Data center computing power and electric power cooperative regulation and control system based on big data

Abstract

The invention relates to the technical field of electric power energy data management, and particularly discloses a big data-based data center computing power and electric power collaborative regulation and control system, which comprises a data sensing module, a fusion modeling module, a simulation analysis module and a collaborative regulation and control module. According to the scheme, a unified computing power-electric power fusion model is constructed, an accurate and quantitative bridge is established between a computing power scheduling instruction and electric power load change, the influence of an environment temperature and computing power task mixed mode on energy consumption is accurately reflected through dynamic CLF model and data driving calibration, and the electric power load prediction precision is effectively improved; through high-precision prediction and simulation, the adjustable potential of the data center is quantified, the power consumption behavior is dynamically adjusted according to a power grid signal, automatic optimization is carried out among multiple targets through an intelligent optimization algorithm, and the operation of a power grid is stabilized.

Description

Technical Field

[0001] This invention relates to the field of power energy data management technology, specifically to a data center computing power-electricity collaborative control system based on big data. Background Technology

[0002] With the booming development of cloud computing, artificial intelligence, and the digital economy, the global demand for computing power and energy consumption of data centers has exploded. Data centers have become critical energy-consuming units, with electricity costs accounting for a very high proportion of their operating costs. At the same time, the intensive power consumption of data centers also puts pressure on the stable operation of regional power grids, especially during peak electricity consumption periods. Traditional computing power models and power models are heterogeneous, one based on task queues and resource utilization, and the other based on physical power consumption and thermodynamics. The two cannot communicate directly, making it impossible to assess the impact of computing power scheduling decisions on power load from a global perspective. Traditional solutions are mostly passive and reactive in their regulation, unable to proactively and actively utilize computing power as a flexible resource to participate in the power grid's DSR (demand-side response). Summary of the Invention

[0003] To address the above issues and overcome the shortcomings of existing technologies, this invention provides a data center computing power and power coordinated control system based on big data. Addressing the problem that traditional computing power and power models are heterogeneous—one based on task queues and resource utilization, and the other on physical power consumption and thermodynamics—they cannot directly communicate, making it impossible to assess the impact of computing power scheduling decisions on power load from a global perspective. This solution constructs a unified computing power-power fusion model, establishing a precise and quantitative bridge between computing power scheduling commands and power load changes. Through a dynamic CLF (Cooling Load Factor) model and data-driven calibration, it accurately reflects the impact of ambient temperature and mixed computing power task modes on energy consumption, effectively improving the accuracy of power load prediction. Furthermore, addressing the problem that traditional solutions are mostly passive and reactive in their control, unable to proactively and actively utilize computing power as a flexible resource in the power grid's DSR (Dynamic Resource Regulation), this solution quantifies the adjustable potential of data centers through high-precision prediction and simulation, dynamically adjusts power consumption behavior based on power grid signals, and automatically seeks optimization among multiple objectives through intelligent optimization algorithms to stabilize power grid operation.

[0004] The data center computing power and power coordinated control system based on big data provided by this invention includes a data sensing module, a fusion modeling module, a simulation analysis module, and a coordinated control module;

[0005] The data sensing module collects operational and energy consumption data of IT equipment inside the data center, as well as external power grid and environmental data.

[0006] The fusion modeling module constructs a data center computing power-power fusion model that describes the intrinsic relationship between computing power tasks and power load through data mechanism fusion modeling.

[0007] The simulation analysis module is based on the computing power-power fusion model to simulate different computing power task scheduling schemes, predict the resulting spatiotemporal changes in power load, and generate a complete simulation evaluation report.

[0008] The coordinated control module uses an optimization algorithm based on the simulation evaluation report to solve for the optimal computing power-electricity coordinated control strategy, and performs joint control of computing power resources and electricity resources.

[0009] Furthermore, the fusion modeling module includes a parameter calculation unit, a power load modeling unit, a computing power load modeling unit, a data-driven unit, and a model fusion unit;

[0010] The parameter calculation unit takes in internal and external data collected by the data sensing module, calculates PUE (Power Usage Effectiveness), sets initial parameters, and constructs a dynamic CLF model. The formula used is as follows: ; ;

[0011] In the formula, Indicates energy efficiency. This represents the total power consumption of the data center. This indicates the total power consumption of IT equipment. Indicates the cooling load factor. Indicates ambient temperature. This indicates the total load factor of IT equipment. Indicates the environmental temperature sensitivity coefficient. This represents the IT load sensitivity coefficient. Indicates the basic coefficient of performance (COP).

[0012] The power load modeling unit, based on the operating data and energy consumption data of IT equipment within the data center, describes the total power consumption on the power load side of the data center from a macro perspective and constructs a power load mechanism model, the model of which is as follows: ; ;

[0013] In the formula, Indicates infrastructure energy consumption;

[0014] The computing load modeling unit combines data center operation data to analyze the server's operating status when handling different computing tasks, establishes the relationship between server power consumption and computing load at a micro level, and constructs a computing load mechanism model, the model of which is as follows: ;

[0015] In the formula, This indicates the total power consumption of the server. This indicates the idle power consumption of the server when there are no computing tasks. This indicates the server's full-load power consumption. Indicates the utilization rate of the central processing unit;

[0016] The data-driven unit constructs a data-driven model based on the gradient boosting decision tree algorithm. A high-dimensional feature vector is constructed using historical operational data of data center IT equipment. A data-driven model is then used to extract the correlation features between the high-dimensional feature vector and server power consumption. The model is as follows: ;

[0017] In the formula, This represents the predicted server power consumption. This represents a data-driven model. Represents a high-dimensional feature vector;

[0018] The model fusion unit calibrates the parameters of the power load mechanism model based on the data-driven model to form a data center computing power-power fusion model. .

[0019] Furthermore, the model fusion unit includes a load characterization subunit, a parameter calibration subunit, and a model fusion subunit;

[0020] The load characterization subunit analyzes the distribution of high-dimensional feature vectors to generate a context vector characterizing the current computing load characteristics of the data center. ;

[0021] The parameter calibration subunit constructs a calibration model based on a shallow neural network. The process involves taking the context vector and external environment data as input, using a calibration model to output the optimal parameters of the dynamic CLF model, enabling the dynamic CLF model to adapt to the specific computing power task hybrid mode of the current data center. The formula used is as follows: ;

[0022] In the formula, Represents the context vector. Indicates the calibration model, Represents the optimal parameters of the dynamic CLF model;

[0023] The model fusion subunit substitutes the optimal parameters into the dynamic CLF model to form and output a data center computing power-power fusion model. The updated power load mechanism model is represented as follows: .

[0024] Furthermore, the simulation analysis module includes a simulation scenario definition unit, a simulation deduction unit, a power load calculation unit, and a result quantification unit;

[0025] The simulation scenario definition unit obtains a set of candidate computing power task scheduling schemes for the data center. and the external environment data sequence for the future period. The candidate scheduling schemes in the candidate computing power task scheduling scheme set are structured instruction sets that describe the spatiotemporal redistribution of computing power tasks.

[0026] The simulation and deduction unit simulates each candidate scheduling scheme. Within each simulation time step, it updates the server's task load based on the real-time operating data of the internal IT equipment and calculates the computing power index at each moment.

[0027] The power load calculation unit inputs the current task load and external environment data sequence into the computing power-power fusion model to calculate the total power consumption of the data center at that moment, and generates a total power consumption curve for each candidate scheduling scheme. The formula used is as follows: ;

[0028] In the formula, The total power consumption curve in the simulation is shown. This represents the computing power task scheduling scheme. Represents a sequence of data from the external environment;

[0029] The result quantization unit performs in-depth analysis on the total power consumption curve of the simulation output, generates multi-dimensional evaluation indicators, and generates a complete simulation evaluation report for each candidate scheduling scheme.

[0030] Furthermore, the collaborative control module includes an objective function construction unit, a constraint modeling unit, an optimization algorithm solving unit, and a strategy output unit;

[0031] The objective function construction unit performs multi-objective optimization based on the simulation evaluation report, transforming multi-dimensional evaluation indicators into a comprehensive objective function. The optimization objective is to minimize the total cost, and the formula used is as follows: ;

[0032] In the formula, This indicates the operation of minimizing the comprehensive objective function. Represents the overall objective function. Represents the function to be minimized. This represents the electricity cost obtained from the simulation. This represents the carbon emissions obtained from the simulation. This refers to the additional benefits gained by responding to grid signals. Indicates the economic cost weight. Indicates the environmental cost weight. Indicates the weight of grid revenue;

[0033] The constraint modeling unit constructs the policy constraints of the data center, including computing resource constraints, power capacity constraints, and other constraints.

[0034] The optimization algorithm solution unit uses a genetic algorithm to iteratively update all candidate scheduling scheme combinations, calculates the comprehensive objective function value, and converges to obtain a set of optimal computing power task scheduling schemes. ;

[0035] The strategy output unit outputs the optimal computing power task scheduling scheme, which is decomposed into an executable computing power scheduling instruction set and a power control instruction set, and then sent to the computing power scheduling engine and power control engine of the data center, respectively.

[0036] The beneficial effects achieved by the present invention using the above solution are as follows:

[0037] (1) In view of the fact that traditional computing power models and power models are heterogeneous, one is based on task queues and resource utilization, and the other is based on physical power consumption and thermodynamics. The two cannot communicate directly, which makes it impossible to evaluate the impact of computing power scheduling decisions on power load from a global perspective. This solution constructs a unified computing power-power fusion model, establishes an accurate and quantitative bridge between computing power scheduling instructions and power load changes, and accurately reflects the impact of ambient temperature and computing power task hybrid mode on energy consumption through dynamic CLF model and data-driven calibration, effectively improving the accuracy of power load prediction.

[0038] (2) In view of the fact that traditional schemes are mostly passive and responsive in their regulation and control, and cannot proactively and actively use computing power as a flexible resource to participate in the DSR of the power grid, this scheme quantifies the adjustable potential of the data center through high-precision prediction and simulation, dynamically adjusts the power consumption behavior according to the power grid signal, and automatically seeks the best among multiple objectives through intelligent optimization algorithms to stabilize the operation of the power grid. Attached Figure Description

[0039] Figure 1 This is a schematic diagram of the data center computing power and power coordinated control system based on big data proposed in this invention;

[0040] Figure 2 This is a schematic diagram of the fusion modeling module.

[0041] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. Detailed Implementation

[0042] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0043] Example 1, see Figure 1 The data center computing power and power coordinated control system based on big data provided by the present invention includes a data sensing module, a fusion modeling module, a simulation analysis module and a coordinated control module;

[0044] The data sensing module collects operational and energy consumption data of IT equipment inside the data center, as well as external power grid and environmental data.

[0045] The fusion modeling module constructs a data center computing power-power fusion model that describes the intrinsic relationship between computing power tasks and power load through data mechanism fusion modeling.

[0046] The simulation analysis module is based on the computing power-power fusion model to simulate different computing power task scheduling schemes, predict the resulting spatiotemporal changes in power load, and generate a complete simulation evaluation report.

[0047] The coordinated control module uses an optimization algorithm based on the simulation evaluation report to solve for the optimal computing power-electricity coordinated control strategy, and performs joint control of computing power resources and electricity resources.

[0048] Example 2, see Figure 1 This embodiment is based on the above embodiment, and in the data sensing module:

[0049] Internal IT equipment operation data includes: CPU utilization, memory utilization, disk I / O rate, network bandwidth utilization, GPU utilization, task queue length, process / service list, number and status of virtual machines / containers;

[0050] Energy consumption data includes: server rack power consumption, single server power consumption, storage device power consumption, network device power consumption, total cooling system power consumption, power supply and distribution system losses, and total data center input power consumption.

[0051] External grid data includes: time-of-use pricing, real-time pricing, demand-side response incentive signals, peak demand alerts, and carbon emission factors;

[0052] Environmental data include: outdoor dry-bulb temperature, outdoor wet-bulb temperature, relative humidity, atmospheric pressure, wind speed and direction, and weather forecast data.

[0053] Example 3, see Figure 1 and Figure 2 This embodiment is based on the above embodiment, and the fusion modeling module includes a parameter calculation unit, a power load modeling unit, a computing power load modeling unit, a data driving unit, and a model fusion unit;

[0054] The parameter calculation unit takes into account the internal and external data collected by the data sensing module, calculates the PUE, sets initial parameters, constructs a dynamic CLF model, collects historical operating data samples from the data center, and calculates the fitting environmental temperature sensitivity coefficient, IT load sensitivity coefficient, and basic cooling coefficient by means of the average values. The initial values ​​are 0.01, 0.005, and 0.1, respectively, and the formulas used are as follows: ; ;

[0055] In the formula, Indicates energy efficiency. This represents the total power consumption of the data center. This indicates the total power consumption of IT equipment. Indicates the cooling load factor. Indicates ambient temperature. This indicates the total load factor of IT equipment. Indicates the environmental temperature sensitivity coefficient. This represents the IT load sensitivity coefficient. Indicates the basic coefficient of performance (COP).

[0056] The power load modeling unit, based on the operating data and energy consumption data of IT equipment within the data center, describes the total power consumption on the power load side of the data center from a macro perspective and constructs a power load mechanism model, the model of which is as follows: ; ;

[0057] In the formula, Indicates infrastructure energy consumption;

[0058] The computing load modeling unit combines data center operation data to analyze the server's operating status when handling different computing tasks, establishes the relationship between server power consumption and computing load at a micro level, and constructs a computing load mechanism model, the model of which is as follows: ;

[0059] In the formula, This indicates the total power consumption of the server. This indicates the idle power consumption of the server when there are no computing tasks. This indicates the server's full-load power consumption. Indicates the utilization rate of the central processing unit;

[0060] The data-driven unit employs the XGBoost framework, constructing high-dimensional feature vectors using historical operating data of data center IT equipment over the past 3 to 6 months. These vectors are randomly divided into training and validation sets in a 7:3 ratio. The predicted server power consumption is iteratively trained on the training set, and the model loss is calculated on the validation set. Training terminates when the model loss no longer decreases after 10 consecutive rounds, and the model at this point is saved as the data-driven model. To predict server power consumption, the following methods are used: ;

[0061] In the formula, This represents the predicted server power consumption. This represents a data-driven model. Represents a high-dimensional feature vector;

[0062] The model fusion unit calibrates the parameters of the power load mechanism model based on the data-driven model to form a data center computing power-power fusion model. .

[0063] Example 4, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In the data-driven unit, the high-dimensional feature vector includes:

[0064] Core resource utilization characteristics: CPU utilization, memory utilization, disk I / O throughput, disk I / O operation frequency, and network I / O throughput;

[0065] Semantic features of computational tasks: task type encoding, process / service name;

[0066] Hardware architecture and status characteristics: CPU core operating frequency, CPU core voltage, instructions per clock cycle, cache hit rate, hardware performance counter events;

[0067] System-level and contextual characteristics: system load, number of concurrent threads, and time characteristics.

[0068] Example 5, see Figure 1 and Figure 2 This embodiment is based on the above embodiment, and the model fusion unit includes a load characterization subunit, a parameter calibration subunit, and a model fusion subunit;

[0069] The load characterization subunit analyzes the distribution of high-dimensional feature vectors to generate a context vector characterizing the current computing load characteristics of the data center. ;

[0070] The parameter calibration subunit uses a fully connected feedforward neural network to construct the calibration model. Input layer settings and context vectors With the same number of neurons in the same dimension, a single hidden layer is set, using the ReLU activation function. The output layer has three neurons, corresponding to the three optimal parameters calibrated by the dynamic CLF model. The formula used is as follows: ;

[0071] In the formula, Represents the context vector. Indicates the calibration model, Represents the optimal parameters of the dynamic CLF model;

[0072] The model fusion subunit substitutes the optimal parameters into the dynamic CLF model to form and output a data center computing power-power fusion model. The updated power load mechanism model is represented as follows: .

[0073] By performing the aforementioned operations, this solution addresses the problem that traditional computing power models and power models are heterogeneous—one based on task queues and resource utilization, and the other on physical power consumption and thermodynamics—and cannot directly communicate, making it impossible to assess the impact of computing power scheduling decisions on power load from a global perspective. This solution constructs a unified computing power-power fusion model, establishing a precise and quantitative bridge between computing power scheduling instructions and power load changes. Through a dynamic CLF model and data-driven calibration, it accurately reflects the impact of ambient temperature and mixed computing power task modes on energy consumption, effectively improving the accuracy of power load forecasting.

[0074] Example 6, see Figure 1 This embodiment is based on the above embodiment, and the simulation analysis module includes a simulation scenario definition unit, a simulation deduction unit, a power load calculation unit, and a result quantification unit;

[0075] The simulation scenario definition unit obtains a set of candidate computing power task scheduling schemes for the data center. and the external environment data sequence for the next 24 hours. The candidate scheduling schemes in the candidate computing power task scheduling scheme set are structured instruction sets that describe the spatiotemporal redistribution of computing power tasks, including time migration, spatial migration, load solidification, and dynamic performance adjustment; the external environment data sequence includes the grid time-of-use price curve, demand-side response incentive signals, future temperature curves, and renewable energy predicted output curves.

[0076] The simulation and deduction unit simulates each candidate scheduling scheme. Within each simulation time step, it updates the server's task load based on the real-time operating data of the internal IT equipment and calculates the computing power index at each moment. The computing power index includes total CPU utilization and average memory utilization.

[0077] The power load calculation unit inputs the current task load and external environment data sequence into the computing power-power fusion model to calculate the total power consumption of the data center at that moment, and generates a total power consumption curve for each candidate scheduling scheme. The formula used is as follows: ;

[0078] In the formula, The total power consumption curve in the simulation is shown. This represents the computing power task scheduling scheme. Represents a sequence of data from the external environment;

[0079] The result quantification unit performs in-depth analysis on the total power consumption curve of the simulation output, generates multi-dimensional evaluation indicators, including power load spatiotemporal transfer quantification, adjustability potential assessment, economic and environmental pre-assessment, and generates a complete simulation evaluation report for each candidate scheduling scheme.

[0080] Example 7, see Figure 1 This embodiment is based on the above embodiment, and the collaborative control module includes an objective function construction unit, a constraint condition modeling unit, an optimization algorithm solving unit, and a strategy output unit;

[0081] The objective function construction unit performs multi-objective optimization based on the simulation evaluation report, transforming multi-dimensional evaluation indicators into a comprehensive objective function. The optimization objective is to minimize the total cost. Economic cost weights, environmental cost weights, and grid revenue weights are set according to the multi-dimensional evaluation indicators, with values ​​ranging from 0 to 1, and satisfying normalization conditions. The formula for the overall objective function is as follows: ;

[0082] In the formula, This indicates the operation of minimizing the comprehensive objective function. Represents the overall objective function. Represents the function to be minimized. This represents the electricity cost obtained from the simulation. This represents the carbon emissions obtained from the simulation. This refers to the additional benefits gained by responding to grid signals. Indicates the economic cost weight. Indicates the environmental cost weight. Indicates the weight of grid revenue;

[0083] The constraint modeling unit constructs the policy constraints of the data center, including computing resource constraints, power capacity constraints, and other constraints.

[0084] The optimization algorithm solution unit uses a genetic algorithm to iteratively update all candidate scheduling scheme combinations. Real-number encoding is used, with a population size of 100 individuals, each representing a complete computing task scheduling scheme. A tournament selection method with a size of 3 is employed, simulating binary crossover with a crossover probability of 0.9, and polynomial mutation is used. Iteration stops when the optimal solution shows an improvement of less than 1e-6 over 50 consecutive generations, converging to obtain a set of optimal computing task scheduling schemes. ;

[0085] The strategy output unit outputs the optimal computing power task scheduling scheme, which is decomposed into an executable computing power scheduling instruction set and a power control instruction set, and then sent to the computing power scheduling engine and power control engine of the data center, respectively.

[0086] By performing the aforementioned operations, we can address the problem that traditional solutions are mostly passive and reactive in their regulation, failing to proactively and actively utilize computing power as a flexible resource to participate in the DSR of the power grid. This solution quantifies the adjustable potential of data centers through high-precision prediction and simulation, dynamically adjusts power consumption behavior based on power grid signals, and automatically seeks optimization among multiple objectives through intelligent optimization algorithms to stabilize the operation of the power grid.

[0087] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0088] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

[0089] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. A data center computing power and power coordinated control system based on big data, characterized in that: It includes a data perception module, a fusion modeling module, a simulation analysis module, and a collaborative control module; The data sensing module collects operational and energy consumption data of IT equipment inside the data center, as well as external power grid and environmental data. The fusion modeling module constructs a data center computing power-power fusion model that describes the intrinsic relationship between computing power tasks and power load through data mechanism fusion modeling. The simulation analysis module is based on the computing power-power fusion model to simulate different computing power task scheduling schemes, predict the resulting spatiotemporal changes in power load, and generate a complete simulation evaluation report. The coordinated control module uses an optimization algorithm based on the simulation evaluation report to solve for the optimal computing power-electricity coordinated control strategy, and performs joint control of computing power resources and electricity resources.

2. The data center computing power and power coordinated control system based on big data according to claim 1, characterized in that: The fusion modeling module includes a parameter calculation unit, a power load modeling unit, a computing power load modeling unit, a data driving unit, and a model fusion unit; The parameter calculation unit takes in the internal and external data collected by the data sensing module, calculates the PUE, sets the initial parameters, and constructs a dynamic CLF model. The power load modeling unit describes the total power consumption on the power load side of the data center from a macro perspective, based on the operating data and energy consumption data of the IT equipment inside the data center, and constructs a power load mechanism model. The computing load modeling unit combines data center operation data to analyze the operating status of the server when processing different computing tasks, establishes the relationship between server power consumption and computing load from a micro level, and constructs a computing load mechanism model. The data-driven unit constructs a data-driven model based on the gradient boosting decision tree algorithm and uses historical operating data of data center IT equipment to construct a high-dimensional feature vector. The model fusion unit calibrates the parameters of the power load mechanism model based on the data-driven model to form a data center computing power-power fusion model.

3. The data center computing power and power coordinated control system based on big data according to claim 2, characterized in that: The model fusion unit includes a load characterization subunit, a parameter calibration subunit, and a model fusion subunit; The load characterization subunit analyzes the distribution of high-dimensional feature vectors and generates a context vector characterizing the current computing load characteristics of the data center. The parameter calibration subunit constructs a calibration model based on a shallow neural network, takes context vectors and external environment data as input, and uses the calibration model to output the optimal parameters of the dynamic CLF model. The model fusion subunit substitutes the optimal parameters into the dynamic CLF model to form and output the data center computing power-power fusion model, and updates the power load mechanism model.

4. The data center computing power and power coordinated control system based on big data according to claim 1, characterized in that: The simulation analysis module includes a simulation scenario definition unit, a simulation deduction unit, a power load calculation unit, and a result quantification unit. The simulation scenario definition unit obtains a set of candidate computing power task scheduling schemes for the data center, as well as a sequence of external environment data for a future period of time; The simulation and deduction unit simulates each candidate scheduling scheme. Within each simulation time step, it updates the server's task load based on the real-time operating data of the internal IT equipment and calculates the computing power index at each moment. The power load calculation unit inputs the current task load and external environment data sequence into the computing power-power fusion model to calculate the total power consumption of the data center at that moment and generate a total power consumption curve for each candidate scheduling scheme. The result quantization unit performs in-depth analysis on the total power consumption curve of the simulation output, generates multi-dimensional evaluation indicators, and generates a complete simulation evaluation report for each candidate scheduling scheme.

5. The data center computing power and power coordinated control system based on big data according to claim 1, characterized in that: The coordinated control module includes an objective function construction unit, a constraint modeling unit, an optimization algorithm solving unit, and a strategy output unit; The objective function construction unit performs multi-objective optimization based on the simulation evaluation report, transforming multi-dimensional evaluation indicators into a comprehensive objective function, with the optimization objective being to minimize the total cost. The constraint modeling unit constructs the policy constraints of the data center, including computing resource constraints, power capacity constraints, and other constraints. The optimization algorithm solution unit uses a genetic algorithm to iteratively update all candidate scheduling scheme combinations, calculates the comprehensive objective function value, and converges to obtain a set of optimal computing power task scheduling schemes. The strategy output unit outputs the optimal computing power task scheduling scheme, which is decomposed into an executable computing power scheduling instruction set and a power control instruction set, and then sent to the computing power scheduling engine and power control engine of the data center, respectively.

Images