Dynamic voltage frequency regulation control method and device of audio system and electronic equipment

Abstract

The invention provides a dynamic voltage frequency regulation control method and device of an audio system and electronic equipment, and belongs to the technical field of audio processing. The method comprises the following steps: determining a comprehensive weight of each resource request according to a basic performance weight, a QoS weight and a scene adaptation factor of each resource request; obtaining a weighted value of each resource request according to the request value of each resource request and the comprehensive weight, and taking the resource request corresponding to the maximum weighted value as an arbitration result; selecting a plurality of candidate working points according to the request value of the arbitration result; obtaining an energy efficiency ratio of each candidate working point, and multiplying the energy efficiency ratio of each candidate working point by the temperature correction coefficient to obtain a final energy efficiency score of each candidate working point; and determining an optimal working point according to the final energy efficiency score of each candidate working point, and switching to a target voltage frequency state according to the optimal working point. Therefore, in a complex application scene, the optimal energy efficiency performance and the cruising ability of the audio system are improved, and meanwhile, the user experience is guaranteed.

Description

Technical Field

[0001] This application relates to the field of audio processing technology, and in particular to a dynamic voltage frequency adjustment control method, device and electronic device for an audio system. Background Technology

[0002] With the widespread use of smart terminal devices such as smartphones, tablets, smart speakers, and wearable devices, users' demands for audio experience are constantly increasing. In various application scenarios, including voice calls, music playback, video viewing, virtual reality, and augmented reality, high-quality audio output has become one of the important indicators for measuring device performance. To this end, modern audio systems typically integrate a variety of audio processing technologies, such as noise suppression, echo cancellation, dynamic range control, spatial sound rendering, and adaptive equalization, to improve the clarity, immersion, and realism of the sound.

[0003] Meanwhile, due to limitations in battery capacity, heat dissipation, and computing resources, the overall power consumption and performance management of terminal devices become particularly critical. Especially in mobile scenarios, processor load, memory usage, and power consumption must be comprehensively considered to maintain stable device operation and extended battery life. Currently, most audio systems employ static or semi-dynamic configuration strategies, making it difficult to flexibly adjust audio processing intensity and resource allocation under different usage environments. For example, continuing to use high-intensity noise reduction algorithms in quiet environments, or continuing to run highly complex spatial audio rendering when the battery is low, leads to unnecessary waste of computing power and increased energy consumption.

[0004] Furthermore, existing audio systems largely rely on preset scene selection or manual user intervention for mode switching, lacking real-time perception and intelligent response capabilities to environmental changes, usage status, and system load. Therefore, when facing diverse and dynamically changing application scenarios, existing technologies cannot achieve synergistic optimization between audio quality, system performance, and energy efficiency. This often results in situations where pursuing high-fidelity sound quality significantly shortens battery life, or advanced audio functions are forcibly disabled to reduce power consumption, thus impacting the listening experience. Summary of the Invention

[0005] To address the aforementioned technical problems, this application provides a dynamic voltage frequency regulation control method, apparatus, and electronic device for an audio system.

[0006] In a first aspect, the present invention provides a dynamic voltage frequency regulation control method for an audio system, the method comprising: A dynamic weighted arbitration algorithm is used to determine the comprehensive weight of each resource request based on its basic performance weight, QoS weight, and scenario adaptation factor. The weighted value of each resource request is obtained based on the request value of each resource request and the comprehensive weight, and the resource request corresponding to the maximum weighted value is taken as the arbitration result. Based on the requested values ​​of the arbitration results, multiple candidate operating points that meet the performance requirements are selected, where the requested values ​​of the arbitration results include voltage and frequency; The energy efficiency ratio of each candidate operating point is obtained, and the energy efficiency ratio of each candidate operating point is multiplied by the temperature correction factor to obtain the final energy efficiency score of each candidate operating point. The optimal operating point is determined based on the final energy efficiency score of each candidate operating point, and the target voltage and frequency state is switched based on the optimal operating point.

[0007] In an optional implementation, the step of using a dynamic weighted arbitration algorithm to determine the comprehensive weight of each resource request based on its basic performance weight, QoS weight, and scenario adaptation factor includes: The basic performance weight is determined based on the request value of each resource request; The QoS weights are determined based on latency weights, throughput weights, and audio quality weights. The scenario adaptation factor is determined based on the audio stream characteristics and the application scenario; The product of the basic performance weight, the QoS weight, and the scenario adaptation factor is determined as the comprehensive weight.

[0008] In an optional implementation, determining the basic performance weight based on the request value of each resource request includes: The basic performance weights are obtained by mapping the request values ​​using a non-linear function. The process of determining the QoS weight based on latency weight, throughput weight, and audio quality weight includes: The QoS weight is obtained by weighting the first weight coefficient, the latency weight, the second weight coefficient, the throughput weight, the third weight coefficient, and the sound quality weight. The sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1, and the values ​​of the first weight coefficient, the second weight coefficient, and the third weight coefficient are adjusted according to the application scenario.

[0009] In an optional implementation, the nonlinear function includes:

[0010] J represents the basic performance weight. This represents the adjustment coefficient. Indicates each resource request The requested value, This represents the intermediate operating value of the audio system; The delay weight is calculated using the following formula:

[0011] Where YC represents the delay weight, DQY represents the current delay, and ZDY represents the maximum allowable delay; The throughput weight is calculated using the following formula:

[0012] TT represents the throughput weight. This indicates the current throughput demand. Indicates maximum throughput capability; The sound quality weights are calculated using the following formula:

[0013] This represents the sound quality weight. Indicates the sound quality level.

[0014] In an optional implementation, determining the scene adaptation factor based on audio stream characteristics and application scenario includes: The scene adaptation factor is determined based on the audio stream features, the application scenario, and the scene factor mapping table. The scenario adaptation factor is dynamically adjusted based on the system load.

[0015] In an optional implementation, the step of switching to the target voltage frequency state based on the optimal operating point includes: When performing a frequency upsampling operation, a voltage margin is set until the voltage is increased to a stable level before increasing the frequency. When performing a frequency reduction operation, the frequency is reduced until it reaches a stable frequency, and then the voltage is reduced.

[0016] In an optional implementation, the setting of the voltage margin includes: The static margin is determined based on the base voltage offset and frequency step compensation. The temperature margin is determined based on the temperature coefficient, the current temperature, and the reference temperature. The voltage margin is determined based on the static margin and the temperature margin.

[0017] In a second aspect, the present invention provides a dynamic voltage frequency adjustment control device for an audio system, the device comprising: The determination module is used to determine the comprehensive weight of each resource request based on the basic performance weight, QoS weight, and scenario adaptation factor of each resource request using a dynamic weighted arbitration algorithm. The first acquisition module is used to acquire the weighted value of each resource request based on the request value of each resource request and the comprehensive weight, and take the resource request corresponding to the maximum weighted value as the arbitration result; The selection module is used to select multiple candidate operating points that meet the performance requirements based on the requested values ​​of the arbitration result, wherein the requested values ​​of the arbitration result include voltage and frequency; The second acquisition module is used to acquire the energy efficiency ratio of each candidate operating point, multiply the energy efficiency ratio of each candidate operating point by the temperature correction coefficient, and obtain the final energy efficiency score of each candidate operating point. The switching module is used to determine the optimal operating point based on the final energy efficiency score of each candidate operating point, and to switch to the target voltage frequency state based on the optimal operating point.

[0018] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the computer program executes the dynamic voltage frequency adjustment control method of the audio system described in the foregoing embodiments when the processor is running.

[0019] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when run on a processor, executes the dynamic voltage frequency adjustment control method for the audio system described in the foregoing embodiments.

[0020] The dynamic voltage and frequency adjustment control method for audio systems provided in this application employs a dynamic weighted arbitration algorithm to determine the comprehensive weight of each resource request based on its basic performance weight, QoS weight, and scene adaptation factor. It then obtains the weighted value of each resource request based on its request value and the comprehensive weight, and uses the resource request with the highest weighted value as the arbitration result. Based on the request value of the arbitration result, it selects multiple candidate operating points that meet performance requirements, where the request value includes voltage and frequency. It obtains the energy efficiency ratio of each candidate operating point, multiplies it by a temperature correction coefficient, and obtains the final energy efficiency score for each candidate operating point. Based on the final energy efficiency scores of each candidate operating point, it determines the optimal operating point and switches to the target voltage and frequency state based on the optimal operating point. This achieves synergistic optimization between audio quality, system performance, and energy efficiency in complex application scenarios, resulting in optimal energy efficiency, improved battery life, and a superior user experience. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this application and should not be considered as a limitation on the scope of protection of this application. In the various drawings, similar components are numbered similarly.

[0022] Figure 1 A flowchart of the dynamic voltage frequency adjustment control method for the audio system provided in this application is shown. Figure 2 Another schematic diagram of the dynamic voltage frequency adjustment control method for the audio system provided in this application is shown; Figure 3 A schematic diagram of the dynamic voltage frequency adjustment control device for the audio system provided in this application is shown. Detailed Implementation

[0023] The technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0024] The components of this application, typically described and illustrated in the accompanying drawings, can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0025] In the following, the terms “comprising,” “having,” and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as excluding, firstly, the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations thereof.

[0026] Furthermore, the terms "first," "second," and "third" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0027] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0028] Example 1 This application provides a dynamic voltage frequency adjustment control method for an audio system.

[0029] See Figure 1 The dynamic voltage frequency adjustment control method of this audio system includes steps S110-S150, which will be described below.

[0030] In this embodiment, to implement the dynamic voltage and frequency regulation control method for the audio system, an intelligent energy efficiency optimization architecture is constructed. This architecture includes a perception layer, a decision layer, and an execution layer. The perception layer includes a multi-dimensional Quality of Service (QoS) monitor, the decision layer includes a Dynamic Weighted Arbiter (DWA), and the execution layer includes a multi-objective optimized Dynamic Voltage and Frequency Scaling (DVFS) coordinator. This intelligent energy efficiency optimization architecture elevates the power consumption management of the audio system from passive resource allocation to proactive energy efficiency optimization, achieving "just right" performance supply through intelligent arbitration.

[0031] In addition, a unified request acquisition interface, resource setting interface, and resource release interface can be set up to achieve complete request lifecycle management; a core management structure can also be established to uniformly manage voltage regulators, clock frequencies, and dynamic voltage frequency adjustment nodes. Unified management can eliminate the island effect of traditional decentralized control and provide consistent infrastructure support for upper-level intelligent decision-making.

[0032] In this embodiment, a unified resource management interface and core management structure were created, which fundamentally avoids resource allocation conflicts and realizes the possibility of global optimization.

[0033] Step S110: A dynamic weighted arbitration algorithm is used to determine the comprehensive weight of each resource request based on the basic performance weight, QoS weight, and scenario adaptation factor of each resource request.

[0034] In this embodiment, a multi-dimensional QoS monitor collects performance metrics and user experience parameters at each stage of the audio pipeline in real time. These performance metrics include latency, throughput, and bit error rate. The QoS weight can be determined by combining the monitored latency, throughput, bit error rate, latency weight, throughput weight, and audio quality weight.

[0035] Abstract audio quality requirements (such as maximum latency, minimum throughput, and fidelity) are quantified into computable comprehensive weights, where the weight factors are adjustable, enabling the system to adapt to complex and ever-changing application scenarios and achieve the best balance between experience and energy efficiency.

[0036] See Figure 2 Step S110 includes steps S111-S114, and each step is explained below.

[0037] Step S111: Determine the basic performance weight based on the request value of each resource request.

[0038] As an example, based on the size of the requested value (such as frequency or voltage value) itself, a higher requested value implies a higher performance requirement and should therefore receive a higher base weight.

[0039] In this embodiment, to avoid excessively high request values ​​leading to decreased energy efficiency, a non-linear function (e.g., a logarithmic function) is used to map the request values ​​to the corresponding basic performance weights.

[0040] In this embodiment, step S111 includes: The basic performance weights are obtained by mapping the request values ​​using a non-linear function.

[0041] In one embodiment, the nonlinear function includes:

[0042] Where J represents the basic performance weight, This represents the adjustment coefficient. This represents the request value for each resource request. This represents the intermediate operating value of the audio system; It can be adjusted according to the importance of high-performance requirements, for example, The value can be between 0.2 and 0.5, or other ranges, without any restrictions. It can be determined based on the typical operating points of the audio system.

[0043] Step S112: Determine the QoS weight based on the latency weight, throughput weight, and audio quality weight.

[0044] In this embodiment, step S112 includes: The QoS weight is obtained by weighting the first weight coefficient, the latency weight, the second weight coefficient, the throughput weight, the third weight coefficient, and the sound quality weight. The sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1, and the values ​​of the first weight coefficient, the second weight coefficient, and the third weight coefficient are adjusted according to the application scenario.

[0045] As an example, the QoS weight can be calculated using the following formula:

[0046] in, Indicates the QoS weight, Indicates the delay weight, Indicates the throughput weight, This represents the sound quality weight. Indicates the first weighting coefficient, Indicates the second weighting coefficient, This represents the third weighting coefficient. The importance of each dimension can be adjusted according to the application scenario, that is, adjusted according to the application scenario. , , The size of the QoS weight can guarantee the quality of critical audio streams (such as calls vs. music playback).

[0047] It should be noted that the Audio Quality Service (QoS) profile includes parameters such as latency budget, throughput requirements, and audio quality level. Each QoS parameter is assigned a weight, and then the weighted sum is obtained to obtain the total QoS weight.

[0048] In one implementation, the delay weight is calculated using the following formula:

[0049] Where YC represents the delay weight, DQY represents the current delay, and ZDY represents the maximum allowed delay.

[0050] It is understandable that the stricter the latency requirement, the higher the latency weight. For example, real-time voice calls have a latency weight of 1.8-2.0 (low latency); music playback has a latency weight of 1.3-1.6 (medium latency); and background audio processing has a latency weight of 1.0-1.2 (relaxed latency).

[0051] In one implementation, the throughput weight is calculated using the following formula:

[0052] TT represents the throughput weight. This indicates the current throughput demand. This indicates the maximum throughput capacity.

[0053] It's understandable that the higher the throughput requirement, the higher the throughput weight. For example, high bitrate audio streams have a throughput weight of 1.4-1.6 (high throughput); standard quality audio has a throughput weight of 1.1-1.3 (standard throughput); and low bitrate speech has a throughput weight of 1.0-1.1 (low throughput).

[0054] The sound quality weights are calculated using the following formula:

[0055] This represents the sound quality weight. Indicates the sound quality level.

[0056] As an example, sound quality levels can be divided as follows: Lossless sound quality (Level 10): Sound quality weight 2.0; High-quality music (Levels 8-9): Sound quality weight 1.7-1.9; Standard sound quality (Levels 5-7): Sound quality weight 1.4-1.6; Speech quality (Levels 3-4): Sound quality weight 1.1-1.3. Other forms of sound quality classification are also possible and are not limited here.

[0057] Step S113: Determine the scene adaptation factor based on the audio stream characteristics and application scenario.

[0058] In one embodiment, step S113 includes: The scene adaptation factor is determined based on the audio stream features, the application scenario, and the scene factor mapping table. The scenario adaptation factor is dynamically adjusted based on the system load.

[0059] In this embodiment, audio stream characteristics include sampling rate, number of channels, data mode, etc., which are not limited here.

[0060] Referring to Table 1, the scene factor mapping table includes audio scene type (application scene), scene adaptation factor, optimization focus (audio stream features), adaptation conditions, etc. Among them, application status can also be understood as applicable conditions.

[0061] Table 1 Scene Factor Mapping Table

[0062] In this embodiment, the scene adaptation factor can also be dynamically adjusted. Specifically, real-time load monitoring is used to dynamically fine-tune the scene factor based on the system load and adjust the scene priority.

[0063] Step S114: The product of the basic performance weight, the QoS weight, and the scenario adaptation factor is determined as the comprehensive weight.

[0064] As an example, the comprehensive weights are calculated using the following formula:

[0065] in, This represents the overall weight. This represents the basic performance weight. Indicates the QoS weight, This represents the scene adaptation factor.

[0066] The dynamic weighted arbitration algorithm in this embodiment comprehensively considers basic performance requirements, quality service weights, and scenario adaptation factors. By calculating the comprehensive weight of each resource request, it selects the optimal resource allocation scheme. Simultaneously, a quality service-aware energy efficiency optimization model is established, quantifying audio quality indicators such as maximum allowable latency, minimum throughput requirements, and audio fidelity requirements into calculable constraints.

[0067] Step S120: Obtain the weighted value of each resource request based on the request value of each resource request and the comprehensive weight, and take the resource request corresponding to the maximum weighted value as the arbitration result.

[0068] In this embodiment, a dynamic weighted arbitrator obtains the weighted value of each resource request based on the request value and the overall weight, and uses the resource request with the highest weighted value as the arbitration result. In this way, the dynamic weighted arbitrator upgrades traditional fixed-maximum-value arbitration to a multi-objective optimization decision based on QoS requirements, energy efficiency targets, and workload prediction. It intelligently selects the resource request that should be satisfied most at present, realizing a shift from "resource contention" to "intelligent arbitration."

[0069] In this embodiment, the weighted value of each resource request can be calculated using the following formula.

[0070]

[0071] in, This represents the weighted value for each resource request. Indicates the requested value. This indicates the overall weight.

[0072] In this embodiment, each resource request corresponds to a weighted value, and multiple resource requests have multiple weighted values. All weighted values ​​are compared, and the resource request with the maximum value is selected as the arbitration result.

[0073] In this embodiment, dynamic weight adjustment achieves an intelligent shift from allocating based on the highest voltage frequency demand to allocating based on the voltage frequency with optimal efficiency. This ensures that the configuration that best meets the system's energy efficiency optimization goals is selected from multiple competing requests.

[0074] Step S130: Select multiple candidate operating points that meet the performance requirements based on the requested values ​​of the arbitration results, wherein the requested values ​​of the arbitration results include voltage and frequency.

[0075] In this embodiment, the multi-objective optimized DVFS coordinator actively scores and makes decisions, selecting the operating point with the highest final energy efficiency score as the execution target; it introduces a fine voltage margin design to support asymmetric timing control of frequency boosting and frequency reduction, ensuring the reliability of state switching.

[0076] In this embodiment, a pre-obtainable static DVFS operating point table is used to select all candidate operating points that meet the performance requirements based on the frequency / voltage value of the highest weighted request in the dynamic weighted arbitration (i.e., the arbitration result). Exemplarily, the static DVFS operating point table can be provided by the chip manufacturer. Candidate operating points that meet the performance requirements can be selected from the static DVFS operating point table based on the frequency / voltage value of the arbitration result.

[0077] It is understandable that each operating point in the static DVFS operating point table is a Pareto optimal solution determined through extensive testing during the chip design phase. That is, the lowest voltage point that can stably operate at a specific frequency, thereby achieving the best energy efficiency at that frequency.

[0078] Step S140: Obtain the energy efficiency ratio of each candidate operating point, multiply the energy efficiency ratio of each candidate operating point by the temperature correction factor, and obtain the final energy efficiency score of each candidate operating point.

[0079] In this embodiment, the following companies are used to calculate the energy efficiency ratio for each candidate operating point:

[0080] in, This indicates the energy efficiency ratio. This indicates the effective computing power. This indicates the power consumption of the system.

[0081] In this embodiment, the effective computing power is calculated using the following formula:

[0082] in, This indicates the effective computing power. This indicates the actual number of audio frames processed. This represents the processing quality coefficient.

[0083] In this embodiment, the system power consumption is calculated using the following formula:

[0084] in, Indicates system power consumption. Indicates dynamic power consumption. This indicates static power consumption.

[0085] In this embodiment, the dynamic power consumption is calculated using the following formula:

[0086] in, This represents dynamic power consumption, where V represents voltage. C represents frequency, and C represents capacitance.

[0087] It should be noted that the chip junction temperature and ambient temperature are collected in real time, and the energy efficiency ratio of each candidate operating point is multiplied by a temperature correction factor to obtain the final performance score.

[0088] In this embodiment, the final performance score is calculated using the following formula:

[0089] in, This indicates the final performance score. Indicates the energy efficiency ratio. This represents the temperature correction factor.

[0090] Furthermore, the static DVFS operating point table provided by the chip manufacturer is based on an ideal laboratory environment, which is out of sync with the actual operating environment. A multi-objective optimization decision-making process incorporating a real-time temperature correction coefficient improves the long-term reliability of the audio system.

[0091] In this embodiment, the temperature correction factor is calculated using the following formula:

[0092] in, This represents the temperature correction factor. Indicates the current temperature. Indicates the reference temperature.

[0093] Step S150: Determine the optimal operating point based on the final energy efficiency score of each candidate operating point, and switch to the target voltage frequency state based on the optimal operating point.

[0094] In this embodiment, the optimal operating point is determined based on the final energy efficiency score of each candidate operating point, so as to decide whether to take one of the following operations: frequency increase, frequency decrease, or maintenance, and switch the value to the target voltage frequency state corresponding to the optimal operating point.

[0095] In one embodiment, the step S150 of switching to the target voltage frequency state based on the optimal operating point includes: When performing a frequency upsampling operation, a voltage margin is set until the voltage is increased to a stable level before increasing the frequency. When performing a frequency reduction operation, the frequency is reduced until it reaches a stable frequency, and then the voltage is reduced.

[0096] In this embodiment, the state switching process may include frequency increase operation and frequency decrease operation. The frequency increase operation includes: voltage margin setting, voltage increase, stabilization waiting, frequency increase, and voltage optimization. The frequency decrease operation includes: frequency decrease, stabilization waiting, voltage decrease, and state confirmation.

[0097] In this embodiment, the frequency upsampling and downsampling operations employ an asymmetrical design, primarily due to the critical voltage requirements during frequency upsampling (insufficient voltage will lead to circuit failure) and the voltage redundancy during frequency downsampling (excessive voltage will not cause failure, but will only result in wasted power consumption). Therefore, the frequency upsampling operation uses a "voltage up first, frequency up second" approach to ensure safety, while the frequency downsampling operation uses a "frequency down first, voltage down second" approach to optimize power consumption.

[0098] In one embodiment, the setting of the voltage margin includes: The static margin is determined based on the base voltage offset and frequency step compensation. The temperature margin is determined based on the temperature coefficient, the current temperature, and the reference temperature. The voltage margin is determined based on the static margin and the temperature margin.

[0099] In this embodiment, a timing process for asymmetric frequency boost / blow-up operations is provided, along with a refined voltage margin setting process, which improves the accuracy of state switching.

[0100] In this embodiment, the static margin is calculated using the following formula:

[0101] in, This represents the temperature correction factor. Indicates the base voltage offset. This indicates frequency step compensation.

[0102] In this embodiment, the temperature margin is calculated using the following formula:

[0103] in, Indicates the temperature margin. Indicates the temperature coefficient. Indicates the current temperature. This represents the reference temperature. The reference temperature can be statically configured or dynamically adaptively adjusted based on one or more factors, including chip process characteristics, package heat dissipation capabilities, ambient temperature, equipment reliability requirements, and historical operating temperature data. Its typical range is 15°C to 35°C. For ordinary audio systems such as mobile phones, a room temperature of 25°C is usually used; for car audio systems, the typical operating temperature is higher, and 35°C can be used. In other words, the reference temperature is not a fixed value and can be set according to the specific circumstances.

[0104] In this embodiment, the voltage margin is calculated using the following formula:

[0105] in, Indicates voltage margin. Indicates static margin. This indicates the temperature margin.

[0106] In this embodiment, the base voltage offset is 50mV (for example, this 50mV is determined based on empirical values); the frequency step compensation can be set according to requirements, for example, the frequency step compensation is 10mV per 100MHz; the temperature coefficient is 0.5mV / °C (typical value), and the margin is increased to compensate for the decrease in carrier mobility at high temperatures.

[0107] In this embodiment, an intelligent arbitration mechanism is employed, replacing the traditional fixed-priority arbitration with a dynamic weighted arbitration algorithm to achieve coordinated resource allocation among multiple audio subsystems, transforming passive resource allocation into proactive intelligent adjudication. A DVFS coordination control mechanism is used to internally coordinate the switching between voltage and frequency; externally, the execution of DVFS is coordinated through arbitration results obtained via dynamic weighted arbitration. This maximizes system energy efficiency and extends battery life while meeting audio quality requirements.

[0108] The dynamic voltage and frequency adjustment control method for audio systems provided in this embodiment employs a dynamic weighted arbitration algorithm to determine the comprehensive weight of each resource request based on its basic performance weight, QoS weight, and scene adaptation factor. It then obtains the weighted value of each resource request based on its request value and the comprehensive weight, and uses the resource request with the highest weighted value as the arbitration result. Based on the request value of the arbitration result, it selects multiple candidate operating points that meet performance requirements; the request value of the arbitration result includes voltage and frequency. It obtains the energy efficiency ratio of each candidate operating point, multiplies the energy efficiency ratio of each candidate operating point by a temperature correction coefficient, and obtains the final energy efficiency score for each candidate operating point. Based on the final energy efficiency scores of each candidate operating point, it determines the optimal operating point and switches to the target voltage and frequency state based on the optimal operating point. This achieves synergistic optimization between audio quality, system performance, and energy efficiency in complex application scenarios, resulting in optimal energy efficiency, improved battery life, and a superior user experience.

[0109] Example 2 In addition, this application provides a dynamic voltage frequency adjustment control device for an audio system.

[0110] like Figure 3 As shown, the dynamic voltage frequency adjustment control device 300 of the audio system includes: The determination module 310 is used to determine the comprehensive weight of each resource request based on the basic performance weight, QoS weight and scenario adaptation factor of each resource request using a dynamic weighted arbitration algorithm. The first acquisition module 320 is used to acquire the weighted value of each resource request based on the request value of each resource request and the comprehensive weight, and take the resource request corresponding to the maximum weighted value as the arbitration result; The selection module 330 is used to select multiple candidate operating points that meet the performance requirements based on the requested values ​​of the arbitration result, wherein the requested values ​​of the arbitration result include voltage and frequency. The second acquisition module 340 is used to acquire the energy efficiency ratio of each candidate operating point, multiply the energy efficiency ratio of each candidate operating point by a temperature correction coefficient, and obtain the final energy efficiency score of each candidate operating point. The switching module 350 is used to determine the optimal operating point based on the final energy efficiency score of each candidate operating point, and switch to the target voltage frequency state based on the optimal operating point.

[0111] In one embodiment, the determining module 310 is further configured to determine the basic performance weight based on the request value of each resource request; The QoS weights are determined based on latency weights, throughput weights, and audio quality weights. The scenario adaptation factor is determined based on the audio stream characteristics and the application scenario; The product of the basic performance weight, the QoS weight, and the scenario adaptation factor is determined as the comprehensive weight.

[0112] In one embodiment, the determining module 310 is further configured to obtain the basic performance weight by mapping the request value using a nonlinear function; The QoS weight is obtained by weighting the first weight coefficient, the latency weight, the second weight coefficient, the throughput weight, the third weight coefficient, and the sound quality weight. The sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1, and the values ​​of the first weight coefficient, the second weight coefficient, and the third weight coefficient are adjusted according to the application scenario.

[0113] In one embodiment, the nonlinear function includes:

[0114] J represents the basic performance weight. This represents the adjustment coefficient. Indicates each resource request The requested value, This represents the intermediate operating value of the audio system; The determining module 310 is further configured to calculate the delay weight using the following formula:

[0115] Where YC represents the delay weight, DQY represents the current delay, and ZDY represents the maximum allowable delay; The throughput weight is calculated using the following formula:

[0116] TT represents the throughput weight. This indicates the current throughput demand. Indicates maximum throughput capability; The sound quality weights are calculated using the following formula:

[0117] This represents the sound quality weight. Indicates the sound quality level.

[0118] In one embodiment, the determining module 310 is further configured to determine the scene adaptation factor based on the audio stream features, the application scenario, and the scene factor mapping table; The scenario adaptation factor is dynamically adjusted based on the system load.

[0119] In one embodiment, the switching module 350 is further configured to set a voltage margin when performing a frequency upsampling operation, and then increase the frequency after the voltage has been increased to a stable voltage. When performing a frequency reduction operation, the frequency is reduced until it reaches a stable frequency, and then the voltage is reduced.

[0120] In one embodiment, the switching module 350 is further configured to adjust the switching based on the base voltage offset and frequency step. Compensation determines the static margin; The temperature margin is determined based on the temperature coefficient, the current temperature, and the reference temperature. The voltage margin is determined based on the static margin and the temperature margin.

[0121] The dynamic voltage and frequency adjustment control device 300 for the audio system provided in this embodiment can implement the dynamic voltage and frequency adjustment control method for the audio system provided in Embodiment 1. To avoid repetition, it will not be described again here.

[0122] The dynamic voltage and frequency adjustment control device for the audio system provided in this embodiment employs a dynamic weighted arbitration algorithm to determine the comprehensive weight of each resource request based on its basic performance weight, QoS weight, and scene adaptation factor. It then obtains the weighted value of each resource request based on its request value and the comprehensive weight, and uses the resource request with the highest weighted value as the arbitration result. Based on the request value of the arbitration result, it selects multiple candidate operating points that meet performance requirements; the request value of the arbitration result includes voltage and frequency. It obtains the energy efficiency ratio of each candidate operating point, multiplies the energy efficiency ratio of each candidate operating point by a temperature correction coefficient, and obtains the final energy efficiency score for each candidate operating point. Based on the final energy efficiency scores of each candidate operating point, it determines the optimal operating point and switches to the target voltage and frequency state based on the optimal operating point. This achieves synergistic optimization between audio quality, system performance, and energy efficiency in complex application scenarios, resulting in optimal energy efficiency, improved battery life, and a superior user experience.

[0123] Example 3 In addition, this application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the computer program executes the dynamic voltage frequency adjustment control method of the audio system provided in Embodiment 1 when running on the processor.

[0124] The electronic device provided in this embodiment can implement the dynamic voltage and frequency adjustment control method of the audio system provided in Embodiment 1. To avoid repetition, it will not be described again here.

[0125] Example 4 This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the dynamic voltage and frequency adjustment control method for the audio system provided in Embodiment 1.

[0126] In this embodiment, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0127] The computer-readable storage medium provided in this embodiment can implement the dynamic voltage and frequency adjustment control method of the audio system provided in Embodiment 1. To avoid repetition, it will not be described again here.

[0128] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.

[0129] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0130] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A dynamic voltage frequency adjustment control method for an audio system, characterized in that, The method includes: A dynamic weighted arbitration algorithm is used to determine the comprehensive weight of each resource request based on its basic performance weight, QoS weight, and scenario adaptation factor. The weighted value of each resource request is obtained based on the request value of each resource request and the comprehensive weight, and the resource request corresponding to the maximum weighted value is taken as the arbitration result. Based on the requested values ​​of the arbitration results, multiple candidate operating points that meet the performance requirements are selected, where the requested values ​​of the arbitration results include voltage and frequency; The energy efficiency ratio of each candidate operating point is obtained, and the energy efficiency ratio of each candidate operating point is multiplied by the temperature correction factor to obtain the final energy efficiency score of each candidate operating point. The optimal operating point is determined based on the final energy efficiency score of each candidate operating point, and the target voltage and frequency state is switched based on the optimal operating point.

2. The method according to claim 1, characterized in that, The dynamic weighted arbitration algorithm determines the comprehensive weight of each resource request based on its basic performance weight, QoS weight, and scenario adaptation factor, including: The basic performance weight is determined based on the request value of each resource request; The QoS weights are determined based on latency weights, throughput weights, and audio quality weights. The scenario adaptation factor is determined based on the audio stream characteristics and the application scenario; The product of the basic performance weight, the QoS weight, and the scenario adaptation factor is determined as the comprehensive weight.

3. The method according to claim 2, characterized in that, Determining the basic performance weight based on the request value of each resource request includes: The basic performance weights are obtained by mapping the request values ​​using a non-linear function. The process of determining the QoS weight based on latency weight, throughput weight, and audio quality weight includes: The QoS weight is obtained by weighting the first weight coefficient, the latency weight, the second weight coefficient, the throughput weight, the third weight coefficient, and the sound quality weight. The sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1, and the values ​​of the first weight coefficient, the second weight coefficient, and the third weight coefficient are adjusted according to the application scenario.

4. The method according to claim 3, characterized in that, The nonlinear function includes: J represents the basic performance weight. This represents the adjustment coefficient. This represents the request value for each resource request. This represents the intermediate operating value of the audio system; The delay weight is calculated using the following formula: Where YC represents the delay weight, DQY represents the current delay, and ZDY represents the maximum allowable delay; The throughput weight is calculated using the following formula: TT represents the throughput weight. This indicates the current throughput demand. Indicates maximum throughput capability; The sound quality weights are calculated using the following formula: This represents the sound quality weight. Indicates the sound quality level.

5. The method according to claim 4, characterized in that, The step of determining the scene adaptation factor based on audio stream characteristics and application scenario includes: The scene adaptation factor is determined based on the audio stream features, the application scenario, and the scene factor mapping table. The scenario adaptation factor is dynamically adjusted based on the system load.

6. The method according to claim 1, characterized in that, The step of switching to the target voltage frequency state based on the optimal operating point includes: When performing a frequency upsampling operation, a voltage margin is set until the voltage is increased to a stable level before increasing the frequency. When performing a frequency reduction operation, the frequency is reduced until it reaches a stable frequency, and then the voltage is reduced.

7. The method according to claim 6, characterized in that, The voltage margin setting includes: The static margin is determined based on the base voltage offset and frequency step compensation. The temperature margin is determined based on the temperature coefficient, the current temperature, and the reference temperature. The voltage margin is determined based on the static margin and the temperature margin.

8. A dynamic voltage frequency adjustment and control device for an audio system, characterized in that, The device includes: The determination module is used to determine the comprehensive weight of each resource request based on the basic performance weight, QoS weight, and scenario adaptation factor of each resource request using a dynamic weighted arbitration algorithm. The first acquisition module is used to acquire the weighted value of each resource request based on the request value of each resource request and the comprehensive weight, and take the resource request corresponding to the maximum weighted value as the arbitration result; The selection module is used to select multiple candidate operating points that meet the performance requirements based on the requested values ​​of the arbitration result, wherein the requested values ​​of the arbitration result include voltage and frequency; The second acquisition module is used to acquire the energy efficiency ratio of each candidate operating point, multiply the energy efficiency ratio of each candidate operating point by the temperature correction coefficient, and obtain the final energy efficiency score of each candidate operating point. The switching module is used to determine the optimal operating point based on the final energy efficiency score of each candidate operating point, and to switch to the target voltage frequency state based on the optimal operating point.

9. An electronic device, characterized in that, The system includes a memory and a processor, wherein the memory stores a computer program that executes the dynamic voltage frequency adjustment control method of the audio system according to any one of claims 1 to 7 when the processor is running.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when run on a processor, executes the dynamic voltage frequency adjustment control method of the audio system according to any one of claims 1 to 7.

Images