4G Module Energy Consumption Prediction and Control Method and System

Abstract

This invention relates to the field of energy consumption control technology, and more specifically, to a method and system for predicting and controlling the energy consumption of 4G modules. The method involves monitoring the operating data of 4G modules to generate a monitoring feature sequence of the 4G modules, performing predictive processing on the monitoring feature sequence based on a historical database to obtain a predicted feature sequence, and controlling the operating parameters of the 4G modules accordingly based on the predicted feature sequence.

Description

Technical Field

[0001] This invention relates to the field of energy consumption control technology, and more specifically, to a method and system for predicting and controlling the energy consumption of 4G modules. Background Technology

[0002] For many IoT devices and mobile terminals, battery life is a key indicator. Traditional 4G module power management methods often use fixed parameter settings and strategies, which cannot be dynamically adjusted according to the actual operating conditions of the module. Environmental factors such as the signal strength and interference of the 4G network are constantly changing, and traditional power management methods cannot detect these changes in real time and make corresponding adjustments. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and system for predicting and controlling the energy consumption of 4G modules, so as to realize dynamic management of the energy consumption mode of 4G modules.

[0004] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions: According to one aspect of the present invention, a method for predicting and controlling the energy consumption of a 4G module is provided, comprising: Monitor the operational data of the 4G module to generate a monitoring feature sequence of the 4G module; Based on the historical database, the monitored feature sequence is subjected to prediction processing to obtain the predicted feature sequence; The operating parameters of the 4G module are controlled accordingly based on the predicted feature sequence.

[0005] According to another aspect of the present invention, an energy consumption prediction and control system for a 4G module is provided.

[0006] As can be seen from the above technical solution, the energy consumption prediction and control method for 4G modules provided by the present invention has the following beneficial effects: This invention generates monitoring feature sequences by monitoring operational data, which can accurately grasp the module's operating status. Based on historical databases, it predicts feature sequences to anticipate energy consumption trends. By controlling operating parameters according to the predicted feature sequences, it can dynamically adjust module operation, reduce unnecessary energy consumption, extend equipment battery life, reduce energy waste, lower operating costs, and align with the trend of green communication development, achieving energy conservation and emission reduction goals and improving the overall operating efficiency and economy of 4G modules. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort: Figure 1 A schematic diagram illustrating the steps of the energy consumption prediction and control method for a 4G module provided in an embodiment of the present invention. Detailed Implementation

[0008] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0009] For many IoT devices and mobile terminals, battery life is a key indicator. Traditional 4G module power management methods often use fixed parameter settings and strategies, which cannot be dynamically adjusted according to the actual operating conditions of the module. Environmental factors such as the signal strength and interference of the 4G network are constantly changing, and traditional power management methods cannot detect these changes in real time and make corresponding adjustments.

[0010] In view of this, the present invention provides a method for predicting and controlling the energy consumption of a 4G module, the steps of which are as follows: Figure 1 As shown, it includes: The first step is to monitor the operating data of the 4G module to generate a monitoring feature sequence of the 4G module.

[0011] Specifically, in the first step of the embodiment provided by the present invention, the electrical performance and working status of the 4G module at each moment are monitored, and the electrical performance and working status at each moment are recorded together as operating data, which usually includes parameters such as current, voltage, and power. These parameters can intuitively reflect the energy consumption of the 4G module during operation. For example, the magnitude of the current is directly related to energy consumption. High current usually means higher energy consumption, such as standby state, signal transmission state, signal reception state, etc. The energy consumption of the 4G module varies greatly under different working states. For example, the energy consumption in the signal transmission state is usually much higher than that in the standby state.

[0012] More specifically, the operational data at each moment is processed in a time sequence to generate the original monitoring information stream of the 4G module. The operational data is collected at different times, and arranging these data in chronological order can form an information stream with a time dimension. This can clearly show the operational changes of the 4G module over a period of time, providing a foundation for subsequent feature analysis.

[0013] More specifically, based on the original monitoring information stream, the electrical performance characteristics of the working state at each moment are analyzed to obtain the operation monitoring characteristics at each moment, and the operation monitoring characteristics at each moment are arranged in time sequence to generate a monitoring feature sequence.

[0014] More specifically, the working status at each moment is analyzed to distinguish between standby status and signal transmission status. Different working statuses correspond to different energy consumption modes, and distinguishing them helps to analyze energy consumption characteristics more accurately. Based on the position corresponding to the signal transmission status, the original monitoring information stream is divided into intervals to obtain a deep monitoring information stream composed of several standby intervals and transmission nodes. This division can more clearly structure the original information, making it easier to analyze the electrical performance under different statuses.

[0015] More specifically, based on the deep monitoring information stream, the changes in electrical performance of each standby interval and each transmitting node are analyzed to obtain the electrical change curves in each standby interval and the electrical change data of each transmitting node. By analyzing the electrical change curves and data, the changing patterns of electrical parameters over time under different states can be understood, such as whether the current is stable in the standby interval and the peak current at the signal transmitting node.

[0016] More specifically, based on the electrical change curves and the electrical change data, operational characteristics are analyzed for the standby interval and the transmitting node to obtain operational monitoring characteristics at each time point. These characteristics can be statistical quantities, such as average current, maximum current, and current change rate, which can summarize the operation of the 4G module at different times and states. Finally, the operational monitoring characteristics at each time point are arranged in chronological order to generate a monitoring characteristic sequence.

[0017] More specifically, the energy consumption of a 4G module is closely related to its electrical performance and operating status. By monitoring these data and generating feature sequences, the changing patterns and characteristics of energy consumption can be accurately captured, providing a reliable data foundation for subsequent energy consumption prediction. The operation of a 4G module is a dynamic process, and its energy consumption will change over time. Arranging the data in chronological order and generating feature sequences can fully consider the impact of time factors on energy consumption, making subsequent predictions more accurate and in line with the actual situation.

[0018] More specifically, the monitoring feature sequence is an abstraction and summary of the 4G module's operating status. It contains rich historical information. Based on this sequence and combined with historical databases for predictive processing, it is easier to discover patterns and regularities in the data, thereby improving the accuracy of predictions. Subsequently, the operating parameters of the 4G module need to be controlled based on the prediction results, and the monitoring feature sequence can provide the basis for this control. By analyzing the feature sequence, the energy consumption characteristics of the 4G module under different states can be understood, thereby selecting appropriate control strategies, such as switching to a suitable standby mode to reduce energy consumption.

[0019] The second step is to perform prediction processing on the monitored feature sequence based on the historical database to obtain the predicted feature sequence.

[0020] Specifically, in the second step of the embodiment provided by the present invention, the time characteristics of signal transmission are analyzed on the monitoring feature sequence to obtain the signal transmission characteristics corresponding to the monitoring feature sequence. The data related to signal transmission in the monitoring feature sequence are analyzed to extract the time characteristics of signal transmission, including transmission frequency characteristics (e.g., the number of times the signal is transmitted per unit time) and standby duration characteristics (the length of standby time between each signal transmission).

[0021] More specifically, the timing characteristics of signal transmission are an important feature of 4G module operation, which directly affects energy consumption. By analyzing these characteristics, we can grasp the operating rules of 4G modules and provide key information for subsequent predictions. Different signal transmission timing characteristics correspond to different energy consumption patterns. By matching these characteristics with historical databases, we can find more valuable historical data.

[0022] More specifically, the historical database searches for monitoring feature sequences with the same or similar signal transmission characteristics as the current monitoring feature sequence. By comparing characteristics such as signal transmission frequency and standby time, historical data that meets the criteria is selected as a reference. The historical database stores a large amount of 4G module operation data, which reflects the operation characteristics of 4G modules under various conditions. By retrieving historical data with the same signal transmission characteristics as reference information, past experience can be used to predict future operation. Similar signal transmission characteristics mean that future operation may be similar to historical conditions. Using historical data for prediction can reduce uncertainty and improve the accuracy of prediction.

[0023] More specifically, within the found reference information, a portion matching the current monitoring feature sequence is identified, and a data segment is extracted from this matching point as the base prediction sequence. This sequence reflects the historical operation of the 4G module under similar signal transmission characteristics. The monitoring feature sequence is analyzed for the time characteristics of each signal transmission state of the 4G module, yielding the transmission frequency and standby duration characteristics for each signal transmission state. Based on these time characteristics, the potential correlations of the operational monitoring features at each moment are analyzed to obtain the time characteristic influence patterns of the operational monitoring features. For example, how transmission frequency and standby duration affect operational monitoring features such as current and voltage are analyzed. Based on the current time characteristics, the time characteristics of the monitoring feature sequence for future time periods are predicted to obtain the predicted time characteristics. Combining the time characteristic influence patterns and the predicted time characteristics, the operational performance of the signal transmission state for future time periods is simulated to generate predicted performance characteristics.

[0024] More specifically, the signal transmission state and time characteristics of the basic prediction sequence are located and analyzed to obtain the prediction monitoring features and corresponding time characteristics of the signal transmission state in the basic prediction sequence. The time characteristics are analyzed according to the prediction performance features to generate the prediction performance form corresponding to the prediction monitoring features. The prediction monitoring features of the basic prediction sequence are weighted and corrected based on the prediction performance form to obtain the prediction feature sequence.

[0025] More specifically, the part matching the current monitoring feature sequence is found in the reference information. The basic prediction sequence extracted based on this reflects the historical operating trajectory of the 4G module under similar conditions. Using this sequence as a starting point for prediction allows for a more reasonable inference of future operating conditions. The current monitoring feature sequence only reflects past and current operating conditions, while future operating performance will be affected by various factors, especially the timing characteristics of signal transmission. By conducting in-depth analysis and prediction of these timing characteristics, and combining this with the influence patterns of the timing characteristics of the operating monitoring features, future operating performance can be simulated more accurately. Since the operating conditions of each 4G module are different, by analyzing the current monitoring feature sequence to generate predictive performance characteristics, personalized predictions can be achieved for that 4G module, improving the targeting and accuracy of the predictions.

[0026] More specifically, the basic prediction sequence is based on historical data. Although it has some reference value, it cannot completely and accurately reflect the actual situation in the future. By adjusting the basic prediction sequence according to the prediction performance characteristics, current real-time information and future predictions can be taken into account, making the final prediction feature sequence more in line with the actual situation. The weighted correction method can reasonably adjust each prediction monitoring feature in the basic prediction sequence according to the prediction performance characteristics, highlighting important information and weakening unimportant information, thereby optimizing the prediction results and improving the reliability of the prediction.

[0027] The third step is to control the operating parameters of the 4G module according to the predicted feature sequence.

[0028] Specifically, in the third step of the embodiment provided by this invention, the 4G module typically has multiple standby modes, such as PSM (Power Saving Mode) and eDRX (Extended Discontinuous Reception). For the predicted feature sequence, the energy consumption, communication performance, and other indicators of the 4G module under each standby mode are analyzed. By establishing a corresponding evaluation model, the value parameters of each standby mode for the predicted feature sequence are calculated. This value parameter can comprehensively consider factors such as the degree of energy consumption reduction and the impact on communication services. For example, it can be a comprehensive score. The higher the score, the more suitable the standby mode is under the current prediction conditions.

[0029] Different standby modes have different characteristics in terms of power consumption reduction and communication performance. For example, PSM mode can significantly reduce power consumption, but may increase communication latency; eDRX mode balances power consumption and communication response speed to a certain extent. By analyzing the predicted feature sequence, the adaptability of various standby modes can be evaluated. It can comprehensively consider various factors such as the future operation of the 4G module, power consumption requirements, and communication service requirements to select the most suitable standby mode. Value parameters are a quantitative evaluation index that can comprehensively consider the advantages and disadvantages of different standby modes, making the selection process more objective and scientific. By calculating value parameters, it is possible to avoid selecting standby modes based solely on subjective judgment or a single index, thereby improving the accuracy and reliability of the selection.

[0030] Compare the value parameters of various standby modes, select the standby mode with the highest value parameter as the best standby mode, and then adjust its working parameters by sending corresponding control commands to the 4G module to switch it from the current working mode to the selected best standby mode. For example, if the PSM mode is selected, it is necessary to set the relevant timer parameters and other working parameters to make the 4G module enter the PSM mode.

[0031] The core purpose of selecting the optimal standby mode based on predicted feature sequences is to reduce the power consumption of the 4G module. The optimal standby mode varies depending on the operating conditions. By adjusting the standby mode in real time, the 4G module can minimize energy consumption and extend battery life while meeting communication needs. Reasonable selection of the standby mode not only reduces power consumption but also optimizes the overall performance of the 4G module. For example, selecting a low-power standby mode during periods of low communication demand avoids unnecessary energy waste; while selecting a standby mode that ensures communication performance during periods of high communication demand guarantees timely data transmission. By controlling operating parameters and switching the 4G module to the optimal standby mode, a balance between power consumption and performance can be achieved, improving device efficiency and user experience.

[0032] As can be seen from the above technical solution, the energy consumption prediction and control method for 4G modules provided by the present invention has the following beneficial effects: This invention generates monitoring feature sequences by monitoring operational data, which can accurately grasp the module's operating status. Based on historical databases, it predicts feature sequences to anticipate energy consumption trends. By controlling operating parameters according to the predicted feature sequences, it can dynamically adjust module operation, reduce unnecessary energy consumption, extend equipment battery life, reduce energy waste, lower operating costs, and align with the trend of green communication development, achieving energy conservation and emission reduction goals and improving the overall operating efficiency and economy of 4G modules.

[0033] Furthermore, the step of monitoring the operational data of the 4G module to generate a monitoring feature sequence of the 4G module includes: S11: Monitor the electrical performance and working status of the 4G module at various times, and record the electrical performance and working status at various times as operating data; S12: Perform time-series processing on the operational data at each moment to generate the raw monitoring information stream of the 4G module; S13: Based on the original monitoring information stream, perform electrical performance feature analysis on the working status at each moment to obtain the operation monitoring features at each moment, and arrange the operation monitoring features at each moment in time sequence to generate a monitoring feature sequence.

[0034] Specifically, hardware devices such as current sensors and voltage sensors are used to measure the current, voltage, and other parameters of the 4G module in real time. These sensors can be connected to the circuitry of the 4G module to convert the measured analog signals into digital signals and transmit them to the data acquisition system. By reading the status register or related control signals of the 4G module, its operating status information, such as standby status, signal transmission status, and signal reception status, can be obtained. This information can be obtained by interacting with the communication interface of the 4G module (such as serial port, SPI, etc.). The electrical performance parameters measured at each moment are associated with the corresponding operating status information and stored in data storage devices (such as hard drives, SD cards, etc.). The data can be stored in the form of a database for convenient subsequent data retrieval and processing.

[0035] More specifically, the energy consumption of a 4G module is closely related to its electrical performance (such as current and voltage) and operating status. Electrical performance directly reflects the amount of energy consumed by the module, while operating status determines the energy consumption pattern of the module in different scenarios. By recording data from both aspects simultaneously, the operating status of the 4G module can be comprehensively and accurately reflected, providing basic data for subsequent analysis and prediction. Under different operating states, the electrical performance of the 4G module will have significant differences. For example, in signal transmission state, the current usually increases, and the energy consumption will also increase accordingly. Recording the combined data of electrical performance and operating status helps to capture these energy consumption characteristics, thereby better understanding the energy consumption patterns of the 4G module.

[0036] More specifically, the running data recorded from the storage device is read and sorted according to the timestamp. This can be achieved using sorting algorithms in programming languages ​​(such as Python) such as quicksort and mergesort. The sorted data is then connected sequentially in chronological order to form a continuous data stream. This data stream can be stored as a file or processed in memory as a data stream.

[0037] More specifically, the operation of a 4G module is a dynamic process that changes over time, and its energy consumption also changes over time. By arranging the operating data in a time sequence, information in the time dimension can be incorporated into the data to form a raw monitoring information stream with a time order. This can clearly show the operating status and energy consumption trend of the 4G module at different times, providing richer information for subsequent feature analysis. The raw monitoring information stream after time sequence arrangement has a unified structure and order, which facilitates subsequent feature parsing and processing. When performing feature analysis, the data can be processed in time order, making it easier to discover patterns and regularities in the data.

[0038] More specifically, the working status information in the original monitoring information stream is parsed and classified into different status categories, such as standby status and signal transmission status. Conditional statements (such as if-else statements) can be used to classify the status. Based on the position of the signal transmission status, the original monitoring information stream is divided into several standby intervals and transmission nodes. The position of the transmission node can be determined by looking up the signal transmission status flag in the working status information. Then, the time period between adjacent transmission nodes is divided into standby intervals.

[0039] More specifically, the electrical performance data of each standby interval and transmitting node are analyzed to calculate relevant characteristic parameters, such as average current, maximum current, and current change rate. Statistical analysis methods (such as mean calculation and maximum value search) can be used to calculate these characteristic parameters. The operation monitoring characteristics corresponding to each moment are arranged in chronological order to form a monitoring characteristic sequence, which can be stored in the form of an array or list.

[0040] More specifically, the raw monitoring information stream contains a large amount of raw data. Directly using this data for analysis and prediction would be quite complex. By performing electrical performance feature analysis on the operating status, key feature information, such as average current and maximum current, can be extracted. These features can more concisely describe the operating status and energy consumption of the 4G module at different times, reducing data redundancy and improving the efficiency of analysis and prediction. By arranging the operating monitoring features at each time point in chronological order to generate a monitoring feature sequence, the data has a clearer structure and regularity. This sequence can be used as input for subsequent predictive processing, facilitating time series analysis and training of predictive models, thereby more accurately predicting the future energy consumption of the 4G module.

[0041] Furthermore, the step of performing electrical performance feature analysis on the working status at each moment based on the original monitoring information stream to obtain the operation monitoring features at each moment includes: S121: Perform content analysis on the working status at each moment to distinguish the working status into standby status and signal transmission status; S122: Divide the original monitoring information stream into intervals according to the position corresponding to the signal transmission state to obtain a deep monitoring information stream composed of several standby intervals and transmission nodes. S123: Based on the deep monitoring information stream, analyze the changes in electrical performance of each standby interval and each transmitting node to obtain the electrical change curves in each standby interval and the electrical change data of each transmitting node; S124: Based on the electrical change curve and the electrical change data, perform operational characteristic analysis on the standby interval and the transmitting node to obtain the operational monitoring characteristics at each time point.

[0042] Specifically, the operating status of a 4G module typically follows a certain communication protocol. The operating status is determined by parsing this protocol information. For example, the status register or related control signals of the 4G module can be read, and standby and signal transmission states can be distinguished based on specific flag bits or codes. In some systems, a specific value in a register indicates standby mode; a change in that value indicates signal transmission mode. Electrical performance data is also used for auxiliary judgment. Generally, the current increases significantly in signal transmission mode. Therefore, a current threshold can be set. When the current exceeds this threshold and persists for a certain period, it is determined to be in signal transmission mode; otherwise, it is in standby mode. A logic judgment program can be written using a programming language to perform real-time judgment and classification of the operating status data at each moment.

[0043] More specifically, the energy consumption characteristics of 4G modules vary significantly under different operating states. Dividing the operating states into standby state and signal transmission state simplifies the complex operating conditions into two basic modes, facilitating targeted analysis of energy consumption under different states. Standby state and signal transmission state are two key states in the operation of 4G modules. Accurately distinguishing between these two states can help grasp the key points of energy consumption analysis and provide a more targeted basis for subsequent energy consumption prediction and control.

[0044] More specifically, in the data after state parsing, all time points in the signal transmission state are found and marked as transmission nodes. By traversing the working state data, the timestamps corresponding to all signal transmission states are recorded. Using the transmission nodes as boundaries, the time periods between adjacent transmission nodes are divided into standby intervals. For example, if there are two transmission nodes located at times t1 and t2 respectively, then the time period from t1 + 1 to t2 - 1 is a standby interval. The divided standby intervals and the marked transmission nodes are arranged in chronological order to form a deep monitoring information stream.

[0045] More specifically, the original monitoring information stream is a continuous data stream. By dividing it into standby intervals and marking transmission nodes, it can be transformed into a deep monitoring information stream with a clear structure. This structured data makes it easier to independently analyze and compare the electrical performance under different states. Different standby intervals and transmission nodes correspond to different energy consumption stages. Through interval division, the energy consumption changes of the 4G module during standby and signal transmission can be clearly observed, providing a basis for accurately analyzing energy consumption patterns.

[0046] More specifically, electrical performance data, such as current and voltage, are extracted from each standby interval and transmitting node in the deep monitoring information stream. Based on the defined time ranges for each interval and node, electrical data for the corresponding time period can be filtered from the raw data. For standby intervals, plotting tools (such as Python's Matplotlib library) are used to draw curves of the electrical data (such as current changes over time) to visually demonstrate the electrical changes. For transmitting nodes, relevant statistics of their electrical data, such as average current, maximum current, and rate of change of current, are calculated. These calculations can be performed using statistical analysis methods and programming languages.

[0047] More specifically, electrical change curves can intuitively reflect the changing trend of electrical parameters of a 4G module over time in the standby range, helping to quickly understand the fluctuations in energy consumption. Meanwhile, electrical change data of the transmitting node can quantitatively describe the energy consumption characteristics during signal transmission, providing specific numerical basis for subsequent energy consumption assessment. By analyzing electrical change curves and data, the energy consumption patterns of the 4G module under different states can be discovered. For example, whether the current is stable in the standby range, and what factors affect the peak value and rate of change of the current at the signal transmitting node. These patterns are of great significance for energy consumption prediction and control.

[0048] More specifically, based on electrical change curves and data, a series of parameters that can describe the operating characteristics of the 4G module are defined, such as the average current and current fluctuation range in the standby interval, and the peak current and current rise time of the transmitting node. For each standby interval and transmitting node, calculations are performed based on the defined characteristic parameters. For example, for a standby interval, its average current and current fluctuation range are calculated; for a transmitting node, its peak current and current rise time are calculated. The calculated characteristic parameters are associated with the corresponding time points to form the operating monitoring characteristics at each moment.

[0049] More specifically, while electrical change curves and data can reflect the operation of 4G modules, the data volume is large and complex. By analyzing operational characteristics, these data can be abstracted into a series of key characteristic parameters, which can more concisely describe the operating status of 4G modules at different times, facilitating subsequent data analysis and processing. Operational monitoring characteristics are a quantitative description of the operating status of 4G modules. These characteristics can be used as input data for training energy consumption prediction models and for control decisions of operating parameters. By analyzing and predicting these characteristics, measures can be taken in advance to adjust the operating parameters of 4G modules, thereby achieving effective control of energy consumption.

[0050] Furthermore, the step of performing prediction processing on the monitored feature sequence based on the historical database to obtain the predicted feature sequence includes: S21: Perform time characteristic analysis on the signal transmission of the monitoring feature sequence to obtain the signal transmission characteristics corresponding to the monitoring feature sequence; S22: Based on the historical database, the signal transmission characteristics are matched to retrieve historical monitoring feature sequences with consistent signal transmission characteristics as reference information; S23: Perform future prediction processing on the monitoring feature sequence based on the reference information to obtain the predicted feature sequence.

[0051] Specifically, feature data related to signal transmission is extracted from the monitoring feature sequence, such as the timestamp of each signal transmission and the duration of transmission. This data is usually included when the monitoring feature sequence was generated earlier. Based on the extracted data, the time characteristics of signal transmission are calculated, the number of signal transmissions within a certain time window is counted, and the transmission frequency per unit time (such as per minute or per hour) is calculated. A sliding window method can be used to calculate the frequency in different time windows to capture the dynamic changes in frequency. The time interval between two adjacent signal transmissions, i.e., the standby time, is calculated. Statistical analysis is performed on these standby time data, such as calculating the mean, median, and standard deviation, to understand the distribution of standby time.

[0052] More specifically, the timing characteristics of signal transmission are an important manifestation of the operating rules of 4G modules. Transmission frequency and standby time directly affect the module's energy consumption and communication performance. By analyzing these timing characteristics, we can gain a deeper understanding of the working mode and behavior patterns of 4G modules, providing key basis for subsequent predictions. Different signal transmission timing characteristics correspond to different operating scenarios and energy consumption modes. Accurately extracting the signal transmission characteristics of monitoring feature sequences can more precisely find matching historical data in the historical database, improving the accuracy of predictions.

[0053] More specifically, in the historical database, the same signal transmission time characteristic analysis is performed on each historical monitoring feature sequence to obtain its corresponding transmission frequency characteristic and standby duration characteristic. Using a matching algorithm, the signal transmission characteristics of the current monitoring feature sequence are compared with the characteristics in the historical database. Similarity calculation methods can be used, such as calculating the relative error of transmission frequency and standby duration. A similarity threshold is set. When the similarity between the characteristics of historical data and the current characteristics exceeds the threshold, they are considered to match. All matching historical monitoring feature sequences are filtered out, and these sequences are retrieved from the historical database as reference information. This reference information can be stored in a temporary data structure for later use.

[0054] More specifically, the historical database records the operating data of 4G modules under various conditions, containing a wealth of historical experience. By matching historical data with consistent signal transmission characteristics, past operating patterns and energy consumption can be learned from, providing valuable references for current predictions. Similar signal transmission characteristics mean that future operating conditions may be similar to historical conditions. Predictions based on matched historical data can reduce uncertainty and improve the reliability and accuracy of prediction results.

[0055] More specifically, in the reference information, the part most similar to the current monitoring feature sequence is identified. Using this as a starting point, a segment of data is extracted from this point as the basic prediction sequence. By comparing the feature values ​​of the monitoring feature sequence and the reference information, the starting position with the highest similarity is found. Further analysis of the monitoring feature sequence is then performed, combining current signal transmission time characteristics and operational patterns to predict future performance over a period of time. For example, based on the current transmission frequency and standby duration trend, the timing and duration of signal transmission in the future can be predicted. A prediction model (such as a time series analysis model or machine learning model) is established to generate predicted performance features. Based on these features, the basic prediction sequence is adjusted. A weighted correction method can be used to adjust each feature value in the basic prediction sequence to better align with the predicted future performance. The final prediction feature sequence is then obtained.

[0056] More specifically, the basic prediction sequence is based on historical data and reflects the operating trajectory under similar conditions. However, future operating conditions will change due to various factors. By predicting the future performance of the current monitoring feature sequence and adjusting the basic prediction sequence accordingly, historical experience can be combined with the current situation, making the prediction results more consistent with reality. The prediction feature sequence describes the possible future operating characteristics of the 4G module, providing an important basis for subsequent control of the 4G module's operating parameters. Based on the prediction feature sequence, measures can be taken in advance, such as adjusting the standby mode and optimizing communication strategies, to achieve effective control of energy consumption and optimization of communication performance.

[0057] Furthermore, the step of performing future prediction processing on the monitored feature sequence based on the reference information to obtain the predicted feature sequence includes: S231: Locate the historical monitoring feature sequence on the reference information to select a predictive reference part from the reference information and use the predictive reference part as the basic predictive sequence; S232: Based on the monitoring feature sequence, predict the operational performance for future time periods and generate predicted performance features; S233: Adjust the basic prediction sequence according to the predicted performance characteristics to obtain the prediction feature sequence.

[0058] Specifically, by using appropriate similarity measurement methods, such as Euclidean distance and dynamic time warping (DTW), the monitored feature sequence is compared one by one with each subsequence in the reference information. Euclidean distance calculates the square root of the sum of squares of the differences between corresponding elements of two sequences, which can intuitively reflect the numerical differences between sequences. DTW is more suitable for processing sequences that have time scaling, as it can find the optimal matching path between two sequences.

[0059] More specifically, the starting position of the most similar subsequence in the reference information is identified. This starting position is the location point of the monitoring feature sequence in the reference information. Starting from the location point, a reference information subsequence of a certain length is extracted as the prediction reference part. The extraction length can be determined according to the actual situation. Generally, it should be ensured that this part contains enough information to predict future operation. The selected prediction reference part is used as the basic prediction sequence, which reflects the historical operation trajectory of the 4G module under similar conditions.

[0060] More specifically, the reference information is a sequence selected from the historical database that is consistent with the signal transmission characteristics of the current monitoring feature sequence. By locating similar parts, it means that we can learn from the subsequent operation of 4G modules under similar historical conditions, providing a reasonable starting point for the current prediction. Using similar historical operation sequences as the basis for prediction can reduce the uncertainty of future predictions to a certain extent, because similar input conditions often lead to similar output results, thereby improving the reliability of the prediction.

[0061] More specifically, in-depth analysis of the monitoring feature sequence is conducted to extract the temporal characteristics of each signal transmission state of the 4G module, including transmission frequency characteristics (such as the number of transmissions per unit time, the trend of transmission frequency changes, etc.) and standby duration characteristics (such as average standby duration, the fluctuation range of standby duration, etc.). Through statistical analysis and machine learning algorithms (such as association rule mining, neural networks, etc.), the potential correlation between temporal characteristics and operational monitoring characteristics (such as current, voltage, etc.) is studied to obtain the temporal characteristic influence pattern of operational monitoring characteristics. For example, it is found that the increase in transmission frequency leads to the increase in current peak value, etc.

[0062] More specifically, based on the current time characteristics and their changing trends, time series prediction methods (such as ARIMA models, LSTM networks, etc.) are used to predict the time characteristics of future time periods, obtaining predicted time characteristics. Combining the time characteristic influence patterns and predicted time characteristics, the signal transmission status of future time periods is simulated to predict the corresponding operational performance, such as changes in current and voltage, and generate predicted performance features.

[0063] More specifically, the basic prediction sequence is based on historical data. However, in reality, the operation of 4G modules is affected by a variety of factors, and future performance will differ from historical performance. By conducting in-depth analysis of the monitoring feature sequence and predicting future time characteristics, these dynamic changes can be taken into account, making the prediction more consistent with the actual situation. The operation of each 4G module is unique. By analyzing and predicting the current monitoring feature sequence, personalized prediction performance characteristics can be generated for that module, improving the accuracy and relevance of the prediction.

[0064] More specifically, the signal transmission state of the basic prediction sequence is located, the predictive monitoring characteristics of the corresponding signal transmission state are determined, and their temporal characteristics, such as transmission time and duration, are analyzed. Based on the predictive performance characteristics, the possible future manifestations of the predictive monitoring characteristics in the basic prediction sequence are analyzed, such as the trend of current change and peak size. Based on the predictive performance, different weights are assigned to each predictive monitoring characteristic of the basic prediction sequence, and a weighted correction is performed. The weight allocation can be determined based on factors such as the degree of difference and importance between the predictive performance characteristics and the characteristics of the basic prediction sequence. Through weighted correction, the basic prediction sequence is made to better match the future prediction situation, thus obtaining the predictive feature sequence.

[0065] More specifically, while the basic prediction sequence is based on historical similarities, it does not take into account current real-time information and future dynamic changes. By adjusting it according to the prediction performance characteristics, the latest prediction information can be incorporated into the basic prediction sequence, making the prediction results more accurate and reliable. The weighted correction method can flexibly adjust the various features in the basic prediction sequence, highlighting important information and weakening unimportant information, thereby optimizing the prediction results and making them more reflective of the actual operation of 4G modules in the future, providing a more accurate basis for subsequent energy consumption control.

[0066] Furthermore, the step of predicting operational performance for future time periods based on the monitored feature sequence and generating predicted performance features includes: S2321: Analyze the time characteristics of each signal transmission state of the 4G module in the monitoring feature sequence to obtain the time characteristics of each signal transmission state; wherein, the time characteristics include transmission frequency characteristics and standby duration characteristics; S2322: Analyze the potential correlation of the operation monitoring features at each time point based on the time characteristics to obtain the time characteristic influence pattern of the operation monitoring features; S2323: Based on the time characteristics, predict the time characteristics of the monitoring feature sequence for future time periods to obtain the predicted time characteristics; S2324: Combine the time characteristic influence mode with the predicted time characteristics to simulate the signal transmission status in the future time period to generate predicted performance characteristics.

[0067] Specifically, data related to the 4G module signal transmission status is identified from the monitoring feature sequence. This data includes information such as the signal transmission timestamp and transmission duration. The number of signal transmissions within a certain time window is counted to calculate the transmission frequency. A sliding window method can be used, with different time intervals (such as per minute or per hour) as windows, to calculate the transmission frequency within each window. For example, if the signal is transmitted 10 times within an hourly window, the transmission frequency within that window is 10 times / hour. The time interval between two adjacent signal transmissions is calculated, i.e., the standby time. All standby time data is collected and processed.

[0068] More specifically, transmission frequency and standby time are important temporal characteristics of 4G module signal transmission status. They directly reflect the module's working mode and usage patterns. Understanding these temporal characteristics helps to deeply understand the operating mechanism of 4G modules and provides a foundation for subsequent prediction and control. Accurate temporal characteristic data is a prerequisite for conducting correlation analysis between temporal characteristics and operational monitoring features. Only by clarifying the temporal patterns of signal transmission can we further explore their impact on other operating parameters.

[0069] More specifically, by associating operational monitoring characteristics (such as current, voltage, and power) at various times with corresponding time characteristics (transmission frequency, standby time), a dataset can be constructed. Each row contains the corresponding values ​​of time characteristics and operational monitoring characteristics. Statistical methods, such as correlation analysis and regression analysis, can be used to explore the potential relationship between time characteristics and operational monitoring characteristics. For example, by calculating the correlation coefficient, it can be determined whether there is a linear relationship between transmission frequency and current. Regression analysis can be used to establish a mathematical model between time characteristics and operational monitoring characteristics. Based on the results of statistical analysis, the time characteristic influence patterns of operational monitoring characteristics can be extracted. For example, it can be found that an increase in transmission frequency leads to a linear increase in current, or an extension of standby time leads to a gradual decrease in voltage.

[0070] More specifically, there is a complex intrinsic relationship between the operation monitoring characteristics of 4G modules and the timing characteristics of signal transmission. Through correlation analysis, these potential relationships can be revealed, helping to understand how timing characteristics affect the operation performance of the modules. The timing characteristic influence pattern is an important basis for simulating future operation performance. Only by understanding how timing characteristics affect operation monitoring characteristics can we accurately predict the operation performance of the modules given the future timing characteristics.

[0071] More specifically, based on the characteristics of the time-series data, a suitable time series prediction model is selected, such as the Autoregressive Integral Moving Average (ARIMA) model or the Long Short-Term Memory (LSTM) network. The ARIMA model is suitable for time series data with linear trends and seasonality, while the LSTM network is better at handling time series with complex nonlinear relationships. The selected model is trained using historical time-series data, which is divided into training and validation sets. By continuously adjusting the model's parameters, the prediction error on the validation set is minimized. The trained model is then used to predict the time characteristics of future time periods. By inputting the current time-series data, the model will output predicted values ​​such as future transmission frequency and standby time, i.e., predicted time characteristics.

[0072] More specifically, the operating environment and usage requirements of 4G modules are constantly changing, and their signal transmission timing characteristics will also change accordingly. By predicting future timing characteristics, these dynamic changes can be taken into account, making the prediction results more consistent with the actual situation. Predicting timing characteristics is a key input for simulating future operating performance. Only by knowing the future timing characteristics can we combine the timing characteristic influence patterns and accurately simulate the module's future operating performance.

[0073] More specifically, based on the influence pattern of time characteristics, an operational performance simulation framework is constructed. This framework can be a mathematical model or algorithm that describes how time characteristics affect operational monitoring features. The predicted time characteristics (transmission frequency, standby time, etc.) are taken as input and substituted into the simulation framework. Based on the simulation framework and the predicted time characteristics of the input, the operational monitoring feature values ​​for future time periods, such as current, voltage, and power, are calculated. These calculated values ​​are the predicted performance features.

[0074] More specifically, by combining the influence of time characteristics on the model and the predicted time characteristics, the impact of time characteristics on the operating performance can be comprehensively considered, thereby more comprehensively and accurately predicting the operating status of the 4G module in the future time period. The predicted performance characteristics provide an important basis for subsequent control of the operating parameters of the 4G module. Based on the predicted operating performance, measures can be taken in advance, such as adjusting the standby mode and optimizing the communication strategy, to achieve effective control of energy consumption and optimization of communication performance.

[0075] Furthermore, the step of adjusting the basic prediction sequence based on the predicted performance characteristics to obtain the prediction feature sequence includes: S231: Locate the signal transmission state and analyze the time characteristics of the basic prediction sequence to obtain the prediction monitoring features of the corresponding signal transmission state and the corresponding time characteristics in the basic prediction sequence. S232: Analyze the time characteristics based on the predicted performance characteristics to generate a predicted performance form corresponding to the predicted monitoring characteristics; S233: Based on the predicted performance form, each of the predicted monitoring features of the basic predicted sequence is weighted and corrected to obtain a predicted feature sequence.

[0076] Specifically, in the basic prediction sequence, the signal transmission state is identified according to pre-set rules. For example, if the basic prediction sequence contains current data, when the current value exceeds a certain threshold and lasts for a certain period of time, it is determined to be a signal transmission state. By traversing the sequence, the positions corresponding to all signal transmission states are marked. For the located signal transmission state, its relevant time characteristics are extracted, including the start time, end time, duration of signal transmission, and the time interval between two adjacent signal transmissions. At the same time, the prediction monitoring features corresponding to each signal transmission state, such as parameters such as current, voltage, and power, are recorded.

[0077] More specifically, the energy consumption and operating characteristics of 4G modules in signal transmission state differ significantly from other states. Locating and analyzing the signal transmission state in the basic prediction sequence can focus on these key states, providing targeted data support for subsequent precise adjustments. Clarifying the temporal characteristics of the signal transmission state helps to establish a close link between prediction monitoring characteristics and the time dimension, better understand the operation of 4G modules at different points in time, and provide accurate time references for subsequent adjustments.

[0078] More specifically, the predicted performance characteristics are compared and analyzed with the time characteristics of signal transmission states in the basic prediction sequence. For example, the predicted signal transmission frequency and standby time are compared with the corresponding time characteristics in the basic prediction sequence to find the differences and trends between the two. Based on historical data and known operating rules, pattern matching and inference are performed on the changes in time characteristics. For example, if the predicted signal transmission frequency will increase, it is inferred from past experience that the current peak value will increase, thereby determining the change pattern of the predicted monitoring characteristics (such as current). Based on the results of analysis and inference, the predicted performance form of the corresponding predicted monitoring characteristics is generated. This can be a specific numerical range, a trend curve, or a probability distribution, etc., to describe the possible future performance of the predicted monitoring characteristics.

[0079] More specifically, the predicted performance characteristics reflect the future operating trend of the 4G module, while the time characteristics of the basic prediction sequence are based on historical similarities. By combining the two for analysis, the current real-time prediction information can be fully considered, making the performance of the prediction monitoring characteristics more in line with the actual situation. The accurate prediction performance provides a clear basis for the subsequent weighted correction of the basic prediction sequence. It can guide how to adjust the prediction monitoring characteristics to make them closer to the actual future operation.

[0080] More specifically, based on factors such as the degree of difference and importance between the predicted performance and the predicted monitoring features in the basic prediction sequence, a corresponding weight is determined for each predicted monitoring feature. For example, if the prediction shows that the change in current within a certain period has a significant impact on energy consumption, and the predicted value differs significantly from the basic predicted value, then a higher weight is assigned to the current feature for that period. Each predicted monitoring feature is multiplied by its corresponding weight, and then the predicted monitoring features in the basic prediction sequence are corrected. The correction formula can be expressed as: Corrected feature value = Original feature value × Weight + Adjustment term, where the adjustment term can be specifically set according to the predicted performance. The corrected predicted monitoring features are then rearranged in chronological order to form a predicted feature sequence, which reflects the future operating characteristics of the 4G module after adjustment.

[0081] More specifically, the basic prediction sequence is based on historical data and cannot fully and accurately reflect the actual situation in the future. Through weighted correction, the basic prediction sequence can be adjusted according to the prediction performance, highlighting important information and weakening unimportant information, thereby optimizing the prediction results and making them closer to the actual operating conditions. The predicted feature sequence provides a more accurate basis for subsequent control of the working parameters of the 4G module. Based on the more accurate prediction results, more reasonable control strategies can be formulated to achieve effective management of the energy consumption and optimization of the performance of the 4G module.

[0082] Furthermore, the step of controlling the operating parameters of the 4G module accordingly based on the predicted feature sequence includes: S31: Perform an adaptive analysis of various standby modes on the 4G module based on the predicted feature sequence to obtain the value parameters of each standby mode for the predicted feature sequence. S32: Select the optimal standby mode for the 4G module according to the value parameters, so as to control the working parameters of the 4G module accordingly and switch the 4G module to the corresponding standby mode.

[0083] Specifically, it is necessary to understand the various standby modes supported by the 4G module, such as PSM (Power Saving Mode) and eDRX (Extended Discontinuous Reception), and collect relevant parameters for each standby mode, including the conditions for entering the mode, the energy consumption in the mode, communication latency, etc., and conduct detailed analysis of the predicted feature sequences to extract key information, such as signal transmission frequency, standby time, current fluctuations, etc., which reflect the operating trend of the 4G module in the future.

[0084] More specifically, for each standby mode, its adaptability is evaluated by combining the predicted feature sequence. For example, for the PSM mode, it is analyzed whether the longer standby duration in the predicted feature sequence meets the entry conditions for this mode; for the eDRX mode, the impact of signal transmission frequency on its communication delay and energy consumption is considered. Based on the results of the adaptability evaluation, a value parameter is calculated for each standby mode. The value parameter can comprehensively consider multiple factors such as the degree of energy consumption reduction and the impact on communication performance. A weighted summation method can be used to assign different weights to different factors, such as a weight of 0.6 for energy consumption reduction and a weight of 0.4 for the impact on communication performance. Then, the comprehensive value parameter for each standby mode is calculated based on the evaluation results.

[0085] More specifically, the value parameters of various standby modes are compared, and the standby mode with the highest value parameter is selected as the optimal standby mode. For example, if the value parameter of PSM mode is 80 points and the value parameter of eDRX mode is 70 points, then PSM mode is selected. After determining the optimal standby mode, the working parameters of the 4G module need to be adjusted accordingly. This involves setting timer parameters, communication protocol parameters, etc. For example, when entering PSM mode, appropriate T3324 timer parameters need to be set to control the duration of the module entering sleep mode. By sending control commands to the 4G module, it can be switched from the current working mode to the selected optimal standby mode. These control commands can be sent to the 4G module through serial communication, SPI communication, etc.

[0086] More specifically, 4G modules support multiple standby modes, each with its own applicable scenarios. By analyzing predictive feature sequences and evaluating the adaptability of various standby modes, the advantages of different standby modes can be fully utilized. The most suitable mode can be selected based on the future operation of the 4G module, thereby improving energy efficiency. Value parameters are a quantitative evaluation indicator that comprehensively considers multiple factors such as energy consumption reduction and communication performance, making the comparison between different standby modes more objective and scientific. By calculating value parameters, the selection of standby modes can be avoided based solely on subjective judgment or a single indicator, thus improving the accuracy of the selection.

[0087] More specifically, the core purpose of selecting the optimal standby mode is to reduce the power consumption of the 4G module. The optimal standby mode varies under different operating conditions. By dynamically selecting the standby mode based on predicted feature sequences and adjusting operating parameters, the 4G module can minimize energy consumption and extend battery life while meeting communication needs. Reasonable selection of the standby mode not only reduces power consumption but also optimizes the overall performance of the 4G module. For example, selecting a low-power standby mode during periods of low communication demand avoids unnecessary energy waste; while selecting a standby mode that ensures communication performance during periods of high communication demand guarantees timely data transmission. By controlling operating parameters and switching the 4G module to the optimal standby mode, a balance between power consumption and performance can be achieved, improving device efficiency and user experience.

[0088] Based on the technical content of the 4G module power consumption prediction and control method described in the above-disclosed embodiments, the present invention provides a 4G module power consumption prediction and control system for implementing the 4G module power consumption prediction and control method as described in any one of the first aspects.

[0089] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0090] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0091] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

A method for predicting and controlling the energy consumption of a 1.4G module, characterized in that, include: Monitor the operational data of the 4G module to generate a monitoring feature sequence of the 4G module; Based on the historical database, the monitored feature sequence is subjected to prediction processing to obtain the predicted feature sequence; The operating parameters of the 4G module are controlled accordingly based on the predicted feature sequence.

2. The energy consumption prediction and control method for a 4G module as described in claim 1, characterized in that, The steps of monitoring the operational data of the 4G module to generate a monitoring feature sequence of the 4G module include: Monitor the electrical performance and working status of the 4G module at various times, and record the electrical performance and working status at various times as operating data; The operational data at each moment is processed in a time sequence to generate the raw monitoring information stream of the 4G module; Based on the original monitoring information stream, the electrical performance characteristics of the working state at each moment are analyzed to obtain the operation monitoring characteristics at each moment, and the operation monitoring characteristics at each moment are arranged in time sequence to generate a monitoring feature sequence.

3. The energy consumption prediction and control method for a 4G module as described in claim 2, characterized in that, The steps for analyzing the electrical performance characteristics of the operating status at each moment based on the original monitoring information stream to obtain the operation monitoring characteristics at each moment include: The working status at each moment is analyzed to distinguish between standby status and signal transmission status; The original monitoring information stream is divided into intervals according to the position corresponding to the signal transmission state to obtain a deep monitoring information stream composed of several standby intervals and transmission nodes. Based on the deep monitoring information stream, the electrical performance changes of each standby interval and each transmitting node are analyzed to obtain the electrical change curves in each standby interval and the electrical change data of each transmitting node; Based on the electrical change curve and the electrical change data, the operation characteristics of the standby interval and the transmitting node are analyzed to obtain the operation monitoring characteristics at each time.

4. The energy consumption prediction and control method for a 4G module as described in claim 1, characterized in that, The steps for predicting the monitored feature sequence based on the historical database to obtain the predicted feature sequence include: The time characteristics of signal transmission are analyzed on the monitoring feature sequence to obtain the signal transmission characteristics corresponding to the monitoring feature sequence; The signal transmission characteristics are matched based on the historical database to retrieve historical monitoring feature sequences with consistent signal transmission characteristics as reference information. The monitored feature sequence is processed for future prediction based on the reference information to obtain the predicted feature sequence.

5. The energy consumption prediction and control method for a 4G module as described in claim 4, characterized in that, The steps of performing future prediction processing on the monitored feature sequence based on the reference information to obtain the predicted feature sequence include: The historical monitoring feature sequence is located on the reference information to select a predictive reference part from the reference information and use the predictive reference part as the basic predictive sequence. Based on the monitoring feature sequence, predict the operational performance for future time periods and generate predicted performance features; The basic prediction sequence is adjusted based on the predicted performance characteristics to obtain a prediction feature sequence.

6. The energy consumption prediction and control method for a 4G module as described in claim 5, characterized in that, The steps for predicting operational performance characteristics for future time periods based on the monitored feature sequence include: The monitoring feature sequence is analyzed for the time characteristics of each signal transmission state of the 4G module to obtain the time characteristics of each signal transmission state; wherein, the time characteristics include transmission frequency characteristics and standby duration characteristics; Based on the time characteristics, the potential correlation of the operation monitoring features at each time point is analyzed to obtain the time characteristic influence pattern of the operation monitoring features; Based on the time characteristics, the monitoring feature sequence is used to predict the time characteristics of future time periods to obtain the predicted time characteristics; By combining the aforementioned time characteristic influence pattern with the predicted time characteristics, the operational performance of signal transmission status in future time periods is simulated to generate predicted performance features.

7. The energy consumption prediction and control method for a 4G module as described in claim 5, characterized in that, The step of adjusting the basic prediction sequence based on the predicted performance characteristics to obtain the prediction feature sequence includes: The signal transmission state and time characteristics of the basic prediction sequence are located and analyzed to obtain the prediction monitoring features and corresponding time characteristics of the corresponding signal transmission state in the basic prediction sequence. The time characteristics are analyzed based on the predicted performance characteristics to generate a predicted performance form corresponding to the predicted monitoring characteristics; Based on the predicted performance, each of the predicted monitoring features of the basic predicted sequence is weighted and corrected to obtain a predicted feature sequence.

8. The energy consumption prediction and control method for a 4G module as described in claim 1, characterized in that, The steps for controlling the operating parameters of the 4G module according to the predicted feature sequence include: Based on the predicted feature sequence, an adaptive analysis of various standby modes of the 4G module is performed to obtain the value parameters of each standby mode for the predicted feature sequence. Based on the value parameters, the optimal standby mode is selected for the 4G module to control the operating parameters of the 4G module accordingly and switch the 4G module to the corresponding standby mode. The energy consumption prediction and control system for a 9.4G module is characterized in that, The method for predicting and controlling the energy consumption of a 4G module as described in any one of claims 1-8.

Images