Video equipment energy use optimization system

Abstract

The invention discloses a video equipment energy use optimization system, and relates to the technical field of energy management and energy consumption monitoring. According to the invention, through integrating multiple modules of energy consumption data acquisition, demand model analysis, user behavior analysis, environment monitoring, energy consumption optimization decision, performance prediction and optimization and energy consumption monitoring and evaluation, the energy consumption optimization problem of video equipment in the use process is comprehensively solved; energy consumption data, including voltage and current parameters, of components such as a camera, a microphone and a display screen are monitored in real time through an energy consumption data acquisition module, data compression and encryption processing are carried out to improve transmission efficiency and safety, and then performance and function requirements of equipment are determined through an energy consumption requirement model module according to different use scenes. And an energy consumption threshold value and an adjustment strategy are set to realize dynamic adjustment of energy consumption.

Description

Technical Field

[0001] The invention relates to the technical field of energy management and energy consumption monitoring, and in particular to a video equipment energy use optimization system. Background Art

[0002] Video equipment faces technical challenges in optimizing energy consumption during use. First, video equipment usually contains multiple components, such as cameras, microphones, displays, etc., which consume a lot of energy during operation; second, the usage scenarios of video equipment are diverse, and different scenarios have different requirements for equipment performance and functions, and energy requirements also change accordingly; user usage habits and environmental conditions will also affect the energy consumption of video equipment; therefore, how to monitor the energy consumption of the equipment in real time, dynamically adjust the equipment operation status according to the usage scenario and environmental changes, and maximize energy efficiency while meeting functional requirements is a technical problem that needs to be solved urgently. Summary of the invention

[0003] The purpose of the present invention is to provide a video equipment energy use optimization system to solve the energy consumption optimization problem of video equipment during use.

[0004] The purpose of the present invention can be achieved by the following technical solutions:

[0005] The present application provides a video equipment energy usage optimization system, including an energy consumption data acquisition module, an energy consumption demand model module, a user behavior analysis module, an environment monitoring module, an energy consumption optimization decision module, a performance prediction and optimization module, and an energy consumption monitoring and evaluation module.

[0006] The energy consumption data acquisition module is used to obtain real-time energy consumption data of multiple components of the video equipment, collect voltage and current parameters of each component through energy consumption sensors, and transmit them to the energy management system for analysis and processing;

[0007] The energy consumption demand model module pre-establishes energy consumption demand models according to different video usage scenarios, determines the performance requirements and functional requirements of video equipment in each scenario according to the characteristics of the scenario, and sets corresponding energy consumption thresholds and adjustment strategies.

[0008] The user behavior analysis module is used to obtain the user's usage habit data, model the user's behavior through machine learning algorithms such as support vector machines, predict the user's energy consumption demand change trend, and dynamically generate personalized energy optimization solutions;

[0009] The environmental monitoring module collects temperature and light data of the environment in which the video equipment is located, monitors changes in environmental parameters in real time through sensors, and determines the degree of impact of environmental conditions on equipment energy consumption. When significant changes in the environment are detected, the energy management system is triggered to estimate energy consumption and make optimization decisions;

[0010] The energy consumption optimization decision module integrates and analyzes real-time energy consumption data, scenario requirements, user habits, and environmental factors, and obtains the optimal energy allocation strategy for video equipment through energy consumption optimization algorithms such as evolutionary algorithms, and dynamically adjusts the operating parameters of each component;

[0011] The performance prediction and optimization module, based on the deep learning performance prediction model, evaluates the impact of the optimization strategy on the video quality, weighs the balance between energy consumption and experience through the artificial intelligence algorithm, and selects the best optimization solution;

[0012] The energy consumption monitoring and evaluation module continuously monitors the energy consumption status and performance of video equipment, analyzes the historical trend of energy use through energy consumption statistical algorithms, evaluates the optimization effect of the energy management system, dynamically updates and improves the energy consumption model and optimizes the strategy based on the evaluation results, builds an adaptive energy optimization closed loop, and continuously optimizes the energy consumption of video equipment.

[0013] Furthermore, the energy consumption data collection module includes: selecting energy consumption sensors of appropriate specifications and quantity according to the types of components of the video equipment, and installing them on the power supply lines of each component, real-time collection of energy consumption data of each component, calculating the real-time power data of each component through the voltage and current data collected by the energy consumption sensor, and comparing it with the rated power of the component to determine whether the energy consumption state of the component is normal, and triggering an alarm message when the real-time power of a component exceeds a preset threshold of its rated power;

[0014] The collected energy consumption data is compressed using a data compression algorithm, and the data is encrypted using an encryption algorithm. The compressed and encrypted energy consumption data is transmitted to the energy management system through a wireless or wired network, and the data is decrypted and decompressed to restore the original energy consumption data. A time series analysis algorithm is used to analyze the historical energy consumption data of each component, identify its energy consumption pattern and trend, and predict the energy consumption in the future based on the analysis results; based on the energy consumption data analysis results, an energy consumption report is automatically generated, and the energy consumption of each component is intuitively displayed in the form of visual charts.

[0015] Furthermore, the energy consumption demand model module includes: obtaining the equipment performance demand and function demand data under different video scenes according to the pre-established energy consumption demand model, and using them as the input parameters of the model; then obtaining the energy consumption threshold and adjustment strategy under each video scene by analyzing and calculating the input parameters, and storing them in the strategy database; in the actual video process, collecting the performance parameters and power consumption data of the video equipment in real time, and comparing them with the thresholds in the strategy database;

[0016] When real-time data exceeds the threshold range, the working parameters of the video equipment are dynamically adjusted according to the preset adjustment strategy. After the adjustment, the performance and power consumption data of the video equipment are continuously monitored to determine whether they meet the requirements of the energy consumption demand model. When the adjusted data still does not meet the requirements, the adjustment strategy is optimized or the backup energy-saving plan is started. The energy consumption demand model is regularly updated and optimized according to changes in video scenarios and new needs.

[0017] Furthermore, the user behavior analysis module includes: obtaining habit data such as the duration and frequency of user use of the device, storing the data in a user behavior database, preprocessing the user behavior data, removing abnormal data, extracting key features, constructing a user behavior feature vector, and modeling the user behavior using a support vector machine algorithm based on the user behavior feature vector to obtain a user behavior model;

[0018] Through the user behavior model, the changing trend of the user's energy consumption demand in the future is predicted. When the predicted energy consumption demand shows an upward trend, an energy-saving strategy is generated based on the user's personalized preferences; when the predicted energy consumption demand shows a downward trend, an energy optimization strategy is generated based on the user's personalized preferences; and the generated personalized energy optimization plan is pushed to the user.

[0019] Furthermore, the environment monitoring module includes: by deploying temperature sensors and light sensors in the environment where the video equipment is located, collecting temperature parameters and light parameters of the environment in real time, transmitting the collected temperature parameter and light parameter data to the energy management system, the energy management system determines whether the environment has changed according to a preset environmental parameter threshold, and when it is determined that the environment has changed significantly, the energy management system is triggered to perform energy consumption estimation, and a machine learning algorithm such as a support vector machine or a neural network is used to train an energy consumption estimation model according to historical environmental parameters and equipment energy consumption data;

[0020] The trained energy consumption estimation model is used in combination with the currently collected environmental parameters to predict the energy consumption of video equipment under current environmental conditions. The energy management system uses heuristic optimization algorithms such as genetic algorithms based on the energy consumption estimation results to search for the optimal combination of equipment operating parameters to minimize energy consumption while meeting the performance requirements of the video equipment. The optimized equipment operating parameters are sent to the video equipment to guide the video equipment to dynamically adjust its operating mode. The energy management system then continuously monitors environmental parameters and equipment energy consumption data to optimize the energy consumption of the video equipment in real time.

[0021] Furthermore, the energy consumption optimization decision module includes:

[0022] S11, collecting real-time energy consumption data of video equipment during operation through sensors, and recording light intensity data in the environment, to obtain an energy consumption database and an environment database;

[0023] S12, analyzing the user's behavior of using the video equipment under different ambient light intensities according to the data changes in the energy consumption database and the environmental database, and obtaining a user habit database;

[0024] S13, obtaining data from the user habit database, combining it with the current scenario requirements, building a multi-objective optimization model, taking the video function satisfaction and the whole machine energy consumption as optimization targets, and obtaining the objective function;

[0025] S14. An evolutionary algorithm is used to solve the objective function, and component voltage and component current are used as optimization variables to obtain an optimal solution set that meets the constraints. Based on the operating parameters of each component of the video equipment in the optimal solution set, an energy allocation strategy set is generated to obtain the optimal energy allocation strategy.

[0026] Furthermore, the energy consumption optimization decision module also includes a power management module, which sends the optimal energy allocation strategy to the power management module through the communication interface. After receiving the optimal energy allocation strategy, the power management module obtains the target values ​​of the component voltage and the component current. According to the target values ​​of the component voltage and the component current, the power management module outputs a control signal to the power conversion circuit, dynamically adjusts the voltage and current parameters of each component, and obtains optimized real-time energy consumption data.

[0027] Furthermore, the performance prediction and optimization module includes: collecting multi-dimensional data during the operation of the video service, including frame rate data, resolution data, bit rate data, packet loss rate data, delay data, user subjective rating data and device power consumption data, to obtain the original data set, constructing feature engineering based on the original data set, preprocessing the original data, including data cleaning, data transformation and feature extraction, to obtain a training sample set for the deep learning model; using a long short-term memory network to construct a deep learning model, inputting a training sample set, training the model to obtain a trained deep learning model, outputting a video quality prediction result, obtaining energy consumption data under different strategies by obtaining a variety of energy optimization strategies, including a resolution reduction strategy, a bit rate reduction strategy and a frame rate reduction strategy, predicting the video quality under different strategies according to the trained deep learning model, and obtaining quality prediction data.

[0028] Furthermore, energy consumption data and quality prediction data are processed through a multi-objective optimization algorithm, energy consumption is used as the objective function f1, video quality is used as the objective function f2, and a non-dominated sorting genetic algorithm with an elite strategy is used to solve the problem, thereby obtaining a Pareto optimal solution set; decision information is generated based on the Pareto optimal solution set, and the weight of each solution is calculated using information entropy technology. When the weight of a solution exceeds a preset threshold, the optimization strategy corresponding to the solution is determined as a candidate optimization strategy, and a candidate optimization strategy set is obtained; the user's current network environment information and device status information are obtained, and based on the candidate optimization strategy set, it is determined whether there is an optimization strategy that matches the current network environment and device status. When a matching optimization strategy exists, the optimization strategy is determined as the optimization strategy to be finally executed, and the optimization strategy is output and executed.

[0029] Furthermore, the energy consumption monitoring and evaluation module includes: obtaining network data packets generated by video streams during the operation of the video equipment, marking the acquisition time of each data packet according to the timestamp in the network data packet, obtaining a data packet sequence arranged in chronological order, determining the time interval of each data packet in the data packet sequence according to different timestamps of the data packets in the data packet sequence, accumulating the sizes of multiple data packets in each time interval, and obtaining the workload in each time interval;

[0030] Then obtain the energy consumption value of the video equipment in each time interval, and obtain the unit workload energy consumption in each time interval according to the workload in each time interval and the energy consumption value of the video equipment in each time interval. According to the unit workload energy consumption, workload and energy consumption value, construct an initial energy consumption model of the regression relationship between the three.

[0031] Further, according to the initial energy consumption model, the video stream in the video equipment is obtained, the time stamp corresponding to each frame of the image in the video stream is obtained, the time information of each frame of the image is obtained, and the time difference of each frame of the image is obtained according to the time information of each frame of the image. The size of each frame of the image is accumulated and summed to obtain the image data volume per unit time. When the image data volume per unit time is greater than a preset threshold, it is determined that the encoding efficiency of the current video stream encoder is abnormal, the image resolution and frame rate in the video stream are obtained, and the encoder parameters are adjusted according to the resolution and frame rate.

[0032] According to the adjusted encoder parameters and decoder parameters, the image data volume per unit time is collected, the reduction ratio of the image data volume per unit time is determined, the image data volume change rate per unit time is obtained according to the image data volume reduction ratio, the image data volume change rate per unit time and the image data volume per unit time are obtained according to the image data volume change rate per unit time and the image data volume per unit time, and an updated energy consumption model is obtained according to the change relationship function between the two and the initial energy consumption model;

[0033] According to the updated energy consumption model, the real-time energy consumption prediction value is obtained. According to the real-time energy consumption prediction value and the real-time energy consumption value, the difference is obtained. When the difference is greater than the preset threshold, it is judged that the accuracy of the energy consumption model is reduced, and the packet loss rate is collected again. When the packet loss rate is greater than the preset threshold, it is judged that the current network status is abnormal, and the initial energy consumption model parameters are adjusted according to the packet loss rate.

[0034] The beneficial effects of the present invention are:

[0035] By comprehensively applying multiple modules such as energy consumption data collection, demand model analysis, user behavior analysis, environmental monitoring, energy consumption optimization decision-making, performance prediction and optimization, and energy consumption monitoring and evaluation, the energy consumption optimization problem of video equipment during use is comprehensively solved. The energy consumption data collection module monitors the energy consumption data of components such as cameras, microphones, and display screens in real time, including voltage and current parameters, and performs data compression and encryption processing to improve transmission efficiency and security. Then, the energy consumption demand model module determines the performance and functional requirements of the equipment according to different usage scenarios, and sets energy consumption thresholds and adjustment strategies to achieve dynamic adjustment of energy consumption. On the one hand, it improves energy utilization efficiency, reduces energy waste and overall energy consumption by accurately controlling the energy consumption of each component. On the other hand, it improves the level of intelligent energy management, makes energy consumption more adapted to actual needs, and achieves efficient energy utilization and environmental protection structure optimization. It not only solves the energy consumption optimization problem mentioned in the background technology, but also provides strong technical support for achieving sustainable development goals. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0037] Figure 1 A schematic diagram of the structure of a video equipment energy usage optimization system provided in this application;

[0038] Figure 2 A flow chart of an energy consumption optimization decision module of a video equipment energy usage optimization system provided in this application. DETAILED DESCRIPTION

[0039] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.

[0040] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0041] The specific implementation methods, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0042] See also Figure 1-Figure 2 This embodiment provides a video equipment energy usage optimization system, including an energy consumption data acquisition module, an energy consumption demand model module, a user behavior analysis module, an environment monitoring module, an energy consumption optimization decision module, a performance prediction and optimization module, and an energy consumption monitoring and evaluation module.

[0043] Energy consumption data collection module, used to obtain real-time energy consumption data of multiple components of video equipment, including cameras, microphones, display screens, etc., collect voltage and current parameters of each component through energy consumption sensors, and transmit them to the energy management system for analysis and processing;

[0044] Furthermore, the energy consumption data acquisition module includes: selecting energy consumption sensors of appropriate specifications and quantity according to the types of components of the video equipment, and installing them on the power supply lines of each component, real-time collection of energy consumption data of each component, calculating the real-time power data of each component through the voltage and current data collected by the energy consumption sensor, and comparing it with the rated power of the component to determine whether the energy consumption status of the component is normal; when the real-time power of a component exceeds the preset threshold of its rated power, an alarm message is triggered to prompt relevant personnel to conduct inspections and maintenance to avoid damage caused by component overload.

[0045] The collected energy consumption data is compressed using a data compression algorithm to reduce the data volume and improve data transmission efficiency. The data is encrypted using an encryption algorithm to ensure the security of the data transmission process. The compressed and encrypted energy consumption data is transmitted to the energy management system via a wireless or wired network, and the data is decrypted and decompressed to restore the original energy consumption data. A time series analysis algorithm is used to analyze the historical energy consumption data of each component to identify its energy consumption pattern and trend, and based on the analysis results, the energy consumption in the future is predicted to provide a basis for energy optimization. Based on the energy consumption data analysis results, an energy consumption report is automatically generated, and the energy consumption of each component is intuitively displayed in the form of visual charts, which is convenient for managers to understand the energy usage of the equipment and promptly discover and solve abnormal energy consumption problems.

[0046] Specifically, by integrating the energy consumption data acquisition module, real-time energy consumption data collection of key components such as cameras, microphones, and displays is realized, including voltage and current parameters, and data compression and encryption are performed to improve transmission efficiency and security. The system can identify energy consumption patterns and trends through time series analysis algorithms, predict future energy consumption, and automatically generate visual energy consumption reports to help managers intuitively understand the energy usage of equipment, promptly discover and solve energy consumption anomalies, thereby optimizing energy use and improving equipment operation efficiency and reliability.

[0047] The energy consumption demand model module pre-establishes energy consumption demand models according to different video usage scenarios. According to the characteristics of scenarios such as conferences, distance learning, and medical consultations, it determines the performance and functional requirements of video equipment in each scenario, and sets corresponding energy consumption thresholds and adjustment strategies. The energy consumption threshold refers to the maximum allowable power consumption of each component in different scenarios, and the adjustment strategy includes specific measures such as component power regulation and sleep activation.

[0048] Furthermore, the energy consumption demand model module includes: obtaining the equipment performance demand and function demand data under different video scenes according to the pre-established energy consumption demand model, and using them as the input parameters of the model; then obtaining the energy consumption threshold and adjustment strategy under each video scene by analyzing and calculating the input parameters, and storing them in the strategy database; in the actual video process, collecting the performance parameters and power consumption data of the video equipment in real time, and comparing them with the thresholds in the strategy database;

[0049] When real-time data exceeds the threshold range, the working parameters of the video equipment are dynamically adjusted according to the preset adjustment strategy, such as lowering the encoding and decoding resolution, reducing the transmission bandwidth, etc., to control energy consumption. After the adjustment, the performance and power consumption data of the video equipment are continuously monitored to determine whether they meet the requirements of the energy consumption demand model. When the adjusted data still does not meet the requirements, the adjustment strategy is further optimized, or alternative energy-saving solutions are activated, such as shutting down non-essential functions, using low-power mode, etc.; according to changes in video scenarios and new needs, the energy consumption demand model is regularly updated and optimized to ensure that it is adapted to actual applications.

[0050] Specifically, through the pre-established energy consumption demand model, according to the characteristics of different video scenarios (such as meetings, distance learning, and medical consultations), the performance and functional requirements of the equipment are determined, and energy consumption thresholds and adjustment strategies are set. In actual applications, the module collects device performance and power consumption data in real time and compares it with the preset thresholds. Once it exceeds the range, it dynamically adjusts the working parameters to control energy consumption, such as reducing resolution or bandwidth. After adjustment, the system continuously monitors performance and power consumption to ensure that it meets the model requirements. If it is still not met, it further optimizes the strategy or starts the energy-saving plan. In addition, the module will regularly update the model according to scene changes and new requirements to maintain its adaptability and effectiveness, so that video equipment can optimize energy consumption and improve energy efficiency while meeting functional requirements.

[0051] User behavior analysis module, which is used to obtain user usage habit data, including usage duration, usage frequency, etc., and use machine learning algorithms such as support vector machines to model user behavior, predict the changing trend of user energy consumption demand, and dynamically generate personalized energy optimization solutions;

[0052] Furthermore, the user behavior analysis module includes: obtaining habit data such as the duration and frequency of user use of the device, storing the data in a user behavior database, preprocessing the user behavior data, removing abnormal data, extracting key features, constructing a user behavior feature vector, and modeling the user behavior using a support vector machine algorithm based on the user behavior feature vector to obtain a user behavior model;

[0053] Through the user behavior model, the changing trend of the user's energy consumption demand in the future is predicted. When the predicted energy consumption demand shows an upward trend, energy-saving strategies are generated according to the user's personalized preferences, such as regularly shutting down idle equipment. When the predicted energy consumption demand shows a downward trend, energy optimization strategies are generated according to the user's personalized preferences, such as appropriately raising the air-conditioning temperature. The generated personalized energy optimization plan is then pushed to the user to guide the user to take corresponding measures to achieve the goal of energy saving and efficiency improvement.

[0054] Specifically, by collecting and storing habitual data such as the duration and frequency of user device use, and using machine learning algorithms such as support vector machines to preprocess and extract features from these data, a user behavior model is constructed. This model can predict the changing trend of users' future energy consumption needs, and dynamically generate personalized energy optimization plans such as timing to shut down idle devices or appropriately raising the air conditioning temperature based on the prediction results and the user's personalized preferences. By pushing these plans to users, they are guided to take energy-saving measures, thereby achieving the goals of efficient energy utilization and energy conservation and emission reduction.

[0055] The environmental monitoring module collects data such as temperature and light in the environment where the video equipment is located. It uses sensors to monitor changes in environmental parameters in real time to determine the degree of impact of environmental conditions on equipment energy consumption. When significant changes in the environment are detected, the energy management system is triggered to estimate energy consumption and make optimization decisions.

[0056] Furthermore, the environmental monitoring module includes: by deploying temperature sensors and light sensors in the environment where the video equipment is located, the temperature parameters and light parameters of the environment are collected in real time, and the collected temperature parameter and light parameter data are transmitted to the energy management system. The energy management system determines whether the environment has changed significantly based on preset environmental parameter thresholds. When it is determined that the environment has changed significantly, the energy management system is triggered to perform energy consumption estimation, and a machine learning algorithm such as a support vector machine or a neural network is used to train an energy consumption estimation model based on historical environmental parameters and equipment energy consumption data.

[0057] The trained energy consumption estimation model is used in combination with the currently collected environmental parameters to predict the energy consumption of video equipment under current environmental conditions. The energy management system uses heuristic optimization algorithms such as genetic algorithms based on the energy consumption estimation results to search for the optimal combination of equipment operating parameters to minimize energy consumption while meeting the performance requirements of the video equipment. The optimized equipment operating parameters are sent to the video equipment to guide the video equipment to dynamically adjust its operating mode to achieve energy consumption optimization under changing environmental conditions. The energy management system then continuously monitors environmental parameters and equipment energy consumption data to achieve real-time optimization of the energy consumption of video equipment.

[0058] Specifically, by deploying temperature and light sensors to collect the parameters of the environment in which the video equipment is located in real time, and transmitting the data to the energy management system, the system determines environmental changes based on preset thresholds and triggers energy consumption estimation. The energy consumption estimation model trained by the machine learning algorithm is combined with the current environmental parameters to predict the energy consumption of the equipment, and then the optimal combination of operating parameters is found through heuristic optimization algorithms such as genetic algorithms to minimize energy consumption while meeting performance requirements. The optimized parameters are sent to the device to guide it to dynamically adjust the operating mode to achieve energy consumption optimization. At the same time, the system continuously monitors the environment and energy consumption data to achieve real-time energy consumption optimization of video equipment under changing environmental conditions and improve energy efficiency.

[0059] The energy consumption optimization decision module integrates and analyzes multi-source information such as real-time energy consumption data, scenario requirements, user habits, environmental factors, etc., and obtains the optimal energy allocation strategy for video equipment through energy consumption optimization algorithms such as evolutionary algorithms. It dynamically adjusts the operating parameters such as the operating voltage and current of each component to reduce the energy consumption of the entire machine while meeting the video function requirements. The evolutionary algorithm takes minimizing total energy consumption as the optimization goal and optimizes the component parameter configuration through iteration.

[0060] Furthermore, the energy consumption optimization decision module includes:

[0061] S11, collecting real-time energy consumption data of video equipment during operation through sensors, and recording light intensity data in the environment, to obtain an energy consumption database and an environment database;

[0062] S12, analyzing the user's behavior of using the video equipment under different ambient light intensities according to the data changes in the energy consumption database and the environmental database, and obtaining a user habit database;

[0063] S13, obtaining data from the user habit database, combining it with the current scenario requirements, building a multi-objective optimization model, taking the video function satisfaction and the whole machine energy consumption as optimization targets, and obtaining the objective function;

[0064] S14. An evolutionary algorithm is used to solve the objective function, and component voltage and component current are used as optimization variables to obtain an optimal solution set that meets the constraints. Based on the operating parameters of each component of the video equipment in the optimal solution set, an energy allocation strategy set is generated to obtain the optimal energy allocation strategy.

[0065] Furthermore, the energy consumption optimization decision module also includes a power management module, which sends the optimal energy allocation strategy to the power management module through the communication interface. After receiving the optimal energy allocation strategy, the power management module obtains the target values ​​of the component voltage and the component current. According to the target values ​​of the component voltage and the component current, the power management module outputs a control signal to the power conversion circuit, dynamically adjusts the voltage and current parameters of each component, and obtains optimized real-time energy consumption data.

[0066] Specifically, by collecting real-time energy consumption data and ambient light intensity during the operation of video equipment, analyzing user behavior habits under different light intensities, and combining the current scene requirements to build a multi-objective optimization model, the video function satisfaction and the energy consumption of the whole machine are used as optimization targets. The evolutionary algorithm is used to solve the objective function, dynamically adjust the operating parameters such as component voltage and current, generate the optimal energy allocation strategy, and implement these strategies through the power management module to achieve energy consumption reduction while meeting the video function requirements. This process not only optimizes energy efficiency, but also ensures the energy efficiency and performance of video equipment in different environments, minimizing energy consumption and optimizing equipment performance.

[0067] Performance prediction and optimization module, based on deep learning performance prediction model, evaluates the impact of optimization strategy on video quality, weighs the balance between energy consumption and experience through artificial intelligence algorithm, selects the best optimization solution that takes into account both energy saving and quality, and ensures high-quality video service while minimizing energy consumption;

[0068] Furthermore, the performance prediction and optimization module includes: collecting multi-dimensional data during the operation of the video service, including frame rate data, resolution data, bit rate data, packet loss rate data, delay data, user subjective rating data, and device power consumption data to obtain the original data set, constructing feature engineering based on the original data set, and preprocessing the original data, including data cleaning, data transformation, and feature extraction, to obtain a training sample set for the deep learning model; using a long short-term memory network to construct a deep learning model, inputting a training sample set, training the model to obtain a trained deep learning model, outputting a video quality prediction result, and obtaining energy consumption data under different strategies by obtaining a variety of energy optimization strategies, including a resolution reduction strategy, a bit rate reduction strategy, and a frame rate reduction strategy, and predicting the video quality under different strategies according to the trained deep learning model to obtain quality prediction data.

[0069] Furthermore, energy consumption data and quality prediction data are processed through a multi-objective optimization algorithm, energy consumption is used as the objective function f1, video quality is used as the objective function f2, and a non-dominated sorting genetic algorithm with an elite strategy is used to solve the problem, thereby obtaining a Pareto optimal solution set; decision information is generated based on the Pareto optimal solution set, and the weight of each solution is calculated using information entropy technology. When the weight of a solution exceeds a preset threshold, the optimization strategy corresponding to the solution is determined as a candidate optimization strategy, and a candidate optimization strategy set is obtained; the user's current network environment information and device status information are obtained, and based on the candidate optimization strategy set, it is determined whether there is an optimization strategy that matches the current network environment and device status. When a matching optimization strategy exists, the optimization strategy is determined as the optimization strategy to be finally executed, and the optimization strategy is output and executed.

[0070] Specifically, by collecting multi-dimensional data during the operation of video services, a deep learning model is constructed to predict the video quality under different energy optimization strategies, and combined with energy consumption data, a multi-objective optimization algorithm is used to find the Pareto optimal solution set between energy consumption and video quality. The weight of the solution is calculated through information entropy technology, the candidate optimization strategy set is determined, and the final optimization strategy is selected based on the user's current network environment and device status to achieve the best balance between energy saving and experience while minimizing energy consumption while ensuring the quality of video services.

[0071] The energy consumption monitoring and evaluation module continuously monitors the energy consumption status and performance of video equipment, analyzes the historical trend of energy use through energy consumption statistical algorithms, evaluates the optimization effect of the energy management system, dynamically updates and improves energy consumption models and optimization strategies based on the evaluation results, builds an adaptive energy optimization closed loop, and achieves continuous optimization of energy consumption of video equipment.

[0072] Furthermore, the energy consumption monitoring and evaluation module includes: obtaining network data packets generated by video streams during the operation of the video equipment, marking the acquisition time of each data packet according to the timestamp in the network data packet, obtaining a data packet sequence arranged in chronological order, determining the time interval of each data packet in the data packet sequence according to different timestamps of the data packets in the data packet sequence, accumulating the sizes of multiple data packets in each time interval, and obtaining the workload in each time interval;

[0073] Then obtain the energy consumption value of the video equipment in each time interval, and obtain the unit workload energy consumption in each time interval according to the workload in each time interval and the energy consumption value of the video equipment in each time interval. According to the unit workload energy consumption, workload, and energy consumption value, an initial energy consumption model of the regression relationship between the three is constructed.

[0074] Further, according to the initial energy consumption model, the video stream in the video equipment is obtained, the time stamp corresponding to each frame of the image in the video stream is obtained, the time information of each frame of the image is obtained, and the time difference of each frame of the image is obtained according to the time information of each frame of the image. The size of each frame of the image is accumulated and summed to obtain the image data volume per unit time. When the image data volume per unit time is greater than a preset threshold, it is determined that the encoding efficiency of the current video stream encoder is abnormal, the image resolution and frame rate in the video stream are obtained, and the encoder parameters are adjusted according to the resolution and frame rate.

[0075] According to the adjusted encoder parameters and decoder parameters, the image data volume per unit time is collected, the reduction ratio of the image data volume per unit time is determined, the image data volume change rate per unit time is obtained according to the image data volume reduction ratio, the image data volume change rate per unit time and the image data volume per unit time are obtained according to the image data volume change rate per unit time and the image data volume per unit time, and an updated energy consumption model is obtained according to the change relationship function between the two and the initial energy consumption model;

[0076] According to the updated energy consumption model, the real-time energy consumption prediction value is obtained. According to the real-time energy consumption prediction value and the real-time energy consumption value, the difference is obtained. When the difference is greater than the preset threshold, it is judged that the accuracy of the energy consumption model is reduced, and the packet loss rate is collected again. When the packet loss rate is greater than the preset threshold, it is judged that the current network status is abnormal, and the initial energy consumption model parameters are adjusted according to the packet loss rate.

[0077] Specifically, by continuously monitoring the energy consumption status and performance of video equipment, analyzing historical energy usage trends, evaluating the optimization effect of the energy management system, and dynamically updating the energy consumption model and optimization strategy based on the evaluation results, the energy consumption per unit workload is calculated by analyzing the timestamp and size of network data packets, building an initial energy consumption model, and adjusting the model parameters based on the encoding efficiency of the video stream and the network status. By comparing the real-time energy consumption prediction and the actual energy consumption value, the model accuracy is evaluated, and the model is adjusted under network anomalies such as packet loss rate, so as to achieve continuous optimization and adaptive adjustment of the energy consumption model and ensure the optimization of the energy consumption of video equipment.

[0078] By integrating intelligent sensors, energy monitoring software and efficient power management algorithms, the energy consumption of the device is monitored in real time, and the operating status of the device is automatically adjusted, such as reducing resolution, shutting down unused components or entering sleep mode to reduce energy consumption. At the same time, the system can also predict energy demand based on usage patterns and environmental changes, optimize energy distribution, and ensure that the device achieves maximum energy efficiency while meeting functional requirements.

[0079] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A video equipment energy usage optimization system, characterized by: It includes energy consumption data acquisition module, energy consumption demand model module, user behavior analysis module, environmental monitoring module, energy consumption optimization decision module, performance prediction and optimization module and energy consumption monitoring and evaluation module. The energy consumption data acquisition module is used to obtain real-time energy consumption data of multiple components of the video equipment, collect voltage and current parameters of each component through energy consumption sensors, and transmit them to the energy management system for analysis and processing; The energy consumption demand model module pre-establishes energy consumption demand models according to different video usage scenarios, determines the performance requirements and functional requirements of video equipment in each scenario according to the characteristics of the scenario, and sets corresponding energy consumption thresholds and adjustment strategies. The user behavior analysis module is used to obtain the user's usage habit data, model the user's behavior through machine learning algorithms such as support vector machines, predict the user's energy consumption demand change trend, and dynamically generate personalized energy optimization solutions; The environmental monitoring module collects temperature and light data of the environment in which the video equipment is located, monitors changes in environmental parameters in real time through sensors, and determines the degree of impact of environmental conditions on equipment energy consumption. When significant changes in the environment are detected, the energy management system is triggered to estimate energy consumption and make optimization decisions; The energy consumption optimization decision module integrates and analyzes real-time energy consumption data, scenario requirements, user habits, and environmental factors, and obtains the optimal energy allocation strategy for video equipment through energy consumption optimization algorithms such as evolutionary algorithms, and dynamically adjusts the operating parameters of each component; The performance prediction and optimization module, based on the deep learning performance prediction model, evaluates the impact of the optimization strategy on the video quality, weighs the balance between energy consumption and experience through the artificial intelligence algorithm, and selects the best optimization solution; The energy consumption monitoring and evaluation module continuously monitors the energy consumption status and performance of video equipment, analyzes the historical trend of energy use through energy consumption statistical algorithms, evaluates the optimization effect of the energy management system, dynamically updates and improves the energy consumption model and optimizes the strategy based on the evaluation results, builds an adaptive energy optimization closed loop, and continuously optimizes the energy consumption of video equipment.

2. The video equipment energy usage optimization system according to claim 1, characterized in that: The energy consumption demand model module includes: obtaining the equipment performance demand and function demand data under different video scenes according to the pre-established energy consumption demand model, and taking it as the input parameter of the model; then obtaining the energy consumption threshold and adjustment strategy under each video scene by analyzing and calculating the input parameters, and storing it in the strategy database; in the actual video process, collecting the performance parameters and power consumption data of the video equipment in real time, and comparing it with the threshold in the strategy database; When real-time data exceeds the threshold range, the working parameters of the video equipment are dynamically adjusted according to the preset adjustment strategy. After the adjustment, the performance and power consumption data of the video equipment are continuously monitored to determine whether they meet the requirements of the energy consumption demand model. When the adjusted data still does not meet the requirements, the adjustment strategy is optimized or the backup energy-saving plan is started. The energy consumption demand model is regularly updated and optimized according to changes in video scenarios and new needs.

3. The video equipment energy usage optimization system according to claim 1, characterized in that: The user behavior analysis module includes: obtaining the duration and frequency habit data of the user's use of the device, storing it in the user behavior database, preprocessing the user behavior data, removing abnormal data, extracting key features, constructing a user behavior feature vector, and using a support vector machine algorithm to model the user behavior based on the user behavior feature vector to obtain a user behavior model; Through the user behavior model, the changing trend of the user's energy consumption demand in the future is predicted. When the predicted energy consumption demand shows an upward trend, an energy-saving strategy is generated based on the user's personalized preferences; when the predicted energy consumption demand shows a downward trend, an energy optimization strategy is generated based on the user's personalized preferences; and the generated personalized energy optimization plan is pushed to the user.

4. The video equipment energy usage optimization system according to claim 1, characterized in that: The environment monitoring module includes: deploying temperature sensors and light sensors in the environment where the video equipment is located, collecting temperature parameters and light parameters of the environment in real time, transmitting the collected temperature parameter and light parameter data to the energy management system, and the energy management system determines whether the environment has changed according to a preset environmental parameter threshold. When it is determined that the environment has changed significantly, the energy management system is triggered to estimate energy consumption, and a machine learning algorithm such as a support vector machine or a neural network is used to train an energy consumption estimation model based on historical environmental parameters and equipment energy consumption data; The trained energy consumption estimation model is used in combination with the currently collected environmental parameters to predict the energy consumption of video equipment under current environmental conditions. The energy management system uses heuristic optimization algorithms such as genetic algorithms based on the energy consumption estimation results to search for the optimal combination of equipment operating parameters to minimize energy consumption while meeting the performance requirements of the video equipment. The optimized equipment operating parameters are sent to the video equipment to guide the video equipment to dynamically adjust its operating mode. The energy management system then continuously monitors environmental parameters and equipment energy consumption data to optimize the energy consumption of the video equipment in real time.

5. The video equipment energy usage optimization system according to claim 1, characterized in that: The energy consumption optimization decision module includes: The real-time energy consumption data of video equipment during operation is collected through sensors, and the light intensity data in the environment is recorded to obtain the energy consumption database and the environment database; According to the data changes in the energy consumption database and the environmental database, the user's behavior of using video equipment under different ambient light intensities is analyzed to obtain a user habit database; Then, we obtain data from the user habit database, combine it with the current scenario requirements, build a multi-objective optimization model, take the video function satisfaction and the whole machine energy consumption as the optimization objectives, and get the objective function; An evolutionary algorithm is used to solve the objective function, and the component voltage and component current are used as optimization variables to obtain the optimal solution set that meets the constraints. According to the operating parameters of each component of the video equipment in the optimal solution set, an energy allocation strategy set is generated to obtain the optimal energy allocation strategy.

6. The video equipment energy usage optimization system according to claim 1, characterized in that: The energy consumption optimization decision module also includes a power management module, which sends the optimal energy allocation strategy to the power management module through the communication interface. After receiving the optimal energy allocation strategy, the power management module obtains the target values ​​of the component voltage and the component current. According to the target values ​​of the component voltage and the component current, the power management module outputs a control signal to the power conversion circuit, dynamically adjusts the voltage and current parameters of each component, and obtains optimized real-time energy consumption data.

7. The video equipment energy usage optimization system according to claim 1, characterized in that: The performance prediction and optimization module includes: collecting multi-dimensional data during the operation of the video service, including frame rate data, resolution data, bit rate data, packet loss rate data, delay data, user subjective rating data and device power consumption data, to obtain the original data set, constructing feature engineering based on the original data set, preprocessing the original data, including data cleaning, data transformation and feature extraction, to obtain a training sample set of the deep learning model; using a long short-term memory network to construct a deep learning model, inputting a training sample set, training the model, obtaining a trained deep learning model, outputting a video quality prediction result, obtaining energy consumption data under different strategies by obtaining a variety of energy optimization strategies, including a resolution reduction strategy, a bit rate reduction strategy and a frame rate reduction strategy, predicting the video quality under different strategies according to the trained deep learning model, and obtaining quality prediction data.

8. The video equipment energy usage optimization system according to claim 7, characterized in that: The energy consumption data and quality prediction data are processed by a multi-objective optimization algorithm, with energy consumption as the objective function f1 and video quality as the objective function f2. A non-dominated sorting genetic algorithm with an elite strategy is used to solve the problem and obtain a Pareto optimal solution set. Decision information is generated based on the Pareto optimal solution set, and the weight of each solution is calculated using information entropy technology. When the weight of a solution exceeds a preset threshold, the optimization strategy corresponding to the solution is determined as a candidate optimization strategy, and a candidate optimization strategy set is obtained. Obtain the user's current network environment information and device status information, and determine whether there is an optimization strategy that matches the current network environment and device status based on the candidate optimization strategy set. If there is a matching optimization strategy, the optimization strategy is determined as the optimization strategy to be finally executed, and the optimization strategy is output and executed.

9. The video equipment energy usage optimization system according to claim 1, characterized in that: The energy consumption monitoring and evaluation module includes: obtaining network data packets generated by video streams during the operation of video equipment, marking the acquisition time of each data packet according to the timestamp in the network data packet, obtaining a data packet sequence arranged in chronological order, determining the time interval of each data packet in the data packet sequence according to different timestamps of the data packets in the data packet sequence, accumulating the sizes of multiple data packets in each time interval, and obtaining the workload in each time interval; Then obtain the energy consumption value of the video equipment in each time interval, and obtain the unit workload energy consumption in each time interval according to the workload in each time interval and the energy consumption value of the video equipment in each time interval. According to the unit workload energy consumption, workload and energy consumption value, construct an initial energy consumption model of the regression relationship between the three.

10. The video equipment energy usage optimization system according to claim 9, characterized in that: According to the initial energy consumption model, the video stream of the video equipment in operation is obtained, and the corresponding timestamp of each frame image in the video stream is obtained to obtain the time information of each frame image. According to the time information of each frame image, the time difference of each frame image is obtained, and the image data volume per unit time is obtained by accumulating and summing the size of each frame image. When the image data volume per unit time is greater than the preset threshold, it is determined that the encoding efficiency of the current video stream encoder is abnormal, and the image resolution and frame rate in the video stream are obtained, and the encoder parameters are adjusted according to the resolution and frame rate; According to the adjusted encoder parameters and decoder parameters, the image data volume per unit time is collected, the reduction ratio of the image data volume per unit time is determined, the image data volume change rate per unit time is obtained according to the image data volume reduction ratio, the image data volume change rate per unit time and the image data volume per unit time are obtained according to the image data volume change rate per unit time and the image data volume per unit time, and an updated energy consumption model is obtained according to the change relationship function between the two and the initial energy consumption model; According to the updated energy consumption model, the real-time energy consumption prediction value is obtained. According to the real-time energy consumption prediction value and the real-time energy consumption value, the difference is obtained. When the difference is greater than the preset threshold, it is judged that the accuracy of the energy consumption model is reduced, and the packet loss rate is collected again. When the packet loss rate is greater than the preset threshold, it is judged that the current network status is abnormal, and the initial energy consumption model parameters are adjusted according to the packet loss rate.

Images