Mobile intelligent network storage control method with task power coordination and regulation

Abstract

The present application relates to the technical field of electric energy storage system, specifically to a mobile intelligent network storage control method for task power coordination and regulation. The present application first constructs energy storage resource pool and network storage resource pool respectively; relying on energy storage view data, the power supply capacity curve and dynamic power upper limit constraint of the current and forecast period are calculated to form power supply constraint information. The network storage subsystem combines power upper limit, task priority and deadline to re-plan the task queue, and outputs the optimized execution plan and releasable power potential and returns to the energy storage side. The energy storage subsystem combines the remaining power of energy storage, the state of multiple power supply input sources, and takes the global power supply time and the completion rate of high priority tasks as the joint optimization target to generate joint scheduling instructions, dynamically updates the double pool view and closed loop iterative operation. The present application relies on the double resource pool view to complete the power, task and global scheduling calculation, links the power supply and task control and realizes real-time closed loop regulation, and takes into account the power supply endurance and the execution effect of high priority tasks.

Description

Technical Field

[0001] This invention relates to the field of energy storage system technology, and more specifically, to a mobile intelligent network storage control method for coordinated regulation of task-specific power consumption. Background Technology

[0002] In the field of energy storage systems, a battery management unit monitors battery level and temperature in real time. It dynamically compensates for high power consumption demands when mains power is insufficient and provides emergency power during mains power outages to ensure no data loss. It also integrates a solar charging module and supports a mobile power bank mode, enabling intelligent collaborative scheduling of multiple power inputs and device workloads, thereby optimizing power supply reliability and energy utilization. This method not only allows AINAS (Network Attached Storage) devices to continue operating when the power grid is unstable and to synchronize data for peripherals such as cameras, but also significantly improves data security and outdoor endurance during power outages. This technology breaks through the dependence of traditional storage devices on a fixed power grid, utilizing electricity...

[0003] In existing energy storage system technologies, conventional solutions generally adopt a passive management architecture of monitoring first and then responding. The energy storage unit, power supply circuit and load equipment are functionally isolated from each other. The system usually only performs simple charging and discharging management based on voltage and lacks the ability to sense the load end in real time. In this case, the following problems often occur: (1) the long-term use of one or several NAS devices leads to an imbalance between supply and demand of resources in some cases; (2) because they cannot be mutually assisted, the storage resources are in one pool, while the power resources are significantly unbalanced; (3) the network storage process is not related to the use of electricity, so only the sharing of storage can be considered, and there is a lack of constraints on the load output capacity. Therefore, it is necessary to introduce the task load as an active control variable into the energy management loop, and fundamentally solve the bottleneck of energy storage control through collaborative analysis and dynamic power compensation mechanism. Summary of the Invention

[0004] In view of the above problems, this invention proposes a mobile intelligent network storage control method for task power coordination regulation. By constructing a dual resource pool view of energy storage and storage, it calculates power supply constraints, task scheduling weights and global joint scheduling instructions in a hierarchical manner, and synchronously links power supply compensation and NAS task management and continuously iterates in a closed loop to achieve bidirectional collaborative optimization of energy storage power supply and network storage tasks, taking into account both power supply duration and high priority task completion rate.

[0005] According to a first aspect of the present invention, a mobile intelligent network storage control method for task-based power coordination is provided.

[0006] In one or more embodiments, preferably, the mobile intelligent network storage control method for task power coordinated regulation includes: Construct status views for the energy storage resource pool and the network storage resource pool respectively; Based on the energy storage resource pool status view, calculate the power supply capacity curve and dynamic power upper limit constraint that can be used to support the network storage subsystem in the current and predicted time periods, as power supply capacity constraint information. Based on the dynamic power upper limit constraint in the power supply capacity constraint information, and combined with the task priorities and deadlines in the network storage resource pool status view, the current running task queue is replanned to generate an optimized task execution plan and corresponding releaseable power potential under the dynamic power upper limit constraint. The optimized task execution plan and its corresponding releaseable power potential are returned to the energy storage subsystem. Based on the received information, the energy storage subsystem combines the remaining power of the current energy storage resource pool with the status of the power input source, and generates a joint scheduling instruction with the goal of jointly optimizing the global power supply duration and the completion rate of high-priority tasks. According to the joint scheduling instructions, power supply compensation control and task execution control of each NAS device are executed simultaneously. The system collects real-time status change data of the energy storage resource pool and real-time task execution progress data of each NAS device in the network storage resource pool. It then iterates in a closed loop based on the updated status views of the energy storage resource pool and the network storage resource pool until the system reaches a stable operating state.

[0007] In one or more embodiments, preferably, the step of constructing the energy storage resource pool status view and the network storage resource pool status view respectively specifically includes: The energy storage resource pool status view includes: preset baseline output power parameters of the energy storage module, which are pre-stored in the local parameter list of the energy storage controller; the total available power of the energy storage module, which is obtained by weighted summation of the state of charge and rated capacity of each cell unit; the state of charge, remaining capacity and temperature distribution data of each cell unit, which are collected in real time by the battery management unit; the overall health status data of the energy storage module, which is periodically collected and updated by the battery management unit; the on / off status and power status of the mains power supply, which are obtained in real time by the mains power detection circuit; and the real-time output power of solar energy, which is collected in real time by the output terminal of the solar controller, and the estimated solar input power for the future prediction period is generated based on the real-time collected data and the irradiance time series prediction model. The network storage resource pool status view includes: the storage capacity utilization rate of each NAS device, which is obtained in real time by reading the file system of each device; the current running task queue and the priority and deadline of each task, which are obtained in real time by the task scheduler of each device; and the historical power consumption characteristics of each device, which are obtained by statistically recording the historical operating power consumption data of each device.

[0008] In one or more embodiments, preferably, the step of calculating the power supply capacity curve and dynamic power upper limit constraint available to support the network storage subsystem in the current and predicted time periods based on the energy storage resource pool status view, as power supply capacity constraint information, specifically includes: Calculate the dynamic power upper limit constraint using the first calculation formula; The power supply capacity curve is set as a continuous curve of the dynamic power upper limit constraint changing with time within the prediction time window; The first calculation formula is:

[0009] in, In the prediction time window The dynamic power limit within, This is the reference output power of the energy storage module. This is the power correction factor based on the current state of charge (SOC). This is a power correction factor based on the current cell temperature. This is the aging correction factor based on the current state of health (SOH). The predicted input power for solar energy within the predicted time window.

[0010] In one or more embodiments, preferably, the step of replanning the currently running task queue based on the dynamic power upper limit constraint in the power supply capacity constraint information, combined with the task priorities and deadlines in the network storage resource pool status view, to generate an optimized task execution plan and corresponding releaseable power potential under the dynamic power upper limit constraint, specifically includes: Based on the urgency index of each task, the current power consumption and the remaining execution time, calculate the comprehensive scheduling priority weight of each task under the power limit constraint, and sort the tasks from high to low according to the comprehensive scheduling priority weight, so as to give priority to the continuous execution of high-weight tasks. When the total power consumption demand exceeds the dynamic power limit constraint, the corresponding tasks are sequentially subjected to frequency reduction, delay or migration operations in order of comprehensive scheduling priority weight from low to high, until the total power consumption demand does not exceed the dynamic power limit constraint. The releasable power potential is calculated based on the power consumption of the task being down-clocked, delayed, or migrated. The releasable power potential is the sum of the power consumption of the delayed task, the power consumption of the migrated task, and the power consumption difference of the down-clocked task before and after down-clocking.

[0011] In one or more embodiments, preferably, the optimized task execution plan and its corresponding releaseable power potential are returned to the energy storage subsystem; the energy storage subsystem, based on the received information and in conjunction with the remaining power of the current energy storage resource pool and the status of the power input source, generates a joint scheduling instruction with the joint optimization of global power supply duration and high-priority task completion rate as the objective, specifically including: Based on the execution time period and execution rate of each task in the optimized task execution plan, calculate the estimated total power consumption demand curve of the network storage subsystem at each moment within the prediction time window. And the estimated total power consumption demand curve and the power supply capacity curve are compared. Perform hourly comparison: when At that time, it is determined that supply and demand are in balance; when When a power supply gap is identified, the gap power value at each moment is calculated using the fourth calculation formula. The fourth calculation formula is:

[0012] Based on the described releaseable power potential, calculate the maximum power reserve that can be released in an emergency through task downscaling, delaying, or migration operations. and the gap power value With the maximum power reserve value Compare: If If so, the power reserve is used to fill the gap, and there is no need to adjust the execution status of high-priority tasks; if Then, with the maximization of global power supply duration and the maximization of high-priority task completion rate as the joint optimization objectives, the final execution state of each high-priority task is solved using the fifth calculation formula. The fifth calculation formula is:

[0013] in, To jointly optimize the objective function value, This is the estimated sustainable power supply duration of the current energy storage resource pool, taking into account solar supplementation. The estimated total time required to complete all current high-priority tasks. For a set of high-priority tasks, For the first The final execution status of a high-priority task. Indicates execution. Indicates that it will not be executed. For the first The overall scheduling priority weight of each high-priority task. and To optimize the weighting coefficients and ; Based on the final execution status of each high-priority task The solution results determine the power allocation scheme of each power input source, the charging and discharging timing of the energy storage module, and the final task execution strategy of each NAS device. The power allocation scheme, the charging and discharging timing, and the final task execution strategy together constitute the joint scheduling instruction.

[0014] In one or more embodiments, preferably, the step of simultaneously executing power supply compensation control and task execution control of each NAS device according to the joint scheduling instruction specifically includes: According to the power allocation scheme in the joint dispatch instruction, the actual output power of the power supply supplement unit is collected in real time, compared with the target power allocation value in the joint dispatch instruction, and the deviation is calculated. The dynamic power compensation amount is calculated using proportional-integral-derivative control: when the dynamic power compensation amount is positive, the power supply supplement unit is controlled to increase the corresponding power output, prioritizing the use of solar input sources, and the insufficient part is supplemented by the energy storage module; when the dynamic power compensation amount is negative, the power supply supplement unit is controlled to reduce the corresponding power output, and the excess power is used to charge the energy storage module; when the dynamic power compensation amount is zero, the current power supply state is maintained. The final task execution strategy in the joint scheduling instruction is issued to each NAS device: For tasks that need to be frequency-reduced, the operating frequency after frequency reduction is calculated based on the ratio between the target power consumption value and the current power consumption value, and the frequency reduction operation is executed; For tasks that need to be delayed, the maximum delay time is calculated based on the remaining estimated power consumption requirement, current power consumption, execution efficiency coefficient, and deadline of the task, and the delay operation is executed; For tasks that need to be migrated, the task and its associated data are migrated from the current NAS device to the target NAS device specified in the joint scheduling instruction to continue execution. The power supply compensation control and the task execution control are executed synchronously in time: after each task is down-frequency, delayed, or migrated, the real-time total power consumption requirement of the network storage subsystem is recalculated based on the actual power consumption value of each NAS device, and this real-time total power consumption requirement is used as the input of the power supply compensation control to ensure that the power supply compensation and task execution control form a real-time linkage; when the power supply compensation control detects a sudden drop in power supply capacity, a power warning signal is sent to the task execution control in advance before the power supply compensation response, triggering the task execution control to perform down-frequency or delayed operation in advance, so as to realize a rapid coordinated response between the power supply side and the storage side.

[0015] In one or more embodiments, preferably, the real-time acquisition of state change data of the energy storage resource pool, the real-time acquisition of task execution progress data of each NAS device in the network storage resource pool, and the closed-loop iteration based on the updated state view of the energy storage resource pool and the state view of the network storage resource pool until the system reaches a stable operating state, specifically includes: During the execution of the joint scheduling command, the actual state of charge and actual cell temperature of the energy storage resource pool are collected in real time at a preset sampling period. They are compared with the predicted state of charge and predicted cell temperature within the prediction time window. If the deviation of any parameter exceeds a preset threshold, the power supply capacity curve is recalculated, and the power supply capacity constraint information is regenerated based on the updated power supply capacity curve. Meanwhile, the actual completion progress of the tasks currently being executed by each NAS device is collected in real time at a preset sampling period and compared with the planned completion progress in the optimized task execution plan. If the deviation between the actual completion progress and the planned completion progress of any task exceeds a preset threshold, the optimized task execution plan is recalculated and the corresponding releaseable power potential is regenerated based on the updated optimized task execution plan. When both the energy storage state deviation and the task execution progress deviation remain below their respective preset thresholds for an extended period exceeding the preset stability determination time, the system is determined to have reached a stable operating state and the closed-loop iteration is stopped.

[0016] According to a second aspect of the present invention, a mobile intelligent network storage control system for coordinated control of task power consumption is provided.

[0017] In one or more embodiments, preferably, the mobile intelligent network storage control system for task power coordination includes: The dual-pool status view module is used to build the status view of the energy storage resource pool and the status view of the network storage resource pool, respectively. The power capacity constraint module is used to calculate the power supply capacity curve and dynamic power upper limit constraint that can be used to support the network storage subsystem in the current and predicted time periods based on the energy storage resource pool status view, as power supply capacity constraint information. The replanning module is used to replan the current running task queue based on the dynamic power upper limit constraint in the power supply capacity constraint information, combined with the task priority and deadline in the network storage resource pool status view, and generate an optimized task execution plan and corresponding releaseable power potential under the dynamic power upper limit constraint. The joint decision-making module is used to return the optimized task execution plan and its corresponding releaseable power potential to the energy storage subsystem. Based on the received information, the energy storage subsystem combines the remaining power of the current energy storage resource pool with the status of the power input source, and generates a joint scheduling instruction with the goal of jointly optimizing the global power supply duration and the completion rate of high-priority tasks. The joint scheduling module is used to simultaneously perform power supply compensation control and task execution control of each NAS device according to the joint scheduling instructions. The closed-loop iterative control module is used to collect real-time status change data of the energy storage resource pool and real-time task execution progress data of each NAS device in the network storage resource pool. Based on the updated status view of the energy storage resource pool and the status view of the network storage resource pool, it iterates in a closed loop until the system reaches a stable operating state.

[0018] According to a third aspect of the present invention, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the method as described in any one of the first aspects of the present invention.

[0019] According to a fourth aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in any one aspect of the present invention.

[0020] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: In this invention, by building a dual-pool status view of energy storage and network storage and using a hierarchical calculation formula to quantify the upper limit of power supply and task scheduling weight, the power supply capacity and task load are accurately matched quantitatively.

[0021] In this invention, the dual optimization of maximizing power supply duration and achieving high completion rate of high-priority tasks is achieved through power supply and demand comparison, global joint optimization objective solution, and real-time closed-loop iterative control.

[0022] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0023] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a mobile intelligent network storage control method for task power coordinated regulation according to an embodiment of the present invention.

[0026] Figure 2 This is a flowchart illustrating the construction of an energy storage resource pool state view and a network storage resource pool state view in a mobile intelligent network storage control method for task power collaborative regulation according to an embodiment of the present invention.

[0027] Figure 3 This is a flowchart illustrating the calculation of the power supply capacity curve and dynamic power upper limit constraint available to support the network storage subsystem within the current and predicted time periods, based on the energy storage resource pool status view, in a mobile intelligent network storage control method for task power coordinated regulation according to an embodiment of the present invention.

[0028] Figure 4 This is an embodiment of the mobile intelligent network storage control method for task power coordination regulation. Based on the dynamic power upper limit constraint in the power supply capacity constraint information, and combined with the task priorities and deadlines in the network storage resource pool status view, the method re-plans the currently running task queue to generate an optimized task execution plan and a flowchart of the corresponding releaseable power potential under the dynamic power upper limit constraint.

[0029] Figure 5 This is a flowchart of a mobile intelligent network storage control method for task power collaborative regulation according to an embodiment of the present invention, in which the optimized task execution plan and its corresponding releaseable power potential are returned to the energy storage subsystem; the energy storage subsystem generates a flowchart of a joint scheduling instruction based on the received information, combined with the remaining power of the current energy storage resource pool and the status of the power input source, with the joint optimization of global power supply duration and high-priority task completion rate as the objective.

[0030] Figure 6 This is a flowchart illustrating the process of simultaneously executing power compensation control and task execution control of each NAS device according to the joint scheduling instruction in a mobile intelligent network storage control method for task power coordination regulation according to an embodiment of the present invention.

[0031] Figure 7This is a flowchart illustrating the process of real-time acquisition of state change data of the energy storage resource pool and real-time acquisition of task execution progress data of each NAS device in the network storage resource pool in a mobile intelligent network storage control method for task power coordination regulation according to an embodiment of the present invention. The flowchart describes the process of closed-loop iteration based on the updated state view of the energy storage resource pool and the state view of the network storage resource pool until the system reaches a stable operating state.

[0032] Figure 8 This is a structural diagram of a mobile intelligent network storage control system for task power coordination regulation according to an embodiment of the present invention.

[0033] Figure 9 This is a structural diagram of an electronic device according to one embodiment of the present invention. Detailed Implementation

[0034] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] In the field of energy storage systems, a battery management unit monitors battery level and temperature in real time. It dynamically compensates for high power consumption demands when mains power is insufficient and provides emergency power during mains power outages to ensure no data loss. It also integrates a solar charging module and supports a mobile power bank mode, enabling intelligent collaborative scheduling of multiple power inputs and device workloads, thereby optimizing power supply reliability and energy utilization. This method not only allows AINAS (Network Attached Storage) devices to continue operating when the power grid is unstable and to synchronize data for peripherals such as cameras, but also significantly improves data security and outdoor endurance during power outages. This technology breaks through the dependence of traditional storage devices on a fixed power grid, utilizing electricity...

[0037] In existing energy storage system technologies, conventional solutions generally adopt a passive management architecture of monitoring first and then responding. The energy storage unit, power supply circuit and load equipment are functionally isolated from each other. The system usually only performs simple charging and discharging management based on voltage and lacks the ability to sense the load end in real time. In this case, the following problems often occur: (1) the long-term use of one or several NAS devices leads to an imbalance between supply and demand of resources in some cases; (2) because they cannot be mutually assisted, the storage resources are in one pool, while the power resources are significantly unbalanced; (3) the network storage process is not related to the use of electricity, so only the sharing of storage can be considered, and there is a lack of constraints on the load output capacity. Therefore, it is necessary to introduce the task load as an active control variable into the energy management loop, and fundamentally solve the bottleneck of energy storage control through collaborative analysis and dynamic power compensation mechanism.

[0038] This invention provides a mobile intelligent network storage control method for coordinated adjustment of task power. This scheme constructs a dual resource pool view of energy storage and storage, calculates power supply constraints, task scheduling weights, and global joint scheduling instructions hierarchically, synchronously links power supply compensation and NAS task management, and continuously iterates in a closed loop. This achieves bidirectional coordinated optimization of energy storage power supply and network storage tasks, balancing power supply duration and high-priority task completion rates.

[0039] According to a first aspect of the present invention, a mobile intelligent network storage control method for task-based power coordination is provided.

[0040] Figure 1 This is a flowchart of a mobile intelligent network storage control method for task power coordinated regulation according to an embodiment of the present invention.

[0041] In one or more embodiments, preferably, the mobile intelligent network storage control method for task power coordinated regulation includes: S101. Construct the status view of the energy storage resource pool and the status view of the network storage resource pool respectively; S102. Based on the energy storage resource pool status view, calculate the power supply capacity curve and dynamic power upper limit constraint that can be used to support the network storage subsystem in the current and predicted time periods, as power supply capacity constraint information. S103. Based on the dynamic power upper limit constraint in the power supply capacity constraint information, and combined with the task priority and deadline in the network storage resource pool status view, the current running task queue is replanned to generate an optimized task execution plan and corresponding releaseable power potential under the dynamic power upper limit constraint. S104. The optimized task execution plan and its corresponding releaseable power potential are returned to the energy storage subsystem. Based on the received information, the energy storage subsystem combines the remaining power of the current energy storage resource pool with the status of the power input source, and generates a joint scheduling instruction with the goal of jointly optimizing the global power supply duration and the completion rate of high-priority tasks. S105. According to the joint scheduling instruction, simultaneously execute power supply compensation control and task execution control of each NAS device; S106. Real-time acquisition of status change data of the energy storage resource pool and real-time acquisition of task execution progress data of each NAS device in the network storage resource pool. Closed-loop iteration based on the updated status view of the energy storage resource pool and the status view of the network storage resource pool until the system reaches a stable operating state.

[0042] In this embodiment of the invention, during the execution of the joint scheduling command, the status change data of the energy storage resource pool is collected in real time, and the power supply capacity curve is dynamically updated; at the same time, the task execution progress data of each NAS device in the network storage resource pool is collected in real time, and the optimized task execution plan is dynamically adjusted; the system iterates in a closed loop according to the updated status view of the energy storage resource pool and the status view of the network storage resource pool until the system reaches a stable operating state.

[0043] Figure 2 This is a flowchart illustrating the construction of an energy storage resource pool state view and a network storage resource pool state view in a mobile intelligent network storage control method for task power collaborative regulation according to an embodiment of the present invention.

[0044] like Figure 2 As shown, in one or more embodiments, preferably, the step of constructing the energy storage resource pool status view and the network storage resource pool status view respectively specifically includes: S201. The energy storage resource pool status view includes: preset baseline output power parameters of the energy storage module, which are pre-stored in the local parameter list of the energy storage controller; the total available power of the energy storage module, which is obtained by weighted summation of the state of charge and rated capacity of each cell unit; the state of charge, remaining capacity and temperature distribution data of each cell unit, which are collected in real time by the battery management unit; the overall health status data of the energy storage module, which is periodically collected and updated by the battery management unit; the on / off status and power status of the mains power supply, which are obtained in real time by the mains power detection circuit; and the real-time output power of solar energy, which is collected in real time by the output terminal of the solar controller, and the estimated input power of solar energy in the future prediction period is generated based on the real-time collected data and the irradiance time series prediction model. S202. The network storage resource pool status view includes: the storage capacity utilization rate of each NAS device, which is obtained in real time by reading the file system of each device; the current running task queue and the priority and deadline of each task, which are obtained in real time by the task scheduler of each device; and the historical power consumption characteristics of each device, which are obtained by statistically recording the historical operating power consumption data of each device.

[0045] In this embodiment of the invention, the collected information is divided into two categories: energy storage and storage, which are used for subsequent effective resource scheduling.

[0046] Figure 3 This is a flowchart illustrating the calculation of the power supply capacity curve and dynamic power upper limit constraint available to support the network storage subsystem within the current and predicted time periods, based on the energy storage resource pool status view, in a mobile intelligent network storage control method for task power coordinated regulation according to an embodiment of the present invention.

[0047] like Figure 3 As shown, in one or more embodiments, preferably, the step of calculating the power supply capacity curve and dynamic power upper limit constraint available to support the network storage subsystem within the current and predicted time periods based on the energy storage resource pool status view, as power supply capacity constraint information, specifically includes: S301. Calculate the dynamic power upper limit constraint using the first calculation formula; S302. Set the power supply capacity curve to a continuous curve of the dynamic power upper limit constraint changing with time within the prediction time window; The first calculation formula is:

[0048] in, In the prediction time window The dynamic power limit within, This is the reference output power of the energy storage module. This is the power correction factor based on the current state of charge (SOC). This is a power correction factor based on the current cell temperature. This is the aging correction factor based on the current state of health (SOH). The predicted input power for solar energy within the predicted time window.

[0049] In one specific embodiment of the present invention, the dynamic power upper limit constraint in step S2 is calculated in the following manner, assuming the energy storage module's reference output power... When the current SOC is 80% When the current cell temperature is 35℃ When SOH = 90% Solar power prediction input The dynamic power limit is: This means that within the predicted time window, the energy storage subsystem can provide up to 108.66W of power support to the network storage subsystem.

[0050] Figure 4 This is an embodiment of the mobile intelligent network storage control method for task power coordination regulation. Based on the dynamic power upper limit constraint in the power supply capacity constraint information, and combined with the task priorities and deadlines in the network storage resource pool status view, the method re-plans the currently running task queue to generate an optimized task execution plan and a flowchart of the corresponding releaseable power potential under the dynamic power upper limit constraint.

[0051] like Figure 4 As shown, in one or more embodiments, preferably, the step of replanning the currently running task queue based on the dynamic power upper limit constraint in the power supply capacity constraint information, combined with the task priorities and deadlines in the network storage resource pool status view, to generate an optimized task execution plan and corresponding releaseable power potential under the dynamic power upper limit constraint, specifically includes: S401. Calculate the overall scheduling priority of each task under the power upper limit constraint using the second calculation formula: S402. Based on the comprehensive scheduling priority weight of each task. Sort tasks from highest to lowest priority, ensuring high-priority tasks are handled first. The continuous execution of the value task, and when the total power consumption requirement exceeds At that time, according to The corresponding tasks are downclocked, delayed, or migrated in ascending order of their values ​​until the total power consumption requirement does not exceed [the specified value]. ; S403, the releasable power potential Calculated using the third calculation formula; The second calculation formula is:

[0052] in, For the first The overall scheduling priority weight of each task. This is the urgency index of the task, which is determined based on the task priority and deadline obtained in step S1. The higher the priority, the higher the urgency index. The larger the value and the closer the deadline, the better. The larger the value, The maximum urgency index in the current task queue. This represents the current power consumption of the task. The dynamic power upper limit constraint generated in step S2, The remaining estimated execution time for this task. The total estimated execution time for this task is... , , For preset weighting coefficients and ; The third calculation formula is:

[0053] in, For the set of delayed tasks, The set of tasks to be migrated. The set of tasks that have been downclocked. For the first The power consumption of each task at the current operating frequency. For the first Power consumption after frequency reduction for each task.

[0054] In one specific embodiment of the present invention, the comprehensive scheduling priority weight is calculated in the following manner:

[0055] in, For the first The overall scheduling priority weight of each task. The urgency index for this task (determined based on the task priority and deadline obtained in step S1; the higher the priority, the higher the urgency index). The larger the value and the closer the deadline, the better. (The larger the value) The maximum urgency index in the current task queue. This represents the current power consumption of the task. For dynamic power upper limit constraints, The remaining estimated execution time for this task. The total estimated execution time for this task is... , , For preset weighting coefficients and .

[0056] Suppose there are three tasks A, B, and C running simultaneously on the AI ​​NAS device, and the parameters of each task are shown in the table below:

[0057] Current dynamic power limit Maximum urgency index ,set up , , .

[0058] Overall scheduling priority weight for task A:

[0059] Overall scheduling priority weight for task B:

[0060] Overall scheduling priority weight for task C:

[0061] The task ranking result is: A (0.640) > B (0.495) > C (0.336). The system prioritizes the continuous execution of task A.

[0062] The current total power consumption requirement is Exceeding the power limit Process tasks in ascending order of weight: First, reduce the frequency of task C. If the power consumption of task C drops to [a certain value] after frequency reduction... Then the total power consumption becomes It still exceeds 110W; continue to perform delayed operations on task C, releasing 38W, and the total power consumption is reduced to Stop adjusting if the power does not exceed 110W.

[0063] The release potential of power Calculated using the third formula, for example: Downclocking task C: reducing from 50W to 35W, releasing... Delay execution for task B: release No tasks were migrated.

[0064] The unleashed power potential is:

[0065] Through task replanning, the system can release up to 50W of power reserves to cope with sudden power shortages.

[0066] Figure 5 This is a flowchart of a mobile intelligent network storage control method for task power collaborative regulation according to an embodiment of the present invention, in which the optimized task execution plan and its corresponding releaseable power potential are returned to the energy storage subsystem; the energy storage subsystem generates a flowchart of a joint scheduling instruction based on the received information, combined with the remaining power of the current energy storage resource pool and the status of the power input source, with the joint optimization of global power supply duration and high-priority task completion rate as the objective.

[0067] like Figure 5As shown, in one or more embodiments, preferably, the optimized task execution plan and its corresponding releaseable power potential are returned to the energy storage subsystem; the energy storage subsystem, based on the received information and in conjunction with the remaining power of the current energy storage resource pool and the status of the power input source, generates a joint scheduling instruction with the joint optimization of global power supply duration and high-priority task completion rate as the objective, specifically including: S501. Based on the execution time period and execution rate of each task in the optimized task execution plan, calculate the estimated total power consumption demand curve of the network storage subsystem at each moment within the prediction time window. And the estimated total power consumption demand curve and the power supply capacity curve are compared. Perform time-by-time comparison: when At that time, it is determined that supply and demand are in balance; S502, when At that time, it was determined that there was a power supply shortage; S503. Calculate the gap power value at each time using the fourth calculation formula; S504. Use the fifth calculation formula to solve for the final execution status of each high-priority task; The fourth calculation formula is:

[0068] Based on the described releaseable power potential, calculate the maximum power reserve that can be released in an emergency through task downscaling, delaying, or migration operations. and the gap power value With the maximum power reserve value Compare: If If so, the power reserve is used to fill the gap, and there is no need to adjust the execution status of high-priority tasks; if The joint optimization objectives are to maximize the global power supply duration and maximize the completion rate of high-priority tasks. The fifth calculation formula is:

[0069] in, To jointly optimize the objective function value, This is the estimated sustainable power supply duration of the current energy storage resource pool, taking into account solar supplementation. The estimated total time required to complete all current high-priority tasks. For a set of high-priority tasks, For the first The final execution status of a high-priority task ( Indicates execution. (Indicates not to execute). For the first The overall scheduling priority weight of each high-priority task. and To optimize the weighting coefficients and ; Based on the final execution status of each high-priority task The solution results are used to calculate the power allocation scheme for each power input source using the sixth calculation formula; The sixth calculation formula is:

[0070]

[0071]

[0072] in, , , They are respectively The power values ​​allocated to the mains power, energy storage module, and solar input source at all times. This is the maximum usable power of the mains electricity. This represents the final total power consumption requirement after optimizing the task execution status. This represents the maximum allowable discharge power of the energy storage module. for The actual input power of solar energy at any given time; The charging and discharging sequence of the energy storage module is determined according to the power allocation scheme: when Time control of energy storage module discharge, when Time control of energy storage module charging, when The system keeps the energy storage module in an idle state; simultaneously, it adjusts the execution status of each high-priority task based on its final execution status. Generate the final task execution strategy for each NAS device: The task remains to be performed. Tasks are scheduled according to overall scheduling priority weights Frequency reduction, delay, or migration operations are executed sequentially from low to high; the power allocation scheme, the charging and discharging timing, and the final task execution strategy together constitute the joint scheduling instruction.

[0073] In one specific embodiment of the present invention, based on the final execution state of each high-priority task... Based on the solution results, the power allocation scheme for each power input source is calculated in the following manner:

[0074]

[0075]

[0076] Suppose that after joint optimization, the system determines (Task A executed) (Task B execution) (Task C delay), final total power consumption requirement .

[0077] Current power supply capacity Actual solar energy input Maximum available power of mains electricity Maximum allowable discharge power of energy storage .

[0078] First, calculate the energy storage distribution power:

[0079] Next, calculate the power distribution from the mains:

[0080] A negative value indicates that no mains power is needed, and the 10W of surplus power can be used to charge the energy storage module. The final power allocation is: 20W from solar power, 70W from the energy storage module, and 0W from mains power, meeting the total power consumption requirement of 80W, while the energy storage module receives 10W of charging power.

[0081] Figure 6 This is a flowchart illustrating the process of simultaneously executing power compensation control and task execution control of each NAS device according to the joint scheduling instruction in a mobile intelligent network storage control method for task power coordination regulation according to an embodiment of the present invention.

[0082] like Figure 6 As shown, in one or more embodiments, preferably, the step of simultaneously executing power supply compensation control and task execution control of each NAS device according to the joint scheduling instruction specifically includes: According to the power allocation scheme in the joint dispatch instruction, the actual output power of the power supply supplement unit is collected in real time. Compare it with the target power allocation value in the joint scheduling instruction. Perform comparison and calculate deviation The dynamic power compensation amount is calculated using the seventh calculation formula. The seventh calculation formula is:

[0083] in, for The dynamic power value that needs to be compensated at all times. , , These are the proportional, integral, and derivative control coefficients, respectively. when When the power supply supplement unit increases its corresponding power output, it prioritizes the use of solar energy input, with the remaining portion supplemented by the energy storage module; when When the power supply supplement unit reduces its corresponding power output, it uses the excess power to charge the energy storage module; when Maintain the current power supply status; At the same time, the final task execution strategy in the joint scheduling instruction is issued to each NAS device: for tasks that need to be down-frequency, the operating frequency after down-frequency is calculated according to the eighth calculation formula and the down-frequency operation is executed. The eighth calculation formula is:

[0084] in, For the first The operating frequency of each task after frequency reduction For the first The current running frequency of each task. The joint scheduling instruction assigned to the first The target power consumption value for each task For the first The current power consumption of each task; For tasks that need to be delayed, calculate the maximum delay time according to the ninth calculation formula and perform the delay operation. The ninth calculation formula is:

[0085] in, For the first The maximum delay time for each task For the first The remaining estimated energy demand for each task. For the first The execution efficiency coefficient of each task. For the first The deadline for each task. For the current moment, This is the preset time buffer amount; For tasks that need to be migrated, the task and its associated data are migrated from the current NAS device to the target NAS device specified in the joint scheduling instruction to continue execution. The power supply compensation control and the task execution control are executed synchronously in time: after each task is down-frequency, delayed, or migrated, the real-time total power consumption requirement of the network storage subsystem is recalculated based on the actual power consumption value of each NAS device, and this real-time total power consumption requirement is used as the input of the power supply compensation control to ensure that the power supply compensation and task execution control form a real-time linkage; when the power supply compensation control detects a sudden drop in power supply capacity, a power warning signal is sent to the task execution control in advance before the power supply compensation response, triggering the task execution control to perform down-frequency or delayed operation in advance, so as to realize a rapid coordinated response between the power supply side and the storage side.

[0086] In one specific embodiment of the present invention, the dynamic power compensation amount is calculated using a proportional-integral-derivative (PID) control method, and the control parameters of the power supply supplement unit are assumed to be... , , Current target power Actual output power ,deviation Integral term Differential term .

[0087] The dynamic power compensation amount is:

[0088] The power supply supplement unit needs to increase its power output by 16.2W. Since there is still a surplus in the current solar input (actual input is 25W, 20W has been used, and there is still 5W left), the solar power will be used to increase the output by 5W first, and the remaining 11.2W will be supplemented by the energy storage module.

[0089] For tasks requiring frequency reduction, the eighth calculation formula is used to calculate the reduced operating frequency. Task C (file synchronization task) needs to be reduced from 50W to 35W. The current operating frequency of Task C is... .

[0090]

[0091] Task C is downclocked to 1.68GHz, and its power consumption is reduced to 35W, freeing up 15W of power to ensure high-priority tasks.

[0092] For tasks that need to be delayed, the maximum delay time is calculated using the ninth calculation formula. If task B (data backup task) needs to be delayed, the remaining estimated energy consumption of task B is calculated. Current power consumption Execution efficiency coefficient Deadline (Starting from 00:00 on the current day), current time Preset time buffer .

[0093] First, calculate the maximum delay time under energy consumption constraints:

[0094] Next, calculate the maximum delay time under the deadline constraint:

[0095] Take the smaller of the two values:

[0096] That is, task B can be delayed for up to 30 seconds, which ensures that it is completed before the deadline (including the 30-second buffer) and does not exceed the maximum delay time under its energy consumption constraints.

[0097] Figure 7 This is a flowchart illustrating the process of real-time acquisition of state change data of the energy storage resource pool and real-time acquisition of task execution progress data of each NAS device in the network storage resource pool in a mobile intelligent network storage control method for task power coordination regulation according to an embodiment of the present invention. The flowchart describes the process of closed-loop iteration based on the updated state view of the energy storage resource pool and the state view of the network storage resource pool until the system reaches a stable operating state.

[0098] like Figure 7 As shown, in one or more embodiments, preferably, the real-time acquisition of state change data of the energy storage resource pool, the real-time acquisition of task execution progress data of each NAS device in the network storage resource pool, and the closed-loop iteration based on the updated state view of the energy storage resource pool and the state view of the network storage resource pool until the system reaches a stable operating state, specifically includes: S701. During the execution of the joint scheduling instruction, the actual state of charge and actual cell temperature of the energy storage resource pool are collected in real time at a preset sampling period. They are compared with the predicted state of charge and predicted cell temperature within the prediction time window. If the deviation of any parameter exceeds the preset threshold, the power supply capacity curve is recalculated, and the power supply capacity constraint information is regenerated based on the updated power supply capacity curve. S702. At the same time, the actual completion progress of the current task being executed by each NAS device is collected in real time at a preset sampling period and compared with the planned completion progress in the optimized task execution plan. If the deviation between the actual completion progress and the planned completion progress of any task exceeds a preset threshold, the optimized task execution plan is recalculated and the corresponding releaseable power potential is regenerated according to the updated optimized task execution plan. S703. When the energy storage state deviation and the task execution progress deviation are both continuously lower than their respective preset thresholds and the duration exceeds the preset stability determination time, the system is determined to have reached a stable operating state and the closed-loop iteration is stopped.

[0099] In this embodiment of the invention, if new data is updated during the execution of the above process, the process needs to be readjusted and run to a stable operating state.

[0100] According to a second aspect of the present invention, a mobile intelligent network storage control system for coordinated control of task power consumption is provided.

[0101] Figure 8 This is a structural diagram of a mobile intelligent network storage control system for task power coordination regulation according to an embodiment of the present invention.

[0102] In one or more embodiments, preferably, the mobile intelligent network storage control system for task power coordination includes: Dual-pool status view module 801 is used to construct the energy storage resource pool status view and the network storage resource pool status view respectively. The power capacity constraint module 802 is used to calculate the power supply capacity curve and dynamic power upper limit constraint that can be used to support the network storage subsystem in the current and predicted time periods based on the energy storage resource pool status view, as power supply capacity constraint information. The replanning module 803 is used to replan the current running task queue based on the dynamic power upper limit constraint in the power supply capacity constraint information, combined with the task priority and deadline in the network storage resource pool status view, and generate an optimized task execution plan and corresponding releaseable power potential under the dynamic power upper limit constraint. The joint decision-making module 804 is used to return the optimized task execution plan and its corresponding releaseable power potential to the energy storage subsystem; the energy storage subsystem generates a joint scheduling instruction based on the received information, combined with the remaining power of the current energy storage resource pool and the status of the power input source, with the goal of jointly optimizing the global power supply duration and the completion rate of high-priority tasks. The joint scheduling module 805 is used to simultaneously perform power supply compensation control and task execution control of each NAS device according to the joint scheduling instruction. The closed-loop iterative control module 806 is used to collect real-time status change data of the energy storage resource pool and real-time task execution progress data of each NAS device in the network storage resource pool. Based on the updated status view of the energy storage resource pool and the status view of the network storage resource pool, it iterates in a closed loop until the system reaches a stable operating state.

[0103] In this embodiment of the invention, a system suitable for different structures is realized through a series of modular designs. This system can achieve closed-loop, reliable, and efficient execution through data acquisition, analysis, and control.

[0104] According to a third aspect of the present invention, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the method as described in any one of the first aspects of the present invention.

[0105] According to a fourth aspect of the present invention, an electronic device is provided. Figure 9 This is a structural diagram of an electronic device according to one embodiment of the present invention. Figure 9 The illustrated electronic device is a mobile intelligent network storage control device for general-purpose task power coordination. This electronic device can be a smartphone, tablet, or similar device. As shown, the electronic device 900 includes a processor 901 and a memory 902. The processor 901 and memory 902 are electrically connected. The processor 901 is the control center of the electronic device 900, connecting various parts of the terminal through various interfaces and lines. By running or calling computer programs stored in the memory 902, and by calling data stored in the memory 902, it executes various functions of the terminal and processes data, thereby performing overall monitoring of the terminal.

[0106] In this embodiment, the processor 901 in the electronic device 900 loads the instructions corresponding to the processes of one or more computer programs into the memory 902 according to the following steps, and the processor 901 runs the computer programs stored in the memory 902 to realize various functions: constructing a state view of the energy storage resource pool and a state view of the network storage resource pool respectively; calculating the power supply capacity curve and dynamic power upper limit constraint that can be used to support the network storage subsystem in the current and predicted time periods based on the energy storage resource pool state view, as power supply capacity constraint information; and replanning the currently running task queue based on the dynamic power upper limit constraint in the power supply capacity constraint information, combined with the task priorities and deadlines in the network storage resource pool state view, to generate a new task queue. The system optimizes the task execution plan and corresponding releaseable power potential under dynamic power upper limit constraints; it then returns the optimized task execution plan and corresponding releaseable power potential to the energy storage subsystem; based on the received information, and combined with the remaining power of the current energy storage resource pool and the status of the power input source, the energy storage subsystem generates a joint scheduling instruction with the goal of jointly optimizing the global power supply duration and the completion rate of high-priority tasks; according to the joint scheduling instruction, it simultaneously executes power compensation control and task execution control of each NAS device; it collects the status change data of the energy storage resource pool in real time, and collects the task execution progress data of each NAS device in the network storage resource pool in real time, and iterates in a closed loop according to the updated status view of the energy storage resource pool and the status view of the network storage resource pool until the system reaches a stable operating state.

[0107] Memory 902 can be used to store computer programs and data. The computer programs stored in memory 902 contain instructions that can be executed in the processor. Computer programs can be composed of various functional modules. Processor 901 executes various functional applications and data processing by calling the computer programs stored in memory 902.

[0108] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: In this invention, by building a dual-pool status view of energy storage and network storage and using a hierarchical calculation formula to quantify the upper limit of power supply and task scheduling weight, the power supply capacity and task load are accurately matched quantitatively.

[0109] In this invention, the dual optimization of maximizing power supply duration and achieving high completion rate of high-priority tasks is achieved through power supply and demand comparison, global joint optimization objective solution, and real-time closed-loop iterative control.

[0110] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 and optical storage) containing computer-usable program code.

[0111] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0112] 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 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0113] 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.

[0114] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A mobile intelligent network storage control method for task-based power coordination, characterized in that, The method includes: Construct status views for the energy storage resource pool and the network storage resource pool respectively; Based on the energy storage resource pool status view, calculate the power supply capacity curve and dynamic power upper limit constraint that can be used to support the network storage subsystem in the current and predicted time periods, as power supply capacity constraint information. Based on the dynamic power upper limit constraint in the power supply capacity constraint information, and combined with the task priorities and deadlines in the network storage resource pool status view, the current running task queue is replanned to generate an optimized task execution plan and corresponding releaseable power potential under the dynamic power upper limit constraint. The optimized task execution plan and its corresponding releaseable power potential are returned to the energy storage subsystem. Based on the received information, the energy storage subsystem combines the remaining power of the current energy storage resource pool with the status of the power input source, and generates a joint scheduling instruction with the goal of jointly optimizing the global power supply duration and the completion rate of high-priority tasks. According to the joint scheduling instructions, power supply compensation control and task execution control of each NAS device are executed simultaneously. The system collects real-time status change data of the energy storage resource pool and real-time task execution progress data of each NAS device in the network storage resource pool. It then iterates in a closed loop based on the updated status views of the energy storage resource pool and the network storage resource pool until the system reaches a stable operating state.

2. The mobile intelligent network storage control method for task-based power coordination as described in claim 1, characterized in that, The construction of the energy storage resource pool status view and the network storage resource pool status view respectively includes: The energy storage resource pool status view includes: preset baseline output power parameters of the energy storage module, which are pre-stored in the local parameter list of the energy storage controller; the total available power of the energy storage module, which is obtained by weighted summation of the state of charge and rated capacity of each cell unit; the state of charge and temperature distribution data of each cell unit, which are collected in real time by the battery management unit; the overall health status data of the energy storage module, which is periodically collected and updated by the battery management unit; the on / off status and power status of the mains power supply, which are obtained in real time by the mains power detection circuit; and the real-time output power of solar energy, which is collected in real time by the output terminal of the solar controller, and the estimated solar input power for the future prediction period is generated based on the real-time collected data and the irradiance time series prediction model. The network storage resource pool status view includes: the storage capacity utilization rate of each NAS device, which is obtained in real time through the file system of each device; the current running task queue and the priority and deadline of each task, which are obtained in real time through the task scheduler of each device.

3. The mobile intelligent network storage control method for task-based power coordination as described in claim 1, characterized in that, The step of calculating the power supply capacity curve and dynamic power upper limit constraint that can be used to support the network storage subsystem in the current and predicted time periods based on the energy storage resource pool status view, as power supply capacity constraint information, specifically includes: Calculate the dynamic power upper limit constraint using the first calculation formula; The power supply capacity curve is set as a continuous curve of the dynamic power upper limit constraint changing with time within the prediction time window; The first calculation formula is: in, In the prediction time window Dynamic power upper limit constraint within, This is the reference output power of the energy storage module. This is the power correction factor based on the current state of charge (SOC). This is a power correction factor based on the current cell temperature. This is the aging correction factor based on the current state of health (SOH). The predicted input power for solar energy within the predicted time window.

4. The mobile intelligent network storage control method for task-based power coordination as described in claim 1, characterized in that, The step of replanning the currently running task queue based on the dynamic power upper limit constraint in the power supply capacity constraint information, combined with the task priorities and deadlines in the network storage resource pool status view, to generate an optimized task execution plan and corresponding releaseable power potential under the dynamic power upper limit constraint, specifically includes: Based on the urgency index of each task, the current power consumption and the remaining execution time, the comprehensive scheduling priority weight of each task under the dynamic power limit constraint is calculated, and the tasks are sorted from high to low according to the comprehensive scheduling priority weight, so as to give priority to the continuous execution of high-weight tasks. When the total power consumption demand exceeds the dynamic power limit constraint, the corresponding tasks are sequentially subjected to frequency reduction, delay or migration operations in order of comprehensive scheduling priority weight from low to high, until the total power consumption demand does not exceed the dynamic power limit constraint. The releasable power potential is calculated based on the power consumption of the task being down-clocked, delayed, or migrated. The releasable power potential is the sum of the power consumption of the delayed task, the power consumption of the migrated task, and the power consumption difference of the down-clocked task before and after down-clocking.

5. The mobile intelligent network storage control method for task-based power coordination as described in claim 1, characterized in that, The optimized task execution plan and its corresponding releaseable power potential are returned to the energy storage subsystem. Based on the received information, and considering the remaining power in the current energy storage resource pool and the status of the power input source, the energy storage subsystem generates a joint scheduling instruction with the goal of jointly optimizing the global power supply duration and the completion rate of high-priority tasks. This instruction specifically includes: Based on the execution time period and execution rate of each task in the optimized task execution plan, calculate the estimated total power consumption demand curve of the network storage subsystem at each moment within the prediction time window. And the estimated total power consumption demand curve and the power supply capacity curve are compared. Perform hourly comparison: when At that time, it is determined that supply and demand are in balance; when When a power supply gap is identified, the gap power value at each moment is calculated using the fourth calculation formula. The fourth calculation formula is: Based on the described releaseable power potential, calculate the maximum power reserve that can be released in an emergency through task downscaling, delaying, or migration operations. and the gap power value With the maximum power reserve value Compare: If If so, the power reserve is used to fill the gap, and there is no need to adjust the execution status of high-priority tasks; if Then, with the maximization of global power supply duration and the maximization of high-priority task completion rate as the joint optimization objectives, the final execution state of each high-priority task is solved using the fifth calculation formula. The fifth calculation formula is: in, To jointly optimize the objective function value, This is the estimated sustainable power supply duration of the current energy storage resource pool, taking into account solar supplementation. The estimated total time required to complete all current high-priority tasks. For a set of high-priority tasks, For the first The final execution status of a high-priority task. Indicates execution. Indicates that it will not be executed. For the first The overall scheduling priority weight of each high-priority task. and To optimize the weighting coefficients and ; Based on the solution results of the final execution status of each high-priority task, the power allocation scheme of each power input source, the charging and discharging sequence of the energy storage module, and the final task execution strategy of each NAS device are determined. The power allocation scheme, the charging and discharging sequence, and the final task execution strategy together constitute the joint scheduling instruction.

6. The mobile intelligent network storage control method for task-based power coordination as described in claim 1, characterized in that, The simultaneous execution of power compensation control and task execution control for each NAS device according to the joint scheduling instruction specifically includes: According to the power allocation scheme and charging / discharging sequence in the joint dispatch instruction, the actual output power of the power supply supplement unit is collected in real time, compared with the target power allocation value in the joint dispatch instruction, and the deviation is calculated. The dynamic power compensation is calculated using proportional-integral-derivative control: when the dynamic power compensation is positive, the power supply supplement unit increases the corresponding power output, prioritizing the use of solar energy input, with the remaining portion supplemented by the energy storage module; when the dynamic power compensation is negative, the power supply supplement unit reduces the corresponding power output, and the excess power is used to charge the energy storage module; when the dynamic power compensation is zero, the current power supply state is maintained. The power supply supplement unit includes mains power, solar energy, and an energy storage module. The final task execution strategy in the joint scheduling instruction is issued to each NAS device: For tasks that need to be frequency-reduced, the operating frequency after frequency reduction is calculated based on the ratio between the target power consumption value and the current power consumption value, and the frequency reduction operation is executed; For tasks that need to be delayed, the maximum delay time is calculated based on the remaining estimated power consumption requirement of the task, the current power consumption, the execution efficiency coefficient, and the deadline, and the delay operation is executed; For tasks that need to be migrated, the task and its associated data are migrated from the current NAS device to the target NAS device specified in the joint scheduling instruction to continue execution.

7. The mobile intelligent network storage control method for task-based power coordination as described in claim 1, characterized in that, The process involves real-time acquisition of status change data from the energy storage resource pool and real-time acquisition of task execution progress data from each NAS device in the network storage resource pool. A closed-loop iteration is then performed based on the updated status views of the energy storage resource pool and the network storage resource pool until the system reaches a stable operating state. Specifically, this includes: During the execution of the joint scheduling command, the actual state of charge and actual cell temperature of the energy storage resource pool are collected in real time at a preset sampling period. They are compared with the predicted state of charge and predicted cell temperature within the prediction time window. If the deviation of any parameter exceeds a preset threshold, the power supply capacity curve is recalculated, and the power supply capacity constraint information is regenerated based on the updated power supply capacity curve. Meanwhile, the actual completion progress of the tasks currently being executed by each NAS device is collected in real time at a preset sampling period and compared with the planned completion progress in the optimized task execution plan. If the deviation between the actual completion progress and the planned completion progress of any task exceeds a preset threshold, the optimized task execution plan is recalculated and the corresponding releaseable power potential is regenerated based on the updated optimized task execution plan. When the deviations between the actual state of charge of the energy storage resource pool and the actual cell temperature, as well as the deviations from the planned completion progress, are all consistently lower than their respective preset thresholds, and the duration exceeds the preset stability judgment time, the system is determined to have reached a stable operating state and the closed-loop iteration is stopped.

8. A mobile intelligent network storage control system for coordinated control of task power consumption, characterized in that, The system is used to implement the method as described in any one of claims 1-7, the system comprising: The dual-pool status view module is used to build the status view of the energy storage resource pool and the status view of the network storage resource pool, respectively. The power capacity constraint module is used to calculate the power supply capacity curve and dynamic power upper limit constraint that can be used to support the network storage subsystem in the current and predicted time periods based on the energy storage resource pool status view, as power supply capacity constraint information. The replanning module is used to replan the current running task queue based on the dynamic power upper limit constraint in the power supply capacity constraint information, combined with the task priority and deadline in the network storage resource pool status view, and generate an optimized task execution plan and corresponding releaseable power potential under the dynamic power upper limit constraint. The joint decision-making module is used to return the optimized task execution plan and its corresponding releaseable power potential to the energy storage subsystem. Based on the received information, the energy storage subsystem combines the remaining power of the current energy storage resource pool with the status of the power input source, and generates a joint scheduling instruction with the goal of jointly optimizing the global power supply duration and the completion rate of high-priority tasks. The joint scheduling module is used to simultaneously perform power supply compensation control and task execution control of each NAS device according to the joint scheduling instructions. The closed-loop iterative control module is used to collect real-time status change data of the energy storage resource pool and real-time task execution progress data of each NAS device in the network storage resource pool. Based on the updated status view of the energy storage resource pool and the status view of the network storage resource pool, it iterates in a closed loop until the system reaches a stable operating state.

9. A computer-readable storage medium storing computer program instructions thereon, characterized in that, The computer program instructions, when executed by a processor, implement the method as described in any one of claims 1-7.

10. An electronic device comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in any one of claims 1-7.

Images