Optimized scheduling method and device based on resource collaboration and electronic equipment

Abstract

The invention provides an optimal scheduling method and device based on resource collaboration and electronic equipment, and belongs to the technical field of power systems. The method comprises the following steps: constructing a computing power network objective function based on a computing power task of a computing power network; solving the computing power network objective function to obtain an optimal scheduling result of the computing power task, and determining the computing power load demand quantity of the computing power task based on the optimal scheduling result of the computing power task; determining target influence data of a power grid target function based on a comparison result of the computing power load demand quantity and the maximum power supply quantity of a distributed power supply in the power grid; and constructing a power grid target function based on the target influence data, and solving the power grid target function to obtain an optimal scheduling result of the power grid so as to realize resource collaborative optimal scheduling. The method is used for solving the problem that the stability and the economical efficiency of the whole power system are affected due to the fact that high energy consumption of a computing power center and volatility of the power system are not effectively matched in a traditional optimization scheduling method.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a resource-coordinated optimization scheduling method, a resource-coordinated optimization scheduling device, an electronic device, a machine-readable storage medium, and a computer program product. Background Art

[0002] With the rapid development of technologies like artificial intelligence and big data, the demand for computing power has skyrocketed, placing higher demands on the stability and sustainability of power systems. The power grid serves as the infrastructure for energy transmission, while the computing network serves as the core platform for information processing. Traditional optimization and scheduling methods for the computing network and the power grid often operate independently. This results in an inability to effectively match the high energy consumption of computing centers with the volatility of the power system, impacting the stability and economic efficiency of the overall power system. Summary of the Invention

[0003] The purpose of the embodiments of the present invention is to provide an optimization scheduling method, device and electronic equipment based on resource collaboration to solve the problem that in traditional optimization scheduling methods, the optimization scheduling methods for computing power networks and power grids mostly operate independently, resulting in the high energy consumption of computing power centers and the volatility of power systems not being effectively matched, affecting the stability and economy of the overall power system.

[0004] To achieve the above objectives, an embodiment of the present invention provides an optimization scheduling method based on resource collaboration, comprising:

[0005] Constructing a computing network objective function based on the computing network's computing tasks; the computing network objective function represents minimizing the operating cost of the computing tasks;

[0006] Solving the computing power network objective function to obtain an optimized scheduling result of the computing power task, and determining the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task;

[0007] Determining target impact data for a power grid objective function based on a comparison result of the computing load demand and the maximum power supply of distributed power sources in the power grid; the power grid objective function represents minimizing the operating cost of the power grid;

[0008] A power grid objective function is constructed based on the target impact data, and the power grid objective function is solved to obtain an optimized scheduling result of the power grid, so as to achieve optimized scheduling of resource collaboration.

[0009] Optionally, the computing power task includes power consumption of an online task and power consumption of an offline task; and constructing a computing power network objective function based on the computing power task of the computing power network includes:

[0010] Constructing a computing power network objective function based on the power consumption of the online task, the power consumption of the offline task, and the time-of-use electricity price;

[0011] The time-of-use electricity price at least includes a peak electricity price and a valley electricity price.

[0012] Optionally, the power consumption of the online task is calculated based on the number of online tasks in each time unit within a set time period and a power consumption coefficient of the task quantity.

[0013] Optionally, the number of online tasks in each time unit within the set time period is calculated based on the number of original online tasks, the number of transferred-in online tasks, and the number of transferred-out online tasks in each time unit within the set time period.

[0014] Optionally, the power consumption of the offline task is calculated based on the power consumption of the offline subtask in each time unit within a set time period and the task volume execution state of each offline subtask.

[0015] Optionally, solving the computing power network objective function to obtain an optimized scheduling result of the computing power task, and determining the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task includes:

[0016] Solving the computing power network objective function to obtain optimized scheduling results for the power consumption of the online tasks and the power consumption of the offline tasks; the optimized scheduling results for the power consumption of the online tasks include the number of online tasks in each time unit within a set time period; the optimized scheduling results for the power consumption of the offline tasks include the power consumption of the offline subtasks in each time unit within the set time period;

[0017] Calculating the load demand of the online task based on the number of online tasks and the task power consumption coefficient of each time unit within the set time period;

[0018] Determining the load demand of the offline task based on the power consumption of the offline subtask in each time unit within the set time period and the task execution status of each offline subtask;

[0019] The computing power load requirement of the computing power task is determined based on the load requirement of the online task and the load requirement of the offline task.

[0020] Optionally, determining target impact data of a power grid objective function based on a comparison result of the computing load demand and the maximum power supply of distributed power sources in the power grid includes:

[0021] When the computing load demand is greater than the maximum power supply, determining the target impact data of the power grid objective function as the power generation cost of the distributed power source and the main grid power purchase cost;

[0022] When the computing load demand is less than or equal to the maximum power supply, the target impact data of the power grid objective function is determined to be the power generation cost of the distributed power source.

[0023] Optionally, the distributed power source includes at least one of a wind generator, a photovoltaic generator, a diesel generator and a gas turbine.

[0024] On the other hand, an embodiment of the present invention further provides an optimization scheduling device based on resource collaboration, comprising:

[0025] A construction module is used to construct a computing network objective function based on the computing power tasks of the computing network; the computing network objective function represents minimizing the operating cost of the computing power tasks;

[0026] A first solving module is configured to solve the computing power network objective function, obtain an optimized scheduling result of the computing power task, and determine the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task;

[0027] a determination module configured to determine target impact data of a power grid objective function based on a comparison result of the computing load demand and the maximum power supply of distributed power sources in the power grid; the power grid objective function represents minimizing the operating cost of the power grid;

[0028] The second solving module is used to construct a power grid objective function based on the target impact data, and solve the power grid objective function to obtain an optimized scheduling result of the power grid to achieve optimized scheduling of resource collaboration.

[0029] Optionally, the computing power task includes power consumption of an online task and power consumption of an offline task; and constructing a computing power network objective function based on the computing power task of the computing power network includes:

[0030] Constructing a computing power network objective function based on the power consumption of the online task, the power consumption of the offline task, and the time-of-use electricity price;

[0031] The time-of-use electricity price at least includes a peak electricity price and a valley electricity price.

[0032] Optionally, the power consumption of the online task is calculated based on the number of online tasks in each time unit within a set time period and a power consumption coefficient of the task quantity.

[0033] Optionally, the number of online tasks in each time unit within the set time period is calculated based on the number of original online tasks, the number of transferred-in online tasks, and the number of transferred-out online tasks in each time unit within the set time period.

[0034] Optionally, the power consumption of the offline task is calculated based on the power consumption of the offline subtask in each time unit within a set time period and the task volume execution state of each offline subtask.

[0035] Optionally, solving the computing power network objective function to obtain an optimized scheduling result of the computing power task, and determining the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task includes:

[0036] Solving the computing power network objective function to obtain optimized scheduling results for the power consumption of the online tasks and the power consumption of the offline tasks; the optimized scheduling results for the power consumption of the online tasks include the number of online tasks in each time unit within a set time period; the optimized scheduling results for the power consumption of the offline tasks include the power consumption of the offline subtasks in each time unit within the set time period;

[0037] Calculating the load demand of the online task based on the number of online tasks and the task power consumption coefficient of each time unit within the set time period;

[0038] Determining the load demand of the offline task based on the power consumption of the offline subtask in each time unit within the set time period and the task execution status of each offline subtask;

[0039] The computing power load requirement of the computing power task is determined based on the load requirement of the online task and the load requirement of the offline task.

[0040] Optionally, determining target impact data of a power grid objective function based on a comparison result of the computing load demand and the maximum power supply of distributed power sources in the power grid includes:

[0041] When the computing load demand is greater than the maximum power supply, determining the target impact data of the power grid objective function as the power generation cost of the distributed power source and the main grid power purchase cost;

[0042] When the computing load demand is less than or equal to the maximum power supply, the target impact data of the power grid objective function is determined to be the power generation cost of the distributed power source.

[0043] Optionally, the distributed power source includes at least one of a wind generator, a photovoltaic generator, a diesel generator and a gas turbine.

[0044] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned resource collaboration-based optimization scheduling method when executing the program.

[0045] On the other hand, the present invention also provides a machine-readable storage medium having a computer program stored thereon, which implements the above-mentioned resource collaboration-based optimization scheduling method when executed by a processor.

[0046] On the other hand, the present invention further provides a computer program product, comprising a computer program, which implements the above-mentioned resource collaboration-based optimization scheduling method when executed by a processor.

[0047] Through the above technical solution, the embodiment of the present invention obtains the optimized scheduling result of the computing power task corresponding to minimizing the operating cost of the computing power task by solving the computing power network objective function, and then determines the target impact data of the power grid objective function based on the comparison result of the computing power load demand of the computing power task calculated based on the optimized scheduling result of the computing power task and the maximum power supply of the distributed power source in the power grid, thereby constructing the power grid objective function based on the target impact data and solving the power grid objective function to obtain the optimized scheduling result of the power grid. The embodiment of the present invention forms a new model for the interaction of resources on the power generation side and the load side, and realizes the optimal scheduling of minimizing the operating cost of the computing power task and the operating cost of the power grid through the deep coordination of computing power and electricity, as well as the efficient utilization of resources and the stable operation of the system. Therefore, the embodiment of the present invention realizes the effective matching of the high energy consumption of the computing power center and the volatility of the power system, and improves the stability and economy of the overall power system.

[0048] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0050] Figure 1 It is a flow chart of the optimization scheduling method based on resource collaboration provided by the present invention;

[0051] Figure 2 is a schematic diagram of a distributed power supply provided by the present invention;

[0052] Figure 3 Schematic diagram of the collaborative optimization of the computing power network and the power grid provided by the present invention;

[0053] Figure 4It is a structural diagram of the optimization scheduling device based on resource collaboration provided by the present invention;

[0054] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0055] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0056] The coordinated optimization of power grids and computing power networks has become a key strategy for promoting socioeconomic development. Many researchers are focusing on leveraging the flexible adjustment capabilities of computing power tasks, tapping into their potential for flexible electricity usage, and promoting the coordinated optimization of these two networks. Traditional optimization methods for computing power networks and power grids often operate independently and lack coordination mechanisms, resulting in wasted resources and low operational efficiency. The high energy consumption of computing centers and the volatility of the power system are not effectively matched, impacting the stability and economic efficiency of the overall system.

[0057] The embodiments of the present invention aim to provide an optimization scheduling method based on resource collaboration, which realizes efficient resource utilization, stable system operation and optimal scheduling through deep collaboration between computing power and electricity, thereby achieving effective matching between the high energy consumption of the computing power center and the volatility of the power system, thereby improving the stability and economy of the overall power system.

[0058] Method Example

[0059] Please refer to Figure 1 , an embodiment of the present invention provides an optimization scheduling method based on resource collaboration, comprising:

[0060] Step 100: Construct a computing power network objective function based on the computing power tasks of the computing power network.

[0061] The electronic device constructs a computing network objective function based on the computing tasks of the computing network. In one embodiment, the computing tasks include the electricity consumption of online tasks and the electricity consumption of offline tasks. The computing network objective function represents the operating cost of minimizing the electricity consumption of online tasks and offline tasks. Based on the temporal flexibility model of offline tasks, the embodiment of the present invention considers the spatial flexibility of online tasks and constructs a computing network objective function that integrates the spatiotemporal characteristics of computing tasks. The goal of the computing network objective function in the embodiment of the present invention is to minimize the operating cost of the computing network, integrate the spatial and temporal flexible adjustment capabilities of online and offline tasks, and change the user's electricity consumption behavior. That is, the overall optimization goal is to minimize the operating cost of the computing network and achieve optimal scheduling.

[0062] Online tasks include tasks requiring real-time processing, such as real-time load monitoring and adjustment and distributed resource coordinated control. This is illustrated using real-time load monitoring and adjustment tasks. For example, intelligent terminals collect real-time distribution transformer and line load data to dynamically adjust load distribution and avoid overload or low voltage issues. Offline tasks include tasks requiring long-term analysis, such as load forecasting and model training, and network structure optimization and planning. This is illustrated using load forecasting and model training tasks, for example, using historical load data to train forecasting models and predict future load trends.

[0063] In one embodiment, step 100, constructing a computing power network objective function based on the computing power tasks of the computing power network, includes: constructing a computing power network objective function based on the power consumption of the online task, the power consumption of the offline task and the time-of-use electricity price.

[0064] The electronic device constructs a computing power network objective function based on the power consumption of the online task, the power consumption of the offline task, and the time-of-use electricity price. In one embodiment, the computing power network objective function C s.min The calculation formula is as follows: C s.min =E s ·C fs (t)=(E lx +E zx )·C fs (t); where E s is the total power consumption of the computing network, C fs (t) is the time-of-use electricity price at time t, E zx 、E lx are respectively the electricity consumption of online tasks and offline tasks executed by the computing power network at time t. The time-of-use electricity price includes at least peak electricity price and valley electricity price. In one embodiment, the time-of-use electricity price includes peak electricity price and valley electricity price. In another embodiment, the time-of-use electricity price includes peak electricity price, flat-peak electricity price and valley electricity price within 24 hours. Peak electricity price refers to the electricity price during the peak period of user electricity consumption, valley electricity price refers to the electricity price during the valley period of user electricity consumption, and flat-peak electricity price refers to the electricity price between the peak period of user electricity consumption and the valley period of user electricity consumption. The embodiment of the present invention formulates a time-of-use electricity price within 24 hours to guide users to choose the most appropriate computing task time. The model of the time-of-use electricity price is simulated as follows:

[0065]

[0066] Among them, C av is the off-peak electricity price, C l is the off-peak electricity price, C h is the peak electricity price, λ1 and λ2 are electricity price coefficients, and C l <C av <C h .

[0067] In one embodiment, the power consumption of the online task is calculated based on the number of online tasks in each time unit within the set time period and the power consumption coefficient of the task amount. The electronic device calculates the power consumption of the online task based on the number of online tasks in each time unit within the set time period and the power consumption coefficient of the task amount. Furthermore, the number of online tasks in each time unit within the set time period is calculated based on the original number of online tasks, the number of transferred online tasks, and the number of transferred online tasks in each time unit within the set time period. Thus, the power consumption E of the online task is zx is calculated by the following formula:

[0068]

[0069] Among them, E zx.(t) represents the power consumption of the computing network when executing online tasks at time t, Y zx(t) is the number of online tasks processed by the computing network, and I is the power consumption coefficient of the task volume. ini (t) is the number of online tasks originally submitted to the local machine in each time unit within the set time period, that is, the original number of online tasks in each time unit within the set time period, y in (t) is the number of online tasks transferred into each time unit within the set time period, y to (t) is the number of online tasks transferred per time unit within the set time period. T is the time period, for example, T can be 24 hours. t is per time unit, t can be seconds, then per time unit can be per second. In other embodiments, t can also be per minute or per hour.

[0070] The embodiment of the present invention also needs to set online task quantity constraints. For example, the online task quantity constraints can be set as follows: the number of online tasks transferred out of each time unit within the set time period should not exceed the number of original online tasks originally allocated to local processing: to (t)≤y ini (t); Considering the limited processing capacity, the number of online tasks processed by the computing power network is constrained to not exceed the set maximum value y max , to ensure that the server is not overloaded: Y zx(t) ≤y max .

[0071] In addition, the power consumption of the offline task is calculated based on the power consumption of the offline subtask in each time unit within the set time period and the task execution status of each offline subtask. lx The formula is as follows:

[0072] Among them, E lx.(t)represents the power consumption of the computing network when executing offline tasks at time t, O lx(t) is the power consumption of the offline subtask at time t. K is the task execution status, a 0 / 1 variable where 0 indicates the offline subtask is not executed during the period, and 1 indicates the offline subtask is executed. T is the time period, for example, T can be 24 hours. t is the time unit, where t can be seconds, and each time unit can be one second.

[0073] In some embodiments, computing network constraints can also be set. For example, the computing network constraints are as follows: 1. Total power consumption of the computing network Where P(t) is the power consumption of the computing network at time t; 2. Power Constraints Among them, P lx (t) represents the power of the offline task, P zx (t) represents the power of the online task, P 损耗 (t) represents the power loss of the computing network.

[0074] Step 200: Solve the computing power network objective function to obtain the optimized scheduling result of the computing power task, and determine the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task.

[0075] The electronic device can use linear programming methods, genetic algorithms, simulated degradation algorithms and other methods to solve the computing power network objective function and obtain the optimized scheduling result of the computing power task. Among them, the optimized scheduling result of the computing power task includes the optimized scheduling result of the power consumption of the online task and the optimized scheduling result of the power consumption of the offline task. In one embodiment, the optimized scheduling result of the power consumption of the online task includes the number of online tasks per time unit within a set time period, such as the number of online tasks per second within 24 hours. The optimized scheduling result of the power consumption of the offline task includes the power consumption of the offline subtask per time unit within a set time period, such as the power consumption of the offline subtask per second within 24 hours. Then, step 200, solving the computing power network objective function, obtaining the optimized scheduling result of the computing power task, and determining the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task, includes:

[0076] Step 210: Solve the computing power network objective function to obtain the optimized scheduling results of the power consumption of the online task and the optimized scheduling results of the power consumption of the offline task.

[0077] Electronic devices can use linear programming methods, genetic algorithms, simulated degradation algorithms and other methods to solve the computing power network objective function to obtain the number of online tasks in each time unit within a set time period and the power consumption of each offline subtask in each time unit within a set time period, such as the number of online tasks per second and the power consumption of offline subtasks per second within 24 hours.

[0078] Step 220: Calculate the load demand of the online task based on the number of online tasks and the task power coefficient in each time unit within the set time period.

[0079] The electronic device substitutes the number of online tasks and the power consumption coefficient of each time unit in the set time period into formula (2) to calculate the load demand of the online task.

[0080] Step 230: Determine the load demand of the offline task based on the power consumption of the offline subtask in each time unit within the set time period and the task execution status of each offline subtask.

[0081] The electronic device substitutes the power consumption of the offline subtask in each time unit within the set time period and the task execution status of each offline subtask into formula (3) to calculate the load demand of the offline task.

[0082] Step 240: Determine the computing power load requirement of the computing power task based on the load requirement of the online task and the load requirement of the offline task.

[0083] In one embodiment, the electronic device may determine the computing load requirement of the computing task based on the sum of the load requirements of the online task and the load requirements of the offline task. In other embodiments, the electronic device may determine the computing load requirement of the computing task based on the weighted sum of the load requirements of the online task and the load requirements of the offline task. In this embodiment of the present invention, the power supply of the power grid is determined by the computing load requirement. This facilitates the determination of the power supply and power source type of the power grid based on the calculated computing load requirement.

[0084] The embodiment of the present invention regards the computing power network of the data center as an important dispatchable load, and by constructing and solving the computing power network objective function, obtains the optimized scheduling results of the power consumption of the online task and the optimized scheduling results of the power consumption of the offline task that minimize the operating cost of the computing power task. The embodiment of the present invention can follow the guidance of time-of-use electricity prices, select on-site online calculations when the electricity price is low, and select offline task calculations when the electricity price is peak. The power supply of the power grid is determined by the computing power load demand. After the computing power network load curve changes with the user's behavior, the power supply requirements of the power grid also change accordingly, which can effectively "cut the peak and fill the valley" to reduce the power supply pressure of the distribution network during the peak period of electricity consumption.

[0085] Step 300: Determine target impact data of the power grid objective function based on a comparison result of the computing load demand and the maximum power supply of the distributed power sources in the power grid.

[0086] An embodiment of the present invention determines the power supply of the power grid by the computing load demand of the computing power network. In one embodiment, the target impact data of the power grid objective function is determined based on the comparison result of the computing load demand and the maximum power supply of the distributed power sources in the power grid, including: when the computing load demand is greater than the maximum power supply, the target impact data of the power grid objective function is determined to be the power generation cost of the distributed power sources and the main grid power purchase cost; when the computing load demand is less than or equal to the maximum power supply, the target impact data of the power grid objective function is determined to be the power generation cost of the distributed power sources.

[0087] When the computing load demand is greater than the maximum power supply of the distributed power source in the power grid, electricity will be purchased from the main grid to meet the power consumption on the demand side. Then the target impact data of the power grid objective function at this time is the power generation cost of the distributed power source and the power purchase cost of the main grid. When the computing load demand is less than or equal to the maximum power supply of the distributed power source in the power grid, there is no need to purchase electricity from the main grid to meet the power consumption on the demand side. Then the target impact data of the power grid objective function at this time is the power generation cost of the distributed power source. Wherein, the distributed power source includes at least one of a wind turbine, a photovoltaic generator, a diesel generator and a gas turbine. In order to consider as many energy types as possible for power supply. Please refer to Figure 2 The distributed power sources used in the source-side distribution network energy management system include wind turbines, photovoltaic generators, diesel generators (or diesel generator sets), and gas turbines (or gas turbine sets), representing renewable energy sources. The generation costs of distributed power sources include the costs of wind turbines, photovoltaic generators, diesel generators, and gas turbines.

[0088] The power grid objective function C is constructed based on the power generation cost of distributed power sources. d.min The calculation formula is as follows:

[0089] C d.min =C WT +C PV +C DG +C GT +C L ;Formula (4)

[0090] Among them, C WT represents the cost of wind turbine power generation, C PV represents the cost of photovoltaic generator power generation, C DG represents the cost of diesel generator power generation, C GT represents the cost of gas turbine power generation, C L Indicates the grid loss cost.

[0091] The power grid objective function C is constructed based on the power generation cost of distributed power generation and the main grid power purchase cost. d.min The calculation formula is as follows:

[0092] C d.min =C WT +C PV +C DG +C GT +C G +C L ;Formula (5)

[0093] Among them, C WT represents the cost of wind turbine power generation, C PV represents the cost of photovoltaic generator power generation, C DG represents the cost of diesel generator power generation, C GT represents the cost of gas turbine power generation, C G Indicates the main grid electricity purchase cost, C L Represents the grid loss cost. The embodiment of the present invention is illustrated using formula (5). The power grid objective function represents minimizing the operating cost of the power grid. That is, the power grid optimization goal is to minimize the economic cost of meeting the computing load demand, thereby forming a new model for interaction between new energy generation and load resources.

[0094] Wind turbines are used on the source side of the distribution network. When their own power supply is insufficient, they can be combined with other renewable energy sources to supplement the power supply demand. The power generation cost C of the wind turbine in formula (5) is WT Including wind turbine maintenance costs C WT1 and management expenses C WT2 The cost of electricity generated by a wind turbine is C WT Calculated by the following formula:

[0095]

[0096] where k WT1 is the operation and maintenance coefficient of the unit to which the wind turbine belongs, k WT2 is the management cost coefficient of the unit to which the wind turbine belongs, P WT (t) is the output power of the wind turbine at the tth moment, and T is the period.

[0097] The photovoltaic generator power generation cost C in formula (5) PV Including photovoltaic generator maintenance costs C PV1 and management expenses C PV2 The cost of photovoltaic generator power generation C PV Calculated by the following formula:

[0098]

[0099] where kPV1 is the operation and maintenance coefficient of the unit to which the photovoltaic generator belongs, k PV2 is the management cost coefficient of the unit to which the photovoltaic generator belongs, P PV (t) is the output power of the photovoltaic generator at the tth moment, and T is the period.

[0100] A diesel generator generates electricity by combining a diesel engine with an electric generator, using diesel as fuel to drive the generator. During operation, a diesel generator incurs fuel costs and maintenance costs. The diesel generator power generation cost C in formula (5) is DG Including fuel costs C DG1 , maintenance fee C DG2 and the cost of treating pollutants C DG3 . Diesel generator power generation cost C DG Calculated by the following formula:

[0101]

[0102] Where a, b, c are the fuel consumption cost coefficients of diesel generators, k DG2 Diesel generator maintenance factor, k DG3 is the pollutant treatment cost coefficient, P DG (t) is the actual power of the diesel generator at time t, and T is the period.

[0103] When the power generation of the gas turbine cannot meet the user's demand, the power grid will provide supplementary power to ensure that the unit can operate normally and reach full load. The gas turbine will generate fuel costs and maintenance costs during operation. The gas turbine power generation cost C in formula (5) is GT Including fuel costs C GT1 and maintenance fee C GT2 Gas turbine power generation cost C GT Calculated by the following formula:

[0104]

[0105] Where l, m, n are the fuel consumption cost coefficients of the gas turbine, k GT2 Gas turbine maintenance factor, P GT (t) is the actual power of the gas turbine at time t, and T is the period.

[0106] The main grid electricity purchase cost C in formula (5) G Calculated by the following formula:

[0107]

[0108] Among them C kG (t) is the unit price of electricity purchased from the main network at time t, P G(t) is the main network operating power at time t, and T is the period.

[0109] The grid loss cost C in formula (5) L Calculated by the following formula:

[0110]

[0111] Among them C kL (t) is the power grid loss coefficient at time t, P L (t) is the power loss (dissipation) of the power grid at time t, and T is the period.

[0112] The embodiment of the present invention also requires setting power grid constraints. The power grid constraints include power balance constraints and generator set operating power constraints. The formula for the power balance constraint is as follows:

[0113]

[0114] Where P(t) is the power consumption of the computing network at time t, P1(t) is the power consumption of other power loads at time t, and P WT (t) is the output power of the wind turbine at time t, P PV (t) is the output power of the photovoltaic generator at time t, P DG (t) is the output power of the diesel generator at time t, P GT (t) is the gas turbine output power at time t, P L (t) is the power loss at time t.

[0115] The operating power constraints of the generator set include wind turbine power constraints, photovoltaic generator power constraints, diesel generator power constraints, and gas turbine power constraints. The formula for wind turbine power constraints is as follows: WT (t)≤P WT.i (t). Where P WT.i (t) is the predicted power value of the wind turbine output.

[0116] The formula for the operating power constraint of the photovoltaic generator is as follows: PV (t)≤P PV.i (t). Where P PV.i (t) is the predicted power value of the photovoltaic generator output.

[0117] The formula for diesel generator operating power constraint is as follows: P DG (t) min ≤P DG (t)≤P DG (t) max , where P DG (t) min 、PDG (t) max They are the upper and lower limits of the diesel generator's output power respectively.

[0118] Gas turbine operating power constraint: P GT (t) min ≤P GT (t)≤P GT (t) max , where P GT (t) min 、P GT (t) max are the upper and lower limits of the gas turbine output power respectively.

[0119] Step 400: constructing a power grid objective function based on the target impact data, and solving the power grid objective function to obtain an optimized scheduling result of the power grid to achieve optimized scheduling of resource collaboration.

[0120] In the power grid objective function, the grid needs to calculate the operating cost of the power grid based on information such as power generation and consumption, fuel costs, and line transmission under the optimal operating state to reflect the effect of optimizing resource allocation within the power grid. In the power grid, when renewable energy is able to generate power, the focus is on supplying economical and environmentally friendly electricity. However, it is necessary to consider that the distributed energy on the demand side may not be able to fully meet the power demand on the source side, so the distribution network must be fully utilized to purchase electricity from the main grid. The optimization goal of the power grid objective function is to minimize the cost of wind turbine power generation, photovoltaic generator power generation, diesel generator power generation, gas turbine power generation, and main grid power purchase. Electronic equipment can refer to formula (5) to construct the power grid objective function based on the cost of wind turbine power generation, photovoltaic generator power generation, diesel generator power generation, gas turbine power generation, main grid power purchase cost, and grid loss cost.

[0121] In this embodiment of the present invention, the power grid's power supply is determined by the computing load demand of the computing network. The interactive power of wind and solar generators, diesel and gas turbines, and the distribution network is used to construct a power grid objective function aimed at minimizing economic costs. While meeting power demand and maintaining stability, the power grid's generation costs will also vary based on real-time electricity prices.

[0122] Please refer to Figure 3The present invention focuses on the coordinated optimization of the computing power network and the power grid, establishing a two-tier optimization model (two-tier objective function). The lower-tier model consists of the computing power network's online and offline tasks, while the upper-tier model's power supply energy sources include wind power generation, photovoltaic power generation, diesel generators, gas turbines, and power purchased from the main grid. A smart distribution network performs interactive energy distribution, thereby optimizing the scheduling model. When the power grid's demand load exceeds the maximum power provided by the aforementioned distributed power sources, power is purchased from the main grid to meet the demand. Therefore, the power grid optimization goal is to minimize the economic cost of meeting the computing power network's demand, thereby forming a new model for interaction between renewable energy generation and load resources. The computing power network's objective function is to minimize the computing power network's operating costs, integrating the spatial and temporal flexibility of online and offline tasks to change user electricity consumption behavior. The overall optimization goal is to minimize network operating costs and achieve optimal scheduling. In the embodiment of the present invention, by constructing a dual-objective function for bidirectional collaboration between the power grid and the computing power network, the collaboration between the computing power network and the power grid can not only improve energy utilization efficiency, but also promote the rapid development of information technology, realize the efficient allocation of energy and information resources, reduce operating costs, and improve the reliability and flexibility of the power system.

[0123] The embodiment of the present invention obtains the optimized scheduling result of the computing power task corresponding to minimizing the operating cost of the computing power task by solving the computing power network objective function, and then determines the target impact data of the power grid objective function based on the comparison result of the computing power load demand of the computing power task calculated based on the optimized scheduling result of the computing power task and the maximum power supply of the distributed power source in the power grid, thereby constructing the power grid objective function based on the target impact data and solving the power grid objective function to obtain the optimized scheduling result of the power grid. The embodiment of the present invention forms a new model for the interaction of resources on the power generation side and the load side, and realizes the optimal scheduling of minimizing the operating cost of the computing power task and the operating cost of the power grid through the deep coordination of computing power and electricity, as well as the efficient utilization of resources and the stable operation of the system. Therefore, the embodiment of the present invention realizes the effective matching of the high energy consumption of the computing power center and the volatility of the power system, and improves the stability and economy of the overall power system.

[0124] Device embodiment

[0125] Please refer to Figure 4 On the other hand, an embodiment of the present invention further provides an optimization scheduling device based on resource collaboration, comprising:

[0126] A construction module 401 is configured to construct a computing network objective function based on the computing tasks of the computing network; the computing network objective function represents minimizing the operating cost of the computing tasks;

[0127] A first solving module 402 is configured to solve the computing power network objective function, obtain an optimized scheduling result of the computing power task, and determine the computing power load requirement of the computing power task based on the optimized scheduling result of the computing power task;

[0128] A determination module 403 is configured to determine target impact data of a power grid objective function based on a comparison result of the computing load demand and the maximum power supply of distributed power sources in the power grid; the power grid objective function represents minimizing the operating cost of the power grid;

[0129] The second solving module 404 is configured to construct a power grid objective function based on the target impact data, and solve the power grid objective function to obtain an optimized scheduling result of the power grid, so as to achieve optimized scheduling of resource coordination.

[0130] By solving the objective function of the computing power network, the optimized scheduling result of the computing power task corresponding to minimizing the operating cost of the computing power task is obtained, and then based on the comparison result of the computing power load demand of the computing power task calculated based on the optimized scheduling result of the computing power task and the maximum power supply of the distributed power source in the power grid, the target impact data of the power grid objective function is determined, and then the power grid objective function is constructed based on the target impact data and the power grid objective function is solved to obtain the optimized scheduling result of the power grid. The embodiment of the present invention forms a new model for the interaction of resources on the power generation side and the load side, and through the deep coordination of computing power and electricity, it realizes the optimal scheduling that minimizes the operating cost of computing power tasks and the operating cost of the power grid, as well as the efficient use of resources and the stable operation of the system. Therefore, the embodiment of the present invention realizes the effective matching of the high energy consumption of the computing power center and the volatility of the power system, and improves the stability and economy of the overall power system.

[0131] Optionally, the computing power task includes power consumption of an online task and power consumption of an offline task; and constructing a computing power network objective function based on the computing power task of the computing power network includes:

[0132] Constructing a computing power network objective function based on the power consumption of the online task, the power consumption of the offline task, and the time-of-use electricity price;

[0133] The time-of-use electricity price at least includes a peak electricity price and a valley electricity price.

[0134] Optionally, the power consumption of the online task is calculated based on the number of online tasks in each time unit within a set time period and a power consumption coefficient of the task quantity.

[0135] Optionally, the number of online tasks in each time unit within the set time period is calculated based on the number of original online tasks, the number of transferred-in online tasks, and the number of transferred-out online tasks in each time unit within the set time period.

[0136] Optionally, the power consumption of the offline task is calculated based on the power consumption of the offline subtask in each time unit within a set time period and the task volume execution state of each offline subtask.

[0137] Optionally, solving the computing power network objective function to obtain an optimized scheduling result of the computing power task, and determining the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task includes:

[0138] Solving the computing power network objective function to obtain optimized scheduling results for the power consumption of the online tasks and the power consumption of the offline tasks; the optimized scheduling results for the power consumption of the online tasks include the number of online tasks in each time unit within a set time period; the optimized scheduling results for the power consumption of the offline tasks include the power consumption of the offline subtasks in each time unit within the set time period;

[0139] Calculating the load demand of the online task based on the number of online tasks and the task power consumption coefficient of each time unit within the set time period;

[0140] Determining the load demand of the offline task based on the power consumption of the offline subtask in each time unit within the set time period and the task execution status of each offline subtask;

[0141] The computing power load requirement of the computing power task is determined based on the load requirement of the online task and the load requirement of the offline task.

[0142] Optionally, determining target impact data of a power grid objective function based on a comparison result of the computing load demand and the maximum power supply of distributed power sources in the power grid includes:

[0143] When the computing load demand is greater than the maximum power supply, determining the target impact data of the power grid objective function as the power generation cost of the distributed power source and the main grid power purchase cost;

[0144] When the computing load demand is less than or equal to the maximum power supply, the target impact data of the power grid objective function is determined to be the power generation cost of the distributed power source.

[0145] Optionally, the distributed power source includes at least one of a wind generator, a photovoltaic generator, a diesel generator and a gas turbine.

[0146] The resource collaboration-based optimization scheduling device includes a processor and a memory. The above-mentioned construction module 401, first solution module 402, determination module 403, second solution module 404, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0147] The processor includes a kernel, which calls the corresponding program unit from the memory. There can be one or more kernels.

[0148] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0149] Figure 5 An example of a physical structure diagram of an electronic device is shown below. Figure 5 As shown, the electronic device may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the resource-coordinated optimization scheduling method, which includes: constructing a computing power network objective function based on the computing power tasks of the computing power network; the computing power network objective function represents minimizing the operating cost of the computing power tasks; solving the computing power network objective function to obtain the optimized scheduling result of the computing power tasks, and determining the computing power load demand of the computing power tasks based on the optimized scheduling result of the computing power tasks; determining the target impact data of the power grid objective function based on the comparison result of the computing power load demand and the maximum power supply of the distributed power sources in the power grid; the power grid objective function represents minimizing the operating cost of the power grid; constructing the power grid objective function based on the target impact data, and solving the power grid objective function to obtain the optimized scheduling result of the power grid, so as to realize resource-coordinated optimization scheduling.

[0150] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0151] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a machine-readable storage medium. When the computer program is executed by a processor, the computer can execute an optimization scheduling method based on resource collaboration, which includes: constructing a computing power network objective function based on the computing power task of the computing power network; the computing power network objective function represents minimizing the operating cost of the computing power task; solving the computing power network objective function to obtain the optimization scheduling result of the computing power task, and determining the computing power load demand of the computing power task based on the optimization scheduling result of the computing power task; determining the target impact data of the power grid objective function based on the comparison result of the computing power load demand and the maximum power supply of the distributed power source in the power grid; the power grid objective function represents minimizing the operating cost of the power grid; constructing the power grid objective function based on the target impact data, and solving the power grid objective function to obtain the optimization scheduling result of the power grid, so as to achieve resource-coordinated optimization scheduling.

[0152] On the other hand, the present invention also provides a machine-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform an optimization scheduling method based on resource collaboration, the method comprising: constructing a computing power network objective function based on the computing power tasks of the computing power network; the computing power network objective function represents minimizing the operating cost of the computing power tasks; solving the computing power network objective function to obtain the optimized scheduling result of the computing power tasks, and determining the computing power load demand of the computing power tasks based on the optimized scheduling result of the computing power tasks; determining the target impact data of the power grid objective function based on the comparison result of the computing power load demand and the maximum power supply of the distributed power sources in the power grid; the power grid objective function represents minimizing the operating cost of the power grid; constructing the power grid objective function based on the target impact data, and solving the power grid objective function to obtain the optimized scheduling result of the power grid, so as to achieve resource-coordinated optimization scheduling.

[0153] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0154] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An optimization scheduling method based on resource collaboration, characterized in that: include: Construct the target function of the computing network based on the computing tasks of the computing network; The objective function of the computing network is to minimize the running cost of the computing task; Solving the computing power network objective function to obtain an optimized scheduling result of the computing power task, and determining the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task; Determining target impact data of a power grid objective function based on a comparison result of the computing load demand and the maximum power supply of distributed power sources in the power grid; The power grid objective function represents minimizing the operating cost of the power grid; A power grid objective function is constructed based on the target impact data, and the power grid objective function is solved to obtain an optimized scheduling result of the power grid, so as to achieve optimized scheduling of resource collaboration.

2. The resource-coordinated optimization scheduling method according to claim 1, characterized in that: The computing power tasks include the power consumption of online tasks and offline tasks; The computing power network objective function is constructed based on the computing power task of the computing power network, including: Constructing a computing power network objective function based on the power consumption of the online task, the power consumption of the offline task, and the time-of-use electricity price; The time-of-use electricity price at least includes a peak electricity price and a valley electricity price.

3. The resource-coordinated optimization scheduling method according to claim 2, characterized in that: The power consumption of the online task is calculated based on the number of online tasks in each time unit within a set time period and the power consumption coefficient of the task amount.

4. The resource-coordinated optimization scheduling method according to claim 3, characterized in that: The number of online tasks in each time unit within the set time period is calculated based on the number of original online tasks, the number of transferred-in online tasks, and the number of transferred-out online tasks in each time unit within the set time period.

5. The resource-coordinated optimization scheduling method according to claim 2, characterized in that: The power consumption of the offline task is calculated based on the power consumption of the offline subtask in each time unit within a set time period and the task quantity execution state of each offline subtask.

6. The resource-coordinated optimization scheduling method according to claim 2, characterized in that: Solving the computing power network objective function to obtain an optimized scheduling result of the computing power task, and determining the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task, includes: Solving the computing power network objective function to obtain optimized scheduling results for the power consumption of the online tasks and the power consumption of the offline tasks; the optimized scheduling results for the power consumption of the online tasks include the number of online tasks in each time unit within a set time period; the optimized scheduling results for the power consumption of the offline tasks include the power consumption of the offline subtasks in each time unit within the set time period; Calculating the load demand of the online task based on the number of online tasks and the task power consumption coefficient of each time unit within the set time period; Determining the load demand of the offline task based on the power consumption of the offline subtask in each time unit within the set time period and the task execution status of each offline subtask; The computing power load requirement of the computing power task is determined based on the load requirement of the online task and the load requirement of the offline task.

7. The resource-coordinated optimization scheduling method according to claim 1, characterized in that: The determining of target impact data of the power grid objective function based on a comparison result of the computing load demand and the maximum power supply of distributed power sources in the power grid includes: When the computing load demand is greater than the maximum power supply, determining the target impact data of the power grid objective function as the power generation cost of the distributed power source and the main grid power purchase cost; When the computing load demand is less than or equal to the maximum power supply, the target impact data of the power grid objective function is determined to be the power generation cost of the distributed power source.

8. The resource collaboration-based optimization scheduling method according to any one of claims 1 to 7, characterized in that: The distributed power source includes at least one of a wind generator, a photovoltaic generator, a diesel generator and a gas turbine.

9. An optimization scheduling device based on resource collaboration, characterized in that: include: A construction module is used to construct the target function of the computing network based on the computing tasks of the computing network; The objective function of the computing network is to minimize the running cost of the computing task; A first solving module is used to solve the computing power network objective function, obtain an optimized scheduling result of the computing power task, and determine the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task; a determination module, configured to determine target impact data of a power grid objective function based on a comparison result of the computing load demand and a maximum power supply of a distributed power source in the power grid; The power grid objective function represents minimizing the operating cost of the power grid; The second solving module is used to construct a power grid objective function based on the target impact data, and solve the power grid objective function to obtain an optimized scheduling result of the power grid to achieve optimized scheduling of resource collaboration.

10. The resource collaboration-based optimization scheduling device according to claim 9, characterized in that: The computing power tasks include the power consumption of online tasks and offline tasks; The computing power network objective function is constructed based on the computing power task of the computing power network, including: Constructing a computing power network objective function based on the power consumption of the online task, the power consumption of the offline task, and the time-of-use electricity price; The time-of-use electricity price at least includes a peak electricity price and a valley electricity price.

11. The resource-coordinated optimization scheduling device according to claim 10, characterized in that: The power consumption of the online task is calculated based on the number of online tasks in each time unit within a set time period and the power consumption coefficient of the task amount.

12. The resource collaboration-based optimization scheduling device according to claim 11, characterized in that: The number of online tasks in each time unit within the set time period is calculated based on the number of original online tasks, the number of transferred-in online tasks, and the number of transferred-out online tasks in each time unit within the set time period.

13. The resource-coordinated optimization scheduling device according to claim 10, characterized in that: The power consumption of the offline task is calculated based on the power consumption of the offline subtask in each time unit within a set time period and the task quantity execution state of each offline subtask.

14. The resource-coordinated optimization scheduling device according to claim 10, characterized in that: Solving the computing power network objective function to obtain an optimized scheduling result of the computing power task, and determining the computing power load demand of the computing power task based on the optimized scheduling result of the computing power task, includes: Solving the computing power network objective function to obtain optimized scheduling results for the power consumption of the online tasks and the power consumption of the offline tasks; the optimized scheduling results for the power consumption of the online tasks include the number of online tasks in each time unit within a set time period; the optimized scheduling results for the power consumption of the offline tasks include the power consumption of the offline subtasks in each time unit within the set time period; Calculating the load demand of the online task based on the number of online tasks and the task power consumption coefficient of each time unit within the set time period; Determining the load demand of the offline task based on the power consumption of the offline subtask in each time unit within the set time period and the task execution status of each offline subtask; The computing power load requirement of the computing power task is determined based on the load requirement of the online task and the load requirement of the offline task.

15. The resource-coordinated optimization scheduling device according to claim 9, characterized in that: The determining of target impact data of the power grid objective function based on a comparison result of the computing load demand and the maximum power supply of distributed power sources in the power grid includes: When the computing load demand is greater than the maximum power supply, determining the target impact data of the power grid objective function as the power generation cost of the distributed power source and the main grid power purchase cost; When the computing load demand is less than or equal to the maximum power supply, the target impact data of the power grid objective function is determined to be the power generation cost of the distributed power source.

16. The resource collaboration-based optimization scheduling device according to any one of claims 9 to 15, characterized in that: The distributed power source includes at least one of a wind generator, a photovoltaic generator, a diesel generator and a gas turbine.

17. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the resource collaboration-based optimization scheduling method according to any one of claims 1 to 8 is implemented.

18. A machine-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the resource collaboration-based optimization scheduling method according to any one of claims 1 to 8 is implemented.

19. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the resource collaboration-based optimization scheduling method according to any one of claims 1 to 8 is implemented.

Images