Electric power system interconnection data center sustainable management optimization method and system

Abstract

The invention discloses a sustainable management optimization method and system for an interconnected data center of a power system, and the method comprises the steps: carrying out the modeling of the migration distribution and processing of a data center network operation in an interconnected data center network model, and optimizing the resource distribution and energy consumption during demand response; establishing a green data center mathematical model integrating uncertain renewable energy sources based on the job migration requirement of the data center network job and the job processing model; the green data center mathematical model comprises a dynamic price signal of demand response, a load scheduling strategy and a user demand; solving the green data center mathematical model, and optimizing the response capability and benefit of the data center in demand response. According to the invention, the flexibility and energy efficiency of the data center in the demand response activity can be effectively improved, and the sustainable development of the green data center is promoted.

Description

Technical Field

[0001] The present invention relates to a technical field, and in particular to a sustainable management optimization method and system for an interconnected data center of a power system. Background Art

[0002] The use of information technology services has become an intrinsic part of our daily lives as a part of a connected society. The increasing demand for internet-based data services to acquire, analyze, process, store, retrieve and disseminate data, and the trend of many organizations to offload their information technology needs through cloud computing, has led to a substantial growth in the data center industry. The data center industry is a facility that houses computing resources networked together using communication infrastructure for the purpose of data storage and application hosting.

[0003] Energy consumption in the data center industry has received attention for its overall impact on energy. The combined energy use of the data center industry accounted for 194 TWh in 2010. Optimizing the energy use of DC elements that are critical to their operation, such as CPU computing and server cooling, has slowed the growth of energy consumption compared to the growth in computing power and the number of services. Global data center energy consumption was 205 TWh in 2018, accounting for about 1% of global electricity consumption; between 2010 and 2018, data center computing instances grew by 550%, while energy consumption grew by only 6%. A green data center is a data center industry that seeks to reduce its carbon footprint by powering its operations with renewable energy, either by entering into power purchase agreements with third-party owners, by purchasing green energy offsets for one unit of brown energy from green hosting providers, or by installing its own solutions to generate renewable energy to improve power efficiency. Green data centers can reduce the environmental impact of web hosting. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a sustainable management optimization method and system for interconnected data centers in a power system to solve the problems of existing methods in effectively allocating and migrating jobs on a data center network, optimizing resource allocation during job processing, and not considering dynamic price signals and user needs when managing and scheduling loads through mathematical models in the face of uncertain renewable energy supply.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a method for optimizing sustainable management of interconnected data centers in a power system, which is applicable to an interconnected data center network model including |M| interconnected green data centers, |R| on-site renewable energy sources, and an energy storage system for powering |M| interconnected green data centers; the green data center network processes operations within a planning period |I|, and a green data center m has |N m | servers, each green data center is powered by a power grid and on-site energy technology; the power grid provides |K| energy consumption levels and load reduction requests within a planning range according to a usage time and level plan; the method includes:

[0009] Modeling the data center network job migration allocation and processing in the interconnected data center network model to optimize resource allocation and energy consumption during demand response;

[0010] Based on the job migration requirements and job processing model of the data center network job, a green data center mathematical model integrating uncertain renewable energy is established; the green data center mathematical model includes dynamic price signals of demand response, load scheduling strategy and user demand;

[0011] Solve the green data center mathematical model to optimize the responsiveness and benefits of the data center in demand response.

[0012] As a preferred solution of the sustainable management optimization method of the power system interconnected data center described in the present invention, wherein: modeling the data center network operation migration allocation and processing includes: modeling the data center network operation migration allocation as follows:

[0013]

[0014] ∑J i,m =1

[0015]

[0016] Among them, x i,m,m′,n is the decision variable for job migration from the green data center m to the first server m′ and x i,m,m′,n ∈{0,1},J i,m is a binary parameter, D i is another binary parameter;

[0017] When job i has been assigned to the server and the green data center by direct reception or migration, the job i is processed in the second server n in the green data center as:

[0018]

[0019] Among them, y i,m,n,t is the portion of time period t used to process job i on the second server n in the green data center m, is the time range of the operation plan and is divided into t=1, 2, ..., T time periods.

[0020] As a preferred solution of the sustainable management optimization method of the power system interconnected data center described in the present invention, modeling the migration allocation of data center network operations also includes:

[0021] If job i initially arrives at green data center m, then the binary parameter J i,m Determine whether the job i is on server N in green data center m m Process it on the server within, or migrate it to N m' Server m' in another green data center;

[0022] When x i,m,m′,n = 1, no migration occurs and the job is assigned to the green data center where server n initially arrives; when x i,m,m′,n =0, the job is allowed to migrate;

[0023] If the job migration decision variable does not satisfy the binary parameter D i Migration is not allowed if the job migration decision variable satisfies the binary parameter D i Migration is allowed if requested.

[0024] As a preferred solution of the sustainable management optimization method of the power system interconnected data center described in the present invention, modeling the data center network operation processing also includes:

[0025] Job i processes green data center m in server n if and only if job i has been assigned to this server and green data center by direct ingestion or migration, expressed as:

[0026]

[0027] Among them, T i,m is the estimated time to process job i in the green data center m;

[0028] Assignment i is due on date T i (f) The pre-processing is expressed as:

[0029]

[0030] The non-negativity requirement of the system is modeled as:

[0031]

[0032] Among them, P i,m and Q i,m The number of CPU cores and RAM required to process job i in green data center m, are the CPU / RAM utilization caused by the online job of green data center m at time t, φ m,n and θ m,n are the number of available CPU cores and RAM in green data center m in server n, respectively.

[0033] As a preferred solution of the sustainable management optimization method of the power system interconnected data center described in the present invention, the mathematical model of the green data center integrating uncertain renewable energy is established based on the job migration requirements and job processing model of the data center network operation, including: formulating the optimization problem as follows:

[0034]

[0035] Where x is the decision variable for allocation and migration, a is the vector variable for accepting or not accepting the load reduction request, e is the vector of continuous decision variables related to the energy management system, and C price (t) is the electricity price cost, C LS (t) is the load scheduling cost.

[0036] As a preferred solution of the sustainable management optimization method of the power system interconnected data center described in the present invention, it also includes: the green data center mathematical model introduces a dynamic electricity price variable p(t) in the dynamic price signal part, and the dynamic electricity price variable is dynamically adjusted based on time changes;

[0037] In the load scheduling strategy, a load scheduling variable L(t) is introduced to represent the load level at different times; in user demand, the variable D(t) is used to represent the user's demand level at different times, and the user demand is introduced as a constraint condition into the green data center mathematical model.

[0038] As a preferred solution of the sustainable management optimization method of the power system interconnected data center described in the present invention, wherein: solving the green data center mathematical model and optimizing the response capability and benefit of the data center in demand response include: the green data center mathematical model is a two-stage mixed integer linear programming, and the resource allocation and energy consumption optimization problems during demand response are divided into external problems and internal problems; the internal problem is expressed as:

[0039]

[0040] Among them, C ESS is the cost of the energy storage system, C En is the cost of energy consumption, C DSM Total incentives received for green data centers;

[0041] The external problem is expressed as:

[0042]

[0043] Where, CT is the cost of offsetting credits;

[0044] The constraints are expressed as:

[0045]

[0046]

[0047] Among them, γ m,t , γ′ m,t , l m , and are the dual variables, π m,t , τ m,t 、v m,r,t and χ m,k,t is also a dual variable, S m and are the minimum and maximum storage capacities of the ESS installed in the green data center m, and are the maximum charging and discharging rates of green data center m under green data center, is the available grid energy at the horizontal level in the green data center m at time period t, is the available energy of the on-site source r in the green data center m in time period t, and are the costs associated with reducing the lifetime of the energy storage system of the green data center m when charging and discharging, respectively.

[0048] In a second aspect, the present invention provides a sustainable management and optimization system for interconnected data centers of a power system, which is applicable to an interconnected data center network model including |M| interconnected green data centers, |R| on-site renewable energy sources, and an energy storage system for powering |M| interconnected green data centers; the green data center network processes operations within a planning period |I|, and a green data center m has |N m | servers, each green data center is powered by a power grid and on-site energy technology; the power grid provides |K| energy consumption levels and load reduction requests within the planning range according to the usage time and level plan; the system includes:

[0049] A data center network job modeling module, used to model job migration and allocation between data centers in the interconnected data center network model and data center network job processing, to optimize resource allocation and energy consumption during demand response;

[0050] A green data center mathematical model building module is used to build a green data center mathematical model integrating uncertain renewable energy based on the job migration requirements and job processing model of the data center; the green data center mathematical model includes dynamic price signals of demand response, load scheduling strategies and user needs;

[0051] The optimization module is used to solve the mathematical model of the green data center and optimize the response capability and benefits of the data center in demand response.

[0052] In a third aspect, the present invention provides a computing device, comprising:

[0053] Memory and processor;

[0054] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the sustainable management optimization method of the power system interconnected data center are implemented.

[0055] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for sustainable management optimization of an interconnected data center of a power system.

[0056] Compared with the prior art, the present invention has the following beneficial effects: the present invention constructs a network model with interconnected data centers, models the migration and allocation of data center network jobs, and job processing respectively, so as to optimize resource allocation and energy consumption management in demand response events; constructs a mathematical model of interconnected green data centers with uncertain renewable energy integration, and incorporates the dynamic price signals, load scheduling strategies and user needs of demand response; solves the mathematical model of interconnected green data centers, optimizes the response capability and benefits of data centers in demand response, can effectively improve the flexibility and energy efficiency of data centers in demand response activities, and promote the sustainable development of green data centers. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0058] Figure 1 A flowchart of a method and system for optimizing sustainable management of an interconnected data center of a power system according to an embodiment of the present invention;

[0059] Figure 2 This is an example diagram of a network model with two interconnected data centers according to a method and system for sustainable management optimization of power system interconnected data centers described in an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0061] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0062] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0063] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0064] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0065] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0066] Example 1

[0067] Reference Figure 1-2 , is an embodiment of the present invention, which provides a sustainable management optimization method for interconnected data centers of a power system, applicable to a green data center including |M| interconnected data centers,

[0068] Model of an interconnected data center network with |R| on-site renewable energy sources and energy storage systems powering |M| interconnected green data centers; the green data center network handles jobs within the planning period |I|, and a green data center m has |N m | servers, each green data center is powered by the grid and on-site energy technology; the grid provides |K| energy consumption levels and load reduction requests within the planning range according to the usage time and level scheme; the methods include:

[0069] S1: Model the data center network job migration allocation and processing in the interconnected data center network model to optimize resource allocation and energy consumption during demand response;

[0070] In an embodiment of the present application, modeling the data center network job migration allocation and processing includes: modeling the data center network job migration allocation as follows:

[0071]

[0072] ∑J i,m =1

[0073]

[0074] Among them, x i,m,m′,n is the decision variable for job migration from the green data center m to the first server m′ and x i,m,m′,n ∈{0,1},J i,m is a binary parameter, D i is another binary parameter;

[0075] When job i has been assigned to the server and the green data center by direct reception or migration, the job i is processed in the second server n in the green data center as:

[0076]

[0077] Among them, y i,m,n,t is the portion of time period t used to process job i on the second server n in the green data center m, is the time range of the operation plan and is divided into t=1, 2, ..., T time periods.

[0078] In the embodiment of the present application, modeling the data center network job migration allocation further includes:

[0079] If job i initially arrives at green data center m, then the binary parameter J i,m Determine whether job i is on server N in green data center m m Process it on the server within, or migrate it to N m' Server m' in another green data center;

[0080] When x i,m,m′,n = 1, no migration occurs and the job is assigned to the green data center where server n initially arrives; when x i,m,m′,n =0, the job is allowed to migrate;

[0081] If the job migration decision variable does not satisfy the binary parameter D i Migration is not allowed if the job migration decision variable satisfies the binary parameter D i Migration is allowed if requested.

[0082] In the embodiment of the present application, modeling the data center network operation processing further includes:

[0083] Job i processes green data center m in server n if and only if job i has been assigned to this server and green data center by direct ingestion or migration, expressed as:

[0084]

[0085] Among them, T i,m is the estimated time to process job i in the green data center m;

[0086] Assignment i is due on date T i (f) The pre-processing is expressed as:

[0087]

[0088] The non-negativity requirement of the system is modeled as:

[0089]

[0090] Among them, P i,m and Qi,m The number of CPU cores and RAM required to process job i in green data center m, are the CPU / RAM utilization caused by the online job of green data center m at time t, φ m,n and θ m,n are the number of available CPU cores and RAM in green data center m in server n, respectively.

[0091] It should be noted that the network model with interconnected data centers consists of on-site renewable technologies, which include |R| on-site renewable energy sources and an energy storage system. Once the power is received from the grid and on-site renewable energy sources, it is combined and the operation of the grid-tied inverter is simulated.

[0092] S2: Based on the job migration requirements and job processing model of the data center network operation, a mathematical model of a green data center integrating uncertain renewable energy is established; the mathematical model of the green data center includes dynamic price signals of demand response, load scheduling strategies and user needs;

[0093] In the embodiment of the present application, based on the job migration requirements and job processing model of the data center network job, establishing a green data center mathematical model integrating uncertain renewable energy includes: formulating the optimization problem as:

[0094]

[0095] Where x is the decision variable for allocation and migration, a is the vector variable for accepting or not accepting the load reduction request, e is the vector of continuous decision variables related to the energy management system, and C price (t) is the electricity price cost, C LS (t) is the load scheduling cost.

[0096] It should be noted that the analysis of sustainability management based on decision variables can be divided into two stages. First, a set of jobs arrives at the network of interconnected green data centers GDCs for processing. The network manager needs to assign each job to the interconnected green data centers GDCs and determine the processing schedule for each server. The network decides how many offset credits to buy or sell within the scope of the analysis. After that, the interconnected green data centers GDCs process the assigned jobs, and the interconnected energy management systems EMSs synchronize the energy resources with the power required for processing. Job allocation and scheduling occur before the actual renewable energy availability is realized, and the jobs are processed when the renewable energy is generating electricity.

[0097] In the embodiment of the present application, it also includes: the green data center mathematical model introduces a dynamic electricity price variable p(t) in the dynamic price signal part, and the dynamic electricity price variable is dynamically adjusted based on time changes;

[0098] In the load scheduling strategy, the load scheduling variable L(t) is introduced to represent the load level at different times; in the user demand, the variable D(t) is used to represent the user demand level at different times, and the user demand is introduced as a constraint condition into the green data center mathematical model.

[0099] Specifically, the dynamic price signal can be formulated as:

[0100] C price (t) = p(t)E(t)

[0101] Among them, p(t) is the dynamic electricity price variable, and E(t) is the energy consumption at time t.

[0102] The load scheduling strategy can be formulated as:

[0103] C LS (t) = f(L(t))

[0104] Where L(t) is the load scheduling variable, f(L(t)) is the cost function of load scheduling, C LS (t) is the load scheduling cost.

[0105] User demand constraints can be formulated as:

[0106] L(t)≥D(t)

[0107] Among them, D(t) is a variable used to represent the user's demand level at different times.

[0108] S3: Solve the mathematical model of green data center and optimize the responsiveness and benefits of data center in demand response;

[0109] It should be noted that the two-stage mixed integer linear programming has the opposite maximum and minimum operators in the second stage of the objective function. To solve this problem, the two stages are analyzed separately. First, the internal part is reformulated using the Carlo-Kuhn-Tucker (KKT) conditions to find the dual of the minimization problem and merge the operations of the objective function. Then, this computationally sustainable reformulation allows to apply the nested version of the column and constraint generation (C&CG) algorithm and obtain the optimal decision for the two-stage MILP problem. Therefore, this problem is divided into an external problem and an internal problem.

[0110] In the embodiment of the present application, solving the green data center mathematical model and optimizing the response capability and benefits of the data center in demand response include: the green data center mathematical model is a two-stage mixed integer linear programming, which divides the resource allocation and energy consumption optimization problems in demand response into external problems and internal problems; the internal problem is expressed as:

[0111]

[0112] Among them, C ESS is the cost of the energy storage system, C En is the cost of energy consumption, C DSM Total incentives received for green data centers;

[0113] The external problem is expressed as:

[0114]

[0115] Where, CT is the cost of offsetting credits;

[0116] The constraints are expressed as:

[0117]

[0118] Among them, γ m,t , γ′ m,t , l m , and are the dual variables, π m,t , τ m,t 、v m,r,t and χ m,k,t is also a dual variable, S m and are the minimum and maximum storage capacities of the ESS installed in the green data center m, and are the maximum charging and discharging rates of green data center m under green data center, is the available grid energy at the horizontal level in the green data center m at time period t, is the available energy of the on-site source r in the green data center m in time period t, and are the costs associated with reducing the lifetime of the energy storage system of the green data center m when charging and discharging, respectively.

[0119] It should be noted that for any feasible realization of the uncertain vector and a vector of binary variables This leads to a minimization problem about e, whose dual problem is given by:

[0120]

[0121] Here, Π is the vector of dual variables.

[0122] The above is a schematic scheme of a method for sustainable management optimization of a power system interconnected data center in this embodiment. It should be noted that the technical scheme of the system for sustainable management optimization of a power system interconnected data center and the technical scheme of the method for sustainable management optimization of a power system interconnected data center mentioned above belong to the same concept. For details not described in detail in the technical scheme of the system for sustainable management optimization of a power system interconnected data center in this embodiment, please refer to the description of the technical scheme of the method for sustainable management optimization of a power system interconnected data center mentioned above.

[0123] In this embodiment, a power system interconnected data center sustainable management optimization system is applicable to an interconnected data center network model including |M| interconnected green data centers, |R| on-site renewable energy sources and an energy storage system for powering |M| interconnected green data centers; the green data center network processes operations within a planning period |I|, and a green data center m has |N m | servers, each green data center is powered by the grid and on-site energy technology; the grid provides |K| energy consumption levels and load reduction requests within the planning range according to the usage time and level plan; the system includes:

[0124] Data center network job modeling module, which is used to model the job migration and allocation between data centers in the interconnected data center network model and the data center network job processing, and optimize resource allocation and energy consumption during demand response;

[0125] Green data center mathematical model building module, which is used to build a green data center mathematical model integrating uncertain renewable energy based on the job migration requirements and job processing model of the data center; the green data center mathematical model includes dynamic price signals of demand response, load scheduling strategy and user needs;

[0126] The optimization module is used to solve the mathematical model of the green data center and optimize the responsiveness and benefits of the data center in demand response.

[0127] This embodiment also provides a computing device, which is applicable to the case of the sustainable management optimization method of the power system interconnected data center, including:

[0128] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the sustainable management optimization method for interconnected data centers of power systems as proposed in the above embodiments.

[0129] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing sustainable management optimization of an interconnected data center of a power system as proposed in the above embodiment is implemented.

[0130] The storage medium proposed in this embodiment and the method for realizing sustainable management optimization of power system interconnected data center proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0131] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0132] Example 2

[0133] Reference Figure 1-2 , is an embodiment of the present invention. This embodiment is different from the first embodiment in that this embodiment verifies the beneficial effects of the present invention through specific examples.

[0134] In this embodiment, the operation of a network of two data centers is set, each of which is equipped with on-site green energy technology and migration capabilities. The specific parameter settings of the interconnected green data centers GDCs are shown in Table 1. The operation of the network emits 58,393.50 kg of carbon dioxide and has a green energy coefficient of 36.92%. The energy storage system ESS installed in the first green data center GDC1 was not used, while the ESS installed in the second green data center GDC2 was used extensively, charging in the first half of the planning period and discharging in the second half. Wherein the grid and solar energy represent the power provided by the grid and on-site solar energy, respectively; the operation of EGDC1 is powered by on-site solar panels and the grid without using ESS, while the operation of GDC2 uses a combination of the grid and on-site renewable energy sources RES and ESS. In addition, GDC1 is connected to the grid during operation, while GDC2 is disconnected from the grid during 11 cycles. The cost of the energy management system is $12,664.70, while the cost of the C&T project is $974.00, and the total operating cost is $13,638.70:

[0135] Table 1 Specific parameter settings of GDCs

[0136]

[0137]

[0138] In this embodiment, the network performance is also analyzed for the presence or absence of ESS and RES field technology and migration capabilities, as shown in Tables 2 to 7, where the cost is in US dollars and the carbon emissions are in kilograms:

[0139] Table 2 Performance of two GDCs with and without ESS, RES, migration and load shedding requests

[0140]

[0141] Table 3 Performance of two GDCs with and without ESS, RES, migration and load shedding requests

[0142]

[0143] Table 4 Performance of three GDCs with and without ESS, RES, migration and load reduction requests

[0144]

[0145]

[0146] Table 5 Performance of three GDCs with and without ESS, RES, migration and load shedding requests

[0147]

[0148] Table 6 Performance of NSFNET with and without ESS, RES, migration and load reduction requests

[0149]

[0150] Table 7 Performance of NSFNET with and without ESS, RES, migration and no load request

[0151]

[0152] From Tables 2 to 7, it can be seen that the inclusion of on-site ESS and RES and the immigration policy have a significant impact on economic and environmental impacts. In the cases of two and three GDCs and NSFNET, the total cost is reduced by 26%, 29% and 10%, and the emissions are reduced by 14%, 23% and 17%, respectively. The present invention seeks the operation that maximizes the environmental and economic benefits of the interconnected GDC network with different configurations to evaluate the economic and environmental impacts of green energy technology and optimal immigration policy using ESS and RES, as well as the sensitivity analysis of not implementing on-site technology and optimal immigration policy. The network model with interconnected data centers combined with on-site technology and immigration policy can bring economic and environmental benefits, effectively improve the flexibility and energy efficiency of data centers in demand response activities, and promote the sustainable development of green data centers.

[0153] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A sustainable management optimization method for an interconnected data center of a power system, characterized by: Applicable to an interconnected data center network model including |M| interconnected green data centers, |R| on-site renewable energy sources, and an energy storage system that powers |M| interconnected green data centers; the green data center network processes jobs within a planning period |I|, and a green data center m has |N m | servers, each green data center is powered by the grid and on-site energy technology; The power grid provides |K| energy consumption levels and load reduction requests within the planning range according to the usage time and level plan; the method includes: Modeling the data center network job migration allocation and processing in the interconnected data center network model to optimize resource allocation and energy consumption during demand response; Based on the job migration requirements and job processing model of the data center network job, a green data center mathematical model integrating uncertain renewable energy is established; the green data center mathematical model includes dynamic price signals of demand response, load scheduling strategy and user demand; Solve the green data center mathematical model to optimize the responsiveness and benefits of the data center in demand response.

2. The method for sustainable management optimization of a power system interconnected data center according to claim 1, characterized in that: Modeling the data center network job migration allocation and processing includes: Modeling the data center network job migration allocation as follows: ∑J i,m ＝1 Among them, x i,m,m′,n is the decision variable for job migration from the green data center m to the first server m′ and x i,m,m′,n ∈{0,1},J i,m is a binary parameter, D i is another binary parameter; When job i has been assigned to the server and the green data center by direct reception or migration, the job i is processed in the second server n in the green data center as: Among them, y i,m,n,t is the portion of time period t used to process job i on the second server n in the green data center m, is the time range of the operation plan and is divided into t=1, 2, ..., T time periods.

3. The method for sustainable management optimization of a power system interconnected data center according to claim 2, characterized in that: Modeling data center network job migration distribution also includes: If job i initially arrives at green data center m, then the binary parameter J i,m Determine whether the job i is on server N in green data center m m Process it on the server within, or migrate it to N m' Server m' in another green data center; When x i,m,m′,n = 1, no migration occurs and the job is assigned to the green data center where server n initially arrives; when x i,m,m′,n =0, the job is allowed to migrate; If the job migration decision variable does not satisfy the binary parameter D i If the job migration decision variable satisfies the binary parameter D i Migration is allowed if requested.

4. The method for sustainable management optimization of a power system interconnected data center according to claim 3, characterized in that: Modeling data center network job processing also includes: Job i processes green data center m in server n if and only if job i has been assigned to this server and green data center by direct ingestion or migration, expressed as: Among them, T i,m is the estimated time to process job i in the green data center m; Assignment i is due on T i (f) The pre-processing is expressed as: The non-negativity requirement of the system is modeled as: Among them, P i,m and Q i,m The number of CPU cores and RAM required to process job i in green data center m, are the CPU / RAM utilization caused by the online job of green data center m at time t, φ m,n and θ m,n are the number of available CPU cores and RAM in green data center m in server n, respectively.

5. The method for sustainable management optimization of a power system interconnected data center according to claim 4, characterized in that: Based on the job migration requirements and job processing model of data center network jobs, a mathematical model of a green data center integrating uncertain renewable energy sources is established, including formulating the optimization problem as follows: Where x is the decision variable for allocation and migration, a is the vector variable for accepting or not accepting the load reduction request, e is the vector of continuous decision variables related to the energy management system, and C price (t) is the electricity price cost, C LS (t) is the load scheduling cost.

6. The method for sustainable management optimization of an interconnected data center of a power system according to claim 5, characterized in that: Also includes: The green data center mathematical model introduces a dynamic electricity price variable p(t) in the dynamic price signal part, and the dynamic electricity price variable is dynamically adjusted based on time changes; In the load scheduling strategy, a load scheduling variable L(t) is introduced to represent the load level at different times; in user demand, the variable D(t) is used to represent the user's demand level at different times, and the user demand is introduced as a constraint condition into the green data center mathematical model.

7. The method for sustainable management optimization of an interconnected data center of a power system according to claim 6, characterized in that: Solving the green data center mathematical model and optimizing the response capability and benefits of the data center in demand response includes: the green data center mathematical model is a two-stage mixed integer linear programming, which divides the resource allocation and energy consumption optimization problems in demand response into external problems and internal problems; the internal problem is expressed as: Among them, C ESS is the cost of the energy storage system, C En is the cost of energy consumption, C DSM Total incentives received for green data centers; The external problem is expressed as: Where, CT is the cost of offsetting credits; The constraints are expressed as: Among them, γ m,t , γ′ m,t , l m , and are the dual variables, π m,t , τ m,t 、v m,r,t and χ m,k,t is also a dual variable, S m and are the minimum and maximum storage capacities of the ESS installed in the green data center m, and are the maximum charging and discharging rates of green data center m under green data center, is the available grid energy at the horizontal level in the green data center m at time period t, is the available energy of the on-site source r in the green data center m in time period t, and are the costs associated with reducing the lifetime of the energy storage system of the green data center m when charging and discharging, respectively.

8. A sustainable management and optimization system for an interconnected data center of a power system, characterized by: Applicable to an interconnected data center network model including |M| interconnected green data centers, |R| on-site renewable energy sources, and an energy storage system that powers |M| interconnected green data centers; the green data center network processes jobs within a planning period |I|, and a green data center m has |N m | servers, each green data center is powered by the grid and on-site energy technology; The power grid provides |K| types of energy consumption levels and load reduction requests within the planning range according to the usage time and level plan; the system includes: A data center network job modeling module, used to model job migration and allocation between data centers in the interconnected data center network model and data center network job processing, to optimize resource allocation and energy consumption during demand response; A green data center mathematical model building module is used to build a green data center mathematical model integrating uncertain renewable energy based on the job migration requirements and job processing model of the data center; the green data center mathematical model includes dynamic price signals of demand response, load scheduling strategies and user needs; The optimization module is used to solve the mathematical model of the green data center and optimize the response capability and benefits of the data center in demand response.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the sustainable management optimization method for interconnected data centers of power systems described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for sustainable management optimization of an interconnected data center of a power system as claimed in any one of claims 1 to 7.

Images