Script-based multi-system wireless communication system function test method

Abstract

The invention relates to the technical field of wireless communication, and discloses a script-based multi-system wireless communication system function test method, which comprises the following steps of: S1, compiling and executing an automatic test script, and controlling a wireless communication system to switch among multiple wireless communication systems, the transmitting power and the receiving gain of the system are dynamically adjusted according to the script; s2, executing a test starting instruction and a test stopping instruction of the system through the test script, collecting data in real time in the test process, and performing analysis and evaluation; and S3, dynamically adjusting the working state of the wireless communication system based on the optimal control theory, correcting the test parameters in real time, ensuring the test precision, and estimating and optimizing the state of the system through a Kalman filter. By introducing deep reinforcement learning and the cloud platform, automation, intelligence and remote management of function testing of the wireless communication system are realized, the testing efficiency and accuracy are improved, and the adaptability and flexibility of the system to a complex environment are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a script-based multi-standard wireless communication system function testing method. Background Art

[0002] In modern society, with the rapid development of wireless communication technology, especially the widespread application of new communication technologies such as 5G, multi-standard wireless communication systems have become an indispensable infrastructure. The stability and performance of wireless communication systems directly affect the communication quality and user experience. Therefore, how to efficiently and accurately perform functional testing of wireless communication systems to ensure the stability and reliability of the system in different network environments and device configurations is an important and urgent problem to be solved.

[0003] In the prior art, the functional testing of wireless communication systems mainly relies on the traditional manual adjustment of test parameters and manual operation of equipment to set the transmission power, receiving gain, etc. These methods have achieved certain results in early tests. In some cases, the prior art can adjust the system parameters to a certain extent through manual operation to ensure the normal operation of the system in a common static environment. In addition, the existing wireless communication test methods have introduced some basic automated test systems, which can reduce manual intervention to a certain extent and realize automated execution through preset scripts and equipment configurations.

[0004] However, the existing technology still has some shortcomings when dealing with complex wireless communication environments. First, manual operation is not only inefficient but also prone to errors. Especially in the face of complex multi-standard test scenarios, manual intervention cannot quickly respond to system changes, resulting in inconsistent test results. Second, most of the existing automated testing methods are based on preset rules or static processes, and cannot dynamically adjust the test strategy to cope with environmental uncertainties. In this way, when problems such as signal interference and equipment failure occur, the system often cannot be adjusted in real time, resulting in the accuracy and efficiency of the test results being affected. Finally, most traditional testing methods rely on on-site operations, lack remote management and monitoring capabilities, and cannot meet the needs of large-scale, distributed wireless communication testing. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a script-based multi-standard wireless communication system functional testing method, which solves the problems of cumbersome manual operations, inflexible response to environmental changes, and insufficient remote management and automation capabilities in the prior art wireless communication system functional testing.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A script-based multi-standard wireless communication system function testing method, comprising the following steps:

[0007] S1. Write and execute automated test scripts to control the wireless communication system to switch between multiple wireless communication standards, and dynamically adjust the system's transmit power and receive gain according to the scripts;

[0008] S2, executing the start and stop test instructions of the system through the test script, and collecting data in real time during the test process for analysis and evaluation;

[0009] S3, dynamically adjust the working state of the wireless communication system based on optimal control theory, correct the test parameters in real time to ensure the test accuracy, and estimate and optimize the system state through the Kalman filter;

[0010] S4, using fuzzy logic control to handle uncertainty and nonlinear problems in the test process, and combining non-dominated sorting genetic algorithm to perform multi-objective optimization to balance transmit power, receive gain and signal quality;

[0011] S5. Optimize the test path through deep reinforcement learning, and dynamically adjust the test strategy based on historical data and real-time feedback to ensure the best test results;

[0012] S6. Remotely manage and monitor the test process through the cloud platform, automatically diagnose faults that occur during the test, generate optimization suggestions and automatically adjust the script.

[0013] Preferably, the automated test script includes:

[0014] Control the working mode switching of the wireless communication system, supporting standards including but not limited to GSM, CDMA, WCDMA, FDDLTE, TDDLTE, FDDNR and TDDNR;

[0015] Dynamically adjust the transmit power and receive gain of wireless communication systems, adjust these parameters based on real-time signal quality, and optimize system performance.

[0016] Preferably, the optimal control theory is used to dynamically adjust the test parameters of the system, and the test parameters include but are not limited to:

[0017] Transmit power;

[0018] Receive gain;

[0019] Signal quality.

[0020] Preferably, the Kalman filter is used to estimate the state of the system according to real-time data during the test, and feed back the estimation result to the control module to correct and optimize the test parameters.

[0021] Preferably, the fuzzy logic control includes:

[0022] Based on signal quality, interference level and system performance, fuzzy rules are used to reason and determine the control parameters that need to be adjusted;

[0023] Defuzzify the fuzzy inference results into specific test parameters, including adjusting the transmit power and receive gain.

[0024] Preferably, the non-dominated sorting genetic algorithm is used to solve the multi-objective optimization problem in the testing process, including:

[0025] Balance transmit power, receive gain and signal quality;

[0026] Ensure the optimal performance of wireless communication systems in different standards and network environments.

[0027] Preferably, the deep reinforcement learning includes:

[0028] Through historical test data and real-time feedback, the deep Q network is trained to dynamically optimize the test path;

[0029] Automatically select the appropriate test path based on intelligent optimization strategy and adjust the parameters during the test process to achieve the best test effect.

[0030] Preferably, the cloud platform is used for:

[0031] Remotely upload and download test scripts to support cross-regional automated testing;

[0032] Monitor the test process in real time, collect test data and analyze it;

[0033] Automatically diagnose and report on test failures, provide optimization suggestions, and automatically adjust test scripts to improve test results.

[0034] Preferably, the automatic fault diagnosis includes:

[0035] Analyze failure modes using historical test data and predict and diagnose possible failures through machine learning algorithms;

[0036] Monitor the device status in real time during the test process, adjust the test strategy based on real-time data, and reduce potential errors.

[0037] Preferably, the data collected in real time during the script execution process includes but is not limited to:

[0038] Parameters of signal quality, receiving gain, transmitting power, delay, throughput and packet loss rate during the test;

[0039] The collected test data will be analyzed in real time, and the test strategy will be dynamically adjusted based on the analysis results.

[0040] The present invention provides a script-based multi-standard wireless communication system function testing method, which has the following beneficial effects:

[0041] 1. The present invention realizes automatic test path optimization through deep reinforcement learning technology. In the functional test of multi-standard wireless communication systems, it can not only dynamically adjust the strategy according to real-time feedback, but also optimize the test process through intelligent decision-making. Compared with the existing method that requires manual intervention and adjustment, the present invention greatly improves the test efficiency and accuracy, avoids human errors, and ensures the stability of the test process.

[0042] 2. Through the remote management and real-time monitoring functions of the cloud platform, the present invention solves the management problems caused by geographical restrictions and scattered equipment in traditional testing methods. Testers can monitor the status of each test device in real time, remotely operate the equipment and adjust the test script, which greatly improves the automation level and work efficiency of the test, while avoiding the complexity of on-site inspection.

[0043] 3. The present invention combines fuzzy logic control with non-dominated sorting genetic algorithm (NSGA-II) to achieve a balance in system performance in multi-objective optimization, and can flexibly adapt to various complex environmental changes. Compared with the traditional single-objective optimization method, the multi-objective optimization scheme of the present invention solves the problem of uneven performance and improves the comprehensive performance of the wireless communication system under different test environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments 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 creative work are within the scope of protection of the present invention.

[0046] Please refer to the attached Figure 1 The embodiment of the present invention provides a script-based multi-standard wireless communication system function testing method, comprising the following steps:

[0047] S1. Write and execute automated test scripts to control the wireless communication system to switch between multiple wireless communication standards, and dynamically adjust the system's transmit power and receive gain according to the scripts;

[0048] S1, involves writing and executing automated test scripts to control the working state of the wireless communication system, including multi-mode switching and dynamic adjustment of transmit power and receive gain. The following is a detailed technical implementation method and the applied theoretical support.

[0049] During the functional testing of wireless communication systems, test scripts are the core of automated control. The scripts command the equipment to switch between different communication standards (such as GSM, CDMA, WCDMA, FDDLTE, TDDLTE, FDDNR, TDDNR, etc.) by mobilizing the system interface. Each communication standard has its own unique test requirements, such as transmit power, receive gain, signal quality and other parameters. The scripts will automatically configure these parameters to ensure that the system can be reasonably configured according to the characteristics of different standards in each test phase.

[0050] Transmit power It refers to the power of the signal transmitted by the wireless communication device when sending data.

[0051] Receive gain It refers to the signal gain of the receiving device, which is used to improve the quality of the received signal.

[0052] Signal Quality It is used to quantify the quality of signal transmission, usually expressed by indicators such as bit error rate (BER) and signal-to-noise ratio (SNR).

[0053] During the test, the script monitors the changes of these parameters in real time and dynamically adjusts them according to the set test goals to ensure the best test results. The flexibility of the script enables the test to be completed automatically without human intervention.

[0054] When the script is executed, it triggers the system to switch between different standards according to the predetermined test sequence. For example, when the system switches from FDDLTE to TDDLTE, the script will automatically configure the relevant test parameters such as transmit power, receive gain, signal frequency band, etc.

[0055] Through control instructions, the system can complete the switching between different standards. Each time the switch is made, the system needs to adjust the corresponding transmission power and receiving gain according to the characteristics of the switched network and equipment to maintain the communication quality.

[0056] During each switching process, the script dynamically adjusts the parameters according to the optimal control theory. Specifically, the system corrects the transmit power and receive gain based on real-time feedback to ensure that the test performance is optimal. The cost function of optimal control is:

[0057] ;

[0058] in: is the cost function, which indicates that the system Total cost within is a Lagrange function, which represents the instantaneous cost and is usually related to system error or power consumption; is the system state vector, which contains parameters related to signal quality and device performance; For control input (transmit power, receive gain, etc.); The test period.

[0059] By optimizing , the system can ensure that the best performance and accuracy are always maintained during the switching process of multiple standards.

[0060] As the system executes, the test script continuously monitors signal quality and other key parameters. For example, in a certain format, if the signal quality drops ( deterioration), the system will automatically increase the transmission power , and adjust the receiving gain based on real-time signal quality feedback This dynamic adjustment helps eliminate the impact of adverse factors such as signal attenuation and interference, ensuring communication quality.

[0061] During the actual test, the script will adjust the parameters in real time based on the following feedback mechanisms:

[0062] ;

[0063] in: is the transmit power; is the signal quality feedback value; is the receiving gain; Medium Function The balance between transmit power and receive gain is adjusted according to the actual test environment (such as signal interference, frequency band selection, etc.) so that the system can achieve optimal performance at each stage.

[0064] Through this formula, the system can adaptively optimize test parameters according to real-time feedback during the test process to ensure test accuracy under different standards.

[0065] Automation and efficiency: Through automated test scripts, manual operations are reduced, human errors are avoided, and switching between multiple standards and adjustment of test parameters can be completed quickly and accurately.

[0066] Optimization and precision: Through optimal control theory and real-time feedback mechanism, each step in the testing process will be executed under the guidance of optimal parameters to ensure the accuracy and consistency of each link.

[0067] Flexibility and adaptability: The test script can dynamically adjust parameters according to different test requirements and environmental changes, ensuring that the system can adapt to multi-standard, cross-band and complex wireless environments.

[0068] Robustness and reliability: Through fuzzy logic control and deep reinforcement learning, the system can respond flexibly in uncertain and nonlinear environments, further enhancing the stability and reliability of the testing process.

[0069] Real-time optimization: The combination of real-time data feedback and technologies such as Kalman filtering ensures dynamic optimization throughout the test process, improving test accuracy and reliability of results.

[0070] Through the comprehensive application of multiple advanced technologies such as optimal control theory, fuzzy logic control, and deep reinforcement learning, it is possible to provide efficient and reliable testing solutions for the research and development and maintenance of wireless communication systems.

[0071] S2, execute the start and stop test instructions of the system through the test script, and collect data in real time during the test for analysis and evaluation;

[0072] S2 mainly involves two core tasks: first, the script automatically starts and ends each round of testing by executing the start test and stop test instructions; second, the script will collect various types of data in real time during the test process, and analyze and evaluate these data so as to dynamically adjust the test strategy based on real-time feedback at different stages of the test process.

[0073] First, the test script will automatically initiate the start test command when the system executes the test, and execute the stop test command after the test is completed. Automated control enables the system to stably execute multiple test scenarios and avoid errors caused by human operation.

[0074] As an option, during the test the system will collect the following important parameters in real time:

[0075] Signal Quality To quantify the signal quality through indicators such as bit error rate (BER) and signal-to-noise ratio (SNR), reflecting the stability of the wireless signal during the test phase.

[0076] Transmit power It is the signal power emitted by the communication equipment during the test.

[0077] Receive gain The gain of the signal for the receiving device ensures the quality of the received signal.

[0078] Throughput It is the amount of data transmitted per unit time and is used to measure the communication efficiency of the system.

[0079] Latency It is the time required for a signal to travel from the sender to the receiver, reflecting the communication delay.

[0080] Packet loss rate It is the ratio of data packets lost during the test and is a key indicator for measuring system stability.

[0081] These parameters can fully reflect the performance of the system and help testers to comprehensively evaluate the working status of the wireless communication system.

[0082] Specifically, during the test, the system will use real-time data to adjust the test strategy. If the system detects that the signal quality is poor or other test targets are not met, the script will automatically optimize. For example, when the signal quality decreases, the system can automatically adjust the transmission power. or receive gain , in order to restore the signal quality. This feedback mechanism can achieve adaptive adjustment during the test process and improve the stability and accuracy of the test.

[0083] During the test, in order to optimize the system state and accurately adjust the control parameters (such as transmit power and receive gain), the present invention uses a Kalman filter to estimate the system state in real time. The Kalman filter provides an accurate state estimation for the system by predicting and updating the system state, thereby improving the accuracy of the system test.

[0084] Kalman filter formula:

[0085] Prediction equation:

[0086] ;

[0087] Update equation:

[0088] ;

[0089] in: is the predicted state estimate, which means at time The predicted value of the system state, based on the last moment state estimation and control input; is the state transfer matrix, which indicates the system state from time To time The changing relationship is usually determined by the dynamic equation of the system; is the control input matrix, which represents the influence of the control input (such as transmit power, receive gain, etc.) on the system state; For the moment The estimated value of the state; For the previous moment Control input, i.e. test parameters such as transmit power and receive gain; For the current moment The actual observed value reflects the real status of the system at the current moment, such as signal quality, throughput, etc. is the observation matrix, which describes how the actual observations of the system are related to the state; is the Kalman gain, which determines the weight between the prediction and the actual observation; For the moment The updated state estimate of Based on the predicted value and the actual observed value The updated system status.

[0090] The Kalman filter continuously corrects the system's state estimate through two steps: prediction and update. The system first predicts the current state based on the state at the previous moment, and uses the Kalman gain to correct the observed data. Ultimately, the system obtains a more accurate state estimate and adjusts the test parameters (such as transmit power and receive gain) based on this estimate to ensure the accuracy of the test process.

[0091] In step S2, the collection of real-time data is not only for obtaining parameters such as signal quality, but also for optimizing multiple objectives through a multi-objective optimization algorithm (such as a non-dominated sorting genetic algorithm, NSGA-II) to ensure that the wireless communication system can achieve optimal performance under different standards.

[0092] Multi-objective optimization formula:

[0093] ;

[0094] in: is the optimized objective function value, which represents the optimal solution among multiple objectives; is a number of objective functions, usually including the transmit power , receiving gain and signal quality wait; is the decision variable, which represents the control parameters that need to be optimized during the test, such as transmit power, receive gain, frequency band, etc.

[0095] The system optimizes the transmit power, receive gain, and signal quality through a non-dominated sorting genetic algorithm based on the data collected in real time. The algorithm ensures that the best compromise is found between different objectives by evaluating the relationship between the objective functions. For example, in a certain test phase, the system can adjust the transmit power to and receiving gain To optimize signal quality , ensuring the optimal balance between communication quality and system performance.

[0096] Deep reinforcement learning (DRL) intelligently optimizes the system's test path through Q learning. With real-time feedback, the system can automatically select the best test path based on historical test data and adjust relevant parameters during each execution to achieve the best test results.

[0097] Deep Q-learning formula:

[0098] ;

[0099] in: is the Q value function, which means that in state Next select action the expected returns to be obtained; is the learning rate, which indicates the adjustment rate of the Q value at each update; It is an immediate reward, which indicates the feedback value after performing a certain action. For the test process, the reward usually reflects the optimization of parameters such as signal quality and throughput; The discount factor indicates the degree of discount on future rewards. Value makes the system pay more attention to long-term effects; For the next state The maximum Q value among all possible actions taken under the given condition represents the expected return of the system's optimal action in the future.

[0100] Through reinforcement learning, the system can continuously adjust the test path based on historical experience, so that each test can achieve the best results. By continuously optimizing the Q value, the system can flexibly respond to various changes encountered during the test and ensure that the best strategy is selected at each stage.

[0101] Through the above steps, the test method of the present invention can not only dynamically adjust the control parameters in the test process, but also achieve a balance between multiple goals to ensure the optimal performance of the wireless communication system in a complex environment through real-time data collection, Kalman filtering, optimization algorithm, deep reinforcement learning and other technologies. This process realizes automated testing, intelligent decision-making and adaptive optimization, greatly improving the test efficiency, accuracy and robustness of the system.

[0102] S3, dynamically adjust the working state of the wireless communication system based on optimal control theory, correct the test parameters in real time to ensure the test accuracy, and estimate and optimize the system state through the Kalman filter;

[0103] The core of S3 is to dynamically adjust the working state of the wireless communication system by applying optimal control theory to ensure the accuracy and consistency of the test process. At the same time, the Kalman filter is used to estimate the system state in real time and optimize the system test parameters, thereby improving the system performance during the test process.

[0104] In general, optimal control theory plays a vital role in the testing process of wireless communication systems. It ensures that the system can always maintain the best performance in different network formats and test environments by dynamically calculating and adjusting the control parameters (such as transmit power, receive gain, etc.) during the test. The real-time estimation of the system state through the Kalman filter further improves the robustness of the system in complex environments and ensures the accuracy of each test stage.

[0105] As an option, the application of optimal control theory is implemented in this process through the cost function. The cost function provides the optimization direction according to the different requirements of the system during the test process, such as minimizing signal error, maximizing throughput, etc. Under this framework, the system optimizes the test process in real time by dynamically adjusting the control input.

[0106] In this embodiment, the system uses optimal control theory to guide the transmission power , receiving gain Optimization of control inputs such as . Optimal control achieves optimal control of the wireless communication system by minimizing the cost function, thereby achieving the purpose of improving test accuracy and performance, using the "cost function of optimal control" disclosed in S1.

[0107] By optimizing the cost function Optimal control theory enables the system to dynamically adjust the control input according to the current state at each moment. , thereby ensuring optimal performance of the wireless communication system. This process ensures that the system can efficiently and accurately perform functional testing of the wireless communication system.

[0108] Specifically, during the multi-standard switching process, the system adjusts the transmit power and receive gain in real time according to the requirements of different standards and network environments. For example, in the case of poor signal quality, the system can optimize the test effect by increasing the transmit power or adjusting the receive gain to ensure the stability and accuracy of the test.

[0109] In order to further improve the test accuracy, this embodiment introduces a Kalman filter to estimate and optimize the system state in real time. The Kalman filter predicts and updates the system state, corrects the system parameters, and ensures that the system maintains the best state in a dynamic environment. Its prediction and update formula can help the system to make adaptive adjustments during the test process to ensure the efficiency of the test, using the "Kalman filter formula" disclosed by S2.

[0110] The introduction of the Kalman filter enables the system to correct the test parameters based on real-time data. It continuously improves the system's adaptability to the test environment through the prediction and update process, ensuring that the control input at each stage can be dynamically optimized. For example, during the test, the system can use the Kalman gain to correct the prediction error of the signal quality, thereby adjusting the transmission power. or receive gain , in order to achieve the best testing effect.

[0111] In the implementation process of the present invention, the combination of optimal control theory and Kalman filter ensures that the system can adjust the test parameters in real time during the multi-standard switching process. Through the feedback data collected in real time, the system can continuously optimize the control input and improve the accuracy and stability of the test. Specifically, the system automatically adjusts the transmit power and receive gain to cope with environmental changes by real-time monitoring of parameters such as signal quality and throughput during the test.

[0112] For example, during the test, if the signal quality of the wireless communication system under a certain standard is Decrease, the Kalman filter will be based on the actual observation value and predicted values Difference, adjust the transmission power or receive gain , to optimize system performance. At the same time, optimal control theory dynamically adjusts these control parameters according to the test objectives (such as minimizing error or maximizing throughput).

[0113] As an option, the real-time feedback mechanism can also be used for multi-objective optimization. During the test, the system will not only adjust the transmit power and receive gain in real time, but also balance the relationship between multiple objectives such as throughput, signal quality and latency through optimization algorithms (such as NSGA-II) to ensure the optimization of system performance.

[0114] Optimal control provides mathematical guidance for test parameters (such as transmit power and receive gain), while the Kalman filter further improves the system's adaptability to environmental changes by accurately estimating the system state. This combination not only ensures the accuracy and stability of the test, but also enables the system to automatically optimize performance in multi-standard and complex environments, further improving the efficiency and reliability of the test.

[0115] S4, using fuzzy logic control to handle uncertainty and nonlinear problems in the test process, and combining non-dominated sorting genetic algorithm to perform multi-objective optimization to balance transmit power, receive gain and signal quality;

[0116] S4 further optimizes the process of wireless communication system function testing based on S3, uses fuzzy logic control to deal with nonlinear and uncertainty problems that may arise during the test process, and combines the non-dominated sorting genetic algorithm (NSGA-II) for multi-objective optimization, thereby achieving adaptive adjustment and efficient operation of the system.

[0117] Generally speaking, wireless communication systems often encounter some nonlinear problems that are difficult to accurately model during multi-mode switching. For example, in a complex channel environment, factors such as interference and noise may affect system performance, making traditional linear control methods no longer effective. Therefore, fuzzy logic control can flexibly deal with these uncertainties and provide real-time adjustment capabilities.

[0118] As an option, the non-dominated sorting genetic algorithm (NSGA-II) is combined for multi-objective optimization, which can compromise and optimize multiple objectives such as transmit power, receive gain, signal quality, etc., to ensure that each objective can achieve the optimal balance. This optimization method can effectively balance the various performance requirements in the communication system and improve the overall performance of the system.

[0119] Fuzzy logic control systems generate appropriate control outputs by converting input data into fuzzy sets and reasoning based on fuzzy rules. During the testing of wireless communication systems, factors such as signal quality, interference level, and device response may not be completely certain. Fuzzy logic control can effectively deal with these uncertainties.

[0120] Fuzzification: Fuzzify input data (such as signal quality, interference intensity, etc.) into fuzzy sets. Each input variable will be divided into multiple fuzzy values ​​(such as "low", "medium", "high").

[0121] Fuzzy reasoning: Reasoning based on a fuzzy rule base to generate control inputs. The rules in the rule base will determine how to adjust the control variable (such as transmit power or receive gain) based on the input data.

[0122] Defuzzification: Based on the inference results, the fuzzy control output is converted into actual control parameters to adjust the transmission power or receive gain .

[0123] Typically, in wireless communication systems, fuzzy logic control responds to changes in signal quality by adjusting transmit power and receive gain in real time. For example, if the system detects poor signal quality, fuzzy control may increase transmit power. Or increase the receiving gain , thereby improving signal quality.

[0124] Specifically, in one possible implementation, when the system detects the signal quality When it is low, the fuzzy control rules will determine whether to increase the transmit power or adjust the receive gain according to the preset rule base to improve the signal quality.

[0125] In step S4, NSGA-II is used to handle multi-objective optimization problems. During the testing process, wireless communication systems often face the optimization requirements of multiple objectives, such as transmit power, receive gain, and signal quality. These objectives are usually conflicting. For example, increasing transmit power may improve signal quality, but it may also increase the energy consumption of the system. The NSGA-II algorithm can find an optimal compromise solution between multiple objectives through a non-dominated sorting method.

[0126] The NSGA-II multi-objective optimization formula uses the “multi-objective optimization formula” disclosed by S2.

[0127] Specifically, NSGA-II determines the fitness of each individual in the solution set by evaluating their performance on multiple objectives and ultimately selects the optimal solution. In this way, the system can find an optimal compromise between objectives such as transmit power, receive gain, and signal quality, ensuring that each objective can be optimized and avoiding over-optimization of a single objective while ignoring the impact of other objectives.

[0128] In one possible implementation, the NSGA-II algorithm generates new solutions through crossover and mutation operations in each iteration and selects the optimal solution based on non-dominated sorting. This process can automatically optimize various control parameters at each test stage and ensure the optimal balance of system performance.

[0129] In this embodiment, the combination of fuzzy logic control and NSGA-II can effectively improve the performance of the wireless communication system during the test process. Fuzzy logic control can handle the uncertainty and nonlinear problems in the test process, while NSGA-II finds a balance between multiple performance indicators through a multi-objective optimization algorithm.

[0130] Specifically, fuzzy logic control first adjusts control inputs (such as transmit power and receive gain) in real time based on the system's current signal quality, interference, and other factors. Then, NSGA-II performs multi-objective optimization based on these control inputs to ensure that each system objective (such as signal quality, throughput, latency, etc.) is optimally optimized.

[0131] For example, during system testing, if the signal quality is poor, the fuzzy logic control will automatically increase the transmit power. At this time, NSGA-II will evaluate the impact of this control input on signal quality and throughput, and determine the optimal combination of transmit power, receive gain and other parameters through multi-objective optimization.

[0132] Fuzzy logic control copes with the nonlinearity and uncertainty that the system may face in a complex environment, while NSGA-II finds the optimal balance between multiple performance indicators through a multi-objective optimization algorithm. This combination not only improves the accuracy and stability of the test process, but also ensures the adaptability and robustness of the system in a changing environment.

[0133] S5. Optimize the test path through deep reinforcement learning, and dynamically adjust the test strategy based on historical data and real-time feedback to ensure the best test results;

[0134] S5 further optimizes the test path by introducing deep reinforcement learning (DRL), dynamically adjusts the test strategy using historical data and real-time feedback, and ensures that the test process always maintains the best results. Through the deep Q network (DQN), the system can adjust the control parameters in real time during the execution process to adapt to the changing wireless environment.

[0135] Deep reinforcement learning (DRL) mainly optimizes the decision-making process through the Q-learning algorithm. In Q-learning, the system gradually adjusts the strategy and selects the optimal test path by learning the relationship between the state and action in the environment. By training the deep Q network (DQN), the system can make the best decision at each moment and maximize the long-term reward. Use the "deep Q-learning formula" disclosed by S2.

[0136] Specifically, the deep Q network learns how to select the optimal test path by continuously updating the Q value. As the training process progresses, the system continuously tries and adjusts to find the test strategy that can achieve the best performance. This approach allows the system to automatically make the best decision in a complex and uncertain test environment, reduce human intervention, and improve test efficiency.

[0137] The advantage of deep reinforcement learning is that it can optimize strategies based on a large amount of historical data and real-time feedback. Historical data provides the test results of the system in different environments. DQN uses this data to train the network, so that the system can make more accurate decisions based on the actual environment and historical experience.

[0138] Generally, historical data includes previous test parameters and test results, such as signal quality, transmit power, receive gain, etc. The system is trained with this data and continuously adjusts its strategy so that it can quickly adapt to environmental changes and select the optimal path in the new test phase.

[0139] As an option, by training a deep Q network, the system can transform historical test data into valuable knowledge for model training. Each time a test task is performed, the system can select the optimal action based on the current state through DQN, and update the Q value through rewards, and finally find the most suitable test strategy.

[0140] The Deep Q Network not only relies on historical data for training, but can also be dynamically adjusted based on real-time test feedback. During the test, the system receives real-time data (such as throughput, latency, bit error rate, etc.) to evaluate the effectiveness of the current test strategy and adjust the control parameters based on the feedback.

[0141] Specifically, at each test stage, the system selects appropriate actions based on the current state (such as signal quality, network environment, device configuration, etc.). Assume that the current state Contains information such as signal quality and receiving gain. The system will select the best action (such as adjusting the transmit power or receiving gain) based on this information to ensure optimal system performance.

[0142] For example, if the signal quality is poor during the test, DQN will automatically increase the transmit power or adjust the receive gain based on the learning of historical data to improve the test results. Through this dynamic adjustment, the deep Q network can help the system adaptively adjust parameters to achieve the best test results in complex environments.

[0143] The deep Q network gradually optimizes the test path by continuously updating the Q value and selecting the optimal strategy, ensuring that the system can always maintain the best test path and test parameter configuration in multiple test stages.

[0144] Generally, the system may encounter multiple choices when testing, and DQN will determine the best action in each state by updating the Q value. Each action is selected based on the immediate reward. and the expectation of future rewards (via the discount factor ) to maximize the test effect.

[0145] In one possible implementation, when the system's test path or strategy is adjusted, DQN will dynamically select the test path based on historical data during training, thereby maximizing test efficiency and accuracy. For example, the system may need to improve signal quality by increasing the receiving gain at a certain stage, but may also need to choose a different strategy at other stages. This decision-making process is automatically performed by the deep Q network.

[0146] The test path is further optimized through deep reinforcement learning (DQN), and the test strategy is dynamically adjusted by combining historical data and real-time feedback. Each time a test is performed, the deep Q network selects the optimal action (such as adjusting the transmit power, receive gain, etc.) according to the current state, and optimizes the test effect through Q value updates. Through this process, the system can continuously optimize the test strategy in a complex wireless communication environment to ensure the best test results.

[0147] S6. Remotely manage and monitor the test process through the cloud platform, automatically diagnose faults that occur during testing, generate optimization suggestions and automatically adjust scripts;

[0148] On this basis, S6 further strengthens the system's adaptive capabilities and intelligence level, and realizes remote management, real-time monitoring, fault diagnosis, optimization suggestion generation, and automatic script adjustment functions of the test process through the cloud platform. The application of this platform effectively improves the automation and efficiency of the test process and ensures the consistency and accuracy of the test results.

[0149] Generally speaking, wireless communication systems require a lot of equipment and resources when conducting multi-standard tests. When conducting tests in a distributed environment, it is also necessary to ensure the consistency and efficiency of the tests. Through the cloud platform, testers can remotely manage all test equipment, obtain test data in real time, and quickly diagnose and repair any anomalies during the test.

[0150] As an option, the cloud platform can not only upload and download test scripts remotely through the automated script management function, but also adjust the scripts according to real-time test results to ensure that every link in the test process is kept in the best state. The introduction of this function significantly improves the automation of testing, reduces manual intervention, and improves the system's response speed to faults and environmental changes.

[0151] The remote management and monitoring function of the cloud platform allows testers to monitor the operating status of all test equipment in real time without being restricted by geographical location. The platform can provide a visual display of the equipment status, real-time data flow of the test, and the execution progress of the test task.

[0152] Specifically, the cloud platform displays the status information of all test equipment through a unified interface, such as whether the test equipment is running, various performance indicators (such as signal quality, transmission power, receiving gain, etc.), and test timestamps. Through the platform, testers can remotely start, stop or pause the test, and can also adjust the configuration or set parameters of the equipment as needed. In this way, the platform not only simplifies the equipment management process, but also provides flexible cross-regional and cross-device management capabilities.

[0153] In one possible implementation, the cloud platform can achieve cross-regional, multi-device synchronous testing and data aggregation. Testers can upload or adjust test scripts as needed and monitor the test status of devices in multiple regions in real time. For example, the system can execute the same set of test scripts on different base stations or wireless communication nodes, and centralize all test results on the cloud platform for data analysis and comparison.

[0154] The cloud platform is not just a management tool, it also has built-in automatic fault diagnosis and data analysis functions. By receiving test data in real time, the platform can identify any anomalies that occur during the test and generate fault reports through a preset fault pattern recognition algorithm. In this way, the system can quickly diagnose the cause of the fault and provide a repair solution.

[0155] In general, the system automatically analyzes the status of the device and determines whether it is normal through real-time collected data (such as signal quality, throughput, latency, etc.) combined with machine learning or rule-driven algorithms. If the system finds that a test device is operating abnormally, the platform will automatically generate an alert and report detailed information.

[0156] For example, if during testing of a device, the signal quality Decrease, or transmit power If the preset range is not reached, the platform will identify the problem and analyze its cause through automatic diagnosis, reporting that it may be caused by hardware failure, configuration error or environmental interference. The platform will not only identify the problem, but also provide specific repair steps or adjustment suggestions to help testers quickly solve the problem.

[0157] Specifically, the fault diagnosis system uses anomaly detection algorithms to monitor various indicators in real time, such as transmit power, receive gain, signal quality, etc. If a test indicator exceeds the preset threshold, the system will trigger an alarm and conduct a detailed fault analysis. If the system finds that the transmit power exceeds the preset range, it may recommend reducing the transmit power or adjusting the device position to reduce interference.

[0158] The optimization suggestion generation function of the cloud platform can make suggestions for improving the testing process based on the analysis of real-time test data and historical data, and automatically adjust the test script to ensure the best testing results.

[0159] Generally, when the system performs multi-standard testing, the platform automatically calculates the test results based on the feedback data collected in real time (such as signal quality, throughput, latency, etc.) and generates optimization suggestions. For example, if the signal quality at a certain test stage is If the performance is not ideal, the platform may suggest adjusting the transmit power or increasing the receive gain and automatically feed these suggestions back into the test script.

[0160] As an option, the platform can not only generate optimization suggestions, but also modify existing test scripts through automated processes. For example, if the system detects that the signal quality of certain test devices continues to decline, the platform may automatically modify the test script to increase the transmission power of certain devices or adjust the device configuration to adapt to the new environmental conditions, thereby improving the test results.

[0161] Specifically, if the system finds that the test results are not ideal when executing a certain standard test, the platform may automatically adjust the parameters in the test script to increase the transmit power or adjust the receive gain to improve the test performance. Through this process, the tester does not need manual intervention, and the platform can autonomously adjust the test process to achieve the predetermined goal.

[0162] Remote script management is one of the core functions of the cloud platform, which enables testers to upload, download and modify test scripts to ensure that all test devices are tested under the same conditions.

[0163] Generally, testers only need to upload the test script to the cloud platform, and the platform will automatically distribute the script to all test devices to ensure that all devices perform the same test tasks. In this way, the test consistency between devices is guaranteed, and the management of test scripts is more efficient and centralized.

[0164] As an option, the cloud platform supports cross-region and cross-device script management. Testers can adjust scripts according to different test requirements and update them remotely through the platform. For example, the system can run the same set of scripts on multiple base stations or nodes and synchronize the test results through the cloud platform. The platform can also automatically adjust the script according to changes in test results to ensure that every link in the test process can run in the best condition.

[0165] The cloud platform provides comprehensive management and monitoring support for the functional testing of wireless communication systems. The cloud platform can not only perform remote management and real-time monitoring, but also ensure the efficiency and accuracy of the test process through automatic diagnosis, optimization suggestion generation and script adjustment.

[0166] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A script-based multi-standard wireless communication system function testing method, characterized in that: The following steps are involved: S1. Write and execute automated test scripts to control the wireless communication system to switch between multiple wireless communication standards, and dynamically adjust the system's transmit power and receive gain according to the scripts; S2, executing the start and stop test instructions of the system through the test script, and collecting data in real time during the test process for analysis and evaluation; S3, dynamically adjust the working state of the wireless communication system based on optimal control theory, correct the test parameters in real time to ensure the test accuracy, and estimate and optimize the system state through the Kalman filter; S4, using fuzzy logic control to handle uncertainty and nonlinear problems in the test process, and combining non-dominated sorting genetic algorithm to perform multi-objective optimization to balance transmit power, receive gain and signal quality; S5. Optimize the test path through deep reinforcement learning, and dynamically adjust the test strategy based on historical data and real-time feedback to ensure the best test results; S6. Remotely manage and monitor the test process through the cloud platform, automatically diagnose faults that occur during the test, generate optimization suggestions and automatically adjust the script.

2. A script-based multi-standard wireless communication system function testing method according to claim 1, characterized in that: The automated test script includes: Control the working mode switching of the wireless communication system, supporting standards including but not limited to GSM, CDMA, WCDMA, FDDLTE, TDDLTE, FDDNR and TDDNR; Dynamically adjust the transmit power and receive gain of wireless communication systems, adjust these parameters based on real-time signal quality, and optimize system performance.

3. The script-based multi-standard wireless communication system function testing method according to claim 1, characterized in that: The optimal control theory is used to dynamically adjust the test parameters of the system, which include but are not limited to: Transmit power; Receive gain; Signal quality.

4. The script-based multi-standard wireless communication system function testing method according to claim 1, characterized in that: The Kalman filter is used to estimate the state of the system according to the real-time data during the test, and feed back the estimation result to the control module to correct and optimize the test parameters.

5. The script-based multi-standard wireless communication system function testing method according to claim 1, characterized in that: The fuzzy logic control includes: Based on signal quality, interference level and system performance, fuzzy rules are used to reason and determine the control parameters that need to be adjusted; Defuzzify the fuzzy inference results into specific test parameters, including adjusting the transmit power and receive gain.

6. The script-based multi-standard wireless communication system function testing method according to claim 1, characterized in that: The non-dominated sorting genetic algorithm is used to solve the multi-objective optimization problem in the testing process, including: Balance transmit power, receive gain and signal quality; Ensure the optimal performance of wireless communication systems in different standards and network environments.

7. The script-based multi-standard wireless communication system function testing method according to claim 1, characterized in that: The deep reinforcement learning includes: Through historical test data and real-time feedback, the deep Q network is trained to dynamically optimize the test path; Automatically select the appropriate test path based on intelligent optimization strategy and adjust the parameters during the test process to achieve the best test effect.

8. The script-based multi-standard wireless communication system function testing method according to claim 1, characterized in that: The cloud platform is used for: Remotely upload and download test scripts to support cross-regional automated testing; Monitor the test process in real time, collect test data and analyze it; Automatically diagnose and report on test failures, provide optimization suggestions, and automatically adjust test scripts to improve test results.

9. The script-based multi-standard wireless communication system function testing method according to claim 1, characterized in that: The automatic fault diagnosis includes: Analyze failure modes using historical test data and predict and diagnose possible failures through machine learning algorithms; Monitor the device status in real time during the test process, adjust the test strategy based on real-time data, and reduce potential errors.

10. The script-based multi-standard wireless communication system function testing method according to claim 1, characterized in that: The data collected in real time during the script execution includes but is not limited to: Parameters of signal quality, receiving gain, transmitting power, delay, throughput and packet loss rate during the test; The collected test data will be analyzed in real time, and the test strategy will be dynamically adjusted based on the analysis results.

Images