A Multi-Energy Flow Cooperative Control Method and System for an Edge Data Center Cluster

Abstract

The present invention discloses a multi-energy flow collaborative control method and system for an edge data center cluster, which relates to the technical field of multi-energy flow collaborative control, and includes: S1. According to the data load type and data load scheduling method of the edge data center, and in combination with the server power consumption control strategy, a power consumption model of the edge data center server is constructed; S2. Based on the power consumption model, a water-cooling system for the edge data center cluster in the water aggregation mode is constructed; S3. Based on the data load scheduling method and power consumption model of the edge data center, in combination with the water-cooling system for the edge data center cluster in the aggregation mode, a multi-energy flow coupling model is constructed, and multi-energy flow collaborative control of the edge data center cluster is performed. The present invention breaks the situation of isolated operation of each system in the traditional data center, realizes efficient interaction and collaboration of multi-energy flows, makes the entire edge data center cluster operate more stably and smoothly, greatly shortens the data load response time, and reduces the emission of greenhouse gases such as carbon dioxide.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-energy flow collaborative control, and particularly relates to a multi-energy flow collaborative control method and system for an edge data center cluster. Background Art

[0002] Relying on its unique geographical location advantage close to the user side, the edge data center can quickly respond to various data requirements with ultra-low latency, providing strong computing power support for many scenarios such as real-time interactive applications and local data analysis, and facilitating intelligent use in fields such as the intelligent Internet of Things and the industrial Internet.

[0003] With the iteration of information technology and the expansion of business requirements, the scale of edge data centers shows a continuous expansion trend. Correspondingly, its energy consumption problem becomes increasingly severe, and the phenomenon of waste heat emission becomes increasingly prominent.

[0004] Therefore, in the prior art, methods for optimizing the computing power and power resources of a data center park by considering the guidance of a multi-source power market, depicting the aggregated adjustable characteristics of the data center park and the ways and benefits of participating in the electricity-frequency-regulation-capacity market, or simulating the performance of the waste heat recovery system of a lake-source data center, provide a theoretical basis for the design and energy-saving operation of the data center waste heat recovery system to further solve this problem. However, the prior art all focuses on the main body of large and medium-sized data centers and fails to fully consider the unique characteristics of edge data center clusters, such as small scale, cluster distribution, and proximity to users, making it difficult to directly transplant and apply the traditional information flow-electricity flow-thermal flow collaborative control technology suitable for large and medium-sized data centers.

[0005] Therefore, this application specifically proposes a multi-energy flow collaborative control method for an edge data center cluster to solve the above technical problems. Summary of the Invention

[0006] The main purpose of the present invention is to provide a multi-energy flow collaborative control method and system for an edge data center cluster, which is used to construct an information flow-electricity flow-thermal flow collaborative mechanism for the edge data center cluster, and provide a practical information flow-electricity flow-thermal flow collaborative operation scheme for the efficient and energy-saving operation of the edge data center cluster, so as to improve the overall stability and sustainability of the edge data center and solve the technical problems proposed in the background art.

[0007] The present invention adopts the following technical solutions to solve the above technical problems:

[0008] A multi-energy flow collaborative control method for an edge data center cluster includes the following steps:

[0009] S1. Edge data center energy consumption modeling based on the flexible characteristics of data load time-space scheduling:

[0010] According to the data load type and data load scheduling method of the edge data center, determine the amount of data load processed in each period, and combine with the server power consumption control strategy to realize the power consumption modeling of auxiliary devices such as edge data center servers, refrigeration equipment, and power supply and distribution systems, and construct the power consumption model of edge data center servers;

[0011] S2. Modeling of the waste heat recovery mechanism of the edge data center cluster under the aggregation mode with water cooling:

[0012] Based on the power consumption model of the edge data center server, construct the heat transfer model between the water cooling module and the server and the water distribution network model of the edge data center cluster, realize the refined simulation of the water cooling system of the edge data center cluster, establish the waste heat recovery model of the edge data center cluster under the aggregation mode, collect and preliminarily process the low-grade waste heat generated by the edge data center to form the water cooling system of the edge data center cluster under the aggregation mode;

[0013] S3. Establish the collaborative control mechanism of information flow - power flow - heat flow in the edge data center cluster:

[0014] Based on the data load scheduling method of the edge data center and the power consumption model of the edge data center server, combined with the water cooling system of the edge data center cluster under the aggregation mode, used to construct a multi-energy flow coupling model, realize the refined simulation of the collaborative interaction of information flow, power flow, and heat flow in the edge data center cluster, and then carry out the collaborative control of information flow - power flow - heat flow in the edge data center cluster;

[0015] Among them, the overall energy consumption cost of the edge data center cluster within the time period is expressed as: is expressed as:

[0016]

[0017] Among them, represents the power purchased from the main power grid by the th edge data center; represents the working power of the heat pump; represents the time-of-use electricity price in the area where the th edge data center is located; represents the carbon emission factor; represents the carbon emission cost coefficient; represents the waste heat recovery benefit coefficient; represents the heat of the cooling water obtained after being heated by the heat pump at the waste heat recovery point; represents the total number of time periods; represents the number of edge data centers; represents the time consumed for the edge data centers to converge to a unified waste heat recovery point.

[0018] Preferably, in the step S1, the edge data center is deployed at the access network level, a data center close to the user side, with a single scale not exceeding 100 standard racks, and equipped with lithium iron phosphate energy storage batteries for maintaining its uninterrupted operation.

[0019] Preferably, in the step S1, each edge data center is set as a uniform data center, that is, the technical indicators such as the performance and rated power of the servers deployed in each edge data center are the same. Then the total energy consumption of the th edge data center

[0020]

[0021] where represents the power consumption of the IT equipment of the th edge data center; represents the power consumption of the refrigeration equipment of the th edge data center; represents the power consumption of auxiliary equipment such as the power supply and distribution system of the th edge data center.

[0022] Preferably, for the power consumption of the IT equipment of the th edge data center, the energy consumption modeling of the IT equipment can be completed based on the server utilization model in combination with parameters such as the server peak power and idle power. The calculation formula is:

[0023]

[0024] where represents the set of servers in the th edge data center that are in the running state; represents the set of servers in the th edge data center that are in the dormant state; represents the static power of the servers in the IT equipment of the edge data center in the running state; represents the peak power of the servers in the IT equipment of the edge data center in the running state; represents the th server in the th edge data center's real-time data load processing volume; represents the rated data load processing volume of a single server in the edge data center; represents the standby power of the servers in the IT equipment of the edge data center in the dormant state.

[0025] Preferably, for the Power consumption of refrigeration equipment in an edge data center , based on the power usage effectiveness (PUE) and combined with the energy consumption of IT equipment and auxiliary equipment Calculation, since the defined period of PUE is the ratio of the total input energy consumption of the data center to the total energy consumption of IT equipment, there is: .

[0026] Preferably, in the S1 step, the data load types in the edge data center include two categories: online load and offline load, where:

[0027] The online load includes real-time interactive loads;

[0028] The offline load includes time-shiftable data loads and space-shiftable data loads, for service requests including load data analysis and scientific computing.

[0029] Preferably, in the S1 step, the data load scheduling method in the edge data center includes: a method of migrating data loads based on spatial flexibility and a method of transferring data loads based on temporal flexibility.

[0030] Preferably, in the S2 step, the heat loss coefficient of IT equipment in the edge data center is set constant, and the heat generated by the IT equipment is completely recovered by the cooling water. Then, the formula for the heat energy output by the water-cooled heat dissipation module of the th edge data center is:

[0031]

[0032] Where , are the specific heat capacity and density values of water at normal temperature and pressure, respectively; , respectively represent the cooling water flow rate per unit time and the inlet water temperature of the first th edge data center.

[0033] Preferably, in the S2 step, the heat loss coefficient of the IT equipment server in the edge data center is set constant, and the heat generated by the equipment can be completely recovered by the cooling water. Then, the water temperature of the cooling water at the outlet of the water-cooled heat dissipation module of each edge data center is calculated by the formula:

[0034]

[0035] Where represents the basic value of the waste heat recovery temperature; represents the specific heat capacity value of the cooling water at normal temperature and pressure; represents the The cooling water flow rate at the outlet of the water-cooled heat dissipation module of an edge data center.

[0036] Preferably, in the S3 step, the water-cooled system of the edge data center cluster in the aggregation mode is used to transport cooling water to each edge data center node via a preset water distribution network through a water pump, so as to realize the refrigeration of each edge data center.

[0037] Preferably, in the S3 step, the heat transfer model in the water-cooled system of the edge data center cluster is used to centrally guide the low-grade waste heat of each edge data center to a unified waste heat recovery point, and use a heat pump to reheat the collected low-grade waste heat.

[0038] Preferably, in the start-stop control process of the heat pump at the unified waste heat recovery point in the S3 step, a heat energy recovery threshold is set to determine whether to start the heat pump.

[0039] Preferably, a multi-energy flow collaborative control system for an edge data center cluster is constructed based on the multi-energy flow collaborative control method for an edge data center cluster described in any one of the above, and is used for performing collaborative control of information flow - power flow - thermal flow in the edge data center cluster. The system is obtained by coupling the water-cooled system of the edge data center cluster in the aggregation mode and the power consumption model of the edge data center server.

[0040] Preferably, multiple groups of the power consumption models are set, and through data load coordination, the power consumption models include: energy storage batteries, distributed photovoltaics, and edge data centers. The edge data center is used for power regulation and obtaining the energy consumption of energy storage batteries and distributed photovoltaics.

[0041] The water-cooled system of the edge data center cluster includes: a refrigeration water source, a water distribution network connected to the power consumption model, and a heat pump for upgrading the waste heat recovery of the water distribution network.

[0042] It can be seen from the above technical solutions that the present invention provides a multi-energy flow collaborative control method for an edge data center cluster. Compared with the prior art, the present invention has the following advantages:

[0043] 1. By setting a collaborative control mechanism among the information flow - power flow - thermal flow in the edge data center cluster, the present invention can ensure efficient and smooth data processing, thus greatly shortening the data load response time, providing an excellent user experience for real-time interactive applications, and reducing the emissions of greenhouse gases such as carbon dioxide.

[0044] 2. By establishing a collaborative control mechanism for the information flow - power flow - thermal flow in the edge data center cluster, the present invention can facilitate the efficient and energy-saving operation of the edge data center cluster, improve the overall stability and sustainability of the edge data center, and further promote the green and healthy development of the edge computing industry.

[0045] 3. The present invention conducts energy consumption modeling by comprehensively considering data load types, scheduling methods, and server power consumption control strategies, delves into the refined management of each time period and component in the edge data center, and can dynamically adjust power consumption according to actual data processing requirements.

[0046] 4. By further constructing a water-cooled waste heat recovery mechanism in the aggregation mode for the edge data center cluster, the present invention solves the problem that the existing waste heat recovery methods in data centers are difficult to be directly transplanted and applied to edge data centers, realizes the precise collection and utilization of low-grade waste heat generated by edge data centers, and improves the overall energy utilization rate of the edge data center cluster.

[0047] 5. By constructing a collaborative control mechanism for information flow - power flow - heat flow in the edge data center cluster, the present invention breaks the situation where each system in the traditional data center operates in isolation, realizes the efficient interaction and collaboration among the three, and makes the operation of the entire edge data center cluster more stable and smooth.

[0048] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Of course, any product implementing the present invention does not necessarily need to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings forming a part of this application are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0050] Figure 1 is a schematic diagram of the overall process of an embodiment of the present invention;

[0051] Figure 2 is a schematic diagram of the structural framework of the coupling system of an embodiment of the present invention;

[0052] Figure 3 is a schematic diagram of the simulation experiment results of an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0054] In the embodiments, refer in detail to Figures 1 to 3 .

[0055] As Figure 1 shown, a multi-energy flow collaborative control method for an edge data center cluster proposed in an embodiment of the present invention mainly focuses on information flow - power flow - heat flow in multi-energy flows, including:

[0056] S1. Edge data center energy consumption modeling based on the flexible characteristics of data load scheduling:

[0057] According to the data load type and data load scheduling method of the edge data center, determine the negative load volume of the data processed in each period, and combine the server power consumption control strategy to realize the power consumption modeling of auxiliary devices such as servers, refrigeration equipment, and power supply and distribution systems in the edge data center, and construct the power consumption model of the servers in the edge data center.

[0058] Among them, the edge data center is deployed at the access network level, close to the user side, with a single scale not exceeding 100 standard racks, and is equipped with lithium iron phosphate energy storage batteries for maintaining its uninterrupted operation.

[0059] Specifically, each edge data center is set as a uniform data center, that is, the technical indicators such as the performance and rated power of the servers deployed in each edge data center are the same. Then the total energy consumption of the th edge data center can be expressed as the sum of the power consumption of IT equipment, refrigeration equipment, and auxiliary equipment, as shown in the following formula:

[0060]

[0061] Among them, represents the power consumption of IT equipment in the th edge data center; represents the power consumption of refrigeration equipment in the th edge data center; represents the power consumption of auxiliary equipment such as the power supply and distribution system in the th edge data center.

[0062] For the power consumption of IT equipment in the th edge data center, the energy consumption modeling of IT equipment can be completed based on the server utilization model in combination with parameters such as the server peak power and idle power. The calculation formula is:

[0063]

[0064] Among them represents the set of servers in the th edge data center in the running state; Indicates the set of servers when the th edge data center is in the dormant state; Indicates the static power of the servers when the IT equipment of the edge data center is in the operating state; Indicates the peak power of the servers when the IT equipment of the edge data center is in the operating state; Indicates the th edge data center's th server's real-time data load processing volume; Indicates the rated data load processing volume of a single server in the edge data center; Indicates the standby power of the servers when the IT equipment of the edge data center is in the dormant state;

[0065] At this time, for the th edge data center's refrigeration equipment power consumption , based on the power usage effectiveness PUE and combined with the IT equipment energy consumption and auxiliary equipment calculate. Since the PUE defined period is the ratio of the total input energy consumption of the data center to the total energy consumption of the IT equipment, there is:

[0066]

[0067] In addition, it can be further explained that the data load types of the edge data center include online load and offline load, where: the online load includes real-time interactive loads; the offline load includes time-shiftable data loads and space-shiftable data loads, for service requests including load data analysis and scientific computing. At this time, the data load scheduling methods of the edge data center include: the method of migrating data loads based on spatial flexibility and the method of transferring data loads based on time flexibility.

[0068] Therefore, based on the above energy consumption modeling analysis of the edge data center, according to the edge data center cluster data load scheduling technology, that is, the technology of migrating data loads based on spatial flexibility and the technology of transferring data loads based on time flexibility, then the real-time data load processing volume of the first in the th edge data center within the defined period is as follows:

[0069]

[0070] Among them, Indicates the online load arrival volume of the th edge data center within the period ; Indicates the th within the period The edge data center can time-shift the data load arrival; Indicates time period Neidi The amount of data load that can be spatially transferred by edge data centers; Indicates time period Neidi The edge data center The amount of load moved into the edge data center; It indicates the time period Neidi The edge data center The amount of load moved out of edge data centers; express Edge data center slots The amount of load shifted to future time periods; express Edge data centers past period to period The amount of load moved in.

[0071] Among them, the period Neidi Real-time data load processing capacity of edge data centers It can be further combined with the data load processing capacity of the edge data center server to express as:

[0072]

[0073] In addition, the above-mentioned migration data load technology based on spatial flexibility and the transfer data load technology based on time flexibility should satisfy the following constraint formula conditions:

[0074]

[0075] Among them, c1 represents the time period First Edge Data Center The real-time data load processing capacity of the server in the running state is subject to the rated data load processing capacity as the upper limit; c2 represents the time period No. The edge data center The load volume removed from each edge data center is capped by the amount of data load that can be transferred spatially in the current period; c3 represents the period No. The load amount that the edge data center moves out to the future period is capped by the amount of data load that can be transferred in the current period; the data load transfer flag matrix between edge data centers is constructed in c4 ,but Indicates time period From the first edge data center to the th edge data center, the data load transfer flag bit. If the data load is transferred, it is 1; otherwise, it is 0. This constraint means that if an edge data center receives the transferred data load from other edge data centers, it cannot transfer the data load to other edge data centers anymore; c5 represents the time period From the first edge data center, the average queuing delay of the data load , the average processing delay , the communication delay and the transmission delay The sum is capped by the maximum tolerable delay duration in the current time period.

[0076] Furthermore, in the content of the c5 constraint condition, the average queuing delay of the data load in the th edge data center, the average processing delay , the communication delay and the transmission delay are specifically defined as follows:

[0077] (1) Calculate the average queuing delay of the data load based on the M / M / 1 queuing theory , there is:

[0078]

[0079] (2) Calculate the average processing delay of the data load based on the reciprocal of the average service rate of the data center , there is:

[0080]

[0081] (3) Calculate the communication delay and the transmission delay based on the communication delay, bandwidth, and the amount of data load transmitted in the data network branch. There is:

[0082]

[0083] Where represents the data network branch number and the corresponding set; represents whether the data load in the time period is communicated and transmitted through the branch . If it flows through this branch, it is 1; otherwise, it is 0; , respectively represent the communication delay and bandwidth corresponding to the data network branch ; represents the time period Inbound data network branch The amount of data payload transferred.

[0084] In summary, by comprehensively considering the data load type, scheduling method and server power consumption control strategy to carry out energy consumption modeling, we can carry out refined management of each time period and each component of the edge data center, and dynamically adjust the power consumption according to the actual data processing needs.

[0085] S2. Modeling of water cooling waste heat recovery mechanism for edge data center clusters in aggregation mode:

[0086] Based on the power consumption model of edge data center servers, a heat transfer model between the water cooling module and the server and a water distribution network model of the edge data center cluster are constructed to achieve refined simulation of the edge data center cluster water cooling system, establish an edge data center cluster waste heat recovery model under aggregation mode, collect and preliminarily process the low-grade waste heat generated by the edge data center, and form an edge data center cluster water cooling system under aggregation mode;

[0087] In the specific use process, the edge data center cluster water cooling waste heat recovery system constructed by this application is as follows: Figure 2 As shown in the figure, cooling water is pumped to each edge data center node through a preset water network. At each node, advanced water cooling technology is used to meet the cooling needs of its server IT equipment, ensuring the stable operation of the edge data center while collecting and preliminarily processing the low-grade waste heat generated. Subsequently, the preliminarily processed low-grade waste heat will be centrally guided to a unified waste heat recovery point, and the collected low-grade waste heat will be upgraded using heat pump technology to convert it into high-grade thermal energy that can meet the heating needs of surrounding communities or industrial facilities, thereby realizing the cascade utilization of waste heat resources.

[0088] Therefore, by further constructing a water-cooled waste heat recovery mechanism under an aggregated mode for edge data center clusters, the problem that the existing data center waste heat recovery methods are difficult to directly transplant and apply to edge data centers is solved, and the accurate collection and utilization of low-grade waste heat generated by edge data centers is achieved, thereby improving the overall energy utilization rate of edge data center clusters.

[0089] Specifically, heat is transferred between the water cooling module and the server's heating components by conduction, so the heat loss coefficient of IT equipment in the edge data center is set If the heat generated by IT equipment is completely recovered by cooling water, then The calculation formula for the heat energy output by the water cooling module of an edge data center is:

[0090]

[0091] in, , are the specific heat capacity and density values of water at normal temperature and pressure respectively; , respectively represent the cooling water flow rate and inlet water temperature per unit time of the first edge data center.

[0092] At this time, set the heat loss coefficient of the IT equipment server in the edge data center to be constant, and assume that the heat generated by the equipment can be completely recovered by the cooling water. Then, the water temperature of the cooling water at the outlet of the water-cooled heat dissipation module of each edge data center is calculated as follows:

[0093]

[0094] where, represents the basic value of the waste heat recovery temperature; represents the specific heat capacity value of the cooling water at normal temperature and pressure; represents the th cooling water flow rate at the outlet of the water-cooled heat dissipation module of the edge data center.

[0095] Furthermore, for the cooling water of each edge data center converging to a unified waste heat recovery point and being reheated by a heat pump, the recoverable heat after convergence is calculated as follows:

[0096]

[0097] where, represents the initial heat collected when the cooling water of each edge data center converges to a unified waste heat recovery point; represents the heat dissipation coefficient during the convergence process caused by the different distances between each edge data center and the unified waste heat recovery point; represents the heat of the cooling water obtained after being heated by the heat pump at the waste heat recovery point; represents the working power of the heat pump; represents the coefficient of performance of the heat pump; represents the time taken for the cooling water of each edge data center to converge to a unified waste heat recovery point.

[0098] In addition, the water-cooled waste heat recovery of the edge data center cluster in the aggregation mode should satisfy the following constraint formula conditions:

[0099]

[0100] where, c6 represents the flow balance constraint of the water distribution network node; c7 represents the working power constraint of the water pump; c8 and c9 are the inlet and outlet water flow constraints of the th edge data center respectively; represents the time period within the The unit flow rate of cooling water consumed by a single-edge data center water-cooling heat dissipation module; is the rated working power of the heat pump; and respectively represent the maximum inlet and outlet water flow rates of the first

[0101] S3. Establish a collaborative control mechanism for information flow - power flow - heat flow in the edge data center cluster:

[0102] Based on the load scheduling method of edge data center data and the power consumption model of edge data center servers, combined with the water-cooling system of the edge data center cluster in the aggregation mode, it is used to construct a multi-energy flow coupling model to realize the refined simulation of the collaborative interaction of information flow, power flow, and heat flow in the edge data center cluster, and then carry out the collaborative control of information flow - power flow - heat flow in the edge data center cluster.

[0103] Among them, based on the edge data center energy consumption modeling in the above S1, the spatio-temporal redistribution of the edge data center cluster load can be realized through the migration data load technology based on spatial flexibility and the transfer data load technology based on time flexibility.

[0104] Among them, based on the waste heat recovery mechanism of the water-cooling system of the edge data center cluster in the aggregation mode in the above S2, the efficient recovery and cascade utilization of waste heat resources of the edge data center cluster with small scale, cluster distribution, and close to users can be realized.

[0105] Furthermore, to ensure that the edge data center can achieve uninterrupted power supply in the case of power grid power failure and guarantee the user service quality, each edge data center is equipped with a storage battery (herein referred to as a lithium iron phosphate storage battery in the present invention) as an emergency power supply. Therefore, based on the flexible charging and discharging characteristics of the storage battery, the collaborative control of information flow - power flow - heat flow in the edge data center cluster can be realized.

[0106] Furthermore, the present invention application can reduce the power expenditure cost of the edge data center and effectively reduce the carbon emissions in the operation link. Some edge data centers are equipped with distributed photovoltaic devices to provide green energy supply for the data center.

[0107] In summary, the power supply composition of the edge data center at this time is expressed as:

[0108]

[0109] Among them, and respectively represent the during the time period charging and discharging power of the storage battery equipped in the represents the time period Output power of distributed photovoltaic equipment equipped in the nth edge data center; Indicates the time period in the Electric power purchased from the main power grid by the nth edge data center.

[0110] Therefore, the overall energy consumption cost of the edge data center cluster can be described as follows:

[0111]

[0112] Among them, is the overall energy consumption cost of the edge data center cluster; Indicates the time period in the Electric power purchased from the main power grid by the nth edge data center; Indicates the time period in the Time-of-use electricity price in the area where the nth edge data center is located; Indicates the carbon emission factor; Indicates the carbon emission cost coefficient; Indicates the waste heat recovery benefit coefficient; Indicates the time period Heat of the cooling water obtained after being heated by the heat pump at the waste heat recovery point within the time period; Indicates the total number of time periods; Indicates the number of edge data centers in the edge data center cluster; Indicates the time consumed for each edge data center to converge to a unified waste heat recovery point.

[0113] In addition, for the energy storage battery equipped in the edge data center, the following constraint formula conditions should be met:

[0114]

[0115] Among them, c10 and c11 respectively represent the charge and discharge power constraints of the energy storage battery; c12 represents the capacity constraint of the energy storage battery; c13 represents the charge and discharge state constraint of the energy storage battery; c14 represents the charge and discharge cycle constraint of the energy storage battery; , respectively represent the charge and discharge power of the energy storage battery equipped in the nth edge data center within the time period ; , , , respectively represent the minimum and maximum values of the charge and discharge power of the energy storage battery equipped in the nth edge data center within the time period ; Indicates the maximum capacity value of the energy storage battery equipped in the th edge data center; , Indicates the number of charge and discharge changes and the maximum number of changes of the energy storage battery equipped in the th edge data center within the total time period.

[0116] Among them, the calculation formula for the number of charge and discharge changes of the energy storage battery equipped in the th edge data center within the total time period is as follows:

[0117]

[0118]

[0119] Among them, Indicates the equivalent conversion of the charge and discharge power of the energy storage battery equipped in the first th edge data center. When its value is greater than 0, it means the energy storage battery is in the charging state; when its value is less than 0, it means the energy storage battery is in the discharging state; Indicates an infinitely large positive integer; Indicates the charge and discharge state switching flag bit of the energy storage battery equipped in the th edge data center.

[0120] In the specific implementation process, the water-cooling system of the edge data center cluster in the aggregation mode is used to transport the cooling water to each edge data center node through a water pump via a preset water distribution network to achieve the refrigeration of each edge data center.

[0121] At this time, the heat transfer model in the water-cooling system of the edge data center cluster is used to centrally guide the low-grade waste heat of each edge data center to a unified waste heat recovery point and use a heat pump to reheating the collected low-grade waste heat.

[0122] Specifically, a heat energy recovery threshold is set in the start-stop control process of the heat pump at the unified waste heat recovery point to determine whether to start the heat pump. It can be specifically expressed as the following formula condition:

[0123]

[0124] Among them, Indicates the initial heat collected by each edge data center converging to the unified waste heat recovery point; Indicates the heat energy recovery threshold; Indicates the start-stop flag bit of the heat pump at the unified waste heat recovery point. When it is enabled, it is 1, otherwise it is 0.

[0125] In summary, based on the above S1, S2, and S3, the collaborative control of information flow - power flow - heat flow in the edge data center cluster can be achieved. The spatio - temporal redistribution of the load in the edge data center cluster is realized through the migration data load technology based on spatial flexibility and the transfer data load technology based on temporal flexibility. The energy - using flexibility of the edge data center is enhanced through the flexible charging and discharging characteristics of the energy storage battery in the edge data center. At the same time, based on the waste heat recovery mechanism of the water - cooled system in the edge data center cluster under the aggregation mode, the efficient recovery and cascade utilization of waste heat resources in the edge data center cluster are realized.

[0126] Therefore, by establishing the collaborative control mechanism of information flow - power flow - heat flow in the edge data center cluster, it is convenient for the efficient energy - saving operation of the edge data center cluster, improves the overall stability and sustainability of the edge data center, and further promotes the green and healthy development of the edge computing industry. At this time, carrying out the collaborative control of information flow - power flow - heat flow for the edge data center cluster can ensure the efficient and smooth data processing, greatly shorten the data load response time, provide an excellent user experience for real - time interactive applications, and at the same time help the edge data center improve the utilization efficiency of electric energy and computing resources, effectively reduce the emissions of greenhouse gases such as carbon dioxide. In addition, it can also inject new impetus into the economic feasibility of the edge data center industry through the recycling and reuse of waste heat.

[0127] In addition, it should also be noted that by constructing the collaborative control mechanism of information flow - power flow - heat flow in the edge data center cluster, the situation of isolated operation of each system in the traditional data center is broken, the efficient interaction and collaboration among the three are realized, and the operation of the entire edge data center cluster becomes more stable and smooth.

[0128] On the other hand, referring to Figure 2 , the present invention also discloses a multi - energy - flow collaborative control system for an edge data center cluster, which is constructed based on any of the above - mentioned multi - energy - flow collaborative control methods for an edge data center cluster and is used for carrying out the collaborative control of information flow - power flow - heat flow in the edge data center cluster. The system is obtained by coupling the water - cooled system of the edge data center cluster under the aggregation mode and the power consumption models of the edge data center servers.

[0129] There are multiple groups of power consumption models, and through data load coordination, the power consumption models include: energy storage batteries, distributed photovoltaics, and edge data centers. The edge data center is used for power regulation and obtains the energy consumption of energy storage batteries and distributed photovoltaics.

[0130] The water - cooled system of the edge data center cluster includes: a cooling water source, a water distribution network connected to the power consumption model, and a heat pump for upgrading the waste heat recovery of the water distribution network.

[0131] Based on the above methods and the constructed system, the effectiveness of the proposed collaborative mechanism for information flow - power flow - heat flow in the edge data center cluster is further verified. Therefore, the following joint scheduling scenario for the edge data center cluster is built: The problem is solved and simulated based on the MATLAB R2020a simulation platform using the Gurobi solver.

[0132] In this simulation experiment scenario, it is set that there are 3 edge data centers deployed within a range of 30 square kilometers, and their geographical locations are distributed according to the Poisson distribution. The time - of - use electricity price in the region is determined according to the specified value of City A within a designated time period. The key technical parameter information of the edge data centers refers to the settings of the B prefabricated modular data center; the data load conditions in each period refer to the real - world dataset of the C cloud computer cluster, and the distributed photovoltaic output information refers to the real data of a certain day in City A. There are:

[0133] Reference Figure 3 , taking the No. 1 edge data center in the edge data center cluster as an example, the simulation analysis of the collaborative mechanism for information flow - power flow - heat flow in the edge data center cluster proposed by the present invention is as follows:

[0134] On the premise of ensuring that the user service quality is not affected, based on the collaborative mechanism for information flow - power flow - heat flow in the edge data center cluster, in the time dimension, it is possible to migrate the internal data load of the edge data center to the period when the distributed photovoltaic output reaches the peak (11:00 - 14:00) for processing, so as to make full use of the high - efficiency period of solar power generation and avoid local server overload problems, reducing the dependence on traditional energy; in the space dimension, it is possible to redistribute the data load between different edge data centers, thereby comprehensively improving the overall energy utilization efficiency and computing utility of the edge data center cluster.

[0135] Based on the flexible charging and discharging characteristics of the energy storage batteries equipped in the edge data center, when the mains supply is sufficient and the electricity price is in the low - valley period (23:00 - 7:00 the next day), the energy storage batteries are in the charging period; when there are fluctuations or faults in the mains supply, or the electricity price is in the peak period (10:00 - 13:00, 17:00 - 22:00), the energy storage batteries switch to the discharging period to ensure stable power supply for various devices in the edge data center. At the same time, it can be seen that when the edge data center cannot fully absorb the distributed photovoltaic output during the period (11:00 - 14:00), the edge data center increases the data load processing share during this period through data load time - of - use scheduling and uses the charging operation of the energy storage battery to absorb the excess power.

[0136] Based on the water - cooled waste heat recovery mechanism of the edge data center cluster in the aggregation mode, it is possible to effectively utilize the small - scale and low - grade waste heat of each edge data center node. The available waste heat resources of each node have a linear - correlation functional relationship with its computing power load curve. The simulation analysis of this part will not be elaborated here.

[0137] Based on the above simulation analysis results, the daily operating costs of each edge data center can be calculated. After considering the information flow - power flow - heat flow collaborative mechanism of an edge data center cluster proposed in this application, the daily operating cost of the edge data center cluster in the non - collaborative scenario is significantly reduced. Therefore, the overall daily operating cost of the edge data center cluster can be reduced.

[0138] In another embodiment provided by this application, a computer program product containing instructions is also provided. When it runs on a computer, it enables the computer to execute the multi - energy - flow collaborative control method of any edge data center cluster in the above - mentioned embodiments.

[0139] It can be understood that the system provided by the embodiments of the present invention corresponds to the method provided by the embodiments of the present invention. For the explanations, examples, and beneficial effects of relevant content, reference can be made to the corresponding parts in the above - mentioned method.

[0140] The embodiments of this application also provide an electronic device, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus.

[0141] The memory is used to store a computer program.

[0142] The processor is used to implement the multi - energy - flow collaborative control method of the above - mentioned edge data center cluster when executing the program stored in the memory.

[0143] The communication bus mentioned in the above - mentioned electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0144] The communication interface is used for communication between the above - mentioned electronic device and other devices.

[0145] The memory can include a random access memory and can also include a non - volatile memory, such as at least one disk memory. Optionally, the memory can also be at least one storage device located far from the aforementioned processor.

[0146] The above - mentioned processor can be a general - purpose processor, including a central processing unit, a network processor, etc.; it can also be a digital signal processor, an application - specific integrated circuit, a field - programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0147] It should also be noted that the electronic device further includes a terminal device, which can also be referred to as a terminal, user equipment, mobile station, mobile terminal, etc. The terminal device can be a mobile phone, smart TV, wearable device, tablet computer, computer with wireless transceiver function, virtual reality terminal device, augmented reality terminal device, wireless terminal in industrial control, wireless terminal in autonomous driving, wireless terminal in remote surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, and so on. The embodiments of the present application do not limit the specific technologies and specific device forms adopted by the terminal device.

[0148] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access, or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state drive), etc.

[0149] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

[0150] In addition, it should be noted that if there are directional indications (such as up, down, left, right, front, back...) involved in the embodiments of the present invention, the directional indications are only used to explain the relative position relationship and movement conditions between components in a specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0151] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the meaning of "and / or" appearing throughout the text includes three parallel scenarios. Taking "A and / or B" as an example, it includes Scenario A, or Scenario B, or the scenario where both A and B are satisfied simultaneously. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

Claims

1. A multi-energy flow collaborative control method for an edge data center cluster, characterized in that Including: S1. According to the data load type and data load scheduling method of the edge data center, combined with the server power consumption control strategy, construct the power consumption model of the edge data center server; S2. Based on the power consumption model, construct a heat transfer model and a water distribution network model to form a cluster water cooling system for the edge data center under the aggregation mode; S3. A load scheduling method and power consumption model based on the data of the edge data center, combined with the cluster water cooling system of the edge data center in the aggregation mode, are used to construct a multi-energy flow coupling model and perform collaborative control of the information flow - power flow - heat flow in the edge data center cluster. The overall energy consumption cost of the edge data center cluster within the time period is expressed as: For the edge data center cluster as a whole within the time period Indicates the electricity purchase power of the th edge data center from the main power supply; Indicates the working power of the heat pump; Indicates the th time-of-use electricity price in the area where the edge data center is located; Indicates the carbon emission factor; Indicates the carbon emission cost coefficient; Indicates the waste heat recovery benefit coefficient; Indicates the heat of the cooling water obtained after being heated by the heat pump at the waste heat recovery point; Indicates the total number of time periods; Indicates the number of edge data centers; Indicates the time consumed for the edge data centers to converge to a unified waste heat recovery point.

2. The multi-energy flow collaborative control method for the edge data center cluster according to claim 1, wherein In the S1 step, the edge data center is deployed at the access network level, a data center close to the user side, with a single scale not exceeding 100 standard racks, and equipped with lithium iron phosphate energy storage batteries for maintaining its uninterrupted operation.

3. The multi-energy flow collaborative control method for the edge data center cluster according to claim 1, wherein In the S1 step, the data load types of the edge data center include two categories: online load and offline load, where: The online load includes real-time interactive loads; The offline load includes time-transferable data loads and space-transferable data loads, and is used for service requests including load data analysis and scientific computing.

4. The multi-energy flow collaborative control method for the edge data center cluster according to claim 1, characterized in that In the S1 step, the data load scheduling method of the edge data center includes: a method for migrating data loads based on spatial flexibility and a method for transferring data loads based on time flexibility.

5. The multi-energy flow collaborative control method for the edge data center cluster according to claim 1, characterized in that In the S2 step, a waste heat recovery model for the edge data center cluster under the aggregation mode is also established, which is used to collect and preliminarily process the low-grade waste heat generated by the edge data center.

6. The multi-energy flow collaborative control method for the edge data center cluster according to claim 1, characterized in that, In the S3 step, the cluster water cooling system for the edge data center under the aggregation mode is used to pump cooling water through a preset water distribution network to each edge data center node to achieve refrigeration of each edge data center.

7. The multi-energy flow collaborative control method for the edge data center cluster according to claim 6, characterized in that In the S3 step, the heat transfer model in the cluster water cooling system for the edge data center is used to centrally guide the low-grade waste heat of each edge data center to a unified waste heat recovery point, and use a heat pump to reheat the collected low-grade waste heat.

8. The multi-energy flow collaborative control method for the edge data center cluster according to claim 7, characterized in that In the start-stop control process of the heat pump at the unified waste heat recovery point in the S3 step, a heat energy recovery threshold is set to determine whether to turn on the heat pump.

9. A multi-energy flow collaborative control system for an edge data center cluster, constructed based on the multi-energy flow collaborative control method for an edge data center cluster according to any one of the above claims 1-8, and used for performing collaborative control of information flow - power flow - heat flow in the edge data center cluster, characterized in that, The system is obtained by coupling the cluster water cooling system for the edge data center under the aggregation mode and the power consumption model of the edge data center server.

10. The multi-energy flow collaborative control system of the edge data center cluster according to claim 9, characterized in that, There are multiple groups of the power consumption models, and through data load coordination, the power consumption models include: energy storage batteries, distributed photovoltaics, and edge data centers. The edge data centers are used for power regulation and obtain the energy consumption of energy storage batteries and distributed photovoltaics. The cluster water cooling system for the edge data center includes: a refrigeration water source, a water distribution network connected to the power consumption model, and a heat pump for waste heat recovery and upgrade of the water distribution network.

Images