Power distribution master station computing resource adaptive scheduling method and device

Abstract

The application provides a power distribution master station computing resource adaptive scheduling method and device, the method comprises: monitoring the dynamic change of each business decompression data volume in real time according to a preset time section division strategy, and obtaining a computing resource allocation scheme through preset constraint condition analysis according to the change; calculating the decompression time length of each business in the current time section according to the computing resource allocation scheme, accumulating the decompression total time length of each business according to the decompression time length, and calculating the time delay redundancy rate and the timeout percentage; constructing a network support force objective function through the time delay redundancy rate and the timeout percentage according to the Markowitz mean-variance model, and constructing an objective function according to the network support force with the goal of maximizing the network support force; obtaining the optimized computing resource allocation parameters and the time section division strategy through the objective function analysis, dynamically adjusting the power distribution master station resource according to the computing resource allocation parameters, and triggering the time section reset to re-allocate the idle resources.

Description

Technical Field

[0001] This application relates to the field of communication technology for power distribution systems, and more particularly to an adaptive scheduling method and apparatus for computing resources of a power distribution master station. Background Technology

[0002] With the rapid development of smart grids and the energy internet, sensing devices deployed in distribution networks (such as PMUs, smart meters, and fault indicators) generate massive amounts of real-time monitoring data, including high-frequency sampling information such as voltage, current, power, and harmonics. This data forms the basis for state estimation, fault diagnosis, and optimized scheduling. However, limited by communication bandwidth and storage costs, the raw data typically needs to be compressed before being transmitted to edge servers or the cloud for processing. Traditional compression algorithms (such as Huffman coding in lossless compression or wavelet transform in lossy compression) face two major challenges in distribution network scenarios: first, the temporal-spatial correlation of high-frequency data is not fully exploited, making it difficult to balance compression ratio and accuracy; second, the decompression process consumes significant computing power, while the computing resources of distribution network edge nodes are limited, requiring dynamic allocation of computing power to balance real-time performance and energy efficiency.

[0003] In terms of computing resource allocation, traditional static allocation strategies struggle to adapt to the dynamic fluctuations in distribution network load (such as data surges during sudden fault events). In recent years, dynamic resource scheduling methods based on reinforcement learning (RL) or federated learning (FL) have been proposed. These methods achieve coordinated optimization of decompression tasks and computing resources by sensing network topology, data priority, and node computing power status. For example, decompression of critical fault data can be prioritized for GPU acceleration, while historical archived data can be processed in batches using CPUs. Furthermore, joint optimization of computing power and communication has become a research hotspot. For instance, deploying lightweight decompression models (such as pruned neural networks) at the edge, uploading only feature vectors to the cloud for reconstruction, reduces transmission overhead.

[0004] Therefore, the industry urgently needs a scheduling method to solve some or all of the above-mentioned technical problems. Summary of the Invention

[0005] The purpose of this application is to provide an adaptive scheduling method and device for computing resources in a power distribution master station. By monitoring the changes in the amount of data to be decompressed in real time, the method dynamically adjusts the allocation scheme of computing resources, improves resource utilization and reduces timeout risk. It introduces a variable step size mechanism to dynamically adjust the length and number of time segments according to the progress of service decompression, thereby reducing resource fragmentation. It constructs a network support objective function by combining latency redundancy rate and timeout percentage to balance real-time requirements and resource efficiency. It designs a distributed asynchronous collaborative strategy to trigger resource reallocation immediately when service decompression is completed, thereby realizing on-demand recovery and redistribution of computing resources.

[0006] To achieve the above objectives, this application provides an adaptive scheduling method for computing resources in a power distribution master station. The method includes: real-time monitoring of the dynamic changes in the amount of data to be decompressed for each service according to a preset time segmentation strategy; obtaining a computing resource allocation scheme based on the changes in the amount of data to be decompressed through preset constraints; calculating the decompression duration of each service within the current time segment according to the computing resource allocation scheme; accumulating the decompression durations of each time segment to obtain the total decompression duration of each service; calculating the latency redundancy rate and timeout percentage based on the total decompression duration; constructing a network support objective function based on the Markowitz mean-variance model using the latency redundancy rate and timeout percentage; constructing an objective function based on the network support with the goal of maximizing network support; obtaining optimized computing resource allocation parameters and a time segmentation strategy through analysis of the objective function; dynamically adjusting the power distribution master station resources according to the optimized computing resource allocation parameters; and triggering a time segment reset when service decompression is completed to reallocate idle resources.

[0007] In the above adaptive scheduling method for computing power resources of the distribution master station, optionally, the constraint conditions include a first constraint condition and a second constraint condition; the first constraint condition is that the total computing power resources allocated to each service do not exceed the total computing power resources of the distribution master station; the second constraint condition is that the computing power resources allocated to each service are non-negative and not greater than their maximum demand value.

[0008] In the above-mentioned adaptive scheduling method for computing power resources of the power distribution master station, optionally, the calculation of the decompression time of each service within the current time segment according to the computing power resource allocation scheme includes: calculating the decompression time of each service using the following formula based on the number of processor cycles required to decompress a unit bit, the amount of data to be decompressed, a preset minimum constant, and a time segment constant:

[0009]

[0010] In the above formula, ρ k The number of CPU cycles required to decompress a unit bit of data (k), D k,i Let $i$ be the amount of data remaining to be decompressed in service $k at the start of time segment $i$. It is a very small constant to prevent f from being a constant during the problem-solving process. k,i When t is 0, there is an unbounded solution. i Let t be the length of time segment i. k,i The decompression time is for service k.

[0011] In the aforementioned adaptive scheduling method for power distribution station computing resources, optionally, the network support objective function constructed based on the Markowitz mean-variance model using the delay redundancy rate and timeout percentage includes:

[0012] The objective function for network support force is constructed using the following formula:

[0013]

[0014] In the above formula, E(θ) k ) represents the delay redundancy rate θ k The mean, E(γ) k γ represents the percentage of business timeouts. k The mean, It provides network support for all services within the network.

[0015] In the above adaptive scheduling method for power distribution station computing resources, optionally, the objective function constructed based on the network support capacity with the goal of maximizing the network support capacity includes:

[0016] The analytical model is constructed using the following formula:

[0017]

[0018] In the above formula, To provide network support for all services in the network; Constraint C1 is a computing resource constraint, meaning the sum of computing resources allocated to each service by the distribution master station cannot exceed its total computing power; Constraint C2 indicates that the computing resources allocated to each service are non-negative and cannot exceed the total computing resources; Constraint C3 is a time segment number constraint, the number of time segments cannot exceed the total number of service types; Constraint C4 is a time segment length constraint, the sum of the lengths of all time segments cannot exceed the total decompression time of the distribution master station's services; k is the service set; δ is the number of time segments; t i f is the length of time segment i; all The total computing power resources of the power distribution master station; f k The computing frequency allocated to each service.

[0019] In the above adaptive scheduling method for computing power resources of the power distribution master station, optionally, obtaining the optimized computing power resource allocation parameters through the objective function analysis includes: constructing a Lagrangian function based on the objective function, obtaining the optimal solution of the objective function based on the Lagrangian function and KKT conditions; and obtaining the computing power resource allocation parameters by iteratively solving the optimal solution of the objective function.

[0020] The Lagrange function mentioned therein includes:

[0021]

[0022] The KKT conditions include:

[0023]

[0024] In the above formula, ε and ηk and χ k These correspond to the Lagrange multipliers of constraints C1 and C2, respectively. for The first derivative, The optimal solution for allocating computing resources to each business, ε * , and It is ε, η k and χ k The corresponding optimal solution; For the allocated computing resources f k The network support capacity corresponding to the affected service k.

[0025] In the above-mentioned adaptive scheduling method for computing power resources of the power distribution master station, optionally, obtaining the time segmentation strategy through the objective function analysis includes: using a distributed asynchronous collaborative mechanism to analyze the objective function to obtain the time segmentation strategy.

[0026] In the above-mentioned adaptive scheduling method for computing resources of the power distribution master station, optionally, the distributed asynchronous coordination mechanism includes: interrupting the current time segment when it is detected that any service has completed decompression; releasing the computing resources occupied by the decompressed service, and dynamically adjusting the priority according to the latency redundancy rate of the remaining services, and reallocating computing resources; generating a new time segment partitioning scheme based on the updated amount of data to be decompressed and the objective function; wherein the time segment partitioning step size is dynamically adjusted according to the service type.

[0027] This application also provides an adaptive scheduling device for computing power resources of a power distribution master station. The device includes a monitoring module, a calculation module, a construction module, and an analysis module. The monitoring module is used to monitor the dynamic changes of the amount of data to be decompressed for each service in real time according to a preset time segmentation strategy, and to obtain a computing power resource allocation scheme by analyzing the changes in the amount of data to be decompressed through preset constraints. The calculation module is used to calculate the decompression duration of each service in the current time segment according to the computing power resource allocation scheme, to accumulate the decompression duration of each service to obtain the total decompression duration of each service, and to calculate the latency redundancy rate and timeout percentage based on the total decompression duration. The construction module is used to construct a network support objective function based on the Markowitz mean-variance model through the latency redundancy rate and timeout percentage, and to construct an objective function based on the network support with the goal of maximizing network support. The analysis module is used to obtain optimized computing power resource allocation parameters and time segmentation strategy through the objective function analysis, to dynamically adjust the resources of the power distribution master station according to the optimized computing power resource allocation parameters, and to trigger a time segment reset when the service decompression is completed to reallocate idle resources.

[0028] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method.

[0029] This application also provides a computer-readable storage medium storing a computer program that performs the above-described methods.

[0030] This application also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0031] The beneficial technical effects of this application are as follows: By adaptively allocating computing resources, the overall computing resource utilization rate of the power distribution station is improved, especially under scenarios with fluctuating data volumes. The decompression timeout percentage for differentiated services is reduced, and the latency redundancy rate of critical services (such as fault alarms) is increased. The variable-step long-time segmentation strategy enables the system to quickly respond to changes in business needs, and the granularity of time segmentation can be dynamically adjusted according to the load, reducing computational overhead. The distributed asynchronous collaboration mechanism ensures real-time linkage between resource allocation and decompression events, reduces the latency of idle computing power recovery to the millisecond level, and improves the target function value of support capacity. Attached Figure Description

[0032] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, do not constitute a limitation thereof. In the drawings:

[0033] Figure 1 This is a flowchart illustrating an embodiment of the adaptive scheduling method for power distribution master station computing resources provided in this application.

[0034] Figure 2 This is a schematic diagram of the process for obtaining computing power resource allocation parameters according to an embodiment of this application;

[0035] Figure 3 This is a schematic diagram illustrating the implementation process of a distributed asynchronous collaboration mechanism provided in an embodiment of this application;

[0036] Figure 4 This is a schematic diagram of the structure of an adaptive scheduling device for power distribution master station computing resources provided in an embodiment of this application;

[0037] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0038] The following will describe in detail the implementation methods of this application with reference to the accompanying drawings and embodiments, so as to fully understand how this application uses technical means to solve technical problems and achieve technical effects, and to implement it accordingly. It should be noted that, as long as there is no conflict, the various embodiments and features in each embodiment of this application can be combined with each other, and the resulting technical solutions are all within the protection scope of this application.

[0039] Furthermore, the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0040] Please refer to Figure 1 As shown, this application provides an adaptive scheduling method for computing resources of a power distribution master station, the method comprising:

[0041] S101 monitors the dynamic changes of the amount of data to be decompressed in each service in real time according to the preset time segmentation strategy, and obtains a computing resource allocation scheme by analyzing the changes in the amount of data to be decompressed through preset constraints.

[0042] S102 calculates the decompression duration of each service within the current time segment according to the computing power resource allocation scheme, accumulates the decompression duration of each time segment to obtain the total decompression duration of each service, and calculates the latency redundancy rate and timeout percentage based on the total decompression duration.

[0043] S103 constructs a network support objective function based on the Markowitz mean-variance model using the delay redundancy rate and timeout percentage, and constructs an objective function based on the network support with the goal of maximizing network support.

[0044] S104 obtains optimized computing power resource allocation parameters and time segmentation strategy through the objective function analysis, dynamically adjusts the power distribution master station resources according to the optimized computing power resource allocation parameters, and triggers time segment reset when the service decompression is completed to reallocate idle resources.

[0045] The constraints include a first constraint and a second constraint; the first constraint is that the total computing resources allocated to each service do not exceed the total computing resources of the power distribution master station; the second constraint is that the computing resources allocated to each service are non-negative and do not exceed their maximum demand value.

[0046] Specifically, in practical work, considering that the compression ratio of differentiated services in the network is not constant, the power distribution master station can adaptively adjust the computing resource allocation scheme in real time according to the changes in the amount of data to be decompressed for each service during the service decompression process. To improve resource utilization efficiency and reduce the probability of service decompression timeout, the concept of a time segment is introduced. The length between the moment when computing resource allocation is re-allocated and the moment when computing resource allocation was previously re-allocated is defined as a time segment. The computing resource allocation scheme within a given time segment i must satisfy the following constraint:

[0047] Σ k∈κ f k,i ≤f all ;

[0048] Where κ is the set of services in the network, f k,i f represents the computing power resources allocated by the power distribution master station to service k within time segment i. all The total computing power resources of the power distribution master station are fixed within a certain time segment, and the allocation scheme of computing power resources is fixed.

[0049] In one embodiment of this application, calculating the decompression time of each service within the current time segment according to the computing power resource allocation scheme includes: calculating the decompression time of each service using the following formula based on the number of processor cycles required to decompress one bit, the amount of data to be decompressed, a preset minimum constant, and a time segment constant:

[0050]

[0051] In the above formula, ρ k The number of CPU cycles required to decompress a unit bit of data (k), D k,i Let $i$ be the amount of data remaining to be decompressed in service $k at the start of time segment $i$. It is a very small constant to prevent f from being a constant during the problem-solving process. k,i When t is 0, there is an unbounded solution. i Let t be the length of time segment i. k,i The decompression time is for service k.

[0052] In the above embodiments, at the beginning of each time segment, computing resources are allocated only to services that have not yet completed decompression. Therefore, the decompression time of other services within this time segment can be recorded as 0. Furthermore, to prevent errors in the calculation, when f occurs... k,i =0, meaning the computing resources allocated to the service k to be decompressed are 0, indicates that service k will not be decompressed within the corresponding time segment i. Let t be the time interval. k,i=0. Considering the latency requirements of differentiated services and the efficient utilization of computing resources, and addressing multiple time segments of uncertain quantity and length, the adaptive adjustment of the power distribution master station's computing resource allocation scheme will affect the total decompression time of each service. Therefore, the total decompression time t of service k can be... k It is expressed as follows:

[0053] t k =Σ i∈[1,δ] t k,i ;

[0054] Where δ represents the number of time segments. Based on the method for calculating the total decompression time of services, after all decompression work is completed at the distribution master station, taking service k as an example, its decompression delay redundancy rate θ k and timeout percentage γ k The calculation methods are as follows:

[0055]

[0056] Where, τ k For the latency requirement of service k, t k ≤τ k This indicates that service k can complete decompression within its latency requirement without timeout; otherwise, service k has timed out. To improve service latency redundancy and reduce the service timeout percentage, the setting of time segments must consider both their number and the length of each time segment, thus satisfying the following constraints:

[0057] ∑ i∈[1,δ] t i =T;

[0058] 1≤δ≤|κ|;

[0059] Where T is the total time required for the power distribution master station to complete the decompression of all services. To prevent the fragmentation of time segments, its total number is stipulated to not exceed the total number of service types.

[0060] In one embodiment of this application, the network support objective function constructed based on the Markowitz mean-variance model using the delay redundancy rate and timeout percentage includes:

[0061] The objective function for network support force is constructed using the following formula:

[0062]

[0063] In the above formula, E(θ) k ) represents the delay redundancy rate θ k The mean, E(γ) k γ represents the percentage of business timeouts. k The mean, This provides network support capabilities for all services within the network. Specifically, this embodiment comprehensively considers the impact of latency redundancy and timeout percentage of all services on network support capabilities. Referring to the Markowitz mean-variance model, the network support capabilities for all services within the network can be... The specific details are as shown above.

[0064] Furthermore, the objective function constructed based on the network support force to maximize the network support force includes:

[0065] The analytical model is constructed using the following formula:

[0066]

[0067] In the above formula, To provide network support for all services in the network; Constraint C1 is a computing resource constraint, meaning the sum of computing resources allocated to each service by the distribution master station cannot exceed its total computing power; Constraint C2 indicates that the computing resources allocated to each service are non-negative and cannot exceed the total computing resources; Constraint C3 is a time segment number constraint, the number of time segments cannot exceed the total number of service types; Constraint C4 is a time segment length constraint, the sum of the lengths of all time segments cannot exceed the total decompression time of the distribution master station's services; k is the service set; δ is the number of time segments; t i f is the length of time segment i; all The total computing power resources of the power distribution master station; f k The computing frequency allocated to each service.

[0068] In this embodiment, computing resources are redistributed by setting time segments to improve network support. An optimization problem is constructed for a decompression model containing a service set κ. The optimization objective is to maximize network support. Considering three types of variables, resource allocation scheme f, time segment duration t, and number of time segments δ, the optimization problem can be expressed as above.

[0069] Please refer to Figure 2 As shown, the optimized computing resource allocation parameters obtained through the objective function analysis include:

[0070] S201 Constructs a Lagrangian function based on the objective function, and obtains the optimal solution of the objective function based on the Lagrangian function and the KKT conditions;

[0071] S202 obtains the computing resource allocation parameters by iteratively solving the optimal solution of the objective function;

[0072] The Lagrange function mentioned therein includes:

[0073]

[0074] The KKT conditions include:

[0075]

[0076] In the above formula, ε and η k and χ k These correspond to the Lagrange multipliers of constraints C1 and C2, respectively. for The first derivative, The optimal solution for allocating computing resources to each business, ε * , and It is ε, η k and χ k The corresponding optimal solution; For the allocated computing resources f k The network support capacity corresponding to the affected service k.

[0077] Specifically, in practical work, within a fixed time segment i, an optimal computing resource allocation scheme for each business is generated based on the given computing resources of the power distribution master station. The corresponding optimization problem is as follows:

[0078]

[0079] in, For network support capacity affected only by the computing power resource allocation scheme, the influencing factor is the total computing power resource f of the distribution master station. all The optimization problem involves considering the computational frequency f allocated to each service. k It is strictly concave, therefore it has a unique extremum point that satisfies the KKT conditions, and the corresponding Lagrangian function is shown below:

[0080]

[0081] Wherein, ε, η k and χ k The KKT conditions for the Lagrange multipliers corresponding to constraints C1 and C2 are as follows:

[0082]

[0083] in, yes The first derivative, It is the optimal solution for the computing resources allocated to each business, ε * , and It is ε, η k and χ k The corresponding optimal solution. Accordingly, the properties of the optimal solution are summarized as follows:

[0084] 1): When hour, at the same time and

[0085] 2): When and hour, at this time

[0086] 3): When hour, and

[0087] Based on the above properties, it can be found that... and There is a correlation between them. Will follow The value decreases monotonically with the increase of ε. * Perform iterations based on ε * , and The optimal solution can be calculated from the relationship between them. Specifically, when When, property 1) is satisfied, at this time when When, property 3) is satisfied, at this time when and When, property 2 is satisfied. By iterating ε * until Approaching f all The optimal computing resource allocation scheme can be obtained in time. and the maximum network support force at a given time section

[0088] In one embodiment of this application, obtaining the time segmentation strategy through the objective function analysis includes: using a distributed asynchronous collaborative mechanism to analyze the objective function to obtain the time segmentation strategy. For details, please refer to... Figure 3 As shown, the distributed asynchronous cooperation mechanism includes:

[0089] S301 interrupts the current time segment when it detects that any service has completed decompression.

[0090] S302 releases the computing resources occupied by the decompressed services and dynamically adjusts the priorities based on the latency redundancy rate of the remaining services, and reallocates computing resources.

[0091] S303 generates a new time segmentation scheme based on the updated amount of data to be decompressed and the objective function;

[0092] The time segment division step size is dynamically adjusted according to the business type.

[0093] Specifically, in practical work,

[0094] Based on the original problem (OP), and considering the feedback from the computing resource allocation layer, the optimization problem of time segmentation can be expressed as follows:

[0095]

[0096] in This represents the network support capacity under a given time-division partitioning scheme {t, δ}. The network support capacity obtained by solving the computational resource allocation problem involves a distributed asynchronous collaborative mechanism for solving the above problem, oriented towards time-division partitioning. The specific process is shown in Table 1 below:

[0097] Table 1

[0098]

[0099] Where γ is the time segmentation step size. In step 5 of Table 1, within a fixed time segment, for a given computing resource allocation scheme, if service k has completed decompression, its corresponding computing resources cannot be reused within this time segment. Therefore, to improve resource utilization and maximize network support, the time segment needs to be reset and computing resources allocated. In this embodiment, the core idea of ​​the distributed asynchronous cooperation mechanism is that the power distribution master station updates the optimal computing resource allocation scheme only when a certain service has completed decompression, without considering whether other services have completed decompression. The guarantee of decompression latency depends on the driving force of network support. When the latency redundancy of other services is too low, more computing resources will be automatically obtained.

[0100] Please refer to Figure 4As shown, this application also provides an adaptive scheduling device for computing power resources of a power distribution master station. The device includes a monitoring module, a calculation module, a construction module, and an analysis module. The monitoring module is used to monitor the dynamic changes of the amount of data to be decompressed for each service in real time according to a preset time segmentation strategy, and to obtain a computing power resource allocation scheme by analyzing the changes in the amount of data to be decompressed through preset constraints. The calculation module is used to calculate the decompression duration of each service in the current time segment according to the computing power resource allocation scheme, to accumulate the decompression duration of each service to obtain the total decompression duration of each service, and to calculate the latency redundancy rate and timeout percentage based on the total decompression duration. The construction module is used to construct a network support objective function based on the Markowitz mean-variance model through the latency redundancy rate and timeout percentage, and to construct an objective function based on the network support with the goal of maximizing network support. The analysis module is used to obtain optimized computing power resource allocation parameters and time segmentation strategy through the objective function analysis, to dynamically adjust the resources of the power distribution master station according to the optimized computing power resource allocation parameters, and to trigger a time segment reset when the service decompression is completed to reallocate idle resources.

[0101] Since the principle behind this device for solving the problem is similar to the adaptive scheduling method for computing resources of the power distribution master station, the implementation of this device can be found in the implementation of the adaptive scheduling method for computing resources of the power distribution master station. The repetitive parts will not be repeated.

[0102] The beneficial technical effects of this application are as follows: By adaptively allocating computing resources, the overall computing resource utilization rate of the power distribution station is improved, especially under scenarios with fluctuating data volumes. The decompression timeout percentage for differentiated services is reduced, and the latency redundancy rate of critical services (such as fault alarms) is increased. The variable-step long-time segmentation strategy enables the system to quickly respond to changes in business needs, and the granularity of time segmentation can be dynamically adjusted according to the load, reducing computational overhead. The distributed asynchronous collaboration mechanism ensures real-time linkage between resource allocation and decompression events, reduces the latency of idle computing power recovery to the millisecond level, and improves the target function value of support capacity.

[0103] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method.

[0104] This application also provides a computer-readable storage medium storing a computer program that performs the above-described methods.

[0105] This application also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0106] like Figure 5As shown, the electronic device 600 may also include: a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily need to include these components. Figure 5 All components shown; in addition, the electronic device 600 may also include Figure 5 For components not shown, please refer to existing technology.

[0107] like Figure 5 As shown, the central processing unit 100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device. The central processing unit 100 receives inputs and controls the operation of various components of the electronic device 600.

[0108] The memory 140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 100 may execute the program stored in the memory 140 to perform information storage or processing, etc.

[0109] Input unit 120 provides input to central processing unit 100. Input unit 120 may be, for example, a keypad or touch input device. Power supply 170 provides power to electronic device 600. Display 160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0110] The memory 140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 140 can also be some other type of device. The memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application / function storage unit 142 for storing application programs and function programs or processes for executing the operation of the electronic device 600 via the central processing unit 100.

[0111] The memory 140 may also include a data storage unit (data 143) for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit (driver 144) of the memory 140 may include various drivers for the electronic device's communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0112] The communication module 110 is a transmitter / receiver 110 that transmits and receives signals via antenna 111. The communication module (transmitter / receiver) 110 is coupled to the central processing unit 100 to provide input signals and receive output signals, which can be the same as in a conventional mobile communication terminal.

[0113] Based on different communication technologies, multiple communication modules 110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module (transmitter / receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132, thereby enabling typical telecommunications functions. The audio processor 130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 130 is coupled to a central processing unit 100, enabling on-device recording via the microphone 132 and on-device playback of stored audio via the speaker 131.

[0114] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0116] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0118] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An adaptive scheduling method for computing resources of a power distribution master station, characterized in that, The method includes: Based on a preset time segmentation strategy, the dynamic changes of the amount of data to be decompressed in each service are monitored in real time, and a computing resource allocation scheme is obtained by analyzing the changes in the amount of data to be decompressed through preset constraints. The decompression time of each service within the current time segment is calculated according to the computing power resource allocation scheme. The total decompression time of each service is obtained by summing the decompression times of each time segment. The latency redundancy rate and timeout percentage are calculated based on the total decompression time. Based on the Markowitz mean-variance model, a network support objective function is constructed using the delay redundancy rate and timeout percentage. Based on the network support, an objective function is constructed with the goal of maximizing the network support. The objective function analysis yields optimized computing power resource allocation parameters and time segmentation strategies. Based on the optimized computing power resource allocation parameters, the power distribution master station resources are dynamically adjusted, and a time segment reset is triggered when the service decompression is completed to reallocate idle resources. Based on the Markowitz mean-variance model, the network support objective function is constructed using the aforementioned delay redundancy rate and timeout percentage, which includes: The objective function for network support force is constructed using the following formula: ； In the above formula, Delay redundancy rate The mean, Percentage of business timeout The mean, Network support capabilities for all services within the network; latency redundancy rate The percentage of the remaining timeout amount in the time constraint when service k completes decompression; service timeout percentage. The percentage of the time elapsed between the completion of decompression for service k and the delay constraint in the delay constraint.

2. The adaptive scheduling method for power distribution master station computing resources according to claim 1, characterized in that, The constraints include a first constraint and a second constraint. The first constraint is that the total computing resources allocated to each service do not exceed the total computing resources of the power distribution master station; the second constraint is that the computing resources allocated to each service are non-negative and do not exceed their maximum demand value.

3. The adaptive scheduling method for power distribution master station computing resources according to claim 1, characterized in that, The decompression time for each service within the current time segment is calculated based on the aforementioned computing resource allocation scheme, including: The decompression time for each service is calculated using the following formula based on the number of processor cycles required to decompress one bit, the amount of data to be decompressed, the preset minimum constant, and the time section constant: ； In the above formula, To decompress unit bit services Number of CPU cycles required Time section Business at the start The remaining amount of data to be decompressed It is a very small constant to prevent problems from occurring during the solution process. When the value is 0, there is an unbounded solution. Time section Internal power distribution master station is assigned to business computing resources Time section Length, The decompression time is for service k.

4. The adaptive scheduling method for power distribution master station computing resources according to claim 1, characterized in that, Based on the network support strength, the objective function constructed with the goal of maximizing network support strength includes: The analytical model is constructed using the following formula: ； In the above formula, This represents the network support capacity for all services within the network; Constraint C1 is a computing resource constraint, meaning the sum of computing resources allocated to each service by the distribution master station cannot exceed its total computing power; Constraint C2 indicates that the computing resources allocated to each service are non-negative and cannot exceed the total computing resources; Constraint C3 is a time segment number constraint, the number of time segments cannot exceed the total number of service types; Constraint C4 is a time segment length constraint, the sum of the lengths of all time segments cannot exceed the total decompression time of the distribution master station's services; k is the service set. The number of time sections; Time section Length; This refers to the total computing power resources of the power distribution master station; The computing resources allocated to each business unit.

5. The adaptive scheduling method for power distribution master station computing resources according to claim 4, characterized in that, The optimized computing resource allocation parameters obtained through the objective function analysis include: Construct a Lagrange function based on the objective function, and obtain the optimal solution of the objective function based on the Lagrange function and the KKT conditions; The computing resource allocation parameters are obtained by iteratively solving the optimal solution of the objective function. The Lagrange function mentioned therein includes: ； The KKT conditions include: ； In the above formula, , and These correspond to the Lagrange multipliers of constraints C1 and C2, respectively. for The first derivative, The optimal solution for allocating computing resources to each business unit. , and yes , and The corresponding optimal solution; For the allocated computing resources Business affected Corresponding network support capacity.

6. The adaptive scheduling method for power distribution master station computing resources according to claim 4, characterized in that, The time segmentation strategy obtained through the analysis of the objective function includes: using a distributed asynchronous collaborative mechanism to analyze the objective function to obtain the time segmentation strategy.

7. The adaptive scheduling method for power distribution master station computing resources according to claim 6, characterized in that, The distributed asynchronous collaboration mechanism includes: The current time segment is interrupted when any service is detected to have completed decompression. Release the computing resources occupied by the decompressed services, and dynamically adjust the priority based on the latency redundancy rate of the remaining services to reallocate computing resources; Based on the updated amount of data to be decompressed and the objective function, a new time segmentation scheme is generated. The time segment division step size is dynamically adjusted according to the business type.

8. A power distribution master station computing power resource adaptive scheduling device, characterized in that, The device includes a monitoring module, a calculation module, a construction module, and an analysis module; The monitoring module is used to monitor the dynamic changes of the amount of data to be decompressed in each service in real time according to a preset time segmentation strategy, and to obtain a computing resource allocation scheme by analyzing the changes in the amount of data to be decompressed through preset constraints. The calculation module is used to calculate the decompression duration of each service within the current time segment according to the computing power resource allocation scheme, accumulate the decompression duration of each time segment to obtain the total decompression duration of each service, and calculate the latency redundancy rate and timeout percentage based on the total decompression duration. The construction module is used to construct a network support objective function based on the Markowitz mean-variance model using the delay redundancy rate and timeout percentage, and to construct an objective function based on the network support with the goal of maximizing the network support. The analysis module is used to obtain optimized computing power resource allocation parameters and time segmentation strategies through the objective function analysis, dynamically adjust the power distribution master station resources according to the optimized computing power resource allocation parameters, and trigger time segment reset when the service decompression is completed to reallocate idle resources. Based on the Markowitz mean-variance model, the network support objective function is constructed using the aforementioned delay redundancy rate and timeout percentage, which includes: The objective function for network support force is constructed using the following formula: ； In the above formula, Delay redundancy rate The mean, Percentage of business timeout The mean, Network support capabilities for all services within the network; latency redundancy rate The percentage of the remaining timeout amount in the time constraint when service k completes decompression; service timeout percentage. The percentage of the time elapsed between the completion of decompression for service k and the delay constraint in the delay constraint.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 7.

11. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 7.

Images