Computer room air conditioning linkage management system

By adopting balanced adjustment and monitoring modules in the computer room air conditioner linkage management system, combined with air conditioner temperature regulation and server load balancing, the problem of failure to effectively consider the server's requested heat in the existing technology, achieving more efficient energy utilization.

CN118250962BActive Publication Date: 2024-12-06GUANGDONG ZHIXIANG INFORMATION TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410246670.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-03-05
Publication Date
2024-12-06
Estimated Expiration
2044-03-05

AI Technical Summary

Technical Problem

The existing machine room air conditioner linkage management system fails to effectively combine temperature regulation and server load balancing, resulting in load balancing not taking into account the heat generated by the server's processing request, resulting in excessive waste of linked air conditioner energy.

Method used

Using the balance adjustment module and the monitoring module, external requests are allocated through the smooth weighted polling algorithm, and the server temperature and load data are monitored and analyzed in real time in the balance correction unit, and the request allocation is determined and adjusted to reduce the impact of heat on temperature and optimize the air conditioner. Resource utilization.

Benefits of technology

By combining air conditioning temperature regulation and server load balancing, the impact of heat generated by server processing requests on the computer room temperature is reduced, unnecessary energy waste is avoided, and the utilization efficiency of air conditioning resources is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118250962B_ABST
    Figure CN118250962B_ABST
Patent Text Reader

Abstract

The invention discloses a computer room air-conditioning linkage management system, and relates to the technical field of air-conditioning linkage management. The invention provides a monitoring module to monitor and collect temperature and load data of servers in a computer room in real time, a data analysis module to analyze the number of external request processing that generates heat that affects the temperature rise in the computer room, a balancing allocation unit to select the optimal server for the external request, a balancing correction unit to determine the number of all external requests stored in an interval correction period, and based on the fact that the influence of the external request on the temperature in the computer room that appears in the determination result can be corrected by balancing, the external request is balanced to other servers, the linkage air-conditioning temperature adjustment and the server load balancing are combined, and excessive waste of linkage air-conditioning energy is avoided due to excessive unnecessary heat generated in the processing requests of each server not being considered in the load balancing.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of air-conditioning linkage management, and in particular to a computer room air-conditioning linkage management system. Background Art

[0002] With the rapid development of the Internet, the increasing requirements of bandwidth, management and maintenance of website systems have posed a severe challenge to many enterprises. Therefore, enterprises began to hand over matters related to website hosting services to companies specializing in providing network services, and focus on businesses that enhance core competitiveness. As a result, computer rooms were created to store servers and provide IT services to users and employees. Computer rooms are the center of data storage and data circulation.

[0003] Load balancing is to evenly distribute workloads (such as network traffic, data processing tasks, etc.) to multiple servers or devices to improve the overall system's processing power and resource utilization;

[0004] At present, a computer room air conditioning linkage management system maintains the temperature in the computer room by real-time monitoring of the temperature in the computer room. However, the temperature in the computer room is mostly generated by the server. The server processes too many external requests, which will cause it to generate a lot of heat. The amount of heat will greatly affect the loss of air conditioning resources in the computer room.

[0005] The optimization method for the server in the computer room to handle external requests is mainly to use load balancing. This method tends to focus on the processing capacity of each server to evenly distribute the number of external requests handled by the server, but does not take into account the heat that may be generated during the server processing. This will undoubtedly cause the computer room linkage air conditioner to consume more resources to reduce the temperature in the computer room;

[0006] In order to solve the above problems, the present invention proposes a solution. Summary of the invention

[0007] The purpose of the present invention is to provide a computer room air conditioning linkage management system, in order to solve the problem that the prior art does not combine linkage air conditioning temperature control with server load balancing, resulting in excessive waste of linkage air conditioning energy due to excessive unnecessary heat generated by each server processing request not being considered in load balancing;

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] The computer room air conditioning linkage management system includes:

[0010] A balancing and adjusting module, used for evenly distributing requests from the outside to all servers in the computer room, the balancing and adjusting module includes a balancing distribution unit and a balancing correction unit;

[0011] When an external request arrives, the load balancing unit uses the smooth weighted round-robin algorithm to select the optimal server for it, and binds the external request with the IP address of the selected optimal server to obtain the load balancing data of the external request.

[0012] The load balancing correction unit temporarily stores the load balancing data of all external requests, and performs load balancing correction on the load balancing data of all external requests temporarily stored during the current load balancing correction period according to the preset load balancing correction rules every other load balancing correction period.

[0013] The monitoring module is used to collect the temperature data and load data of the servers in the computer room for real-time monitoring.

[0014] The data analysis module analyzes the temperature data and load data of the servers in the computer room to obtain the balanced characteristic load of all servers in the computer room.

[0015] Further, in the current load balancing correction period, the specific preset load balancing correction rules for the load balancing correction unit to perform load balancing correction on the load balancing data of all external requests temporarily stored during the current load balancing correction period are as follows:

[0016] S11: Traverse the load balancing data of all external requests temporarily stored during the current load balancing correction period, and mark the servers containing IP addresses therein as F1, F2,..., Ff respectively, where f ≥ 1.

[0017] S12: Calculate and obtain the load balancing overload J1 of the current load balancing correction period according to the preset calculation rules.

[0018] S13: Compare the magnitudes of J1, Jmax, and Jmin. If J1 < Jmin, it is determined that the servers processing external requests during the current load balancing correction period will not affect the temperature in the computer room, and no processing is performed.

[0019] S14: If J1 > Jmax, it is determined that the servers processing external requests during the current load balancing correction period cannot be balanced, and no processing is performed.

[0020] S15: If Jmin ≤ J1 ≤ Jmax, the load balancing correction is performed according to the following steps, specifically as follows:

[0021] Step 1: Re-label all load balancing overloads greater than P4 in I1, I2,..., If in descending order as K1, K2,..., Kk, where 1 ≤ k < f.

[0022] Step 2: Obtain all balanced overloads less than 0 from I1, I2, ..., If, and recalibrate the balanced overloads to L1, L2, ..., Lf in order from small to large;

[0023] Step 3: If K>L, proceed as follows:

[0024] SS1: extract K1 external request balancing data from all external request balancing data temporarily stored in the current balancing correction period, and the K1 external request balancing data all contain the IP address of the server corresponding to the balancing overload K1;

[0025] SS2: The server corresponding to the balanced overload L1 is preferentially selected as the replacement server. L1 external request balanced data is randomly selected from the K1 external request balanced data. The IP address of the server contained in the L1 external request balanced data is replaced with the IP address of the server corresponding to the balanced overload L1. After the replacement is completed, the server corresponding to the balanced overload L2 is selected as the replacement server in the order of L1, L2, ..., Lf, until the IP addresses of the servers in the K1 external request balanced data are completely replaced.

[0026] SS3: In the order of K1, K2, ..., Kk, K2 external request balancing data are extracted again from all external request balancing data temporarily stored in the current balancing correction period. The K2 external request balancing data all contain the IP address of the server corresponding to the balancing overload K2.

[0027] SS4: According to SS2 and SS3, the IP addresses of the servers included in the balancing data of the K2 external requests are replaced. It should be noted that when replacing the IP addresses of the servers, the selection of the replacement servers is still in the order of L1, L2, ..., Lf. For the replacement servers whose corresponding balancing data has been replaced by the same amount as their balancing overload, they are no longer selected as replacement servers.

[0028] SS5: According to SS2 to SS4, in the order of K1, K2, ..., Kk, corresponding numbers of K3, K4, ..., Kk of external request balancing data are extracted from all external request balancing data temporarily stored in the current balancing correction period, and the IP addresses of the servers therein are replaced until the number of replaced server IP addresses in the extracted external request balancing data reaches L;

[0029] For the remaining balanced data of external requests that have been extracted but not replaced, all external requests contained therein are extracted, and a smooth weighted polling algorithm is used to reselect the optimal server for generating the corresponding balanced data of external requests;

[0030] Step 4: If K≤L, then according to the same replacement method as SS1 to SS5, the corresponding number of K1, K2, K3, K4, ..., Kk external request balance data will be extracted from the balance data of all external requests temporarily stored in the current balance correction period and the IP addresses of the servers therein will be replaced until the IP addresses of the servers in all the extracted external request balance data are replaced;

[0031] The Jmin and Jmax are the preset minimum and maximum thresholds for equalization correction determination. The interval duration of one equalization correction cycle is P1, and P1 is the preset equalization correction duration threshold.

[0032] Beneficial effects of the present invention:

[0033] The present invention monitors and collects temperature data and load data of servers in a computer room in real time by setting a monitoring module. The data analysis module analyzes the number of external request processing that generates heat that affects the temperature rise in the computer room based on the temperature and load data of the servers in the computer room, and obtains the balanced characteristic load of each server. The balanced distribution unit selects the optimal server for the external request using a smooth weighted round-robin algorithm. The balanced correction unit determines the number of all external requests stored in an interval correction period. There are three determination results, namely, the external request will not affect the temperature in the computer room, the external request needs to be controlled by the linkage air conditioning, and the impact of the external request on the temperature in the computer room can be corrected by balancing. According to the determination of the external request that needs to be controlled by the linkage air conditioning and the impact of the external request on the temperature in the computer room, the external request is balanced to other servers. In this way, the linkage air conditioning temperature adjustment and the load balancing of the server are combined to avoid excessive waste of linkage air conditioning energy due to the load balancing not taking into account the heat generated in the processing requests of each server. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The present invention will be further described below in conjunction with the accompanying drawings.

[0035] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] like Figure 1 As shown, the computer room air conditioning linkage management system includes a balancing adjustment module, a monitoring module and a linkage air conditioning adjustment module;

[0038] The balancing and adjusting module is used to evenly distribute requests from the outside to all servers in the computer room, wherein the requests from the outside refer to requests from external clients, and the balancing and adjusting module includes a balancing distribution unit and a balancing correction unit;

[0039] The balanced distribution unit pre-stores a basic server array, the basic server array includes a elements, one element corresponds to a server in the computer room, and a is the total number of servers in the computer room;

[0040] Each element in the basic server array corresponds to a basic allocation weight and a current weight. The basic allocation weight is a different weight assigned to each element by the computer room manager according to the processing capacity of the server corresponding to the element, so that it can receive service requests with a corresponding weight number;

[0041] The initial current weight is 0, and the current weight is dynamically updated;

[0042] When an external request arrives, the balancing allocation unit uses a smooth weighted polling algorithm to select the best server for it, binds the external request and the IP address of the best server selected for it to obtain the balancing data of the external request, and transmits it to the balancing correction unit;

[0043] In the process of selecting the optimal server, for each element, the current weight corresponding to the element is first added to the basic allocation weight of the element and the final value is updated to the current weight of the element. Then, the current weight corresponding to each element is compared, and the server corresponding to the element with the largest current weight is selected as the optimal server. After the selection is completed, the current weight of the optimal server is subtracted from the total weight, and the final value is updated to the current weight of the optimal server. The total weight here is the sum of the basic allocation weights of all elements.

[0044] The equalization correction unit temporarily stores the equalization data of the external request after receiving the transmitted data;

[0045] The equilibrium correction unit performs equilibrium correction on the equilibrium data of all external requests temporarily stored within an equilibrium correction period every other equilibrium correction period;

[0046] For the current equilibrium correction period, the equilibrium correction unit performs equilibrium correction on the equilibrium data of all external requests temporarily stored within the current equilibrium correction period according to a preset equilibrium correction rule, specifically as follows:

[0047] S11: Traverse the equilibrium data of all external requests temporarily stored within the current equilibrium correction period, and mark the servers containing ip addresses therein as F1, F2,..., Ff respectively, where f≥1;

[0048] S12: Calculate and obtain the equilibrium overload J1 of the current equilibrium correction period according to a preset calculation rule, specifically as follows:

[0049] S121: Obtain the quantity G1 of the ip addresses of the server F1 contained in the equilibrium data of all external requests temporarily stored within the current equilibrium correction period;

[0050] S122: Obtain the equilibrium characteristic load H1 of the server F1 currently stored within the equilibrium correction unit;

[0051] S123: Calculate the equilibrium overload I1 of the server F1 within the current equilibrium correction period using the formula I1 = H1 - G1;

[0052] S124: Calculate and obtain the equilibrium overloads I1, I2,..., If of the servers F1, F2,..., Ff within the current equilibrium correction period respectively according to S121 to S123;

[0053] S125: Compare the magnitudes of I1, I2,..., If and P4 in sequence, obtain the average value of all equilibrium overloads greater than P4 among them, and calibrate it as the equilibrium overload of the current equilibrium correction period, marked as J1, where P4 is a preset overload standard screening threshold and is a positive value;

[0054] S13: Compare the magnitudes of J1, Jmax, and Jmin. If J1 < Jmin, it is determined that the servers processing external requests within the current equilibrium correction period will not affect the temperature in the computer room, and no processing is performed;

[0055] S14: If J1 > Jmax, it is determined that the servers processing external requests within the current equilibrium correction period need to be controlled through linkage with the air conditioner, and no processing is performed;

[0056] S15: If Jmin ≤ J1 ≤ Jmax, perform equilibrium correction according to the following steps, specifically as follows:

[0057] Step 1: Recalibrate all balanced overloads greater than P4 in I1, I2, ..., If in descending order to K1, K2, ..., Kk, 1≤k <f;

[0058] Step 2: Obtain all balanced overloads less than 0 from I1, I2, ..., If, and recalibrate the balanced overloads to L1, L2, ..., Lf in order from small to large;

[0059] Step 3: If K>L, all externally requested balancing data temporarily stored in the current balancing correction period are processed according to the preset first processing rule, as follows:

[0060] SS1: extract K1 external request balancing data from all external request balancing data temporarily stored in the current balancing correction period, and the K1 external request balancing data all contain the IP address of the server corresponding to the balancing overload K1;

[0061] SS2: The server corresponding to the balanced overload L1 is preferentially selected as the replacement server. L1 external request balanced data is randomly selected from the K1 external request balanced data. The IP address of the server contained in the L1 external request balanced data is replaced with the IP address of the server corresponding to the balanced overload L1. After the replacement is completed, the server corresponding to the balanced overload L2 is selected as the replacement server in the order of L1, L2, ..., Lf, until the IP addresses of the servers in the K1 external request balanced data are completely replaced.

[0062] SS3: In the order of K1, K2, ..., Kk, K2 external request balancing data are extracted again from all external request balancing data temporarily stored in the current balancing correction period. The K2 external request balancing data all contain the IP address of the server corresponding to the balancing overload K2.

[0063] SS4: According to SS2 and SS3, the IP addresses of the servers included in the balancing data of the K2 external requests are replaced. It should be noted that when replacing the IP addresses of the servers, the selection of the replacement servers is still in the order of L1, L2, ..., Lf. For the replacement servers whose corresponding balancing data has been replaced by the same amount as their balancing overload, they are no longer selected as replacement servers.

[0064] SS5: According to SS2 to SS4, in the order of K1, K2, ..., Kk, corresponding numbers of K3, K4, ..., Kk of external request balancing data are extracted from all external request balancing data temporarily stored in the current balancing correction period, and the IP addresses of the servers therein are replaced until the number of replaced server IP addresses in the extracted external request balancing data reaches L;

[0065] For the remaining balanced data of external requests that have been extracted but not replaced, all external requests contained therein are extracted, and a smooth weighted polling algorithm is used to reselect the optimal server for generating the corresponding balanced data of external requests;

[0066] The balance correction unit transmits the balance data of the external requests of the server whose IP address is changed or the optimal server is reselected temporarily stored in the current balance correction period to the corresponding server based on the IP address of the server contained therein, and the corresponding server receives and processes the external request;

[0067] Step 4: If K≤L, all externally requested balancing data temporarily stored in the current balancing correction period are processed according to the preset second processing rule, as follows:

[0068] According to the same replacement method as SS1 to SS5, the corresponding number K1, K2, K3, K4, ..., Kk of external request balancing data are extracted from the balancing data of all external requests temporarily stored in the current balancing correction period, and the IP addresses of the servers therein are replaced until the IP addresses of the servers in all the extracted external request balancing data are replaced;

[0069] The balance correction unit transmits the balance data of the external requests temporarily stored in the current balance correction period and having changed IP addresses to the corresponding servers based on the IP addresses of the servers contained therein, and the corresponding servers receive and process the external requests;

[0070] The balancing correction unit transmits the balancing data of the external requests that have not been replaced or reselected in the current balancing correction cycle to the corresponding server based on the IP address of the server contained therein, and the corresponding server receives and processes the external request;

[0071] The Jmin and Jmax are the preset minimum and maximum thresholds for equalization correction determination, and the interval length of one equalization correction cycle is P1, and P1 is the preset equalization correction duration threshold;

[0072] The linked air-conditioning adjustment module is used to perform linked control on the air conditioners in the computer room. In an embodiment of the invention, the linked air-conditioning adjustment module monitors the temperature and humidity in the computer room in real time, and keeps the temperature and humidity in the computer room within their corresponding preset threshold ranges;

[0073] The monitoring module is used to monitor the working data of the servers in the computer room in real time. The monitoring module includes a first monitoring unit and a second monitoring unit. The first monitoring unit obtains the temperature data of all the servers in the computer room through real-time monitoring;

[0074] The second monitoring unit obtains the load data of all the servers in the computer room through real-time monitoring. The load data of one server refers to the number of requests from the outside processed by the server;

[0075] The data analysis module is used to analyze the temperature data and load data of each server periodically. The specific analysis steps are as follows:

[0076] S21: First, select a server in the computer room as the server to be analyzed;

[0077] S22: Calculate and obtain the load limit B1 and the average load D1 of the server to be analyzed in an analysis period according to the preset calculation rules, as follows:

[0078] S221: Obtain the number of external requests processed simultaneously by the server to be analyzed at each moment within an analysis period. In the order from far to near according to the distance of each moment from the current moment, mark the number of external requests processed simultaneously at the corresponding moment as A1, A2,..., Aa, where a≥1;

[0079] S222: Use the formula to calculate and obtain the discrete value B1 of the number of external requests processed simultaneously by the server to be analyzed at each moment within the analysis period. Compare B1 with B. If B1≥B, then delete the corresponding Ab in the order from largest to smallest according to |Ab - A|, and calculate the discrete value B1 of the remaining Ab, and compare B1 with B again until B1 < B. B is the discrete value threshold of the number of external requests processed simultaneously at the same preset moment, and A is the average value of the remaining Ab participating in the discrete value calculation, which is re-designated as the average load of the server to be analyzed in this analysis period, marked as C1;

[0080] In an embodiment of the present invention, the selection of an analysis period satisfies the following conditions: the time length of the analysis period is less than or equal to P2, and the heat generation of the server to be analyzed within the analysis period is greater than or equal to P3. P2 is the preset server heat generation time threshold, and P3 is the preset server heat generation threshold;

[0081] S23: According to S22, calculate and obtain the average load amounts B1, B2, ..., Bt of the servers to be analyzed in t analysis periods in sequence.

[0082] S24: Use the formula 1 ≤ d ≤ t to calculate and obtain the discrete value D1 of the average load amounts B1, B2, ..., Bt of the servers to be analyzed in t analysis periods, and compare the magnitudes of D1 and D.

[0083] If D1 ≥ D, then in the order from largest to smallest of |Bd - C|, delete the corresponding Bd in sequence, calculate the discrete value D1 of the remaining Bd, and compare the magnitudes of D1 and D again until D1 < D. Here, D is the discrete value threshold of the average load amount of the servers to be analyzed in the preset t analysis periods, and C is the average value of Bd participating in the calculation of the remaining discrete value. Redefine it as the balanced characteristic load amount of the server to be analyzed, and mark it as E1.

[0084] S24: Take each server in the computer room as the server to be analyzed in sequence according to S21 to S23, calculate and obtain the balanced characteristic load amount corresponding to each server in the computer room, and transmit it to the balance correction unit for update and storage.

[0085] In the description of the specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0086] The above content is only an example and illustration of the present invention. Those skilled in the art of the present technology make various modifications or supplements to the described specific embodiments or use similar methods for substitution. As long as they do not deviate from the invention or exceed the scope defined by the claims of the present invention, they should all fall within the protection scope of the present invention.

[0087] The above has described a specific embodiment of the present invention in detail, but the content described is only the preferred embodiment of the present invention and cannot be considered as used to limit the implementation scope of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the patent coverage scope of the present invention.

Claims

1. The computer room air conditioning linkage management system is characterized by: Including: An equilibrium adjustment module for evenly distributing requests from the outside to all servers in the computer room. The equilibrium adjustment module includes an equilibrium distribution unit and an equilibrium correction unit; When an external request arrives, the equilibrium distribution unit uses the smooth weighted round-robin algorithm to select the optimal server for it, and binds the external request and the IP address of the selected optimal server to obtain the equilibrium data of the external request; The equilibrium correction unit temporarily stores the equilibrium data of all external requests, and performs equilibrium correction on the equilibrium data of all external requests temporarily stored within the equilibrium correction period according to the preset equilibrium correction rules every other equilibrium correction period; A monitoring module for collecting temperature data and load data of the servers in the computer room through real-time monitoring; A data analysis module analyzes the temperature data and load data of the servers in the computer room to obtain the equilibrium characteristic load of all servers in the computer room; During the current equilibrium correction period, the specific preset equilibrium correction rules for the equilibrium correction unit to perform equilibrium correction on the equilibrium data of all external requests temporarily stored within the current equilibrium correction period are as follows: S11: Traverse the equilibrium data of all external requests temporarily stored within the current equilibrium correction period, and mark the servers containing IP addresses therein as F1, F2,..., Ff respectively, where f≥1; S12: Calculate and obtain the equilibrium overload J1 of the current equilibrium correction period according to the preset calculation rules, specifically as follows: S121: Obtain the number G1 of the IP addresses of the server F1 contained in the equilibrium data of all external requests temporarily stored within the current equilibrium correction period; S122: Obtain the equilibrium characteristic load H1 of the server F1 currently stored in the equilibrium correction unit; S123: Use the formula I1 = H1 - G1 to calculate the equilibrium overload I1 of the server F1 during the current equilibrium correction period; S124: Calculate and obtain the equilibrium overloads I1, I2,..., If of the servers F1, F2,..., Ff during the current equilibrium correction period respectively according to S121 to S123; S125: Compare the sizes of I1, I2,..., If and P4 in turn, obtain the average value of all equilibrium overloads greater than P4 among them, and calibrate it as the equilibrium overload of the current equilibrium correction period, marked as J1. The P4 is a preset overload standard screening threshold and is a positive value; S13: Compare the sizes of J1, Jmax, and Jmin. If J1 < Jmin, it is determined that the servers in the current equilibrium correction period processing requests from the outside will not affect the temperature in the computer room, and no processing is performed; S14: If J1 > Jmax, it is determined that the servers in the current equilibrium correction period cannot balance the processing of external requests, and no processing is performed; S15: If Jmin ≤ J1 ≤ Jmax, perform equilibrium correction according to the following steps, specifically as follows: Step 1: Re-calibrate all equilibrium overloads greater than P4 among I1, I2,..., If in descending order as K1, K2,..., Kk, where 1≤k<f; Step 2: Obtain all balanced overloads less than 0 from I1, I2, ..., If, and recalibrate the balanced overloads to L1, L2, ..., Lf in order from small to large; Step 3: If K>L, all externally requested balancing data temporarily stored in the current balancing correction period are processed according to the preset first processing rule. The preset first processing rule is as follows: SS1: extract K1 external request balancing data from all external request balancing data temporarily stored in the current balancing correction period, and the K1 external request balancing data all contain the IP address of the server corresponding to the balancing overload K1; SS2: The server corresponding to the balanced overload L1 is preferentially selected as the replacement server. L1 external request balanced data is randomly selected from the K1 external request balanced data. The IP address of the server contained in the L1 external request balanced data is replaced with the IP address of the server corresponding to the balanced overload L1. After the replacement is completed, the server corresponding to the balanced overload L2 is selected as the replacement server in the order of L1, L2, ..., Lf, until the IP addresses of the servers in the K1 external request balanced data are completely replaced. SS3: In the order of K1, K2, ..., Kk, K2 external request balancing data are extracted again from all external request balancing data temporarily stored in the current balancing correction period. The K2 external request balancing data all contain the IP address of the server corresponding to the balancing overload K2. SS4: According to SS2 and SS3, the IP addresses of the servers included in the balancing data of the K2 external requests are replaced. It should be noted that when replacing the IP addresses of the servers, the selection of the replacement servers is still in the order of L1, L2, ..., Lf. For the replacement servers whose corresponding balancing data has been replaced by the same amount as their balancing overload, they are no longer selected as replacement servers. SS5: According to SS2 to SS4, in the order of K1, K2, ..., Kk, corresponding numbers of K3, K4, ..., Kk of external request balancing data are extracted from all external request balancing data temporarily stored in the current balancing correction period, and the IP addresses of the servers therein are replaced until the number of replaced server IP addresses in the extracted external request balancing data reaches L; For the remaining balanced data of external requests that have been extracted but not replaced, all external requests contained therein are extracted, and a smooth weighted polling algorithm is used to reselect the optimal server for generating the corresponding balanced data of external requests; Step 4: If K≤L, all externally requested balancing data temporarily stored in the current balancing correction period are processed according to the preset second processing rule. The preset second processing rule is as follows: According to the same replacement method as SS1 to SS5, the corresponding number K1, K2, K3, K4, ..., Kk of external request balancing data are extracted from the balancing data of all external requests temporarily stored in the current balancing correction period, and the IP addresses of the servers therein are replaced until the IP addresses of the servers in all the extracted external request balancing data are replaced; The Jmin and Jmax are the preset minimum and maximum thresholds for equalization correction determination. The interval duration of one equalization correction cycle is P1, and P1 is the preset equalization correction duration threshold.

2. The computer room air conditioning linkage management system according to claim 1, characterized in that: External requests refer to requests from external clients.

3. The computer room air conditioning linkage management system according to claim 1, characterized in that: The load data of a server refers to the number of requests from the outside that the server processes.

4. The computer room air conditioning linkage management system according to claim 1, characterized in that: The balance correction unit transmits the balance data of the external requests with changed IP addresses temporarily stored in the current balance correction period to the corresponding servers based on the IP addresses of the servers contained therein, and the corresponding servers receive and process the external requests.

5. The computer room air conditioning linkage management system according to claim 1, characterized in that: The balancing correction unit transmits the balancing data of the external requests that have not been replaced or reselected in the current balancing correction cycle to the corresponding server based on the IP address of the server contained therein, and the corresponding server receives and processes the external request.

6. The computer room air conditioning linkage management system according to claim 1, characterized in that: It also includes a linkage air conditioning adjustment module for linkage control of the air conditioner in the computer room. The linkage air conditioning adjustment module monitors the temperature and humidity in the computer room in real time, and keeps the temperature and humidity in the computer room within the corresponding preset threshold range.

Citation Information

Patent Citations

  • Load balancing mechanism for WEB server in electric power scheduling system

    CN102882959A

  • Server, load balancer as well as server load balancing method and system

    CN105208133A