Multi-node computing network energy collaborative planning method for computing power task multi-time-space-dimension scheduling

Abstract

The invention relates to the technical field of computers, in particular to multi-node computing network energy collaborative planning for computing power task multi-time-space-dimension scheduling. According to the computing power multi-objective planning design, minimum carbon emission, minimum energy consumption and maximum profit are taken as objectives, various energy supply curves and prices of each node data center are taken as boundary conditions, and an energy multi-objective planning design module takes a computing power load demand curve of each node data center as a boundary condition; and optimizing to obtain the energy supply facility capacity and the energy transaction scale of the integrated energy system by taking the maximum income and the minimum carbon emission in the planning period as targets. According to the computing power multi-objective planning design and the energy multi-objective planning design, computing power task multi-time-space-dimension distribution and multi-node energy supply serve as coupling point and boundary interaction, through multiple iterations, a computing network energy integrated optimal planning scheme is finally obtained through optimization, and multi-node computing network energy collaborative planning of computing power task multi-time-space-dimension scheduling is achieved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a multi-node computing network collaborative planning method for scheduling computing tasks in multiple time and space dimensions. Background Art

[0002] In the current multi-node computing network energy planning problem, multi-node computing network system planning and multi-node energy supply system planning are usually carried out separately. During the planning process, the computing network system and energy supply system of each node are unknown. When planning the computing network system, the spatial and temporal allocation of computing tasks needs to consider the energy supply characteristics of each node energy supply system. When planning the multi-node energy supply system, the changes in the load demand of all node computing network systems need to be considered.

[0003] The current multi-node computing network energy planning problem is that the multi-node computing network system planning and energy supply system planning are usually carried out separately. Usually, each node computing network system plans and then proposes energy requirements, and each node energy supply system matches them, which makes it impossible for the two modules to interact and collaborate. Therefore, it is necessary to consider the multi-level interactive collaboration of computing resources-computing tasks-load requirements-energy supply, and propose a multi-node computing network energy collaborative planning method that considers the multi-temporal and spatial dimension scheduling of computing tasks.

[0004] Based on this, there is an urgent need for a multi-node computing network that can coordinate planning for the scheduling of computing tasks in multiple spatiotemporal dimensions to solve the technical problem of how to achieve the multi-node computing network that can coordinate planning for the scheduling of computing tasks in multiple spatiotemporal dimensions. Summary of the invention

[0005] In order to solve the technical problem of how to achieve collaborative planning of multi-node computing networks for scheduling computing tasks in multiple spatiotemporal dimensions, an embodiment of the present invention provides a collaborative planning of multi-node computing networks for scheduling computing tasks in multiple spatiotemporal dimensions.

[0006] In a first aspect, an embodiment of the present invention provides a multi-node computing network capable of collaborative planning for multi-temporal and spatial dimension scheduling of computing tasks. The method is applied to a multi-node computing network, including:

[0007] Establish a multi-node computing power network planning model and a multi-node energy supply planning model; wherein the multi-node computing power network planning model and the multi-node energy supply planning model are both double-layer model structures, the multi-node computing power network planning model includes a first upper layer model and a first lower layer model, and the multi-node energy supply planning model includes a second upper layer model and a second lower layer model;

[0008] The first upper-layer model takes the maximum benefit and the minimum carbon emission of the multi-node data center as the objective function, takes the delay constraint and the multi-node computing power scale constraint as the constraint conditions, determines the multi-node center computing power scale, and sends the multi-node center computing power scale to the first lower-layer model;

[0009] The first lower-layer model takes the maximum revenue and minimum carbon emissions of the multi-node data center as the objective function, takes the energy constraint and the multi-node computing power scale constraint as the constraint conditions, determines the carbon emissions and profits of the multi-node data center, and sends the carbon emissions and profits of the multi-node data center to the first upper-layer model;

[0010] The first upper model and the first lower model are repeatedly iterated to determine a first optimal solution; wherein the first optimal solution includes a multi-node computing power equipment planning scheme and a multi-node computing power energy consumption load curve, and the multi-node computing power energy consumption load curve is used as an input of the energy supply planning model to perform coupling interaction;

[0011] The second upper-layer model takes the maximum profit and the minimum carbon emission in the multi-node planning period as the objective function, takes the upper limit constraint of the multi-node equipment planning capacity and the multi-node equipment commissioning planning constraint as the constraint conditions, determines the multi-node equipment configuration strategy and the planning capacity, and sends the multi-node equipment configuration strategy and the planning capacity to the second lower-layer model;

[0012] The second lower-layer model takes the minimization of multi-node operation cost as the objective function, and takes the multi-node power balance constraint, the equipment commissioning planning constraint, the energy system and the upper-level network power exchange constraint, and the green electricity proportion constraint as the constraint conditions to determine the optimal operation plan and the total operation cost, and sends the optimal operation plan and the total operation cost to the second upper-layer model;

[0013] The second upper model and the second lower model are repeatedly iterated to determine a second optimal solution; wherein the second optimal solution includes an energy supply planning scheme, a power curve of power generation equipment, a public grid thermal power curve, and a green electricity trading curve, and the power curve of power generation equipment, the public grid thermal power curve, and the green electricity trading curve are used as inputs of a multi-node computing power network planning model for coupling interaction;

[0014] The multi-node computing power network planning model and the multi-node energy supply planning model are cyclically coupled and interacted, and multi-node computing network collaborative planning for scheduling computing power tasks in multiple time and space dimensions has been realized.

[0015] In a second aspect, an embodiment of the present invention further provides a multi-node computing network collaborative planning device for multi-temporal and spatial dimension scheduling of computing tasks, including:

[0016] A model building module, used to establish a multi-node computing power network planning model and a multi-node energy supply planning model; wherein the multi-node computing power network planning model and the multi-node energy supply planning model are both double-layer model structures, the multi-node computing power network planning model includes a first upper layer model and a first lower layer model, and the multi-node energy supply planning model includes a second upper layer model and a second lower layer model;

[0017] A first data processing module is used for the first upper-layer model to determine the multi-node center computing power scale with the maximum multi-node data center revenue and the minimum carbon emission as the objective function, and with the delay constraint and the multi-node computing power scale constraint as the constraint conditions, and send the multi-node center computing power scale to the first lower-layer model;

[0018] A second data processing module is used for the first lower-layer model to determine the carbon emissions and profits of the multi-node data center with the maximum revenue and minimum carbon emissions of the multi-node data center as the objective function, and with the energy constraint and the multi-node computing power scale constraint as the constraint conditions, and to send the carbon emissions and profits of the multi-node data center to the first upper-layer model;

[0019] A third data processing module is used for repeatedly iterating the first upper model and the first lower model to determine a first optimal solution; wherein the first optimal solution includes a multi-node computing power equipment planning scheme and a multi-node computing power energy consumption load curve, and the multi-node computing power energy consumption load curve is used as an input of the energy supply planning model to perform coupling interaction;

[0020] A fourth data processing module is used for the second upper-layer model to determine the multi-node equipment configuration strategy and planning capacity with the maximum profit and the minimum carbon emission in the multi-node planning period as the objective function, and the multi-node equipment planning capacity upper limit constraint and the multi-node equipment commissioning planning constraint as the constraint conditions, and send the multi-node equipment configuration strategy and planning capacity to the second lower-layer model;

[0021] A fifth data processing module is used for the second lower-layer model to determine the optimal operation plan and the total operation cost with the minimum multi-node operation cost as the objective function, the multi-node power balance constraint, the equipment commissioning planning constraint, the energy system and the upper network power exchange constraint, and the green electricity proportion constraint as the constraint conditions, and send the optimal operation plan and the total operation cost to the second upper-layer model;

[0022] a sixth data processing module, configured to repeatedly iterate the second upper model and the second lower model to determine a second optimal solution; wherein the second optimal solution includes an energy supply planning scheme, a power curve of power generation equipment, a public grid thermal power curve, and a green electricity trading curve, and the power curve of power generation equipment, the public grid thermal power curve, and the green electricity trading curve are used as inputs of a multi-node computing power network planning model for coupling interaction;

[0023] The loop coupling interaction module is used for loop coupling interaction between the multi-node computing power network planning model and the multi-node energy supply planning model, and has realized the collaborative planning of multi-node computing network for scheduling computing power tasks in multiple time and space dimensions.

[0024] In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in any embodiment of the present invention is implemented.

[0025] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the method described in any embodiment of the present invention.

[0026] An embodiment of the present invention provides a multi-node computing network collaborative planning for scheduling computing tasks in multiple spatiotemporal dimensions. When the present invention performs multi-node computing network collaborative planning, each node data center establishes a comprehensive energy system (electricity-cold-heat-hydrogen-gas, etc.) and a computing network equipment construction plan with optimal economy and lowest carbon emissions based on resource endowment conditions. The computing power multi-objective planning and design aims to minimize carbon emissions, minimize energy consumption, and maximize profits. The various energy supply curves and prices of each node data center are used as boundary conditions to optimize the timing of computing tasks such as interactive workloads and batch workloads and optimize the spatial allocation of multi-node data centers. The energy multi-objective planning and design module uses the computing power load demand curve of each node data center as a boundary condition, and aims to maximize profits and minimize carbon emissions during the planning period, and optimizes the capacity of energy supply facilities and the scale of energy transactions of the comprehensive energy system. The multi-objective planning and design of computing power and the multi-objective planning and design of energy use the multi-temporal and spatial dimensional allocation of computing power tasks and the multi-node energy supply as coupling points and boundary interactions. Through multiple iterations, the optimal planning scheme for the integration of computing, network and energy is finally optimized. It can overcome the inconsistency problem of the configuration scheme of traditional independent planning, achieve a high degree of coupling between multi-temporal and spatial computing power tasks and renewable energy power generation, improve the renewable energy consumption rate, reduce the energy cost of data centers, and realize multi-level interaction of computing power resources-computing power tasks-load demand-energy supply, so as to achieve the optimal overall configuration scheme of multi-node computing network energy, and realize the collaborative planning of multi-node computing network energy for multi-temporal and spatial dimensional scheduling of computing power tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 A multi-node computing network collaborative planning flow chart for scheduling computing tasks in multiple time and space dimensions provided by an embodiment of the present invention;

[0029] Figure 2 is a hardware architecture diagram of an electronic device provided by an embodiment of the present invention;

[0030] Figure 3 It is a structural diagram of a multi-node computing network collaborative planning device for scheduling computing tasks in multiple time and space dimensions provided by an embodiment of the present invention;

[0031] Figure 4 is a structural diagram of a multi-node energy supply planning model provided by an embodiment of the present invention;

[0032] Figure 5 It is a structural diagram of a multi-node computing power network planning model provided by an embodiment of the present invention;

[0033] Figure 6 It is a multi-node computing network collaborative planning architecture diagram for scheduling computing tasks in multiple time and space dimensions provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0035] Please refer to Figure 1 , an embodiment of the present invention provides a multi-node computing network collaborative planning method for multi-temporal and spatial dimension scheduling of computing tasks, the method comprising:

[0036] Step 100: Establish a multi-node computing power network planning model and a multi-node energy supply planning model; wherein the multi-node computing power network planning model and the multi-node energy supply planning model are both double-layer model structures, the multi-node computing power network planning model includes a first upper layer model and a first lower layer model, and the multi-node energy supply planning model includes a second upper layer model and a second lower layer model;

[0037] Step 102: The first upper-layer model takes the maximum revenue of the multi-node data center and the minimum carbon emission as the objective function, takes the delay constraint and the multi-node computing power scale constraint as the constraint conditions, determines the multi-node center computing power scale, and sends the multi-node center computing power scale to the first lower-layer model;

[0038] Step 104: The first lower-layer model takes the maximum revenue and minimum carbon emissions of the multi-node data center as the objective function, and takes the energy constraint and the multi-node computing power scale constraint as the constraint conditions, determines the carbon emissions and profits of the multi-node data center, and sends the carbon emissions and profits of the multi-node data center to the first upper-layer model;

[0039] Step 106: the first upper layer model and the first lower layer model are repeatedly iterated to determine a first optimal solution; wherein the first optimal solution includes a multi-node computing power equipment planning scheme and a multi-node computing power energy consumption load curve, and the multi-node computing power energy consumption load curve is used as an input of the energy supply planning model to perform coupling interaction;

[0040] Step 108: The second upper-layer model takes the maximum profit and the minimum carbon emission in the multi-node planning period as the objective function, takes the upper limit constraint of the multi-node equipment planning capacity and the multi-node equipment commissioning planning constraint as the constraint conditions, determines the multi-node equipment configuration strategy and the planning capacity, and sends the multi-node equipment configuration strategy and the planning capacity to the second lower-layer model;

[0041] Step 110: The second lower-layer model takes the minimization of multi-node operation cost as the objective function, and takes the multi-node power balance constraint, the equipment commissioning planning constraint, the power exchange constraint between the energy system and the upper network, and the green electricity proportion constraint as the constraint conditions to determine the optimal operation plan and the total operation cost, and sends the optimal operation plan and the total operation cost to the second upper-layer model;

[0042] Step 112: the second upper model and the second lower model are repeatedly iterated to determine a second optimal solution; wherein the second optimal solution includes an energy supply planning scheme, a power curve of power generation equipment, a public grid thermal power curve, and a green electricity trading curve, and the power curve of power generation equipment, the public grid thermal power curve, and the green electricity trading curve are used as inputs of a multi-node computing power network planning model for coupling interaction;

[0043] Step 114: The multi-node computing power network planning model and the multi-node energy supply planning model are cyclically coupled and interacted, and the multi-node computing network energy collaborative planning for the multi-temporal and spatial dimension scheduling of computing power tasks has been realized.

[0044] In the embodiment of the present invention, a multi-node computing power network planning model and a multi-node energy supply planning model are established; wherein the multi-node computing power network planning model and the multi-node energy supply planning model are both double-layer model structures, the multi-node computing power network planning model includes a first upper layer model and a first lower layer model, and the multi-node energy supply planning model includes a second upper layer model and a second lower layer model;

[0045] The first upper-level model takes the maximum profit and minimum carbon emission of the multi-node data center as the objective function, takes the delay constraint and the multi-node computing power scale constraint as the constraint conditions, determines the multi-node center computing power scale, and sends the multi-node center computing power scale to the first lower-level model; the first lower-level model takes the maximum profit and minimum carbon emission of the multi-node data center as the objective function, takes the energy constraint and the multi-node computing power scale constraint as the constraint conditions, determines the carbon emissions and profits of the multi-node data center, and sends the carbon emissions and profits of the multi-node data center to the first upper-level model; the first upper-level model and the first lower-level model are repeatedly iterated to determine the first optimal solution; wherein the first optimal solution includes the multi-node computing power equipment planning scheme and the multi-node computing power energy consumption load curve, and the multi-node computing power energy consumption load curve is used as the input of the energy supply planning model for coupling interaction; the second upper-level model takes the maximum profit and minimum carbon emission in the multi-node planning period as the objective function, takes the multi-node equipment planning capacity upper limit constraint and the multi-node equipment commissioning planning constraint as the constraint conditions The second lower-layer model takes the minimization of multi-node operation cost as the objective function, and takes the multi-node power balance constraint, the equipment commissioning planning constraint, the energy system and the upper network power exchange constraint, and the green electricity proportion constraint as the constraint condition to determine the optimal operation plan and the total operation cost, and sends the optimal operation plan and the total operation cost to the second upper-layer model; the second upper-layer model and the second lower-layer model are repeatedly iterated to determine the second optimal solution; the second optimal solution includes the energy supply planning scheme, the power curve of the power generation equipment, the public grid thermal power curve and the green electricity trading curve, and the power curve of the power generation equipment, the public grid thermal power curve and the green electricity trading curve are used as the input of the multi-node computing power network planning model for coupling interaction; the multi-node computing power network planning model and the multi-node energy supply planning model are cyclically coupled and interacted, and the multi-node computing network collaborative planning for multi-temporal and spatial dimension scheduling of computing power tasks has been realized.

[0046] Described below Figure 1 How the various steps are performed.

[0047] Regarding step 102:

[0048] In one embodiment of the present invention, the computing power scale constraint: Meaning: The total computing power scale needs to consider the sum of the computing power scales corresponding to delay-tolerant and delay-sensitive requests. The computing power scale of the sensitive request at time t is K′m (t), the computing power scale of the tolerant request at time t is K m (t). The final computing power scale of the data center can be expressed as:

[0049]

[0050] C2: K′≤K max

[0051] Where: The constraints indicate that the task processing time must be before the tolerable time point, and the data center scale cannot exceed the maximum computing resource capacity. max Indicates the maximum computing capacity that a data center can support.

[0052] In one embodiment of the present invention, the objective function is to maximize the revenue of a multi-node data center and minimize carbon emissions, including the following formula:

[0053]

[0054]

[0055] S t,c =C t,c ·(E t,nom -E t,co2 ) / 10000

[0056]

[0057] f i,ntp =f i,tp (1-λ int )=(f i,ep -f i,ep λ vat λ umt -f i,ep λ vat λ est )(1-λ int )

[0058] f i,ep =f i,in -f i,c

[0059]

[0060] In the formula, The number of production facilities supplying the i-th energy source put into operation in year t; The capacity of the selected model of production equipment for the i-th energy supply; is the number of the i-th energy storage device put into operation in year t; is the capacity of the model selected for the i-th energy storage device; C invis the initial investment cost; T is the life cycle; r is the capital discount rate; is the investment cost in year t; α lr,t is the loan ratio in year t; i is the number of energy supply production equipment; Ω 1 Assembling of production equipment for energy supply; Unit capacity investment cost of production equipment for the i-th energy supply; is the investment and construction capacity of the i-th energy supply production equipment in year t; j is the energy storage equipment number; Ω 2 Assemble for energy storage equipment; is the unit capacity investment cost of the jth energy storage device; is the investment capacity of the j-th energy storage device in year t, The annual operation and maintenance cost per unit capacity of the production equipment for the i-th energy supply; is the annual operation and maintenance cost per unit capacity of the j-th energy storage device, is the purchase cost of public grid thermal power in year t, is the medium- and long-term transaction cost of the i-th green electricity in the t-th year, is the normal green electricity purchase cost in year t, is the penalty cost for the deviation of the i-th green power medium- and long-term transaction in the t-th year, is the natural gas purchase cost in year t, is the hydrogen purchase cost in year t, S is the number of typical daily scenarios each year; N s is the number of days of a typical day scene s in a year; H is the total number of time periods in a day, C e,t,s,h P is the unit price of public grid electricity purchased in the h period of the typical day scenario in the tth year; e,t,s,h is the amount of electricity purchased from the public grid in the typical day scenario h period in year t, C le,t,i,s,h P is the purchase price of the i-th green power medium- and long-term transaction in the h-th period of the typical day scenario in the t-th year; le,t,i,s,h is the mid- to long-term green electricity purchase volume in the i-th period of the typical day scenario in the t-th year, C ge,t,s,h P is the normal green electricity purchase price in the h period of the typical day scenario in the tth year; ge,t,s,h is the normal green electricity purchase amount in the h period of the typical day scenario in the tth year, C g,t,s,h G is the natural gas purchase price in the typical day scenario h period in year t; g,t,s,h is the natural gas purchase volume in the typical day scenario h period in year t, is the unit price of hydrogen gas purchased in the typical day scenario h period in year t; is the amount of hydrogen purchased in the typical day scenario h period in year t, C le,t,i,s,h,dp The penalty unit price for deviation of the i-th green power medium- and long-term transaction in the h-th period of the typical day scenario in the t-th year; P le,t,i,s,h,dpP is the deviation of the i-th green electricity medium- and long-term transaction caused by the power purchaser’s responsibility in the h-th period of the typical day scenario in the t-th year; lest,t,i,s,h The transaction volume of the i-th green power medium- and long-term trading contract in the h-th period of the typical day scenario in the t-th year; P legm,t,i,s,h The amount of green electricity provided by medium- and long-term transactions in the i-th period of time in the typical day scenario of the t-th year, C fc,t is the financial cost in year t; r i,tt is the annual loan interest rate of the loan in year tt; C inv,tt is the investment cost in year tt; α lr,tt is the loan ratio in year tt; N tt is the repayment period of the loan in year tt, SR t is the energy supply income in year t, C e,t,s,h,S are the electricity selling price in the typical day scenario h period in year t; P eL,t,s,h P is the other electrical load in the typical day scenario h period in year t; cpeL,t,s,h HPR is the power load consumed by computing equipment in the typical day scenario h period of year t; FJ is the heating price per unit area; CPR FJ is the cooling price per unit area; A r,HFJ is the heating area; A r,CFJ is the cooling area, S t,up is the surplus Internet access income in the tth year; S is the number of typical daily scenarios each year; N s is the number of days of a typical day scene s in a year; H is the total number of time periods in a day, C up,e,t,s,h is the unit price of surplus electricity on-grid in the h period of the typical day scenario in the tth year; P up,e,t,s,h is the online power consumption in the h period of the typical day scenario in the tth year, S inv Subsidy for total investment; is the investment subsidy for year t; i is the number of the energy supply production equipment; Ω 1 A collection of production equipment for energy supply; Subsidy for initial investment per unit capacity of production equipment for the i-th energy supply; is the investment and construction capacity of the i-th energy supply production equipment in year t; j is the energy storage equipment number; Ω 2 Assemble for energy storage equipment; is the initial investment subsidy per unit capacity of the jth energy storage device; is the investment capacity of the j-th energy storage device in year t, S t,sub is the power generation subsidy income in the tth year; S is the number of typical daily scenarios each year; N s is the number of days of a typical day scene s in a year; H is the total number of time periods in a day, C wt,e,t,s,h , C pv,q,t,s,hare the electricity subsidies for wind power generation and photovoltaic power generation in the h period of the typical day scenario in the tth year; P wt,e,t,s,h , P pv,e,t,s,h are the wind power generation and photovoltaic power generation in the typical day scenario h period in year t, S t,c is the environmental benefit in year t; C t,c is the carbon trading price in year t; E t,nom is the carbon quota for year t; E t,co2 is the carbon dioxide emissions in year t; The emission coefficient of carbon dioxide generated by the consumption of electricity; is the emission coefficient of carbon dioxide produced by the i-th energy supply production equipment consuming natural gas, S t,i,le,dp is the deviation income of the i-th green power medium- and long-term transaction in the t-th year, C le,t,i,s,h,dp The penalty unit price for deviation of the i-th green power medium- and long-term transaction in the h-th period of the typical day scenario in the t-th year; P le,t,i,s,h,dp P is the deviation of the i-th green electricity medium- and long-term transaction caused by the power purchaser’s responsibility in the h-th period of the typical day scenario in the t-th year; lest,t,i,s,h The transaction volume of the i-th green power medium- and long-term trading contract in the h-th period of the typical day scenario in the t-th year; P legm,t,i,s,h The amount of green electricity provided by medium- and long-term transactions in the i-th period of time in the typical day scenario of the t-th year, E RV is the total residual value of the comprehensive energy system equipment at the end of the planning period, M n is the total number of equipment in the integrated energy system, δ i is the residual value rate of the ith equipment, C INV,i is the initial investment of the i-th device, N is the number of nodes, f i,ntp is the net profit of the energy system of the ith node over its entire life cycle, f i,tp is the total profit of the entire life cycle of the ith node, λ int is the income tax rate, f i,ep is the economic benefit of the entire life cycle of the i-th node, λ vat is the value added tax rate, λ umt Maintaining tax rates for urban construction, λ est is the education surcharge rate, f i,in is the total life cycle benefit of the integrated energy system of the i-th node, f i,c is the total investment cost of the integrated energy system at the i-th node, f i,t,in is the total revenue of the integrated energy system at the i-th node in the t-th year, SR i,t is the energy supply income of the ith node in the tth year, S i,t,up is the surplus Internet access income of the ith node in the tth year, is the investment subsidy of the ith node in the tth year, S i,t,sub is the power generation subsidy income of the ith node in the tth year, Si,t,vs is the value-added service revenue of the ith node in the tth year, S i,t,c is the environmental benefit of the ith node in the tth year, S i,t,le,dp The deviation income of green power medium- and long-term trading in the ith node in the tth year, E i,RV is the total residual value of the integrated energy system equipment at the end of the planning period of the i-th node, is the initial investment cost of the integrated energy system at the i-th node in the t-th year, α lr, t is the loan ratio in year t, is the equipment maintenance cost of the ith node in the tth year, is the energy purchase cost of the ith node in the tth year, C i,fc,t is the financial cost of the ith node in the tth year, N is the number of nodes, and f i,e is the carbon dioxide emissions of the energy system of the ith node throughout its life cycle; T is the planning period, i.e., the total planning period; is the CO2 emission of the energy system of the ith node in the tth year; S is the number of typical daily scenarios per year; N s is the number of days of the typical day scene s in a year; H is the total number of time periods in a day; The emission coefficient of carbon dioxide generated by consuming public grid electricity; is the emission coefficient of carbon dioxide produced by natural gas; P i,e,t,s,h G is the amount of electricity purchased from the public grid in the h period of the typical day scenario in year t; i,g,t,s,h is the natural gas purchase volume in the h period of the typical day scenario in year t.

[0061] In one embodiment of the present invention, multi-node data center planning involves regulation between data centers, and the decision is to determine the selection of computing power nodes and time and further obtain the computing power scale of each data center and the server configuration of each data center.

[0062] Meaning: The time within a day can be expressed as The task arriving at time slot t can be expressed as:

[0063]

[0064] Where:

[0065] As can be seen from 3.2.3 Task Feature Model;

[0066] x∈{delay-tolerant, delay-sensitive}, indicating the type of tasks divided according to their sensitivity to delay;

[0067] sce∈{working day, holiday, weekend}, represents a typical day divided according to the amount of computation;

[0068] I represents the number of routers, i = [1, I] represents the number of routers;

[0069] Indicates the task The corresponding computing resource requirements;

[0070] Indicates the task The corresponding network resource demand;

[0071] Indicates the task The corresponding energy resource demand;

[0072] N i，x represents the number of tasks of type x that arrive at router i,

[0073] n=[1,N i，x ] indicates the number of a specific task;

[0074] t∈{1, 2, ..., 24}, represents the arrival time slot. Since multiple data centers require spatial and temporal scheduling, the spatial decision variable of the request is expressed as:

[0075]

[0076] Because a request can only be dispatched to one data center,

[0077]

[0078] Confirm the request The scheduling decision for forwarding time is

[0079]

[0080] Delay Constraint

[0081]

[0082] Meaning: The total latency of each task is defined as the sum of transmission latency, propagation latency and processing latency.

[0083] The delay under scheduling decisions X, Z can be expressed as:

[0084]

[0085] Where: is the transmission delay, that is, the sum of the tasks passing through the servers on the transmission path, is the propagation delay (actual physical distance divided by the speed of light), and is the computation delay. The computation delay of each task can be expressed as:

[0086]

[0087] Where: Indicates the computing power obtained by each task, Num task (t) is the number of tasks in time slot t. gen (FLOPS) is the computing resource of the general-purpose server, and Num is the number of general-purpose servers in the data center.

[0088] Regarding step 104:

[0089] In one embodiment of the present invention, the energy supply constraint: C2: E total ≤Q total

[0090] Where: Q total It is the total amount of energy that can be provided by the energy supplier.

[0091] Regarding step 106:

[0092] like Figure 5 As shown, in one embodiment of the present invention, the upper model is the main model for computing system planning, the decision variables are task allocation strategy, data center computing scale strategy, and its objective function is to minimize carbon emissions and electricity prices. The lower model is a sub-model of the upper model, which is used to solve the optimization sub-problem of computing equipment construction in the computing system, and coordinate the joint processing tasks of various computing equipment according to the differences in cost, income, environmental protection, etc. of different computing equipment. The data center computing scale of the upper model is passed to the lower model as the boundary condition of the lower model.

[0093] (1) Upper model

[0094] The upper model is the main model for computing system planning. The decision variables are task allocation strategy and data center computing scale strategy. Its objective function is to minimize carbon emissions and electricity prices, as shown below.

[0095] The last generation adds weighted values ​​and normalizes the economic and environmental goals and then sums them up. The comprehensive objective function is as follows.

[0096]

[0097] ω 1 +ω 2 =1

[0098] In the formula, ω 1 ,ω 2 is the weight coefficient, is the normalized value of the economic objective of the i-th solution of the last generation, is the normalized value of the environmental protection target of the i-th solution of the last generation, is the maximum value of the economic objective among all solutions of the last generation, is the minimum value of the economic objective among all solutions of the last generation, is the maximum value of the environmental protection target among all solutions of the last generation, is the minimum value of the environmental protection target among all solutions of the last generation, and M is the number of solutions of the last generation.

[0099] After the upper-level model determines the scale of the data center, it is transmitted to the lower-level model to complete the configuration of the computing equipment in the data center.

[0100] (2) Lower-level model

[0101] The lower model is a sub-model of the upper model, which is used to solve the sub-problem of optimizing the construction of computing power equipment in the computing power system. It coordinates the joint processing tasks of various computing power equipment according to the differences in cost, income, environmental protection, etc. of different computing power equipment. The data center computing power scale of the upper model is passed to the lower model as the boundary condition of the lower model.

[0102] The last generation adds weighted values ​​and normalizes the economic and environmental goals and then sums them up. The comprehensive objective function is as follows.

[0103]

[0104] ω 1 +ω 2 =1

[0105] In the formula, ω 1 ,ω 2 is the weight coefficient, is the normalized value of the economic objective of the i-th solution of the last generation, is the normalized value of the environmental protection target of the i-th solution of the last generation, is the maximum value of the economic objective among all solutions of the last generation, is the minimum value of the economic objective among all solutions of the last generation, is the maximum value of the environmental protection target among all solutions of the last generation, is the minimum value of the environmental protection target among all solutions of the last generation, and M is the number of solutions of the last generation.

[0106] In each optimization process, the upper-level model optimizes the computing power scale of the data center, and the lower-level model uses this as the boundary condition to optimize the optimal computing power configuration of the data center.

[0107] Regarding step 108:

[0108] In one embodiment of the present invention, the maximum profit of the multi-node planning period is determined by the following formula:

[0109]

[0110]

[0111] TrueProfit Total =Profit Total *(1-λ)

[0112] In the formula, Cost Device Cost represents the total cost of initial equipment purchase; Device,l represents the total initial equipment acquisition cost of data center l; Indicates the number of CPU computing devices of type a in data center l; represents the number of b types of GPU computing devices in data center l; represents the number of c types of network devices in data center l; represents the number of d types of cabinets in data center l; Indicates the price of a type of CPU computing equipment in data center l; represents the price of b types of GPU computing devices in data center l; represents the price of c types of network equipment in data center l; represents the price of d types of cabinet equipment in data center l, where represents the planned equipment maintenance cost in year t; The planned equipment maintenance cost of data center l in year t; Indicates the number of CPU computing devices of type a in data center l; represents the number of b types of GPU computing devices in data center l; represents the number of c types of network devices in data center l; represents the number of d types of cabinets in data center l; represents the maintenance cost of type a CPU computing equipment in data center l in year t; represents the maintenance cost of b types of GPU computing equipment in data center l in year t; represents the maintenance cost of c types of network equipment in data center l in year t; represents the maintenance cost of d types of cabinet equipment in data center l in year t, represents the annual equipment electricity consumption cost; represents the annual equipment power consumption cost of data center l; represents the heating price per unit area of ​​data center l; represents the heating area of ​​data center l; represents the cooling price per unit area of ​​data center l; represents the cooling area of ​​data center l; represents the energy efficiency coefficient of data center l in different seasons, where The default value is 1.05; represents the terminal power supply price of data center l in year t; P l task P represents the energy consumption of the computing power request equipment of data center l in year t; l idle represents the basic energy consumption of the equipment in data center l in year t, Cost e，total is the total electricity price,

[0113] T cycle is the life cycle in years, is the total electricity price of the data center corresponding to the typical day scei, T scei is the number of days of a typical day, is the total electricity price of the data center in one day, The electricity price of data center m in time slot t, represents the electricity price of data center m, P m (t) represents the electricity price of data center m at time t, S t,vs is the value-added service revenue in year t; vs,l The value-added service revenue ratio coefficient of the data center; is the comprehensive energy purchase cost of data center l, including: Indicates the total cost of the data center; Total cost of data center l; Energy t,l Indicates the power of all equipment in the data center; Expense t,l Cost represents the construction cost of data center l. Inv Indicates the initial investment cost; Cost Inv,l represents the initial investment cost of data center l; Cost Device,l represents the total initial equipment acquisition cost of data center l; represents the total cost of data center l; considering the delay in project planning and construction, the discount rate needs to be increased, r is the capital discount rate; α l is the loan ratio of data center l, is the financial cost in year t; is the financial cost of data center l in year t; rate l is the annual loan interest rate of the data center l loan; is the investment cost of data center l; α l is the loan ratio of data center l; lim l is the repayment period of the data center loan, Cost Total Cost Total,lis the total planning cycle cost of the data center l of the integrated computing network system, where Income t Indicates the computing power income in the tth year; Income t,l represents the computing power income of data center l in year t; represents the unit price of computing power in data center l in year t; represents the maximum computing power demand at center l in year t, where Residual is the total residual value of computing network system equipment at the end of the planning period, H is the total number of equipment in the computing network system and H = A + B + C + D, β i is the residual value rate of the i-th equipment, Price i is the initial purchase price of the i-th device, where Income Total is the total income of the computing network system over its entire life cycle; r is the capital discount rate,

[0114] To calculate the economic benefits of the entire life cycle of the network system, TrueProfit Total is the total net profit over the entire life cycle; λ is the income tax rate.

[0115] The upper limit constraint of multi-node equipment planning capacity is determined by the following formula:

[0116]

[0117] In the formula, The investment capacity of the i-th energy supply production equipment of the n-th node data center in year t, is the investment capacity of the j-th energy storage device in the n-th node data center in year t, They are the planned capacity upper limits of the energy production equipment and energy storage equipment of the nth node data center in the tth year.

[0118] Regarding step 110:

[0119] In one embodiment of the present invention, the multi-node power balance constraints include electric power balance constraints, thermal power balance constraints, cold power balance constraints, natural gas power balance constraints, and hydrogen power balance constraints;

[0120] The multi-node power balance constraint is determined by the following formula:

[0121]

[0122]

[0123] In the formula, n represents the nth node, N is the number of nodes, Ω 4 A collection of energy supply production equipment for generating electrical energy; Ω 5A collection of power storage devices; Ω 6 A collection of energy supply production equipment that consumes electrical energy; n,e,t,s,h P is the amount of public grid electricity purchased by the nth node data center in the typical day scenario h period in the tth year; n,le,t,i,s,h P is the i-th green electricity mid- and long-term transaction purchase amount in the n-th node data center in the t-th year s typical day scenario h period; n,ge,t,s,h is the normal green electricity purchase amount of the nth node data center in the typical day scenario h period in the tth year; P n,e,m,t,s,h The power generated by the energy supply production equipment of the mth energy generating power in the typical day scenario h period of the tth year s in the nth node data center; P n,e,j,ES-dis,t,s,h P is the discharge power of the jth power storage device in the typical day scenario h period in the tth year in the nth node data center; n,e,k,t,s,h P is the power consumed by the kth energy supply device consuming electricity in the typical day scenario h period of the tth year in the nth node data center; n,eL,t,s,h is the other electrical load of the data center of the nth node in the typical day scenario of the tth year and the hth period; P n,e,j,ES-ch,t,s,h P is the charging power of the jth power storage device in the typical day scenario h period of the tth year in the nth node data center; n,cpeL,t,s,h is the power load consumed by the computing equipment in the data center of the nth node during the h-hour period of the typical day scenario of the tth year, Ω 7 A collection of energy supply production equipment for generating heat energy; 8 is a collection of heat storage devices; Ω 9 A collection of energy supply production equipment that consumes heat energy; Q n,q,i,t,s,h The thermal power generated by the energy supply production equipment of the ith energy generating heat energy in the tth year s typical day scenario h period of the nth node data center; Q n,q,j,HS-dis,t,s,h Q is the heat release power of the jth heat storage device in the nth node data center in the tth year s typical day scenario h period; n,q,k,t,s,h Q is the heat load of the energy supply production equipment of the kth energy consumption heat energy in the typical day scenario h period of the nth node data center in the tth year; n,qL,t,s,h Q is the heat load of the data center of the nth node in the typical day scenario of the tth year and the hth period; n,q,j,HS-ch,t,s,h is the charging power of the jth heat storage device in the typical day scenario h period of the tth year in the nth node data center, Ω 10 A collection of energy supply production equipment for generating cold energy;Ω 11 A collection of cold storage equipment; C n,c,i,t,s,h C is the cooling power generated by the energy supply production equipment that generates cooling energy in the ith energy supply production equipment in the tth year s typical day scenario h period of the nth node data center; n,c,j,CS-dis,t,s,h C is the cooling power of the jth cold storage device in the nth node data center in the tth year s typical day scenario h period; n,cL,t,s,his the cooling load of the nth node data center in the hth period of the typical day scenario in the tth year; C n,c,j,CS-ch,t,s,h is the cooling power of the jth cold storage device in the typical day scenario h period of the nth node data center in the tth year, Ω 3 A collection of energy supply production equipment consuming natural gas; 12 G is a collection of gas storage equipment; n,g,t,s,h G is the natural gas power purchased by the data center of the nth node in the typical day scenario of the tth year and the hth period; n,g,i,GS-dis,t,s,h G is the gas discharge power of the jth gas storage device in the nth node data center in the tth year s typical day scenario h period; n,g,j,t,s,h The natural gas power of the energy supply production equipment of the jth natural gas consumption in the typical day scenario h period of the nth node data center in the tth year; G n,g,i,GS-ch,t,s,h is the gas filling power of the jth gas storage device in the typical day scenario h period of the tth year in the nth node data center, Ω 14 A collection of energy supply and production equipment for consuming hydrogen; 13 Assemble for hydrogen storage equipment; The amount of hydrogen purchased by the nth node data center in the hth period of the tth year s typical day scenario; The hydrogen discharge power of the jth hydrogen storage device in the nth node data center in the tth year s typical day scenario h period; The hydrogen power of the energy supply production equipment for the jth energy consuming hydrogen energy in the typical day scenario h period of the tth year s of the nth node data center; It is the hydrogen charging power of the jth hydrogen storage device in the typical day scenario h period in the tth year in the nth node data center.

[0124] In one embodiment of the present invention, the multi-node equipment operation planning constraint is determined by the following formula:

[0125]

[0126] 1≤n≤N

[0127] In the formula, The minimum value of the green electricity medium- and long-term trading power supply of the nth node data center; The maximum power consumed by the kth energy supply device consuming power in the nth node data center in the tth year; The maximum thermal power of the energy supply production equipment for the kth energy consumption of heat energy in the nth node data center in the tth year; The maximum natural gas power of the energy supply production equipment for the jth natural gas consumption in the nth node data center in the tth year; The maximum hydrogen power of the energy supply production equipment for the jth energy consumption of hydrogen energy in the nth node data center in the tth year; are the rated capacities of the electricity, heat, and cold energy production equipment of the nth node data center in year t, They are respectively the other power loads, power load consumed by computing equipment, heat load, and cooling load peaks of the nth node data center in the tth year.

[0128] In one embodiment of the present invention, the power exchange constraint between the energy system and the upper network is determined by the following formula:

[0129]

[0130] In the formula, are the minimum and maximum power purchased from the public grid thermal power of the nth node data center in year t, respectively; are the minimum and maximum purchased natural gas power of the nth node data center in year t, respectively; are the minimum and maximum purchased hydrogen power for the nth node data center in year t, respectively; are the minimum and maximum green electricity purchase power of the nth node data center in year t; P n,legm,t,i,s,h It is the amount of green electricity medium- and long-term trading power provided by the n-th node data center in the i-th period of h in the typical day scenario of the t-th year.

[0131] Green power ratio constraints

[0132] GE n,rate ≥GE n,rate_nor

[0133] In the formula, GE n,rate is the green power ratio of the nth node data center; GE n,rate_nor It is the lower limit of green power percentage of the nth node data center.

[0134] Regarding step 112:

[0135] like Figure 4As shown, in one embodiment of the present invention, it can be seen from the above model that the decision variables include equipment configuration strategy and system operation optimization variables. The system operation optimization problem takes the system equipment configuration strategy as the boundary condition. It is difficult to optimize both at the same time. It is necessary to split and transform the two parts of the variables. Considering the logical relationship of the variables, the equipment configuration strategy can be determined first, and the system operation optimization decision can be made on this basis. The optimal solution is output by repeated iterations. It can be seen that the two-layer optimization model is suitable for solving the planning model of this project. The original optimization model is converted into a multi-objective two-layer joint optimization configuration model for an integrated energy system. The upper model is the main model, which is an equipment selection and capacity optimization model, which is used to select the optimal equipment configuration combination from the selected equipment set, with the goal of minimizing the total cost and pollutant gas emissions; the lower model is a sub-model, which is an operation scheduling optimization model. The equipment configuration scheme determined by the upper model is used as a boundary condition to formulate the optimal plan for the output of each device under the premise of meeting the regional energy supply and demand balance, with the goal of minimizing the total operating cost. The upper-level model optimizes the configuration strategies and planned capacities of various types of equipment and passes them to the lower-level model. The lower-level model optimizes the scheduling and operation of the comprehensive energy system, and returns the optimal operation plan and total operating cost to the upper-level model. Through the optimization iteration of the upper and lower layers, the optimal configuration strategy of the energy system is solved.

[0136] (1) Upper model

[0137] The upper model is the main model for energy system planning. The decision variables are the configuration and planned capacity of various types of equipment, namely the investment capacity of energy supply production equipment, the investment capacity of energy storage equipment and the rated power of energy storage equipment. Its objective function is to minimize the total planning cost and the emission of polluting gases, as shown below.

[0138] By adding weighted values ​​and normalizing the economic and environmental goals and then summing them up, the comprehensive objective function is as follows.

[0139]

[0140] ω 1 +ω 2 =1

[0141] In the formula, ω 1 ,ω 2 is the weight coefficient, is the normalized value of the economic objective of the ith solution of the current iteration, is the normalized value of the environmental protection target of the i-th solution in the current iteration, max i (f i,ntp ) is the maximum value of the economic objective among all solutions in the current iteration, min i (f i,ntp ) is the minimum value of the economic objective among all solutions in the current iteration, max i(f i,e ) is the maximum value of the environmental protection target among all solutions in the current iteration, min i (f i,e ) is the minimum value of the environmental protection target among all solutions in the current iteration, and M is the number of solutions in the current iteration.

[0142] After the lower-level model determines the operating strategy, it is transmitted to the upper-level model to complete the cost and benefit calculation related to the operating strategy.

[0143] (2) Lower-level model

[0144] The lower model is a sub-model of the upper model, which is used to solve the scheduling and operation optimization sub-problems of various energy supply production equipment and energy storage equipment in the energy system. According to the differences in the supply and demand of different energy sources, various energy needs are met by coordinating the operation of various energy supply production equipment and the charging and discharging of energy storage equipment. The configuration and planned capacity of various equipment produced by the upper model are passed to the lower model as the boundary conditions of the lower model. Its objective function is to minimize the total operating cost, as shown below.

[0145]

[0146] In the nth iteration of the optimization process, the upper-level model optimizes the configuration and planned capacity of various equipment and passes it to the lower-level model. The lower-level model uses this as the boundary condition to optimize the optimal scheduling operation plan, and returns to the upper level to calculate the profit and pollutant gas emissions during the planning period as the initial value of the n+1th iteration.

[0147] Regarding step 114:

[0148] like Figure 6As shown, in one embodiment of the present invention, when multi-node computing network can be collaboratively planned, each node data center establishes an integrated energy system (electricity-cold-heat-hydrogen-gas, etc.) with optimal economy and lowest carbon emissions according to resource endowment conditions. The computing power multi-objective planning and design aims to minimize carbon emissions, minimize energy consumption, and maximize profits. The various energy supply curves and prices of each node data center are used as boundary conditions to optimize the timing of computing power tasks such as interactive workloads and batch workloads and optimize the spatial allocation of multi-node data centers. The initial scale of each node data center and the computing power load demand curve are determined. The energy multi-objective planning and design module calculates the cooling load, heating load and other electrical loads of the data center according to the computing power load demand curve of each node data center, and uses this as the boundary condition, with the maximum profit and the minimum carbon emission during the planning period as the goal, to optimize the energy supply facility capacity of each node data center comprehensive energy system, the trading scale of public grid thermal power and green electricity, the trading scale of natural gas and hydrogen, etc. The multi-objective planning and design of computing power and the multi-objective planning and design of energy use the multi-temporal and spatial dimensional allocation of computing power tasks and multi-node energy supply as coupling points and boundary interactions. Through multiple iterations, the optimal planning scheme for computing, network and energy integration is finally optimized.

[0149] like Figure 2 , Figure 3 As shown, the embodiment of the present invention provides a multi-node computing network collaborative planning device for multi-temporal and multi-spatial dimension scheduling of computing tasks. The device embodiment can be implemented by software, or by hardware or a combination of software and hardware. From the hardware level, Figure 2 As shown, a hardware architecture diagram of an electronic device where a multi-node computing network collaborative planning device for multi-temporal and spatial dimension scheduling of computing tasks provided by an embodiment of the present invention is located, except Figure 2 In addition to the processor, memory, network interface, and non-volatile memory shown in the figure, the electronic device in which the device is located in the embodiment may also generally include other hardware, such as a forwarding chip responsible for processing messages, etc. Taking software implementation as an example, Figure 3 As shown, as a device in a logical sense, the CPU of the electronic device in which it is located reads the corresponding computer program in the non-volatile memory into the internal memory and runs it.

[0150] like Figure 3 As shown, this embodiment provides a multi-node computing network collaborative planning device for scheduling computing tasks in multiple time and space dimensions, and the device includes:

[0151] A model building module 300 is used to establish a multi-node computing network planning model and a multi-node energy supply planning model;

[0152] The first data processing module 302 is used for the first upper-layer model to determine the multi-node center computing power scale with the maximum multi-node data center revenue and the minimum carbon emission as the objective function, and the delay constraint and the multi-node computing power scale constraint as the constraint conditions, and send the multi-node center computing power scale to the first lower-layer model;

[0153] The second data processing module 304 is used for the first lower-layer model to determine the carbon emissions and profits of the multi-node data center with the maximum revenue and minimum carbon emissions of the multi-node data center as the objective function, and with the energy constraint and the multi-node computing power scale constraint as the constraint conditions, and send the carbon emissions and profits of the multi-node data center to the first upper-layer model;

[0154] The third data processing module 306 is used to repeatedly iterate the first upper model and the first lower model to determine a first optimal solution; wherein the first optimal solution includes a multi-node computing power equipment planning scheme and a multi-node computing power energy consumption load curve, and the multi-node computing power energy consumption load curve is used as an input of the energy supply planning model to perform coupling interaction;

[0155] The fourth data processing module 308 is used for the second upper-layer model to determine the multi-node device configuration strategy and planning capacity with the maximum profit and the minimum carbon emission in the multi-node planning period as the objective function, and the multi-node device planning capacity upper limit constraint and the multi-node device commissioning planning constraint as the constraint conditions, and send the multi-node device configuration strategy and planning capacity to the second lower-layer model;

[0156] The fifth data processing module 310 is used for the second lower-layer model to determine the optimal operation plan and the total operation cost with the minimum multi-node operation cost as the objective function, the multi-node power balance constraint, the equipment commissioning planning constraint, the energy system and the upper network power exchange constraint, and the green power proportion constraint as the constraint conditions, and send the optimal operation plan and the total operation cost to the second upper-layer model;

[0157] The sixth data processing module 312 is used for repeatedly iterating the second upper model and the second lower model to determine a second optimal solution; wherein the second optimal solution includes an energy supply planning scheme, a power curve of a power generation device, a public grid thermal power curve, and a green electricity trading curve, and the power curve of the power generation device, the public grid thermal power curve, and the green electricity trading curve are used as inputs of a multi-node computing power network planning model for coupling interaction;

[0158] The loop coupling interaction module 314 is used for loop coupling interaction between the multi-node computing power network planning model and the multi-node energy supply planning model, and has realized the multi-node computing network collaborative planning of computing power task multi-temporal and spatial dimension scheduling.

[0159] In an embodiment of the present invention, the model building module 300 can be used to execute step 100 in the above method embodiment, the first data processing module 302 can be used to execute step 102 in the above method embodiment, the second data processing module 304 can be used to execute step 104 in the above method embodiment, the third data processing module 306 can be used to execute step 106 in the above method embodiment, the fourth data processing module 308 can be used to execute step 108 in the above method embodiment, the fifth data processing module 310 can be used to execute step 110 in the above method embodiment, the sixth data processing module 312 can be used to execute step 112 in the above method embodiment, and the loop coupling interaction module 314 can be used to execute step 114 in the above method embodiment.

Claims

1. A multi-node computing network capable of collaborative planning for multi-temporal and multi-spatial dimension scheduling of computing tasks, characterized in that: The method is applied to a multi-node computing network, comprising: Establish a multi-node computing power network planning model and a multi-node energy supply planning model; wherein the multi-node computing power network planning model and the multi-node energy supply planning model are both double-layer model structures, the multi-node computing power network planning model includes a first upper layer model and a first lower layer model, and the multi-node energy supply planning model includes a second upper layer model and a second lower layer model; The first upper-layer model takes the maximum benefit and the minimum carbon emission of the multi-node data center as the objective function, takes the delay constraint and the multi-node computing power scale constraint as the constraint conditions, determines the multi-node center computing power scale, and sends the multi-node center computing power scale to the first lower-layer model; The first lower-layer model takes the maximum revenue and minimum carbon emissions of the multi-node data center as the objective function, takes the energy constraint and the multi-node computing power scale constraint as the constraint conditions, determines the carbon emissions and profits of the multi-node data center, and sends the carbon emissions and profits of the multi-node data center to the first upper-layer model; The first upper model and the first lower model are repeatedly iterated to determine a first optimal solution; wherein the first optimal solution includes a multi-node computing power equipment planning scheme and a multi-node computing power energy consumption load curve, and the multi-node computing power energy consumption load curve is used as an input of the energy supply planning model to perform coupling interaction; The second upper-layer model takes the maximum profit and the minimum carbon emission in the multi-node planning period as the objective function, takes the upper limit constraint of the multi-node equipment planning capacity and the multi-node equipment commissioning planning constraint as the constraint conditions, determines the multi-node equipment configuration strategy and the planning capacity, and sends the multi-node equipment configuration strategy and the planning capacity to the second lower-layer model; The second lower-layer model takes the minimization of multi-node operation cost as the objective function, and takes the multi-node power balance constraint, the equipment commissioning planning constraint, the energy system and the upper-level network power exchange constraint, and the green electricity proportion constraint as the constraint conditions to determine the optimal operation plan and the total operation cost, and sends the optimal operation plan and the total operation cost to the second upper-layer model; The second upper model and the second lower model are repeatedly iterated to determine a second optimal solution; wherein the second optimal solution includes an energy supply planning scheme, a power curve of power generation equipment, a public grid thermal power curve, and a green electricity trading curve, and the power curve of power generation equipment, the public grid thermal power curve, and the green electricity trading curve are used as inputs of a multi-node computing power network planning model for coupling interaction; The multi-node computing power network planning model and the multi-node energy supply planning model are cyclically coupled and interacted, and multi-node computing network collaborative planning for scheduling computing power tasks in multiple time and space dimensions has been realized.

2. The method according to claim 1, characterized in that The objective function of maximizing the revenue of the multi-node data center and minimizing carbon emissions includes the following formula: S t,c =C t,c ·(E t,nom -E t,co2 ) / 10000 f i,ntp =f i,tp (1-l int )=(f i,ep -f i,ep l vat l umt -f i,ep l vat l est )(1-l int ) f i,ep =f i,in -f i,c In the formula, The number of production facilities supplying the i-th energy source put into operation in year t; The capacity of the selected model of production equipment for the i-th energy supply; is the number of the i-th energy storage device put into operation in year t; is the capacity of the model selected for the i-th energy storage device; C inv is the initial investment cost; T is the life cycle; r is the capital discount rate; is the investment cost in year t; α lr,t is the loan ratio in the tth year; i is the number of energy supply production equipment; Ω1 is the set of energy supply production equipment; Unit capacity investment cost of production equipment for the i-th energy supply; is the investment and construction capacity of the i-th energy supply production equipment in year t; j is the energy storage equipment number; Ω2 is the energy storage equipment set; is the unit capacity investment cost of the jth energy storage device; is the investment capacity of the j-th energy storage device in year t, The annual operation and maintenance cost per unit capacity of the production equipment for the i-th energy supply; is the annual operation and maintenance cost per unit capacity of the j-th energy storage device, is the purchase cost of public grid thermal power in year t, is the medium- and long-term transaction cost of the i-th green electricity in the t-th year, is the normal green electricity purchase cost in year t, is the penalty cost for the deviation of the i-th green power medium- and long-term transaction in the t-th year, is the natural gas purchase cost in year t, is the hydrogen purchase cost in year t, S is the number of typical daily scenarios each year; N s is the number of days of a typical day scene s in a year; H is the total number of time periods in a day, C e,t,s,h P is the unit price of public grid electricity purchased in the h period of the typical day scenario in the tth year; e,t,s,h is the amount of electricity purchased from the public grid in the typical day scenario h period in year t, C le,t,i,s,h P is the purchase price of the i-th green power medium- and long-term transaction in the h-th period of the typical day scenario in the t-th year; le,t,i,s,h is the mid- to long-term green electricity purchase volume in the i-th period of the typical day scenario in the t-th year, C ge,t,s,h P is the normal green electricity purchase price in the h period of the typical day scenario in the tth year; ge,t,s,h is the normal green electricity purchase amount in the h period of the typical day scenario in the tth year, C g,t,s,h G is the natural gas purchase price in the typical day scenario h period in year t; g,t,s,h is the natural gas purchase volume in the typical day scenario h period in year t, C H2,t,s,h G is the unit price of hydrogen purchased in the typical day scenario h period in year t; H2,t,s,h is the amount of hydrogen purchased in the typical day scenario h period in year t, C le,t,i,s,h,dp The penalty unit price for deviation of the i-th green power medium- and long-term transaction in the h-th period of the typical day scenario in the t-th year; P le,t,i,s,h,dp P is the deviation of the i-th green electricity medium- and long-term transaction caused by the responsibility of the power purchaser in the h-th period of the typical day scenario in the t-th year; lest,t,i,s,h The transaction volume of the i-th green power medium- and long-term trading contract in the h-th period of the typical day scenario in the t-th year; P legm,t,i,s,h The amount of green electricity provided by medium- and long-term transactions in the i-th period of time in the typical day scenario of the t-th year, C fc,t is the financial cost in year t; r i,tt is the annual loan interest rate of the loan in year tt; C inv,tt is the investment cost in year tt; α lr,tt is the loan ratio in year tt; N tt is the repayment period of the loan in year tt, SR t is the energy supply income in year t, C e,t,s,h,S are the electricity selling price in the typical day scenario h period in year t; P eL,t,s,h P is the other electrical load in the typical day scenario h period in year t; cpeL,t,s,h HPR is the power load consumed by computing equipment in the typical day scenario h period of year t; FJ is the heating price per unit area; CPR FJ is the cooling price per unit area; A r,HFJ is the heating area; A r,CFJ is the cooling area, S t,up is the surplus Internet access income in the tth year; S is the number of typical daily scenarios each year; N s is the number of days of a typical day scene s in a year; H is the total number of time periods in a day, C up,e,t,s,h is the unit price of surplus electricity on-grid in the h period of the typical day scenario in the tth year; P up,e,t,s,h is the online power consumption in the h period of the typical day scenario in the tth year, S inv Subsidy for total investment; is the investment subsidy for the tth year; i is the number of the energy supply production equipment; Ω1 is the energy supply production equipment set; Subsidy for initial investment per unit capacity of production equipment for the i-th energy supply; is the investment and construction capacity of the i-th energy supply production equipment in year t; j is the energy storage equipment number; Ω2 is the energy storage equipment set; is the initial investment subsidy per unit capacity of the jth energy storage device; is the investment capacity of the j-th energy storage device in year t, S t,sub is the power generation subsidy income in the tth year; S is the number of typical daily scenarios each year; N s is the number of days of a typical day scene s in a year; H is the total number of time periods in a day, C wt,e,t,s,h , C pv,q,t,s,h are the electricity subsidies for wind power generation and photovoltaic power generation in the h period of the typical day scenario in the tth year; P wt,e,t,s,h , P pv,e,t,s,h are the wind power generation and photovoltaic power generation in the typical day scenario h period in year t, S t,c is the environmental benefit in year t; C t,c is the carbon trading price in year t; E t,nom is the carbon quota for year t; E t,co2 is the carbon dioxide emissions in year t; α e,CO2 is the emission coefficient of carbon dioxide generated by the consumption of electricity; α g, i,CO2 is the emission coefficient of carbon dioxide produced by the i-th energy supply production equipment consuming natural gas, S t,i,le,dp is the deviation income of the i-th green power medium- and long-term transaction in the t-th year, C le,t,i,s,h,dp The penalty unit price for deviation of the i-th green power medium- and long-term transaction in the h-th period of the typical day scenario in the t-th year; P le,t,i,s,h,dp P is the deviation of the i-th green electricity medium- and long-term transaction caused by the responsibility of the power purchaser in the h-th period of the typical day scenario in the t-th year; lest,t,i,s,h The transaction volume of the i-th green power medium- and long-term trading contract in the h-th period of the typical day scenario in the t-th year; P legm,t,i,s,h The amount of green electricity provided by medium- and long-term transactions in the i-th period of time in the typical day scenario of the t-th year, E RV is the total residual value of the comprehensive energy system equipment at the end of the planning period, M n is the total number of equipment in the integrated energy system, δ i is the residual value rate of the ith equipment, C INV,i is the initial investment of the i-th device, N is the number of nodes, f i,ntp is the net profit of the energy system of the ith node over its entire life cycle, f i,tp is the total profit of the entire life cycle of the ith node, λ int is the income tax rate, f i,ep is the economic benefit of the entire life cycle of the i-th node, λ vat is the value added tax rate, λ umt Maintaining tax rates for urban construction, λ est is the education surcharge rate, f i,in is the total life cycle benefit of the integrated energy system of the i-th node, f i,c is the total investment cost of the integrated energy system at the i-th node, f i,t,in is the total revenue of the integrated energy system at the i-th node in the t-th year, SR i,t is the energy supply income of the ith node in the tth year, S i,t,up is the surplus Internet access income of the ith node in the tth year, is the investment subsidy of the ith node in the tth year, S i,t,sub is the power generation subsidy income of the ith node in the tth year, S i,t,vs is the value-added service revenue of the ith node in the tth year, S i,t,c is the environmental benefit of the ith node in the tth year, S i,t,le,dp The deviation income of green power medium- and long-term trading in the ith node in the tth year, E i,RV is the total residual value of the integrated energy system equipment at the end of the planning period of the i-th node, is the initial investment cost of the integrated energy system at the i-th node in the t-th year, α lr,t is the loan ratio in year t, is the equipment maintenance cost of the ith node in the tth year, is the energy purchase cost of the ith node in the tth year, C i,fc,t is the financial cost of the ith node in the tth year, N is the number of nodes, and f i,e is the life cycle carbon dioxide emissions of the energy system of the ith node; T is the planning period, i.e. the total planning period; E i,t,CO2 is the CO2 emission of the energy system of the ith node in the tth year; S is the number of typical daily scenarios per year; N s is the duration of the typical day scene s in a year; H is the total number of time periods in a day; α e, CO2 is the emission coefficient of carbon dioxide generated by consuming public grid electricity; α g,CO2 is the emission coefficient of carbon dioxide produced by natural gas; P i,e,t,s,h G is the amount of electricity purchased from the public grid in the h period of the typical day scenario in year t; i,g,t,s,h is the natural gas purchase volume in the h period of the typical day scenario in year t.

3. The method according to claim 2, characterized in that The maximum profit of the multi-node planning period is determined by the following formula: TrueProfit Total =Profit Total *(1-λ) In the formula, Cost Device Cost represents the total cost of initial equipment purchase; Device,l represents the total initial equipment acquisition cost of data center l; Indicates the number of CPU computing devices of type a in data center l; represents the number of b types of GPU computing devices in data center l; represents the number of c types of network devices in data center l; represents the number of d types of cabinets in data center l; Indicates the price of a type of CPU computing equipment in data center l; represents the price of b types of GPU computing devices in data center l; represents the price of c types of network equipment in data center l; represents the price of d types of cabinet equipment in data center l, where represents the planned equipment maintenance cost in year t; The planned equipment maintenance cost of data center l in year t; Indicates the number of CPU computing devices of type a in data center l; represents the number of b types of GPU computing devices in data center l; represents the number of c types of network devices in data center l; represents the number of d types of cabinets in data center l; represents the maintenance cost of type a CPU computing equipment in data center l in year t; represents the maintenance cost of b types of GPU computing equipment in data center l in year t; represents the maintenance cost of c types of network equipment in data center l in year t; Cost represents the maintenance cost of type d cabinet equipment in data center l in year t. Et Indicates the annual equipment power consumption cost; Cost Et,l represents the annual equipment power consumption cost of data center l; represents the heating price per unit area of ​​data center l; represents the heating area of ​​data center l; represents the cooling price per unit area of ​​data center l; represents the cooling area of ​​data center l; represents the energy efficiency coefficient of data center l in different seasons, where The default value is 1.05; represents the terminal power supply price of data center l in year t; P represents the energy consumption of the computing power request equipment of data center l in year t; l idle represents the basic energy consumption of the equipment in data center l in year t, Cost e，total is the total electricity price, T cycle is the life cycle in years, is the total electricity price of the data center corresponding to the typical day scei, T scei is the number of days of a typical day, is the total electricity price of the data center in one day, The electricity price of data center m in time slot t, represents the electricity price of data center m, P m (t) represents the electricity price of data center m at time t, S t,vs is the value-added service revenue in year t; vs,l The value-added service revenue ratio coefficient of the data center; is the comprehensive energy purchase cost of the data center, where Cost Bt Cost represents the total cost of the data center. Bt,l Total cost of data center l; Energy t,l Indicates the power of all equipment in the data center; Expense t,l Cost represents the construction cost of data center l. Inv Indicates the initial investment cost; Cost Inv,l Cost represents the initial investment cost of data center l; Device,l Cost represents the total initial equipment purchase cost of data center l; Bt represents the total construction cost of data center l; considering the delay in project planning and construction, the discount rate needs to be increased, r is the capital discount rate; α l is the loan ratio of data center l, is the financial cost in year t; is the financial cost of data center l in year t; rate l is the annual loan interest rate of the data center l loan; is the investment cost of data center l; α l is the loan ratio of data center l; lim l is the repayment period of the data center loan, Cost Total Cost Total,l is the total planning cycle cost of the data center l of the integrated computing network system, where Income t Indicates the computing power income in the tth year; Income t,l represents the computing power income of data center l in year t; P taskl represents the unit price of computing power in data center l in year t; T runningl represents the maximum computing power demand at center l in year t, where Residual is the total residual value of computing network system equipment at the end of the planning period, H is the total number of equipment in the computing network system and H = A + B + C + D, β i is the residual value rate of the i-th equipment, Price i is the initial purchase price of the i-th device, where Income Total is the total income of the computing network system over its entire life cycle; r is the capital discount rate, To calculate the economic benefits of the entire life cycle of the network system, TrueProfit Total is the total net profit over the entire life cycle; λ is the income tax rate.

4. The method according to claim 3, characterized in that The multi-node power balance constraints include electric power balance constraints, thermal power balance constraints, cold power balance constraints, natural gas power balance constraints and hydrogen power balance constraints; The multi-node power balance constraint is determined by the following formula: Where n represents the nth node, N is the number of nodes, Ω4 is the set of energy supply production equipment that generates electricity; Ω5 is the set of power storage equipment; Ω6 is the set of energy supply production equipment that consumes electricity; P n,e,t,s,h P is the amount of public grid electricity purchased by the nth node data center in the typical day scenario h period in the tth year; n,le,t,i,s,h P is the i-th green electricity mid- and long-term transaction purchase amount in the n-th node data center in the t-th year s typical day scenario h period; n,ge,t,s,h is the normal green electricity purchase amount of the nth node data center in the typical day scenario h period in the tth year; P n,e,m,t,s,h The power generated by the energy supply production equipment of the mth energy generating power in the typical day scenario h period of the tth year s in the nth node data center; P n,e,j,ES-dis,t,s,h P is the discharge power of the jth power storage device in the typical day scenario h period in the tth year in the nth node data center; n,e,k,t,s,h P is the power consumed by the kth energy supply device consuming electricity in the typical day scenario h period of the tth year in the nth node data center; n,eL,t,s,h is the other electrical load of the data center of the nth node in the typical day scenario of the tth year and the hth period; P n,e,j,ES-ch,t,s,h P is the charging power of the jth power storage device in the typical day scenario h period of the tth year in the nth node data center; n,cpeL,t,s,h is the power load consumed by the computing equipment in the typical day scenario h period of the nth node data center in the tth year; Ω7 is the set of energy supply and production equipment that generates heat energy; Ω8 is the set of heat storage equipment; Ω9 is the set of energy supply and production equipment that consumes heat energy; Q n,q,i,t,s,h The thermal power generated by the energy supply production equipment of the ith energy generating heat energy in the tth year s typical day scenario h period of the nth node data center; Q n,q,j,HS-dis,t,s,h Q is the heat release power of the jth heat storage device in the nth node data center in the tth year s typical day scenario h period; n,q,k,t,s,h Q is the heat load of the energy supply production equipment of the kth energy consumption heat energy in the typical day scenario h period of the nth node data center in the tth year; n,qL,t,s,h Q is the heat load of the data center of the nth node in the typical day scenario of the tth year and the hth period; n,q,j,HS-ch,t,s,h is the charging power of the jth heat storage device in the typical day scenario h period of the tth year in the nth node data center, Ω 10 A collection of energy supply production equipment for generating cold energy;Ω 11 A collection of cold storage equipment; C n,c,i,t,s,h The cooling power generated by the energy supply production equipment of the ith energy source generating cooling energy in the tth year s typical day scenario h period for the nth node data center; C n,c,j,CS-dis,t,s,h C is the cooling power of the jth cold storage device in the nth node data center in the tth year s typical day scenario h period; n,cL,t,s,h is the cooling load of the nth node data center in the hth period of the typical day scenario in the tth year; C n,c,j,CS-ch,t,s,h is the cooling power of the jth cold storage device in the typical day scenario h period of the tth year in the nth node data center, Ω3 is the set of energy supply production equipment consuming natural gas; Ω 12 G is a collection of gas storage equipment; n,g,t,s,h G is the natural gas power purchased by the data center of the nth node in the typical day scenario of the tth year and the hth period; n,g,i,GS-dis,t,s,h G is the gas discharge power of the jth gas storage device in the nth node data center in the tth year s typical day scenario h period; n,g,j,t,s,h The natural gas power of the energy supply production equipment of the jth natural gas consumption in the typical day scenario h period of the nth node data center in the tth year; G n,g,i,GS-ch,t,s,h is the gas filling power of the jth gas storage device in the typical day scenario h period of the tth year in the nth node data center, Ω 14 A collection of energy supply and production equipment for consuming hydrogen; 13 G is a collection of hydrogen storage equipment; n,H2,t,s,h G is the amount of hydrogen purchased by the nth node data center in the typical day scenario h period in the tth year; n,H2,i,H2-dis,t,s,h G is the hydrogen discharge power of the jth hydrogen storage device in the nth node data center in the tth year s typical day scenario h period; n,H2,j,t,s,h The hydrogen power of the energy supply production equipment of the jth energy consuming hydrogen energy in the typical day scenario h period of the tth year s of the nth node data center; G n,H2,i,H2-ch,t,s,h It is the hydrogen charging power of the jth hydrogen storage device in the typical day scenario h period in the tth year in the nth node data center.

5. The method according to claim 4, characterized in that The upper limit constraint of the multi-node device planning capacity is determined by the following formula: In the formula, The investment capacity of the i-th energy supply production equipment of the n-th node data center in year t, is the investment capacity of the j-th energy storage device in the n-th node data center in year t, They are the planned capacity upper limits of the energy production equipment and energy storage equipment of the nth node data center in the tth year.

6. The method according to claim 5, characterized in that The power exchange constraint between the energy system and the upper network is determined by the following formula: In the formula, are the minimum and maximum power purchased from the public grid thermal power of the nth node data center in year t, respectively; are the minimum and maximum purchased natural gas power of the nth node data center in year t, respectively; are the minimum and maximum purchased hydrogen power for the nth node data center in year t, respectively; are the minimum and maximum green electricity purchase power of the nth node data center in year t; P n,legm,t,i,s,h It is the amount of green electricity medium- and long-term trading power provided by the n-th node data center in the i-th period of h in the typical day scenario of the t-th year.

7. The method according to claim 6, characterized in that: The multi-node equipment operation planning constraint is determined by the following formula: In the formula, The minimum value of the green electricity medium- and long-term trading power supply of the nth node data center; The maximum power consumed by the kth energy supply device consuming power in the nth node data center in the tth year; The maximum thermal power of the energy supply production equipment for the kth energy consumption of heat energy in the nth node data center in the tth year; The maximum natural gas power of the energy supply production equipment for the jth natural gas consumption in the nth node data center in the tth year; The maximum hydrogen power of the energy supply production equipment for the jth energy consumption of hydrogen energy in the nth node data center in the tth year; are the rated capacities of the electricity, heat, and cold energy production equipment of the nth node data center in year t, They are respectively the other power loads, power load consumed by computing equipment, heat load, and cooling load peaks of the nth node data center in the tth year.

8. A multi-node computing network collaborative planning device for multi-temporal and spatial dimension scheduling of computing tasks, characterized in that: include: A model building module, used to establish a multi-node computing power network planning model and a multi-node energy supply planning model; wherein the multi-node computing power network planning model and the multi-node energy supply planning model are both double-layer model structures, the multi-node computing power network planning model includes a first upper layer model and a first lower layer model, and the multi-node energy supply planning model includes a second upper layer model and a second lower layer model; A first data processing module is used for the first upper-layer model to determine the multi-node center computing power scale with the maximum multi-node data center revenue and the minimum carbon emission as the objective function, and with the delay constraint and the multi-node computing power scale constraint as the constraint conditions, and send the multi-node center computing power scale to the first lower-layer model; A second data processing module is used for the first lower-layer model to determine the carbon emissions and profits of the multi-node data center with the maximum revenue and minimum carbon emissions of the multi-node data center as the objective function, and with the energy constraint and the multi-node computing power scale constraint as the constraint conditions, and to send the carbon emissions and profits of the multi-node data center to the first upper-layer model; A third data processing module is used for repeatedly iterating the first upper model and the first lower model to determine a first optimal solution; wherein the first optimal solution includes a multi-node computing power equipment planning scheme and a multi-node computing power energy consumption load curve, and the multi-node computing power energy consumption load curve is used as an input of the energy supply planning model to perform coupling interaction; A fourth data processing module is used for the second upper-layer model to determine the multi-node equipment configuration strategy and planning capacity with the maximum profit and the minimum carbon emission in the multi-node planning period as the objective function, and the multi-node equipment planning capacity upper limit constraint and the multi-node equipment commissioning planning constraint as the constraint conditions, and send the multi-node equipment configuration strategy and planning capacity to the second lower-layer model; A fifth data processing module is used for the second lower-layer model to determine the optimal operation plan and the total operation cost with the minimum multi-node operation cost as the objective function, the multi-node power balance constraint, the equipment commissioning planning constraint, the energy system and the upper network power exchange constraint, and the green electricity proportion constraint as the constraint conditions, and send the optimal operation plan and the total operation cost to the second upper-layer model; a sixth data processing module, configured to repeatedly iterate the second upper model and the second lower model to determine a second optimal solution; wherein the second optimal solution includes an energy supply planning scheme, a power curve of power generation equipment, a public grid thermal power curve, and a green electricity trading curve, and the power curve of power generation equipment, the public grid thermal power curve, and the green electricity trading curve are used as inputs of a multi-node computing power network planning model for coupling interaction; The loop coupling interaction module is used for loop coupling interaction between the multi-node computing power network planning model and the multi-node energy supply planning model, and has realized the collaborative planning of multi-node computing network for scheduling computing power tasks in multiple time and space dimensions.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images