Data center energy system scheduling method, device, equipment, medium and product

Abstract

The present disclosure relates to a data center energy system scheduling method, device, equipment, medium and product in the technical field of intelligent management system. The method comprises: constructing an economic objective function of minimizing operation cost and an environmental objective function of minimizing carbon emissions; constructing a computing power side model and an energy supply side model; solving the optimal solution of supply and demand matching of the data center energy system according to the supply data information and demand data information in the data center energy system and the constraint conditions; and configuring the data center energy system according to the optimal configuration scheme corresponding to the optimal solution of supply and demand matching, so as to achieve the optimal operation target. Under the condition of taking minimizing operation cost and carbon emissions as the objective function, the present disclosure combines the operation models of the computing power side and the energy supply side and the constraint conditions, and realizes the optimal energy system operation of the data center, the optimal allocation of computing power resources, the minimum carbon emissions and the minimum energy operation cost.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of intelligent management systems, and particularly relates to a data center energy system scheduling method, device, equipment, medium and product. BACKGROUND

[0002] With the rapid development of artificial intelligence and big data technology, the computing power business of data centers has increased dramatically. Under the background of the double carbon target, data centers, as major energy consumers and carbon emitters, are particularly important to implement energy-saving and emission-reducing technical solutions while ensuring data center computing power services. Current data center energy-computing power-carbon emission technical solutions mainly focus on research in computing-heat collaboration and computing-electricity collaboration. Computing-heat collaboration technical solutions focus on sensing server temperature and optimizing the operation of air conditioning systems. Computing-electricity collaboration technical solutions focus on improving the utilization efficiency of IT equipment and reducing the power consumption of equipment. The above technical solutions can improve the utilization efficiency of computing power to a certain extent and save energy and reduce emissions. However, the above technical solutions optimize scheduling from a single aspect of energy, computing power, and carbon emissions, and do not fully exploit the optimization scheduling potential of each aspect and the relationship between deep coupling of comprehensive energy systems, computing power resources, and carbon emissions. SUMMARY

[0003] To solve the above technical problems, the embodiments of the present disclosure provide a data center energy system scheduling method, device, equipment, medium and product, which realize the goals of optimal energy system operation, optimal computing power resource allocation, minimum carbon emissions, and minimum energy operation cost of a data center.

[0004] In a first aspect, a data center energy system scheduling method is provided, comprising:

[0005] constructing an economic objective function of minimizing operation cost and an environmental objective function of minimizing carbon emissions;

[0006] constructing a computing power side model and an energy supply side model;

[0007] solving an optimal supply-demand matching solution of the data center energy system according to supply data information and demand data information in the data center energy system and constraint conditions;

[0008] configuring the data center energy system according to an optimal supply-demand matching configuration scheme corresponding to the optimal supply-demand matching solution to realize an optimal operation target.

[0009] In a second aspect, an apparatus is provided, comprising:

[0010] an objective function module configured to construct an economic objective function of minimizing operation cost and an environmental objective function of minimizing carbon emissions;

[0011] a modeling module configured to construct a computing power side model and an energy supply side model;

[0012] a solving module configured to solve an optimal supply-demand matching solution of the data center energy system according to supply data information and demand data information in the data center energy system and constraint conditions;

[0013] a configuration module configured to configure the data center energy system according to an optimal supply-demand matching configuration scheme corresponding to the optimal supply-demand matching solution, to achieve an optimal operation target.

[0014] A third aspect of the embodiments of the present disclosure provides an electronic device, comprising:

[0015] at least one processor;

[0016] a memory for storing instructions executable by the at least one processor;

[0017] The at least one processor is configured to execute the instructions to implement the method described above.

[0018] A fourth aspect of the embodiments of the present disclosure provides a non-transitory computer-readable storage medium, when instructions in the non-transitory computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method described above.

[0019] A fifth aspect of the embodiments of the present disclosure provides a computer program product, comprising a computer program, which, when executed, implements the method described above.

[0020] The above at least one technical solution adopted by the embodiments of the present disclosure can achieve the following beneficial effects: under the condition of taking minimizing operation cost and carbon emission as the objective function, combining the operation model and constraint conditions of the computing power side and the energy supply side, the optimal supply-demand matching solution of the data center energy system is solved; according to the optimal supply-demand matching configuration scheme corresponding to the optimal supply-demand matching solution, the data center energy system is configured to achieve the optimal operation target, and the comprehensive scheduling of the data center energy system with energy, computing power and carbon emission collaborative optimization is performed. The optimal energy system operation of the data center, the best computing power resource allocation, the lowest carbon emission and the minimum energy operation cost are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present disclosure and serve to explain the principles of the present disclosure together with the specification.

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

[0023] Figure 1 A flowchart of a data center energy system scheduling method provided by an embodiment of the present disclosure;

[0024] Figure 2 A flowchart of a particle swarm optimization algorithm provided by an embodiment of the present disclosure;

[0025] Figure 3 A structural diagram of a data center energy system scheduling device provided by an embodiment of the present disclosure;

[0026] Figure 4 A structural diagram of an electronic device provided by an embodiment of the present disclosure;

[0027] Figure 5 A structural diagram of an exemplary computer system provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] In order to more clearly illustrate the above-mentioned purposes, features and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0029] In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some of the embodiments of the present disclosure, not all the embodiments.

[0030] It should be understood that each step recorded in the method embodiments of the present disclosure can be executed in different order and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the execution of the steps shown. The scope of the present disclosure is not limited in this respect.

[0031] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modification of "one" and "multiple" mentioned in the present disclosure is illustrative but not restrictive, and those skilled in the art should understand that unless the context clearly indicates otherwise, it should be understood as "one or more".

[0033] With the rapid development of artificial intelligence and big data technology, the computing power business of data centers has increased dramatically. At the same time, data centers consume a huge amount of energy and produce a large amount of carbon dioxide. In the context of the national double carbon goal, the collaborative optimization of computing power, electricity, and carbon in data centers has become an important technical direction. In terms of computing power, the computing power of data centers can be optimized according to the changes in load, reducing electricity consumption, and participating in demand-side response, which is conducive to the stability of the power grid. In terms of electricity, with the increase of distributed energy, optimizing the operation of the energy system can greatly improve the economic efficiency of data center operation. In terms of carbon emissions, optimizing the energy structure of data centers and increasing the consumption rate of renewable energy can fundamentally reduce the carbon dioxide emissions of data centers. At present, most researches or technical solutions focus on computing-heat collaboration and computing-electricity collaboration. The computing-heat collaboration technical solution focuses on the joint operation of servers and air conditioning systems, measures the server temperature based on heat perception technology, and then adjusts the operation of the air conditioning system to achieve energy saving. The computing-electricity collaboration technical solution focuses on using high-performance, low-energy servers and storage devices to improve the efficiency of data center IT equipment and reduce data center electricity consumption. At the same time, an intelligent power management system is implemented to dynamically adjust power distribution according to the workload, ensuring efficient use of resources. The above technical solutions can improve the efficiency of computing power utilization to a certain extent and achieve energy saving and emission reduction. However, most technical solutions optimize scheduling from a single aspect of energy, computing power, and carbon emissions, without fully exploiting the optimization and scheduling potential of each aspect and the relationship between deep coupling of comprehensive energy systems, computing power resource adjustment, and carbon emissions.

[0034] Therefore, the present disclosure proposes an energy, computing power, and carbon emission collaborative optimization data center energy system scheduling method, which fully considers the optimization and adjustment space of data center energy, computing power, and carbon emissions to achieve the goals of optimal data center energy system operation, optimal computing power resource allocation, and minimum carbon dioxide emissions.

[0035] One feasible technical route for energy-computing power-carbon collaborative optimization control is to fully utilize the flexibility of data center load and propose a data center energy system scheduling method considering load response characteristics. Specifically, by utilizing the transferable characteristics of data center load, the transferable load of the data center is allocated to time periods with lower electricity prices and larger renewable energy outputs under the condition of ensuring service quality, achieving the goals of load optimization scheduling, improving the energy utilization rate of IT equipment, reducing data center energy costs, promoting renewable energy consumption, and reducing carbon emissions.

[0036] Exemplarily, the supply side of the energy system is photovoltaic, energy storage device, municipal power grid, diesel generator. The demand side is the power consumption equipment of the data center. The scheduling logic of the supply and demand sides is to transfer the load to the period with lower electricity price and more photovoltaic power generation in combination with the electricity price information, photovoltaic power generation information and transferable load constraint condition. The load of the data center first consumes the photovoltaic power generation, and the excess photovoltaic power generation is stored in the energy storage device. When the storage capacity of the energy storage device reaches the maximum limit, the photovoltaic power generation is connected to the grid. The energy storage device can store excess photovoltaic power and store power at low price in the energy system. Secondly, when the photovoltaic power generation is insufficient, the data center uses the energy storage device for power supply. Finally, when the photovoltaic power generation and the energy storage device cannot meet the power consumption of the data center, the data center uses the municipal power grid for power supply. When the municipal power supply is interrupted, the diesel generator starts to supply power to ensure the power safety of the data center.

[0037] The following will be described in combination with Figures 1-5 The data center energy system scheduling method, device, equipment, medium and product provided by the embodiments of the present disclosure are described.

[0038] Figure 1 A flowchart of a data center energy system scheduling method provided by an embodiment of the present disclosure is shown in Figure 1 A data center energy system scheduling method provided by an embodiment of the present disclosure includes:

[0039] S101, constructing an economic objective function of minimizing operation cost and an environmental objective function of minimizing carbon emission;

[0040] Firstly, an economic objective function of minimizing operation cost and an environmental objective function of minimizing carbon emission are constructed, wherein the economic objective function is an energy cost objective function; and the environmental objective function is a carbon dioxide emission objective function.

[0041] That is, the system takes the minimization of operation cost and carbon dioxide emission as the objective function. The energy cost objective function and the carbon dioxide emission objective function can be used as the fusion objective.

[0042] S102, constructing a computing power side model and an energy supply side model;

[0043] The computing power side model and the energy supply side model are constructed respectively.

[0044] Among them, on the computing power side, the load type of the data center providing computing services is classified, and the corresponding load model is established. The load type of the data center providing computing services includes: delay tolerant load and delay sensitive load, delay tolerant load model based on delay tolerant load; delay sensitive load model based on delay sensitive load.

[0045] And on the computing power side, the IT equipment energy consumption model is constructed; the air conditioner and other equipment energy consumption model is constructed.

[0046] On the energy supply side, the operation model of distributed energy in the energy system is constructed. Exemplarily, the energy supply side model includes: photovoltaic power generation model; energy storage device charging and discharging model; diesel generator fuel consumption model. When there are other energy supplies on the energy supply side, other energy supply models such as wind power generation model can also be included.

[0047] S103, according to the supply data information and demand data information in the data center energy system and the constraint condition, solving the supply-demand matching optimal solution of the data center energy system;

[0048] According to the supply and demand data information and the constraint condition in the comprehensive energy system, the algorithm is used to solve the power generation of photovoltaic, the charging and discharging power of energy storage device, the import power of municipal power, the power generation of diesel generator, the transfer amount and transfer time of transferable load in each period, and the best supply-demand matching information of data center energy system in a day is given.

[0049] The above algorithm can be particle swarm optimization algorithm, or genetic algorithm. Particle swarm optimization algorithm has the advantages of fast convergence speed, few parameters, simple algorithm and easy implementation.

[0050] S104, according to the supply-demand matching optimal configuration scheme corresponding to the supply-demand matching optimal solution, the data center energy system is configured to realize the optimal operation target.

[0051] Based on the supply-demand matching optimal configuration scheme corresponding to the supply-demand matching optimal solution of the data center energy system obtained in step S104, the data center energy system is configured, so as to realize the optimal operation target.

[0052] In an embodiment of the present disclosure, under the condition of taking the minimization of operation cost and carbon emission as the objective function, combined with the operation model and constraint condition of the computing power side and the energy supply side, the optimal solution of supply-demand matching of the data center energy system is solved according to the supply data information and demand data information in the data center energy system and the constraint condition; the data center energy system is configured according to the optimal supply-demand matching configuration scheme corresponding to the optimal supply-demand matching solution, so as to realize the optimal operation target, and the comprehensive scheduling of the energy, computing power and carbon emission collaborative optimization data center energy system. The optimal energy system operation of the data center, the optimal computing power resource allocation, the minimum carbon emission and the minimum energy operation cost are realized.

[0053] In an embodiment of the present disclosure, the construction of the computing power side model includes the following parts:

[0054] Data center load type analysis

[0055] The power demand of IT equipment mainly depends on the type of workload it processes, which can be mainly divided into two categories: delay-tolerant and delay-sensitive. Delay-tolerant tasks (such as batch processing, data backup and archiving) are not sensitive to time delay, and the completion time can be arranged flexibly, so the data center can reduce resource occupation through optimization means (such as adjusting priority, data compression). On the contrary, delay-sensitive tasks (such as online games, real-time video) are extremely sensitive to time delay and require immediate response, and the data center needs to use efficient technology (such as fast network equipment, reduce compression and encryption) to ensure fast and reliable data transmission. It should be noted that the distinction between these two load types is not absolute, and the same application may have different delay requirements in different situations. Therefore, during the design and optimization process of the data center, the strategy needs to be adjusted flexibly according to the specific requirements to maximize the satisfaction of various types of workloads.

[0056] Data center load working characteristics

[0057] (1) Delay-tolerant load model

[0058]

[0059] wherein, denotes the earliest and latest completion time of the delay-tolerant load, is the load completion time; is the load arrival time; is the basic processing time of the load; is the maximum delay time responsible for; μ is the user demand processing rate of the data center server, which is the running parameter of the server.

[0060] (2) Delay-sensitive load model

[0061]

[0062] wherein, is the delay-sensitive load completion time; is the load arrival time; is the load basic processing time.

[0063] Data center energy consumption model

[0064] The data center energy consumption model can be composed of IT equipment energy consumption, air conditioning system energy consumption and other equipment energy consumption, and the energy consumption model of the data center is represented as follows in combination with the data center power usage effectiveness PUE index simplified model:

[0065]

[0066] wherein, is the total power consumption of the data center at t; are the power consumptions of the IT equipment and the air conditioning system at t, respectively.

[0067] (1) IT equipment energy consumption model

[0068] Because the demand response problem of the load is involved, a typical linear model considering server utilization is adopted to represent the IT equipment energy consumption, it is assumed that the server energy consumption and the utilization rate are in a linear relationship, the server is in any state between idle and full load according to the user demand size, and then the energy consumption of the IT equipment is:

[0069]

[0070] wherein, P idle is the minimum power consumption of the server in the running state; P peak is the full load power consumption of the server; μ t is the average utilization rate of the CPU (server); n t is the number of servers running at t. Wherein, μ t is related to the number of load task processing at the current time, the average utilization rate of the CPU at the current time is equal to the average utilization rate of the delay-sensitive and delay-tolerant work load task at the time. μ t The calculation method is as follows:

[0071]

[0072] wherein, is the number of delay-sensitive and delay-tolerant work loads at t, are the average utilization rates of a single server processing delay-sensitive and delay-tolerant work loads, respectively.

[0073] (2) Other system energy consumption model

[0074]

[0075] In one embodiment of the present disclosure, the construction of the energy supply side model includes the following parts:

[0076] (1) Photovoltaic power generation model

[0077] According to the open circuit voltage (Uoc), short circuit current (Isc), maximum power point voltage (Um), and maximum power point current (Im) of the photovoltaic cell under standard conditions, the photovoltaic cell is modeled, and the photovoltaic power generation model is as follows:

[0078] ΔT(t) = T(t) - T ref (11)

[0079]

[0080] U ′ m (t) = U m (1 + γΔT(t))(1 + βΔS(t)) (15)

[0081] U ′ oc (t) = U oc (1 - γΔT(t)))1 + βΔS(t)) (16)

[0082]

[0083] Where, T(t) is the temperature under general working conditions at time t, T ref is the temperature under standard test conditions; ΔT(t) is the difference between the actual photovoltaic temperature at time t and the standard temperature; S(t) is the radiation intensity under general working conditions at time t, S ref is the radiation intensity under standard test conditions; ΔS(t) is the difference between the radiation intensity under standard conditions at time t and the radiation intensity under general conditions. I' sc (t), U' oc (t), I' m (t), and U' m (t) are the short circuit current, open circuit voltage, maximum power point current, and maximum power point voltage under general working conditions at time t, respectively. C'1(t) and C'2(t) are two coefficients in the calculation process at time t; I(t) and U(t) are the current and voltage of the PV panel under general working conditions at time t, respectively; P t PV is the power generation of the PV at time t (kW). Coefficients α, β, and γ.

[0084] (2) Energy storage charging and discharging model

[0085] The energy storage device can be charged when the grid price is low or when the photovoltaic power generation is surplus, and discharged when the price is high to meet the power demand of the data center in other periods. The charging and discharging model of the energy storage device is as follows.

[0086]

[0087] wherein, SOC represents the state of charge of the energy storage device at time t; Δt is the time step (h); η ch and η dch respectively represent the charging and discharging efficiency of the energy storage device; and respectively represent the charging and discharging power of the energy storage device; C ESS is the capacity of the energy storage device.

[0088] (3) Diesel generator fuel consumption model

[0089]

[0090] wherein, O represents the oil consumption of the diesel generator at time t; P represents the rated power of the diesel generator; P represents the output power of the diesel generator at time t; A M , B M are model coefficients.

[0091] In the embodiments of the present disclosure, the economic objective function and the environmental objective function are constructed by considering the optimization scheduling under the double constraints of demand side response and carbon emission.

[0092] (1) Economic objective function

[0093] The economic objective function is the energy cost objective function, and the data center energy cost is the data center operation cost.

[0094] Data center energy cost:

[0095]

[0096] wherein, C DC is the data center operation cost; is the grid purchase cost; is the energy storage cost; is the diesel generator power generation cost; is the photovoltaic power generation cost; is the demand response income.

[0097] 1) Grid purchase cost:

[0098]

[0099] wherein, is the grid transmission power at time t; is the time-of-use electricity price.

[0100] 2) Energy storage cost:

[0101]

[0102] wherein, is the energy storage charge and discharge power at time t; π ESS is the energy storage device unit power maintenance cost.

[0103] 3) Diesel generator power generation cost:

[0104]

[0105] wherein, is the diesel consumption at time t; π M is the diesel price.

[0106] 4) Photovoltaic power generation cost:

[0107]

[0108] wherein, is the photovoltaic power generation power at time t; π PV is the unit photovoltaic power generation marginal cost.

[0109] 5) Demand response income (distribution network dispatches the movable load to play the role of peak shaving, and gives the corresponding economic incentive according to the load shifting during the load peak period):

[0110]

[0111] wherein, π tol is the unit movable load dispatching cost; is the number of time scheduling of movable load at time t.

[0112] (2) Environmental objective function (carbon emissions)

[0113] The environmental objective function is the carbon dioxide emission objective function:

[0114]

[0115] wherein, is the CO2 emission of the data center, and σ and β are the carbon emission factors of the grid power generation and the diesel generator power generation, respectively.

[0116] (3) Constraints

[0117] 1) Network load task quantity constraint:

[0118]

[0119] wherein, is the number of network load tasks processed at time t before and after load scheduling.

[0120] 2) QoS (Quality of Service) constraint:

[0121] For delay-sensitive loads:

[0122]

[0123] 0≤n t ≤n max (33)

[0124] wherein, t max is the maximum delay time that can be tolerated by the user data service request; n max represents the upper limit of the number of servers in the data center.

[0125] For delay-tolerant loads:

[0126]

[0127] wherein, is the amount of delay-tolerant load transferred by the data center at time t; is the amount of delay-tolerant load transferred by server σ to the data center at time t; is the amount of delay-tolerant load processed by the data center at time t.

[0128] To meet the requirements of the service level agreement, the total amount of delay-tolerant load at each time satisfies the following conservation relationship:

[0129]

[0130] wherein, is the total amount of delay-tolerant load waiting to be processed at time t; T is the end time of the data load service.

[0131]

[0132] wherein, is the amount of delay-tolerant load that should be processed and completed by the end time t1; Q t、σ is the amount of delay-tolerant load sent by server σ at time t.

[0133] 3) Energy balance constraint:

[0134]

[0135] where, is the power demand of the data center at time t.

[0136] 4) Energy storage constraints:

[0137]

[0138] where, ch，max , P dis，max are the maximum charging and discharging power; SoC min , SoC max are the minimum and maximum state of charge of the energy storage battery.

[0139] 5) Photovoltaic generation constraints:

[0140]

[0141] where, pv，max is the upper limit of the photovoltaic generator output.

[0142] 6) Diesel generator constraints:

[0143]

[0144] where, M,min , P M,max are the lower and upper limits of the diesel generator output; ΔP M,min , ΔP M,max are the maximum downward and upward ramping power of the diesel generator.

[0145] In the embodiments of the present disclosure, in the operation of the data center energy system, the electricity purchase cost of the power grid and the diesel generator cost are usually higher than the photovoltaic power generation cost. In addition, the peak price of the power grid is higher than the valley price. For the data center load power consumption, the delay-tolerant load and the delay-sensitive load are only shifted in time, and the total power consumption does not change. Therefore, reducing the energy consumption cost means, on the one hand, increasing the use of photovoltaic power generation, reducing the purchase of electricity from the power grid and the power generation of the diesel generator; on the other hand, it means that more valley power needs to be used when using power grid power. Therefore, the energy consumption cost target and the carbon dioxide emission target of the scheme of the present disclosure can be converted into one target, and the energy consumption cost target and the carbon dioxide emission target are consistent, the lower the energy consumption cost, the more the photovoltaic power generation is used, and the less the purchase of electricity from the power grid and the power generation of the diesel generator. The lower the carbon dioxide emission target function, that is, the less the CO2 emission. Therefore, S103 of the embodiments of the present disclosure comprises: according to the supply data information and the demand data information in the data center system energy and the constraint condition, taking the minimum energy consumption cost target function as the target, using the particle swarm optimization algorithm to solve, obtaining the photovoltaic power generation power, the charge and discharge power of the energy storage device, the import power of the municipal power, the power generation power of the diesel generator, the transfer amount and the transfer time of the transferable load in each period, and obtaining the supply and demand matching optimal solution of the data center energy system.

[0146] Figure 2 A flowchart for solving by using the particle swarm optimization algorithm provided by the embodiments of the present disclosure is shown in Figure 2 The steps of solving by using the particle swarm optimization algorithm include:

[0147] S201, initializing the particle swarm, including the population size and the position and speed of each particle;

[0148] Each particle of the particle swarm optimization algorithm has a speed and a position. First, the position and speed of the particle are initialized.

[0149] S202, calculating the target function value of each particle, determining the historical optimal value of the particle and the global optimal value in the population;

[0150] The target function value is calculated, and the historical optimal value of the particle and the global optimal value in the population are determined.

[0151] S203, constantly updating the speed and position of the particle;

[0152] The flying speed of the particle i in the N-dimensional space represents the vector v i (v1, v2, …, v N ), and the position represents the vector x i =(x1, x2, …, x N). The position and velocity model is shown in equations (41) and (42).

[0153]

[0154] wherein, is the velocity of the i-th particle in the m-th iteration; is the position of the i-th particle in the m-th iteration; ω is the inertia weight of the velocity; c1 is the learning factor of the individual; c2 is the social learning factor of the particle; r1 and r2 are random numbers; is the best position of the i-th particle after m iterations; G m is the best position of all particles after a maximum of m iterations.

[0155] S204, in each generation evolution, the target function value of each particle is calculated, if the current target function value of the particle is better than its historical optimal value, the current target function value is replaced by the historical optimal value; if the historical optimal value of the particle is better than the global optimal value in the population, the historical optimal value is replaced by the global optimal value in the population;

[0156] If the current target function value of the particle is better than its historical optimal value, the latter is replaced by the former. Similarly, if the historical optimal value of the particle is better than the global optimal value in the population, the latter is replaced by the former.

[0157] S205, iteration reaches the set value or the accuracy reaches the convergence accuracy, the solution is ended, and the global optimal solution is obtained.

[0158] In the embodiments of the present disclosure, the energy consumption cost target and the carbon dioxide emission target are converted into one target, the step of solving the energy, computing power and carbon emission collaborative optimization data center comprehensive energy system scheduling is realized by taking the energy consumption cost target function as the target and using the particle swarm optimization algorithm, so that the optimal energy system operation, the optimal computing power resource allocation, the minimum carbon dioxide emission, and the minimum energy operation cost of the data center are realized.

[0159] The above only describes the preferred embodiments of the present disclosure, and it should be pointed out that corresponding to the general technical personnel in the technical field, without departing from the principles of the present disclosure, a number of improvements, optimizations and decorations can be made, which should be considered within the protection scope of the present disclosure.

[0160] Figure 3 A structural schematic diagram of a device for data center energy system scheduling provided by the embodiments of the present disclosure is shown in FIG. 3, which comprises: Figure 3

[0161] The target function module 301 is configured to construct an economic target function of minimizing the operation cost and an environmental target function of minimizing the carbon emission.​

[0162] The modeling module 302 is configured to construct a computing power side model and an energy supply side model.

[0163] The solving module 303 is configured to solve an optimal supply-demand matching solution of the data center energy system according to supply data information and demand data information in the data center energy system and constraint conditions.

[0164] The configuration module 304 is configured to configure the data center energy system according to an optimal supply-demand matching configuration scheme corresponding to the optimal supply-demand matching solution, so as to achieve an optimal operation target.

[0165] In some embodiments, the economic target function is a power consumption cost target function, and the environmental target function is a carbon dioxide emission target function.

[0166] In some embodiments, the power consumption cost target function is determined by grid electricity purchase cost, energy storage cost, diesel generator power generation cost, photovoltaic power generation cost, and demand response income.

[0167] In some embodiments, the load type of the data center providing computing services includes delay-tolerant load and delay-sensitive load, and the computing power side model includes a delay-tolerant load model constructed based on the delay-tolerant load and a delay-sensitive load model constructed based on the delay-sensitive load.

[0168] In some embodiments, the computing power side model further includes an IT equipment energy consumption model and an air conditioner and other equipment energy consumption model.

[0169] In some embodiments, the energy supply side model includes a photovoltaic power generation model, an energy storage device charging and discharging model, and a diesel generator fuel consumption model.

[0170] In some embodiments, the constraint conditions include network load task quantity constraints, quality of service constraints, energy balance constraints, energy storage device constraints, photovoltaic power generation constraints, and diesel generator constraints.

[0171] In some embodiments, the solving module 303 is configured to, according to the supply data information and the demand data information in the data center system energy and the constraint conditions, adopt a particle swarm optimization algorithm to solve the optimal supply-demand matching solution of the data center energy system with the objective of minimizing the power consumption cost target function.

[0172] In some embodiments, the solving module 303 includes:

[0173] The initialization submodule is configured to initialize a particle swarm, including a population size and a position and a speed of each particle.

[0174] The computation submodule is configured to compute the objective function value for each particle, determine the historical optimum of the particle and the global optimum in the population;

[0175] The update submodule is configured to continuously update the particle's velocity and position;

[0176] The replacement submodule is configured to calculate the objective function value of each particle in each generation of evolution. If the particle's current objective function value is better than its historical best value, then the current objective function value replaces its historical best value; if the particle's historical best value is better than the global best value in the population, then the historical best value replaces the global best value in the population.

[0177] The submodule ends when the iteration reaches a set value or the accuracy reaches the convergence accuracy, at which point the solution ends and the global optimal solution is obtained.

[0178] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure, such as... Figure 4 As shown, this disclosure also provides an electronic device 400, which includes at least one processor 401 and a memory 402 coupled to the processor 401. The memory 402 is used to store at least one processor 401 executable instructions, wherein the at least one processor 401 is used to execute the instructions to implement the steps of the method described above in this disclosure.

[0179] The processor 401 described above can also be referred to as a Central Processing Unit (CPU), which can be an integrated circuit chip with signal processing capabilities. Each step in the method described in this embodiment can be implemented by the integrated logic circuitry in the hardware of the processor 401 or by instructions in software form. The processor 401 described above can be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method in conjunction with this embodiment can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can be located in the memory 402, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor 401 reads information from the memory 402 and, in conjunction with its hardware, completes the steps of the method described above.

[0180] Figure 5 This is a schematic diagram of an exemplary computer system provided by an embodiment of the present disclosure. Various operations / processes according to embodiments of the present disclosure, implemented via software and / or firmware, can be transmitted from a storage medium or network to a computer system with a dedicated hardware architecture, for example... Figure 5 The computer system 500 shown is equipped with the programs that constitute the software. When various programs are installed, the computer system is able to perform various functions, including those described above.

[0181] Computer system 500 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of this disclosure described and / or claimed herein.

[0182] like Figure 5 As shown, the computer system 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. The RAM 503 may also store various programs and data required for the operation of the computer system 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0183] A plurality of components in the computer system 500 are connected to the I / O interface 505, including: an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. The input unit 506 can be any type of device capable of inputting information to the computer system 500, and can receive inputted digital or character information, and generate key signal input related to user settings and / or function control of the electronic device. The output unit 507 can be any type of device capable of presenting information, and can include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 508 can include, but is not limited to, a magnetic disk, an optical disk. The communication unit 509 allows the computer system 500 to exchange information / data with other devices through a network such as the Internet, and can include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, for example, a Bluetooth™ device, a WI-FI device, a WiMax device, a cellular communication device, and / or the like.

[0184] The computing unit 501 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs various methods and processes described above, for example. In some embodiments, the above-described methods of the present embodiments can be implemented as a computer software program, which is tangibly embodied in a machine-readable medium, for example, the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device via the ROM 502 and / or the communication unit 509. In some embodiments, the computing unit 501 can be configured to perform the above-described methods of the present embodiments by any other appropriate means, for example, by means of firmware.

[0185] The present embodiments provide a non-transitory computer-readable storage medium storing one or more programs, which can be executed by one or more processors to implement the above-described methods of the present embodiments.

[0186] The non-transitory computer-readable storage medium can be a volatile memory (volatile memory), such as a random access memory (Random-Access Memory, RAM); or a non-volatile memory (non-volatile memory), such as a read-only memory (Read-Only Memory, ROM), a flash memory, a hard disk (Hard Disk Drive, HDD) or a solid state disk (Solid-State Drive, SSD); or can be a respective device including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc.

[0187] It should be noted that the non-transitory computer-readable storage medium described above in the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer-readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, an RF (radio frequency) or the like, or any suitable combination of the above.

[0188] Embodiments of the present disclosure provide a computer program product comprising a computer program which, when executed by a processor, implements the steps of the uplink signal equalization method described above.

[0189] Computer program code for carrying out operations of the present disclosure can be written in any one or more of a variety of programming languages or combinations of languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on a computer, partly on the computer, as a stand-alone software package, partly on the computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0190] The modules, units or components described in the embodiments of the present disclosure can be implemented by software or by hardware. In some cases, the name of the module, unit or component does not constitute a limitation on the module, unit or component itself.

[0191] The functions described above in the specification of the present disclosure can be performed by one or more hardware logic components. For example, and without limitation, examples of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0192] It should be noted that, in this document, such terms as "comprising", "including", or any other variant thereof are intended to cover a non-exclusive inclusion, such that processes, methods, articles, or apparatuses that comprise a list of elements are not required to include only those elements in the list, but can include other elements not expressly listed or inherent to such processes, methods, articles, or apparatuses. In other words, any process, method, article, or apparatus that includes a list of elements is not limited to processes, methods, articles, or apparatuses that only include those elements in the list, but can include other elements not expressly listed or inherent to such processes, methods, articles, or apparatuses.

[0193] The above description is merely that of the specific embodiments of the present disclosure, and enables a person skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for scheduling a data center energy system, the method comprising: Comprise: An economic objective function of minimizing operating cost and an environmental objective function of minimizing carbon emissions are constructed; A computing power side model and an energy supply side model are constructed; An optimal supply-demand matching solution of the data center energy system is solved according to supply data information and demand data information in the data center energy system and constraint conditions; The data center energy system is configured according to an optimal supply-demand matching configuration scheme corresponding to the optimal supply-demand matching solution to achieve an optimal operation target; The load type of the data center providing computing services includes delay-tolerant load and delay-sensitive load, the computing power side model includes a delay-tolerant load model constructed based on the delay-tolerant load and a delay-sensitive load model constructed based on the delay-sensitive load; The energy supply side model includes a photovoltaic power generation model, an energy storage device charging and discharging model, and a diesel generator fuel consumption model; The photovoltaic power generation model is: ； ； ； ； ； ； ； ； ； ； wherein, T is the temperature at time t under general operating conditions; T is the temperature under standard test conditions; is the difference between the actual photovoltaic temperature at time t and the standard temperature; is the radiation intensity at time t under general operating conditions; is the radiation intensity under standard test conditions; is the difference between the radiation intensity at time t under standard conditions and under general conditions; is the short-circuit current at time t under general operating conditions; is the open-circuit voltage at time t under general operating conditions; is the maximum power point current at time t under general operating conditions; is the maximum power point voltage at time t under general operating conditions; and are two coefficients in the calculation process at time t; and are the current and voltage, respectively, of the PV panel under general operating conditions at time t; is the power generated by the PV panel at time t; α, β and γ are coefficients; The constraint conditions include network load task quantity constraints, quality of service constraints, energy balance constraints, energy storage device constraints, photovoltaic power generation constraints, and diesel generator constraints.

2. The method of claim 1, wherein: The economic objective function is an energy cost objective function, and the environmental objective function is a carbon dioxide emission objective function.

3. The method of claim 2, wherein, The energy cost objective function is determined by grid electricity purchase cost, energy storage cost, diesel generator power generation cost, photovoltaic power generation cost, and demand response income.

4. The method of claim 1, wherein, The computing power side model further includes an IT device energy consumption model and an air conditioner and other device energy consumption model.

5. The method of claim 1, wherein, Solving the optimal supply-demand matching solution of the data center energy system according to the supply data information and demand data information in the data center energy system and the constraint conditions comprises: According to the supply data information and demand data information in the data center system energy and the constraint conditions, the particle swarm optimization algorithm is used to solve the optimal supply-demand matching solution of the data center energy system with the objective of minimizing the energy cost objective function.

6. The method of claim 5, wherein, The particle swarm optimization algorithm solving comprises: Initializing the particle swarm, including the population size and the position and speed of each particle; Calculating the objective function value of each particle to determine the historical optimal value of the particle and the global optimal value in the population; Continuously updating the speed and position of the particle; In each generation evolution, the objective function value of each particle is calculated, and if the current objective function value of the particle is better than its historical optimal value, the current objective function value replaces the historical optimal value; if the historical optimal value of the particle is better than the global optimal value in the population, the historical optimal value replaces the global optimal value in the population; Iterate to reach a set value or the accuracy reaches the convergence accuracy, and the solution is ended to obtain the global optimal solution.

7. An apparatus, comprising: Comprise: An objective function module configured to construct an economic objective function of minimizing operating cost and an environmental objective function of minimizing carbon emissions; A modeling module configured to construct a computing power side model and an energy supply side model; The solving module is configured to solve a supply-demand matching optimal solution of the data center energy system according to supply data information and demand data information in the data center energy system and constraint conditions; The configuration module is configured to configure the data center energy system according to a supply-demand matching optimal configuration scheme corresponding to the supply-demand matching optimal solution, so as to achieve an optimal operation target; The load types of the data center providing computing services include delay-tolerant loads and delay-sensitive loads, and the computing power side model includes a delay-tolerant load model constructed based on the delay-tolerant loads and a delay-sensitive load model constructed based on the delay-sensitive loads; The energy supply side model includes a photovoltaic power generation model, a storage device charging and discharging model, and a diesel generator fuel consumption model; The photovoltaic power generation model is as follows: ； ； ； ； ； ； ； ； ； ； wherein, T is the temperature at time t under general operating conditions; T is the temperature under standard test conditions; ΔT is the difference between the actual PV temperature at time t and the standard temperature; I is the radiation intensity at time t under general operating conditions; I is the radiation intensity under standard test conditions; ΔI is the difference between the radiation intensity under standard conditions and the radiation intensity under general conditions at time t; Isc is the short-circuit current at time t under general operating conditions; Voc is the open-circuit voltage at time t under general operating conditions; Imax is the maximum power point current at time t under general operating conditions; Vmax is the maximum power point voltage at time t under general operating conditions; and a and b are two coefficients during the calculation at time t; and I and V are the current and voltage, respectively, of the PV panel under general operating conditions at time t; P is the power generated by the PV panel at time t; a, b and c are coefficients; The constraint conditions include network load task quantity constraints, quality of service constraints, energy balance constraints, storage device constraints, photovoltaic power generation constraints, and diesel generator constraints.

8. An electronic device, comprising: Comprise: At least one processor; Memory for storing instructions executable by the at least one processor; Wherein the at least one processor is configured to execute the instructions to implement the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium, comprising: The instructions in the non-transitory computer-readable storage medium are executed by the processor of the electronic device, so that the electronic device can execute the method of any one of claims 1-6.

10. A computer program product comprising a computer program, characterized in that, The computer program, after being executed, implements the method of any one of claims 1-6.

Images