a third aspect, the present invention provides a computer device, comprising a processor and a memory:

[0042] The memory is used to store computer programs and send instructions of the computer programs to the processor;

[0043] The processor executes a communication power supply and battery remote core capacity integrated control method based on an improved fish school algorithm according to the instructions of the computer program as described in the first aspect.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a communication power supply and battery remote core capacity integrated control method based on an improved fish school algorithm as in the first aspect is implemented.

[0045] In summary, the present invention provides a method for remote core capacity integrated control of a communication power supply and a storage battery based on an improved fish school algorithm, including obtaining the operating state parameters of the communication power supply and the storage battery; using the parameters of the core capacity control strategy as the fish individuals of the improved fish school algorithm, iteratively solving the algorithm based on the operating state parameters until the termination condition is met to obtain the final optimal solution, and obtaining the parameter set of the core capacity integrated control strategy based on the optimal solution; performing remote core capacity integrated control of the communication power supply and the storage battery based on the parameter set; wherein, the improved fish school algorithm utilizes the differential evolution algorithm to perform the mutation operation of the fish school, and at the same time adjusts the field of view of each fish according to the gap between the current optimal solution and the average solution, thereby achieving improvement. The present invention dynamically adjusts the core capacity control strategy parameters by improving the fish school algorithm, combines the differential evolution mutation operation with the dynamic field of view adjustment, and realizes remote core capacity control with a response of seconds while reducing the consumption of computing resources. The fully automated optimization process greatly reduces maintenance costs and improves operation and maintenance efficiency, accurately considers the differences between single cells, and makes the overall core capacity results more accurate.

[0046] The present invention also provides a communication power supply and battery remote core capacity integrated control device, computer equipment and computer-readable storage medium based on the improved fish school algorithm, which has similar effects to the above method when implemented and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 A flowchart of a method for integrated control of communication power supply and battery remote core capacity based on an improved fish school algorithm provided by an embodiment of the present invention;

[0049] Figure 2 A diagram comparing battery voltage stability under different core capacity control methods provided by an embodiment of the present invention;

[0050] Figure 3 A block diagram of a communication power supply and battery remote core capacity integrated control device based on an improved fish school algorithm provided by an embodiment of the present invention;

[0051] Figure 4 A block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purposes, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0053] The following first introduces some technical terms involved in the present invention.

[0054] (1) Remote capacity verification: Capacity verification, also known as "capacity verification," refers to determining whether the actual capacity of a battery pack meets design requirements through charge and discharge tests. Remote capacity verification uses remote control technology to complete battery capacity testing without manual on-site operation. The core of remote capacity verification is to monitor parameters such as voltage, current, and temperature in real time and dynamically adjust the control strategy.

[0055] (2) Differential Evolution (DE): A global optimization algorithm based on swarm intelligence. It generates mutant individuals through differential vectors between individuals and updates the population through crossover and selection operations. It has the characteristics of fast convergence speed and strong robustness.

[0056] (3) Fish Swarm Algorithm (FSA): An intelligent optimization algorithm that simulates the behaviors of fish schools such as foraging, clustering, and chasing. It updates the individual positions through parameters such as field of view and moving step length to achieve global optimization.

[0057] (4) Modbus RTU protocol: Modbus is a serial communication protocol. The RTU (Remote Terminal Unit) mode transmits information in binary data format. It is often used for communication between industrial field equipment (such as power controllers) and has the characteristics of simple protocol and good real-time performance.

[0058] (5) RS485 bus: A serial communication physical interface standard that supports multi-point differential transmission, has a long communication distance (up to 1200 meters), and has strong anti-interference capabilities. It is widely used in equipment interconnection in the field of industrial automation.

[0059] (6) Analytic Hierarchy Process (AHP): A multi-criteria decision analysis method that decomposes complex problems into a hierarchical structure and uses a pairwise comparison matrix to determine the weight of each indicator. Figure 1 The embodiment of the present invention provides a communication power supply and battery remote core capacity integrated control method based on an improved fish school algorithm, comprising the following steps:

[0060] S1: Obtain the operating status parameters of the communication power supply and battery.

[0061] It should be noted that the operating status parameters acquired in this step are used in the subsequent improved fish-school algorithm solution and may include parameters such as current, voltage, and temperature. In specific implementations, for example, data acquisition and processing can be achieved through the collaboration of multiple high-precision sensors and an embedded control unit. Voltage sensors with an accuracy of ±0.05% and a measurement range of 0-60V are deployed at the power output and battery terminals to monitor voltage stability and cell status in real time. Hall-effect current sensors with a range of ±30A and a sampling frequency of 1kHz are non-invasively installed in the charging and discharging circuits to capture transient current changes. A digital temperature probe with an accuracy of ±0.5°C and a measurement range of -20°C to 80°C is attached to the battery housing to monitor ambient temperature. These sensors comprehensively collect data from various physical dimensions, including electrical and thermal. The embedded control unit integrates a high-performance processor, large-capacity storage, and a variety of communication interfaces. It performs pre-processing on the raw data, including filtering and normalization, and uploads the data to the monitoring center in real time via an RS485 bus or wireless module, where it receives control commands. This process is achieved through multi-dimensional precise monitoring, non-invasive deployment, high-frequency real-time acquisition and edge computing.

[0062] S2: Using the parameters of the core-capacity control strategy as the individual fish in the improved fish-swarm algorithm, the improved fish-swarm algorithm is iteratively solved based on the operating state parameters until the termination condition is met and the final optimal solution is obtained. Based on the optimal solution, the parameter set of the core-capacity integrated control strategy is obtained. The improved fish-swarm algorithm uses a differential evolution algorithm to perform fish mutation operations. At the same time, the field of view of each fish is adjusted according to the difference between the current optimal solution and the average solution, thereby achieving improvement.

[0063] It should be noted that the improved fish swarm algorithm is a hybrid optimization algorithm that combines differential evolution (DE) mutation operations with dynamic field of view adjustment. Each solution vector in the algorithm corresponds to a set of core-capacity control strategy parameters (such as charging current threshold and discharge end voltage). The algorithm encodes the core-capacity control strategy parameters into individual fish swarms and searches for the optimal solution in parameter space by simulating their foraging, flocking, and chasing behaviors. Its core improvement lies in incorporating the mutation mechanism of the differential evolution algorithm, generating mutant individuals through "individual linear combination" to enhance global search capabilities. A dynamic field of view adjustment strategy is also designed to adaptively adjust the search granularity based on the gap between the current optimal solution and the average solution. During the algorithm iteration process, a fitness function constructed based on the real-time operating status parameters of the communication power supply and battery guides the fish swarm to converge towards the optimal parameter region, ultimately outputting the optimal parameter set for core-capacity integrated control, achieving intelligent and efficient control of the power supply and battery.

[0064] In this step, the algorithm first initializes the initial fish swarm and generates new individuals using differential evolution. By replacing the worst solution in the swarm with the optimal solution, the algorithm enhances population diversity and global search capabilities. Simultaneously, the algorithm dynamically adjusts the field of view of each fish based on the gap between the current optimal solution and the average solution. When the gap is large, the field of view is narrowed to focus on a localized, detailed search, while when the gap is small, the field of view is expanded to explore the entire world. Together, these two approaches rapidly approach the optimal solution. When termination conditions, such as an upper limit on the number of iterations or a fitness change rate below a threshold, are met, the final optimal solution is obtained, and the parameter set for the core-capacity integrated control strategy is determined accordingly.

[0065] S3: Remote integrated control of communication power supply and battery capacity based on parameter set;

[0066] It should be noted that core-capacity integrated control means that the communication power supply and battery are regarded as a whole system, and the charging, discharging, maintenance and other processes are coordinated and optimized.

[0067] This embodiment provides a method for remote integrated capacity control of communication power supplies and batteries based on an improved fish-swarm algorithm. This method dynamically adjusts capacity control strategy parameters through the improved fish-swarm algorithm, integrating differential evolution mutation operations with a dynamic field of view adjustment mechanism. This method reduces computing resource consumption while achieving remote capacity control with a response time of seconds. The fully automated optimization process significantly reduces maintenance costs and improves operation and maintenance efficiency. Accurately considering the differences between individual batteries makes the overall capacity results more accurate, breaking through the limitations of traditional methods in efficiency, cost, and accuracy.

[0068] Based on the above embodiment, the method can be implemented by dividing it into four layers: data acquisition layer, evaluation layer, optimization layer, and control layer. The data acquisition layer is responsible for collecting and processing communication power supply and battery data. The evaluation layer constructs a health status scoring model to implement health status scoring for the communication power supply and battery. The optimization layer uses an improved fish school algorithm to solve the optimal control strategy, and ultimately the control layer issues parameters. The following describes the design of these layers in conjunction with some other embodiments of the present invention.

[0069] In the prior art, traditional fish swarm algorithms are prone to falling into local optimal solutions when performing mutation operations, making it difficult to fully search for the optimal control parameters, resulting in poor algorithm optimization results. Therefore, in one embodiment of the present invention, a differential evolution mutation operation design is proposed. When performing a fish swarm mutation operation using a differential evolution algorithm, the optimal solution in the population obtained by the differential evolution mutation operation is replaced with the worst solution in the fish swarm of the improved fish swarm algorithm. The differential evolution mutation operation expression is as follows:

[0070]

[0071] Where, New candidate solutions generated by the mutation operation, is the optimal solution for the current population, is the variation factor, and are two different individuals randomly selected from the population, is the number of iterations of the differential evolution algorithm. The system randomly generates an initial fish swarm, where each fish represents a potential solution, i.e., a set of control strategy parameters. A differential evolution population is also initialized, where each individual also represents a solution, which is used for subsequent information exchange with the fish swarm. For each individual in the differential evolution population, a new candidate solution is generated through mutation. The optimal solution in the differential evolution population is periodically replaced with the worst solution in the fish swarm to achieve information exchange. The above steps are repeated until the preset termination condition is met. The optimal control strategy parameter set found by the algorithm can be used to generate specific control instructions, such as adjusting the charging current, setting the discharge threshold, and planning maintenance cycles.

[0072] In this embodiment, the mutation operation described above generates new candidate solutions, enriching the diversity of solutions. The optimal solution in the population obtained through the differential evolution mutation operation is replaced with the worst solution in the fish swarm of the improved fish swarm algorithm. This information exchange mechanism overcomes the limitations of traditional algorithms, combining the powerful global search capabilities of the differential evolution algorithm with the local optimization characteristics of the fish swarm algorithm, thus resolving the problem that traditional algorithms are prone to falling into local optimality.

[0073] In existing technologies for communication power supply and battery core capacity control, traditional algorithms often have a fixed search range, making it difficult to quickly adapt to complex and changing battery operating environments. This results in slow algorithm convergence and a tendency to fall into local optimal solutions. Therefore, in one embodiment of the present invention, a dynamic field of view adjustment mechanism is proposed. This mechanism adjusts the field of view of each fish based on the difference between the current optimal solution and the average solution. The field of view adjustment expression is as follows:

[0074]

[0075] Where, is the field of view of the i-th fish after adjustment, is the initial field of view of each fish, is the current individual fitness of the fish, is the average fitness of the current fish population, corresponding to the fitness value of the average solution, is the current optimal fitness, corresponding to the fitness value of the optimal solution; Indicates the core capacity control policy parameter set.

[0076] In this embodiment, the algorithm dynamically scales the fish school's search range based on the quality of the current solution. In the early stages of the algorithm, the quality of solutions varies. A larger field of view allows for rapid global search, exploring more potential solutions. As iterations progress, when a superior solution emerges, the field of view is narrowed, focusing on local optimization to accurately approach the optimal solution. Compared to existing technologies, this embodiment significantly improves algorithm convergence speed by leveraging a dynamic field of view adjustment strategy. Experiments show that the improved fish school algorithm converges to the optimal solution within 500 iterations, a convergence speed improvement of over 30% compared to traditional algorithms. It also achieves precise optimization of control parameters such as charging current and discharge threshold, reducing the standard deviation of charging voltage from 0.15V in traditional methods to 0.03V, effectively improving the accuracy and efficiency of communication power supply and battery core capacity control.

[0077] In one embodiment of the present invention, the objective function and constraints of the improved fish swarm algorithm are as follows:

[0078] First, based on the health status assessment results, the objective function is constructed as follows:

[0079]

[0080] Where, It is the parameter set of core capacity control strategy, such as charging strategy, discharge threshold, maintenance cycle, etc. is the current individual fish fitness, and the optimal solution is defined as the improved fish swarm algorithm when the iteration terminates. Get the minimum value , N is the number of communication power supplies and batteries or the number of subsystems, is the health index of the i-th object, is the running cost of the i-th object, is the maintenance efficiency of the i-th object, 、 、 Respectively represent 、 、 The weight coefficient of

[0081] Constraints:

[0082]

[0083]

[0084] Where, and Representing the The minimum and maximum current allowed for each object, and Represents the control strategy parameter set Next The charging and discharging current of each object;

[0085]

[0086] Where, and Representing the objects at time The charging and discharging energies under Represents the length of the time period considered.

[0087] This embodiment constructs a multi-objective optimization model, integrating three core metrics: reliability, cost, and maintenance efficiency, into a unified objective function. The parameter set includes key control variables such as charging current and discharge threshold. The health index can be calculated using the Analytic Hierarchy Process (AHP). Operating costs include energy consumption and maintenance costs, while maintenance efficiency quantifies the impact of maintenance activities on system performance. Adjustable weighting factors (reliability), (cost), and (maintenance efficiency) allow the system to dynamically prioritize different objectives based on actual needs. Regarding constraints, current safety constraints ensure that charging and discharging currents remain within the device's safety range, preventing overcharge and over-discharge. Energy balance constraints ensure that the system's total charge and discharge capacity matches over a long timescale, maintaining energy conservation. This embodiment offers significant advantages over existing technologies. Traditional methods typically focus on a single objective (such as charging speed or capacity accuracy). This embodiment, through multi-objective collaborative optimization, achieves comprehensive improvements in control accuracy (voltage fluctuation ≤ ±1%), real-time response (command generation time ≤ 15 seconds), and operation and maintenance costs (reducing manual intervention by over 30%). Experimental data show that the model can control the capacity calibration error within 0.1%, and the charging voltage standard deviation is reduced from 0.15V of the traditional method to 0.03V, fully verifying its effectiveness.

[0088] In one embodiment of the present invention, the health index is determined based on a health status reliability assessment system, including:

[0089] Step 1: Determine the values of each indicator in the health status reliability assessment system based on the operating status parameters.

[0090] It should be noted that, considering that the health status of the communication power supply and the battery is mainly affected by multiple factors such as the charge and discharge rate, voltage, and ambient temperature, this embodiment takes the reliability of the health status of the communication power supply and the battery as the target layer, and the evaluation index system constructed thereby is shown in Table 1.

[0091] Table 1 Communication power supply and battery health status reliability evaluation system

[0092]

[0093] In the above evaluation system, the values of some indicators can be directly obtained by calling the monitoring report of real-time operation data, while some indicators need to be calculated specifically. Refers to the battery charging and discharging current and battery rated capacity The specific calculation formula is as follows:

[0094]

[0095] Depth of discharge It can reflect the battery usage and life loss, assuming Represents the amount of electricity released by the battery during discharge. The specific calculation formula is as follows:

[0096]

[0097] in, Represents the total battery capacity.

[0098] In the health and reliability assessment system for telecom power supplies and batteries, intuitive indicators such as charge current, discharge current, capacity, electromotive force, terminal voltage, and open-circuit voltage directly demonstrate the current operating effectiveness and performance of the power supply and battery. A decrease in these indicators indicates a decline in key performance during real-time operation, a direct sign of reduced health. Influencing factor indicators, such as charge / discharge rate, depth of discharge, and ambient temperature, while not directly indicative of performance, nonetheless influence the physical and chemical processes within the device. Changes in charge / discharge rate reflect the rate and stability of battery chemical reactions; depth of discharge reflects battery usage and lifespan loss; and abnormal ambient temperature disrupts the battery's internal reaction balance and material properties. Therefore, a decrease in these influencing factor indicators indicates deteriorating equipment operating conditions, which will inevitably lead to long-term performance degradation. Therefore, a decrease in both intuitive and influencing factor indicators indicates a decline in the health of the telecom power supply and battery.

[0099] Step 2: Determine the weight of each indicator.

[0100] It should be noted that, based on the above selected evaluation indicators, this embodiment calculates the indicator weights to achieve a quantitative evaluation of the health status of the communication power supply and battery. Representative in Table 1 The specific value of the normalized indicator is Represents the total amount after normalization of the indicator, then the indicator normalization and weight The calculation formula is as follows:

[0101]

[0102]

[0103] Where, Represents the actual value of the i-th indicator. The arctan function can be used to map the original indicator values of different dimensions and magnitudes to the (0,1) interval, eliminating the impact of dimension and magnitude differences and making different indicators comparable on the same scale. After normalization, the weight is calculated. The original difference interference has been eliminated, which can more reasonably reflect the quantitative importance of each indicator to the health status assessment, make the weight calculation more in line with actual needs, and ensure the accuracy of the quantitative assessment of the health status of communication power batteries.

[0104] Step 3: Based on the values and weights of each indicator, the health status score of the communication power supply and battery is obtained, and the health status score is used as the health index.

[0105] It should be noted that based on the above indicator weight calculation results, the communication power supply and battery health status scores can be obtained The expression is as follows:

[0106]

[0107] By combining the measured or calculated values of each evaluation indicator and the corresponding weight of the indicator, the above formula can be used to calculate the health status score of the communication power supply and battery, thereby realizing status monitoring and evaluation.

[0108] This embodiment utilizes a multi-metric fusion assessment to overcome the limitations of traditional single-parameter monitoring. Weight calibration is employed to adapt to different battery types and application scenarios. A real-time scoring mechanism supports instantaneous status updates, meeting the responsiveness requirements of remote core capacity. Experimental data shows that this assessment model achieves a scoring error of ≤2%, a significant improvement over traditional methods (error ≥5%), effectively addressing the inadequacy of existing technologies in addressing battery performance variations.

[0109] In one embodiment of the present invention, the parameters of the core capacity control strategy are used as fish individuals in the improved fish school algorithm, and the algorithm is iteratively solved based on the operating state parameters, including:

[0110] Step 1: Filter and normalize the operating status parameters.

[0111] For example, filtering (Kalman filtering) and normalizing (Min-Max scaling) the raw sensor data.

[0112] Step 2: Calculate the health status score based on the normalized operating status parameters and issue an early warning when the health status score is lower than the set value.

[0113] In specific implementation, the score can be updated every 5 minutes, and a warning will be triggered if the score is lower than 80 points.

[0114] Step 3: Iterate and solve the improved fish swarm algorithm based on the normalized operating state parameters. The iteration terminates when the number of iterations or the fitness change rate condition is met.

[0115] Fifty "artificial fish" were randomly generated, each representing a set of control parameters θ (including charging current, discharge threshold, etc.). During algorithm execution, differential evolution and dynamic field of view adjustment were combined to establish an information exchange mechanism. Every 20 iterations, the optimal solution from the differential evolution population replaced the worst solution in the fish population to avoid local optima. The algorithm terminated after 1000 iterations or when the fitness change rate was <1e-5, and the optimal parameter set was output. The fitness change rate refers to the difference between the fitness value at a given moment and the fitness value at the previous moment, or the ratio of the fitness value to the previous moment, reflecting the relative degree of fitness change over time or during iterations.

[0116] In one embodiment of the present invention, in remote core-capacity integrated control of a communication power supply and a battery based on a core-capacity integrated control strategy, a parameter set of the core-capacity integrated control strategy is converted into a Modbus RTU protocol instruction and sent to a power controller via an RS485 bus.

[0117] In practice, data transmission uses the MQTT protocol, with the topic format being " / battery / {ID} / command." Data packets contain fields such as timestamp, voltage, current, and temperature. Control commands are transmitted encrypted (AES-256) to ensure remote operation security.

[0118] In addition, exception handling mechanisms can be designed, including overvoltage / undervoltage protection and temperature compensation. Overvoltage / undervoltage protection immediately shuts off the charge and discharge circuit when the voltage exceeds ±10% of the rated value. Temperature compensation dynamically adjusts the charging current based on the ambient temperature (the current decreases by 0.5A for every 1°C increase in temperature).

[0119] In this embodiment, the parameter set determined by the core-capacity integrated control strategy (covering key control parameters such as charging current and discharge threshold) is subjected to protocol conversion processing. Specifically, with the help of the system's control layer function, these parameter sets are converted into Modbus RTU protocol instructions. This protocol, with its high versatility and strong stability, can support the compatibility and adaptation of power supply equipment from multiple brands. Subsequently, the instructions are sent to the power controller quickly and reliably through the RS485 bus as the transmission medium. This embodiment not only improves the compatibility and efficiency of instruction transmission, but also ensures that the response time of emergency instructions (such as overvoltage protection) is ≤1 second, effectively ensuring the safety and stability of system operation, and greatly improving the reliability and effectiveness of remote core-capacity integrated control of communication power supply and battery.

[0120] The following is an example to experimentally verify the integrated control method of communication power supply and battery remote core capacity based on the improved fish school algorithm proposed in the present invention.

[0121] In this example, a comparative experiment was conducted. In addition to the algorithm presented in this paper, two conventional core-capacity integrated control methods were selected as control groups: a core-capacity integrated control method based on deep learning and a core-capacity control method based on PID control. By remotely controlling the core capacity of the same battery pack using each of the three control methods, the actual control effects of the different methods were compared.

[0122] This experiment established an experimental platform that included a communications power supply, multiple battery packs, a remote monitoring and control system, and data acquisition and recording equipment. All equipment was ensured to comply with industry standards and possess remote communication capabilities. PSCAD / EMTDC was used to construct a highly simulated experimental scenario, emulating various complex conditions found in actual operating environments, such as grid fluctuations and sudden load changes.

[0123] We selected multiple representative battery groups as experimental subjects, ensuring they had similar initial conditions and performance parameters. We randomly divided the subjects into three groups, each employing a different control method for remote nuclear capacity control. We ensured that each group was as consistent as possible in terms of number, type, and initial conditions to minimize experimental error. Specific performance parameters for the experimental subjects are shown in Table 2.

[0124] Table 2 Overview of battery pack parameters

[0125]

[0126] The experimental objects selected for this example have different performance parameters such as initial capacity, rated voltage, internal resistance, cycle life (number of cycles at 80% depth of discharge), self-discharge rate, and initial charge efficiency for each battery group. However, the two batteries in the same group were kept as similar as possible to simulate the variables that need to be controlled in actual experiments.

[0127] During the experimental preparation phase, all experimental equipment was calibrated to ensure the accuracy of the measurement data. The initial capacity, voltage, current, and other parameters of each battery group were recorded. Three control strategies based on the optimized fish school algorithm, deep learning, and PID control were deployed to the corresponding experimental groups. When using the method presented in this paper to remotely control the core capacity of the experimental subjects, the health status of the batteries must first be assessed using the constructed evaluation system. The health status assessment result of the experimental sample obtained in this example (using battery A1 as an example) was a reliability of 0.75, which is a reliability level of Level 2.

[0128] The proposed method can evaluate operational status based on different experimental samples and operational data. Based on the evaluation results, this example uses a modified fish school algorithm to solve the control strategy. To achieve this, the algorithm parameters need to be configured. The specific configuration results are shown in Table 3.

[0129] Table 3 Parameter configuration of improved fish swarm algorithm

[0130]

[0131] The improved fish swarm algorithm was configured using the aforementioned parameters. Combined with the individual fish swarm optimization method, the optimal control strategy parameter combination was found. This combination was used as a control instruction to initiate an experiment in simulation software, simulating a real-world operating environment and remotely controlling the battery's capacity. Key data during the experiment was recorded in real time, including the battery's voltage, current, capacity change, and control signal output under the three capacity control methods, enabling experimental comparison.

[0132] In this example, the results of the battery remote capacity control are shown in Table 4.

[0133] Table 4 Remote nuclear capacity control results of different experimental samples using the method of the present invention

[0134]

[0135] The above experimental results clearly show that under the control method of the present invention, the calibrated capacities of the eight different battery packs are relatively close to the initial capacities. At the same time, the control method can quickly respond and adjust the control strategy to achieve the expected calibration effect. To improve the reliability of the experimental results, the experiment uses the battery voltage stability under different core capacity control strategies as a comparison indicator to measure the core capacity control accuracy. The specific experimental results are as follows: Figure 2 shown.

[0136] pass Figure 2 It can be clearly seen that under the control method of the present invention, the voltage stability of the battery is higher than that of conventional method A (core-capacity integrated control method based on deep learning) and conventional method B (core-capacity control method based on PID control). This proves that the core-capacity control method proposed in the present invention can ensure that the battery can maintain a stable voltage output under various operating conditions and has high core-capacity control accuracy.

[0137] According to experimental measurements, compared with the prior art, the present invention has the following advantages:

[0138] (1) Improved control accuracy:

[0139] Experimental data shows that the standard deviation of charging voltage is reduced from 0.15V of the traditional method to 0.03V, and the fluctuation range is reduced by 80%.

[0140] Capacity control was performed on 8 groups of batteries (capacity 100-400Ah). After calibration, the deviation between the capacity and the nominal value was <0.1% (when the rated capacity was 200Ah, the error was ≤0.2Ah).

[0141] The standard deviation of the voltage during the charge and discharge process is 0.032V (rated 12V system); the standard deviation of PID control is 0.12V; and the standard deviation of deep learning is 0.09V.

[0142] (2) Response speed optimization:

[0143] The control command generation time is ≤12 seconds (the traditional PID method takes more than 25 seconds).

[0144] The algorithm convergence time is shortened to within 500 iterations (the traditional fish school algorithm requires 800 times).

[0145] (3) Reduced operation and maintenance costs:

[0146] The automated core capacity strategy reduces the frequency of manual inspections by 50%, and the annual operation and maintenance costs drop by approximately 120,000 yuan (calculated based on 100 battery sets).

[0147] Energy efficiency is increased to 92% (compared to 85% for traditional methods).

[0148] (4) Enhanced adaptability:

[0149] It supports a wide operating temperature range of -20°C to 60°C, and voltage stability is not affected by temperature fluctuations.

[0150] It can be expanded to various battery types such as lead-acid and lithium-ion, with a 100% compatibility verification pass rate.

[0151] In addition, in the solution of the present invention, the particle swarm algorithm (PSO) can be used to replace the improved fish school algorithm, but the inertia weight and learning factor need to be adjusted. Experiments show that the PSO convergence speed is 15% slower; current detection can be replaced by a shunt + high-precision ADC solution, which reduces the cost by 20%, but the accuracy drops from ±0.05% to ±1%; in areas with insufficient 4G signal coverage, it can be switched to a LoRaWAN communication module, and the transmission distance can be increased to 10km, but the data rate is reduced to 50kbps.

[0152] Based on the same inventive concept, the embodiments of the present application also provide a communication power supply and battery remote core capacity integrated control device based on an improved fish school algorithm for implementing the above-mentioned communication power supply and battery remote core capacity integrated control method based on an improved fish school algorithm. The implementation solution provided by this device is similar to the implementation solution described in the above-mentioned method. Therefore, the specific limitations of the embodiment of the communication power supply and battery remote core capacity integrated control device based on an improved fish school algorithm provided below can be found in the limitations of the communication power supply and battery remote core capacity integrated control method based on an improved fish school algorithm above, and will not be repeated here.

[0153] See also Figure 3 The embodiment of the present invention further provides a communication power supply and battery remote core capacity integrated control device based on an improved fish school algorithm, comprising:

[0154] Parameter acquisition module, used to obtain the operating status parameters of the communication power supply and battery in the improved fish school algorithm;

[0155] The strategy solving module is used to use the parameters of the core-capacity control strategy as the fish individuals of the improved fish school algorithm, iteratively solve the improved fish school algorithm based on the operating state parameters until the termination condition is met to obtain the final optimal solution, and then obtain the parameter set of the core-capacity integrated control strategy based on the optimal solution;

[0156] Control module, used for integrated control of communication power supply and battery remote capacity based on parameter set;

[0157] Among them, the fish school algorithm is improved, and the differential evolution algorithm is used to perform the mutation operation of the fish school. At the same time, the field of view of each fish is adjusted according to the gap between the current optimal solution and the average solution, thereby achieving improvement.

[0158] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0159] Reference Figure 4 An embodiment of the present invention further provides a computer device, comprising: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, it implements the communication power supply and battery remote core capacity integrated control method based on the improved fish school algorithm as described in any one of the above methods.

[0160] The computer device may be a desktop computer, notebook computer, PDA, cloud server or other computing device. The computer device may include, but is not limited to, a processor and a memory. It will be understood by those skilled in the art that Figure 4 The computer device is merely an example and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, etc.

[0161] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0162] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard drive or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped with the computer device. Furthermore, the memory may include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is about to be output.

[0163] An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for remote integrated control of a communication power supply and a battery based on an improved fish school algorithm as described in any one of the above methods is implemented.

[0164] In this embodiment, if the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the process steps in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, removable hard drives, magnetic disks, or optical disks. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0165] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0166] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0167] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0168] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A communication power supply and battery remote core capacity integrated control method based on an improved fish school algorithm is characterized in that: The steps include: Obtain operating status parameters of communication power supply and battery; The parameters of the core-capacity control strategy are used as fish individuals of the improved fish school algorithm, the improved fish school algorithm is iteratively solved based on the operating state parameters until a termination condition is met to obtain a final optimal solution, and a parameter set of the core-capacity integrated control strategy is obtained based on the optimal solution; Performing integrated control of communication power supply and battery remote core capacity based on the parameter set; The improved fish school algorithm utilizes a differential evolution algorithm to perform a mutation operation on the fish school, and adjusts the field of view of each fish according to the gap between the current optimal solution and the average solution, thereby achieving improvement.

2. The communication power supply and battery remote core capacity integrated control method based on the improved fish school algorithm according to claim 1 is characterized in that: In the fish swarm mutation operation using the differential evolution algorithm, the optimal solution in the swarm obtained by the differential evolution mutation operation is replaced with the worst solution in the swarm of fish obtained by the improved fish swarm algorithm. The differential evolution mutation operation expression is as follows: Where, New candidate solutions generated by the mutation operation, is the optimal solution for the current population, is the variation factor, and are two different individuals randomly selected from the population, is the number of iterations of the differential evolution algorithm.

3. The communication power supply and battery remote core capacity integrated control method based on the improved fish school algorithm according to claim 1 is characterized in that: The field of view of each fish is adjusted according to the difference between the current optimal solution and the average solution. The adjustment expression of the field of view is as follows: Where, is the visual field of the i-th fish after adjustment; is the initial field of view of each fish; For the core capacity control strategy parameter set Next, the current individual fish fitness; is the average fitness of the current fish population, corresponding to the fitness value of the average solution; is the current optimal fitness, corresponding to the fitness value of the optimal solution; Indicates the core capacity control policy parameter set.

4. The communication power supply and battery remote core capacity integrated control method based on the improved fish school algorithm according to claim 1 is characterized in that: The objective function and constraints of the improved fish swarm algorithm are as follows: Objective function: Where, is the core capacity control strategy parameter set, is the current individual fish fitness, and the optimal solution is defined as the solution when the improved fish swarm algorithm is terminated. Get the minimum value , N is the number of communication power supplies and batteries or the number of subsystems, is the health index of the i-th object, is the running cost of the i-th object, is the maintenance efficiency of the i-th object, 、 、 Respectively represent 、 、 The weight coefficient of Constraints: Where, and Representing the The minimum and maximum current allowed for each object, and Represents the control strategy parameter set Next The charging and discharging current of each object; and Representing the objects at time The charging and discharging energies under Represents the length of the time period considered.

5. The communication power supply and battery remote core capacity integrated control method based on the improved fish school algorithm according to claim 4 is characterized in that: The health index is determined based on a health status reliability assessment system, including: Determining the values of the indicators in the health status reliability assessment system based on the operating status parameters; Determine the weight of each indicator; Based on the values and weights of the indicators, health status scores of the communication power supply and the battery are obtained, and the health status scores are used as the health index.

6. The communication power supply and battery remote core capacity integrated control method based on the improved fish school algorithm according to claim 5 is characterized in that: The parameters of the core capacity control strategy are used as the fish individuals of the improved fish school algorithm, and the algorithm is iteratively solved based on the operating state parameters, including: performing filtering and normalization processing on the operating state parameters; Calculating the health status score based on the normalized operating status parameters, and issuing an early warning when the health status score is lower than a set value; The improved fish swarm algorithm is iteratively solved based on the normalized operating state parameters, and the iteration is terminated when an iteration number condition or a fitness change rate condition is met.

7. The communication power supply and battery remote core capacity integrated control method based on the improved fish school algorithm according to claim 1 is characterized in that: In the remote core-capacity integrated control of the communication power supply and the battery based on the core-capacity integrated control strategy, the parameter set of the core-capacity integrated control strategy is converted into Modbus RTU protocol instructions and sent to the power controller via the RS485 bus.

8. A communication power supply and battery remote core capacity integrated control device based on an improved fish school algorithm, characterized in that: include: Parameter acquisition module, used to obtain the operating status parameters of the communication power supply and battery; a strategy solving module, configured to use the parameters of the core-capacity control strategy as fish individuals of the improved fish school algorithm, iteratively solve the improved fish school algorithm based on the operating state parameters, until a termination condition is met to obtain a final optimal solution, and obtain a parameter set of the core-capacity integrated control strategy based on the optimal solution; A control module for performing integrated control of the communication power supply and the remote core capacity of the battery based on the parameter set; The improved fish school algorithm utilizes a differential evolution algorithm to perform a mutation operation on the fish school, and adjusts the field of view of each fish according to the gap between the current optimal solution and the average solution, thereby achieving improvement.

9. A computer device, characterized in that: The device includes a processor and a memory: The memory is used to store the computer program and send instructions of the computer program to the processor; The processor executes the communication power supply and battery remote core capacity integrated control method based on the improved fish school algorithm according to any one of claims 1 to 7 according to the instructions of the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the communication power supply and battery remote core capacity integrated control method based on the improved fish school algorithm according to any one of claims 1 to 7.

Images