Server load balancing method based on comprehensive score

Abstract

The invention relates to the technical field of computers, and discloses a server load balancing method based on a comprehensive score, computer equipment and a computer readable storage medium in order to solve the problem that in an existing server load balancing method, parameters for determining a server operation state score are not comprehensive enough. The method comprises the following steps: acquiring hardware performance parameters, environmental conditions, a current load state, the number of connection requests successfully processed in unit time and historical fault data of each server; determining a comprehensive score of each server according to the hardware performance parameters, the environmental conditions, the current load state, the number of connection requests successfully processed in unit time and historical fault data; and sending the current task to a target server for processing based on the comprehensive score. By adopting the method, the performance of the server is improved, and the method can cope with complex and changeable operating environments.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more specifically, to a server load balancing method based on comprehensive scoring, a computer device, and a computer-readable storage medium. Background Art

[0002] For server load balancing, ensuring efficient and stable resource allocation is crucial to improving system performance and user experience.

[0003] Existing server load balancing methods all score the operating status of each server based on the server's throughput, CPU occupancy, memory occupancy, and network bandwidth occupancy, and then send the pending tasks to the corresponding server for processing according to the score of each server.

[0004] However, this server load balancing method still has the following defects: it does not take into account servers running in complex environments, and the parameters used to determine the server operation status score are not comprehensive enough. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a server load balancing method based on comprehensive scoring, a computer device and a computer-readable storage medium, which will improve server performance and can cope with complex and changeable operating environments.

[0006] To achieve the above object, according to a first aspect of the present invention, a server load balancing method based on comprehensive scoring is provided, which is applied to a load balancer. The method comprises:

[0007] Obtain the hardware performance parameters, environmental conditions, current load status, number of successfully processed connection requests per unit time, and historical failure data of each server;

[0008] Determine the comprehensive score of each server based on hardware performance parameters, environmental conditions, current load status, number of successfully processed connection requests per unit time, and historical failure data;

[0009] Based on the comprehensive score, the current task is sent to the target server for processing.

[0010] Furthermore, determining a comprehensive score for each server based on hardware performance parameters, environmental conditions, current load status, the number of connection requests successfully processed per unit time, and historical failure data includes determining hardware configuration parameters based on hardware performance parameters; determining environmental factor parameters based on environmental conditions; determining a first connection parameter, a second connection parameter, and a third connection parameter based on the current load status; determining a throughput ratio based on the number of connection requests successfully processed per unit time; determining a failure rate based on historical failure data; and calculating a comprehensive score for each server based on the hardware configuration parameters, environmental factor parameters, the first connection parameter, the second connection parameter, the third connection parameter, the throughput ratio, and the failure rate.

[0011] Further, a comprehensive score of each server is calculated according to the hardware configuration parameter, the environmental factor parameter, the first connection parameter, the second connection parameter, the third connection parameter, the throughput ratio and the failure rate, including calculating the comprehensive score of each server according to the following formula:

[0012]

[0013] In the formula, A1, B1 and C1 are the first connection parameter, the second connection parameter and the third connection parameter respectively, F1 is the environmental factor parameter, G1 is the hardware configuration parameter, D1 is the throughput ratio, E1 is the failure rate, A is the comprehensive score of each server, PA, PB, PE, PF and PG are the weights of the first connection parameter, the second connection parameter, the failure rate, the environmental factor parameter, and the weights of the hardware configuration parameter respectively, and PA+PB+PE+PF+PG=1.

[0014] Furthermore, the hardware performance parameters include CPU performance, memory capacity, and disk read and write speed. According to the hardware performance parameters, the hardware configuration parameters are determined, including calculating the hardware configuration parameters according to the following formula:

[0015]

[0016] In the formula, C is the CPU clock frequency, Ccores is the number of CPU cores, Rcpu is the reference value of CPU performance, M is the memory capacity, Rm is the reference value of memory capacity, S is the average read and write speed of the storage device, Rs is the reference value of the average read and write speed of the storage device, G1 is the hardware configuration parameter, and W is the reference value of the average read and write speed of the storage device. C , W R and W S are the weights of CPU performance, memory capacity, and disk read and write speed, and W C +W R +W S =1.

[0017] Environmental conditions include the temperature, humidity and bandwidth of the equipment room. According to the environmental conditions, the environmental factor parameters are determined, including the calculation of the environmental factor parameters according to the following formula:

[0018]

[0019] Where T is the temperature of the computer room, H is the humidity of the computer room, P is the bandwidth of the computer room, Pmax is the maximum bandwidth of the computer room, F1 is the environmental factor parameter, and W T , W H and W P are the weights of the temperature, humidity and bandwidth of the computer room, and W T +W H +W P =1.

[0020] Further, according to the current load status, the first connection parameter, the second connection parameter and the third connection parameter are determined, including the first connection parameter being the number of connection requests received by the server per unit time; the second connection parameter being the number of connection requests processed by the server per unit time; and the third connection parameter being the number of connection requests currently being processed by the server.

[0021] Furthermore, the throughput ratio is determined based on the number of connection requests successfully processed per unit time, including:

[0022]

[0023] Where Tc is the number of connection requests successfully processed by the server per unit time, Tmax is the maximum throughput of the server, and D1 is the throughput ratio of the server.

[0024] Furthermore, the historical fault data includes fault frequency and average fault recovery time. The failure rate is determined based on the historical fault data, including using a trained fault prediction model to predict the failure rate of the server in the next time period based on the historical fault data.

[0025] According to a second aspect of the present invention, there is also provided a computer device, which includes a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to implement the steps of any one of the above methods.

[0026] According to a third aspect of the present invention, there is also provided a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0027] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0028] The present invention provides a server load balancing method based on comprehensive scoring. The method obtains the hardware performance parameters, environmental conditions, current load status, number of connection requests successfully processed per unit time, and historical fault data of each server in real time, determines the comprehensive score of each server according to these five factors, and selects the server most suitable for the current task for scheduling based on the comprehensive score to achieve load balancing, optimize resource utilization, reduce response time, and improve overall system stability, thereby improving server performance and being able to cope with complex and changeable operating environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 A flow chart of a server load balancing method based on comprehensive scoring provided in an embodiment of the present application;

[0031] Figure 2 A schematic diagram of a process for multiple servers to report comprehensive scores to a load balancer provided in an embodiment of the present application;

[0032] Figure 3 A flow chart of the steps for determining a load balancing decision provided in an embodiment of the present application;

[0033] Figure 4 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0035] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0036] like Figure 1 As shown, a server load balancing method based on comprehensive scoring is provided, which is applied to a load balancer, and the load balancer and multiple servers are communicated and connected. The method includes the following steps:

[0037] Step 101, obtaining hardware performance parameters, environmental conditions, current load status, number of connection requests successfully processed per unit time, and historical fault data of each server.

[0038] Step 102, determining a comprehensive score for each server based on hardware performance parameters, environmental conditions, current load status, the number of connection requests successfully processed per unit time, and historical failure data.

[0039] Exemplarily, hardware configuration parameters are determined based on hardware performance parameters; environmental factor parameters are determined based on environmental conditions; first connection parameters, second connection parameters and third connection parameters are determined based on the current load status; throughput ratio is determined based on the number of connection requests successfully processed per unit time; and failure rate is determined based on historical failure data.

[0040] Then, a comprehensive score of each server is calculated based on the hardware configuration parameters, environmental factor parameters, first connection parameters, second connection parameters, third connection parameters, throughput ratio and failure rate.

[0041] Step 103, based on the comprehensive score, the current task is sent to the target server for processing.

[0042] Among them, the target server is the server that is most suitable for the current task and can best meet the current task requirements.

[0043] In the above-mentioned server load balancing method based on comprehensive scoring, the hardware performance parameters, environmental conditions, current load status, number of connection requests successfully processed per unit time, and historical fault data of each server are obtained in real time, and the comprehensive score of each server is determined according to these five factors. Based on the comprehensive score, the server most suitable for the current task is selected for scheduling to achieve load balancing, optimize resource utilization, reduce response time and improve overall system stability, thereby improving server performance and being able to cope with complex and changing operating environments.

[0044] In one embodiment, Figure 2 As shown, N servers are connected to the load balancer. Each server calculates the comprehensive score regularly and uploads the comprehensive score to the load balancer. The load balancer records the comprehensive score of each server. Specifically, the steps for each server to calculate the comprehensive score are as follows:

[0045] (I) Determine hardware configuration parameters (G1)

[0046] The hardware performance parameters of the server include CPU performance, memory capacity, disk read / write speed, network bandwidth, etc. The hardware performance of the server is evaluated based on the hardware performance parameters of the server. Among them, CPU performance includes CPU clock frequency, number of CPU cores, CPU usage, etc., memory capacity includes memory capacity and memory usage, etc., and network bandwidth includes network bandwidth utilization, etc.

[0047] In one embodiment, the hardware's support for load processing is comprehensively evaluated based on CPU performance, memory capacity, and disk read / write speed, and hardware configuration parameters are determined, including calculating the hardware configuration parameters according to the following formula:

[0048]

[0049] Where C is the CPU clock frequency (e.g., in GHz), Ccores is the number of CPU cores, Rcpu is the reference value of CPU performance (e.g., the performance index of common mid-to-high-end CPUs), M is the memory capacity, Rm is the reference value of larger memory capacity (e.g., 16GB or 32GB), S is the average read and write speed of the storage device (e.g., in MB / s), Rs is the reference value of the average read and write speed of a storage device with good performance, G1 is the hardware configuration parameter, and W is the reference value of the average read and write speed of a storage device with good performance. C , W R and W S are the weights of CPU performance, memory capacity, and disk read and write speed, and W C +W R +W S =1.

[0050] (II) Dynamic Connection Management

[0051] Monitor the current load status of the server to determine the number of connection requests received by the server per unit time (i.e., the first connection parameter A1), the number of connection requests processed by the server per unit time (i.e., the second connection parameter B1), and the number of connection requests currently being processed by the server (i.e., the third connection parameter C1). By monitoring the current load status of the server, the server can be prevented from being overloaded.

[0052] In other embodiments, monitoring the current load status of the server also includes determining the current number of active connections, the average processing time of online connections, predicting future connection needs, etc.

[0053] The first connection parameter A1 refers to the number of connection requests received per unit time, regardless of whether the system can fully process them. These connection requests may be in different states, some may have just been initiated, some may be waiting to be processed, and some may not have started processing due to system busyness. For example, within 1 second, 200 clients send HTTP connection requests to the server, then the number of connection requests received per unit time (1 second) A1 is 200. The first connection parameter A1 is used to reflect the current connection processing capability of the server.

[0054] The second connection parameter B1 refers to the number of connection requests that the system can process (including successful and failed processing) in a unit time. For example, within 1 second, 200 clients send HTTP connection requests to the server, and the server processes 130 connection requests. Then the number of connection requests B1 processed by the server in a unit time (1 second) is 130. The second connection parameter B1 is used to reflect the processing efficiency of the server.

[0055] The third connection parameter C1 is used to reflect the processing efficiency of the server and is directly related to the instantaneous load of the server.

[0056] (III) Determine the environmental factor parameters (i.e. F1)

[0057] The environmental conditions of the server are the environmental conditions of the computer room where the server is located, including temperature (ie T), humidity (ie H), bandwidth (ie P), power stability, risk of harmful particles entering the computer room, and heat dissipation efficiency of the equipment. Among them, when the temperature of the computer room is too high or too low, it will affect the performance and stability of the server; inappropriate humidity may cause electronic components to fail; the bandwidth of the computer room is used to limit the data transmission speed and processing volume. According to the environmental conditions of the computer room where the server is located, the impact of the environment on the server performance is evaluated.

[0058] In one embodiment, according to the environmental conditions, calculating the environmental factor parameters includes:

[0059]

[0060] Where Pmax is the maximum bandwidth of the computer room, F1 is the environmental factor parameter, and W T , W H and W P are the weights of the temperature, humidity and bandwidth of the computer room, and W T +W H +W P =1. For temperature fluctuations and humidity changes, the larger the value, the more unstable the computer room environment is. Therefore, the above formula uses and To convert larger temperature fluctuations and humidity changes into smaller scores to reflect their negative impact on the environment.

[0061] For bandwidth, use Normalize it so that it is between 0 and 1. The larger the bandwidth, the higher the score. P is the actual bandwidth currently used by the computer room. It is used to measure the data transmission capacity of the overall network of the computer room. From the perspective of the evaluation of the computer room environmental factors, it reflects the overall network load of the computer room, which affects the data transmission efficiency and network performance of all devices in the computer room. The value of P will change dynamically with the network activity of the equipment in the computer room. For example, when many servers in the computer room are performing data transmission operations at the same time, the value of P will increase; conversely, when the network activity is less, the value of P will decrease. Pmax is the maximum bandwidth of the computer room. It is a fixed value determined by the computer room network infrastructure during the construction or configuration phase, and represents the upper limit of the computer room network bandwidth. For example, if the maximum bandwidth specified by the computer room network access equipment is 20Gbps, then Pmax is 20Gbps. By comparing P and Pmax, we can understand the current load level of the computer room network, that is, the utilization rate of the computer room bandwidth. When When the value is close to 1, it means that the network in the computer room is close to full load, and network congestion and other problems may occur; If the value is small, it means that there is still a lot of remaining bandwidth in the computer room network and the network load is light.

[0062] (IV) Determine the server throughput ratio (i.e. D1)

[0063] The server throughput is a server operating status parameter that is used to measure the number of connections and data volume successfully processed by the server per unit time.

[0064] The number of connection requests successfully processed by the server per unit time Tc refers to the number of connection requests that the system can successfully process per unit time. It focuses on the actual processing capability of the system for connections, including the successful completion of a series of operations such as establishing connections, transmitting data, and removing connections. For example, if a Web server can successfully process 100 HTTP connection requests from clients within 1 second, then the number of connection requests successfully processed by the server per unit time (1 second) Tc is 100.

[0065] According to the number of connection requests successfully processed by the server per unit time (i.e. Tc) in the current actual operation state, the server throughput ratio is calculated, including:

[0066]

[0067] Where Tmax is the maximum throughput of the server, which is determined by monitoring the throughput of the server within a preset time period.

[0068] In other embodiments, evaluating the data processing capability of the server per unit time also includes the average time consumed in processing the connection.

[0069] Evaluate the server's data processing capabilities per unit time, especially the processing efficiency of complex requests, to improve the overall system throughput.

[0070] (V) Determine the failure rate (i.e. E1)

[0071] The failure rate (ie, E1) ranges from 0 to 1. When E1=0, it means that the server has no failures during this period and the reliability is extremely high. When E1 is closer to 1, the probability of server failure is greater and the reliability is lower.

[0072] In one embodiment, the historical fault data includes fault frequency and average fault recovery time. The failure rate is determined based on the historical fault data, including using a trained fault prediction model to predict the failure rate of the server in the next time period based on the historical fault data.

[0073] In one embodiment, the historical fault data includes mean time between failures and mean time to recover from failures. The failure rate is determined based on the historical fault data, including:

[0074]

[0075] In other embodiments, in addition to predicting the failure rate of the server in the next time period, it is also necessary to predict the failure recovery time of the server after a failure occurs in the next time period. By predicting the failure recovery time, the resilience of the server in the event of a failure can be evaluated to ensure that the business can quickly return to normal. For example, a server has a failure rate of 0.01 (i.e., 1 failure occurs every 100 operating cycles), but each failure takes 10 hours to recover. Compared with another server with a failure rate of 0.02, but each failure can be recovered in only 1 hour, the latter may have an advantage in terms of system availability.

[0076] Through historical failure data and real-time monitoring data, the possibility of server failure and recovery time are predicted to optimize resource allocation strategies.

[0077] (VI) Calculation of comprehensive score

[0078]

[0079] In the formula, A1, B1 and C1 are the first connection parameter, the second connection parameter and the third connection parameter respectively, F1 is the environmental factor parameter, G1 is the hardware configuration parameter, D1 is the throughput ratio, E1 is the failure rate, A is the comprehensive score of each server, PA, PB, PE, PF and PG are the weights of the first connection parameter, the second connection parameter, the failure rate, the environmental factor parameter and the hardware configuration parameter respectively, and PA+PB+PE+PF+PG=1. The weight is determined by the importance of different factors, for example, the first connection parameter accounts for 15%, the second connection parameter accounts for 15%, the failure rate accounts for 10%, the environmental factor parameter accounts for 20%, and the hardware configuration parameter accounts for 40%. The weight can be adjusted at any time according to the actual situation.

[0080] like Figure 3 As shown, the steps of determining the load balancing decision include the load balancer receiving the task, selecting the server with the highest comprehensive score (ie, the target server) from all servers according to the ranking of the comprehensive scores, and sending the task to the target server for processing.

[0081] The server load balancing method based on comprehensive scoring provided in this embodiment can comprehensively and dynamically evaluate the operating status of the server, effectively improve the server performance, and cope with complex and changeable operating environments.

[0082] The present application also provides a computer device, whose internal structure diagram can be as follows: Figure 4As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a server load balancing method based on a comprehensive score is implemented.

[0083] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0084] like Figure 4 As shown, the present application also provides a computer device, which includes a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps in the above-mentioned method embodiments.

[0085] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0086] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0087] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0088] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

[0089] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0090] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A server load balancing method based on comprehensive scoring, characterized in that: Applies to load balancers, including: Obtain the hardware performance parameters, environmental conditions, current load status, number of successfully processed connection requests per unit time, and historical failure data of each server; Determine a comprehensive score for each server according to the hardware performance parameters, the environmental conditions, the current load status, the number of connection requests successfully processed per unit time, and the historical failure data; Based on the comprehensive score, the current task is sent to the target server for processing.

2. The method according to claim 1, characterized in that Determining a comprehensive score of each server according to the hardware performance parameters, the environmental conditions, the current load status, the number of connection requests successfully processed per unit time, and the historical failure data includes: Determining hardware configuration parameters according to the hardware performance parameters; Determining environmental factor parameters according to the environmental conditions; Determining a first connection parameter, a second connection parameter, and a third connection parameter according to the current load state; Determining a throughput ratio according to the number of connection requests successfully processed within the unit time; Determining a failure rate based on the historical failure data; A comprehensive score of each server is calculated according to the hardware configuration parameters, the environmental factor parameters, the first connection parameters, the second connection parameters, the third connection parameters, the throughput ratio and the failure rate.

3. The method according to claim 2, characterized in that The calculating a comprehensive score of each server according to the hardware configuration parameter, the environmental factor parameter, the first connection parameter, the second connection parameter, the third connection parameter, the throughput ratio and the failure rate includes: The comprehensive score of each server is calculated according to the following formula: In the formula, A1, B1 and C1 are the first connection parameter, the second connection parameter and the third connection parameter respectively, F1 is the environmental factor parameter, G1 is the hardware configuration parameter, D1 is the throughput ratio, E1 is the failure rate, A is the comprehensive score of each server, PA, PB, PE, PF and PG are the weights of the first connection parameter, the second connection parameter, the failure rate, the environmental factor parameter, and the weights of the hardware configuration parameter respectively, and PA+PB+PE+PF+PG=1.

4. The method according to claim 2, characterized in that The hardware performance parameters include CPU performance, memory capacity, and disk read and write speed. The hardware configuration parameters are determined based on the hardware performance parameters, including: Calculate the hardware configuration parameters according to the following formula: In the formula, C is the CPU clock frequency, Ccores is the number of CPU cores, Rcpu is the reference value of CPU performance, M is the memory capacity, Rm is the reference value of memory capacity, S is the average read and write speed of the storage device, Rs is the reference value of the average read and write speed of the storage device, G1 is the hardware configuration parameter, and W is the reference value of the average read and write speed of the storage device. C , W R and W S are the weights of CPU performance, memory capacity, and disk read and write speed, and W C +W R +W S =1.

5. The method according to claim 2, characterized in that The environmental conditions include the temperature, humidity and bandwidth of the computer room. The environmental factor parameters are determined according to the environmental conditions, including: Calculate the environmental factor parameters according to the following formula: Where T is the temperature of the computer room, H is the humidity of the computer room, P is the bandwidth of the computer room, Pmax is the maximum bandwidth of the computer room, F1 is the environmental factor parameter, and W T , W H and W P are the weights of the temperature, humidity and bandwidth of the computer room, and W T +W H +W P =1.

6. The method according to claim 2, characterized in that The determining, according to the current load state, a first connection parameter, a second connection parameter, and a third connection parameter comprises: The first connection parameter is the number of connection requests received by the server per unit time; The second connection parameter is the number of connection requests processed by the server per unit time; The third connection parameter is the number of connection requests currently being processed by the server.

7. The method according to claim 2, characterized in that Determining the throughput ratio according to the number of connection requests successfully processed within the unit time includes: Where Tc is the number of connection requests successfully processed by the server per unit time, Tmax is the maximum throughput of the server, and D1 is the throughput ratio of the server.

8. The method according to claim 2, characterized in that The historical fault data includes fault occurrence frequency and mean fault recovery time. The determining of the fault rate according to the historical fault data includes: The trained fault prediction model is used to predict the failure rate of the server in the next time period based on the historical fault data.

9. A computer device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images