Server power-on method and device, electronic equipment and storage medium

Abstract

The invention provides a server power-on method and device, electronic equipment and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: constructing a server power-on sequence through an ant colony algorithm according to the pheromone quantity of the time difference when each server in a to-be-powered server cluster reaches a power peak value in a power-on process; updating the pheromone quantity of the time difference of reaching the power peak value in the starting process of each server in the power-on sequence of the servers according to the total time of reaching the power consumption peak value by staggering peak values of the servers corresponding to the power-on sequence of the servers; and according to the updated pheromone quantity, continuing to construct a server power-on sequence through the ant colony algorithm until a first preset condition is met, and obtaining a server target power-on sequence.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a server power-on method, device, electronic equipment and storage medium. Background Art

[0002] With the continuous development of digital technology, the demand for servers is also increasing. Usually, server maintenance personnel will power on the servers through power-on commands. When there are many servers in the data center, maintenance personnel will issue power-on commands to a batch of servers to power on the servers. However, powering on multiple servers at the same time is very likely to cause a "power surge" phenomenon, causing circuit damage.

[0003] Therefore, how to effectively power on servers has become a problem that needs to be urgently solved in the industry. Summary of the invention

[0004] The present invention provides a server power-on method, device, electronic equipment and storage medium, which are used to solve the problem of how to effectively power on a server in the prior art.

[0005] The present invention provides a method for powering on a server, comprising: According to the pheromone amount of the time difference between each server in the server cluster to be powered on reaching the power peak during the startup process, the server power-on sequence is constructed through the ant colony algorithm; According to the total time for the servers corresponding to the power-on sequence of each server to reach the peak power consumption, the pheromone amount of the time difference for each server in the power-on sequence to reach the peak power consumption is updated; According to the updated pheromone amount, the server power-on sequence is continuously constructed by the ant colony algorithm until the first preset condition is met, thereby obtaining the server target power-on sequence.

[0006] According to a server power-on method provided by the present invention, the server power-on sequence is constructed by an ant colony algorithm according to the initial pheromone amount of the time difference between each server in the server cluster to be powered on reaching the power peak during the startup process, including: When the number of servers in the constructed server power-on sequence is less than a first preset threshold, the ants in the ant colony algorithm calculate the state transition probability according to the heuristic information and the pheromone amount, so as to select the next server to be powered on according to the state transition probability; Writing the next powered-on server into the server power-on sequence in order, and further comparing the relationship between the number of servers in the server power-on sequence and the first preset threshold; When the number of servers in the server power-on sequence is still less than the first preset threshold, continue to select the next power-on server according to the ant colony algorithm; When the number of servers in the server power-on sequence is greater than or equal to the first preset threshold, each ant in the ant colony algorithm completes the traversal of the servers in the server cluster to be powered on and completes the construction of the server power-on sequence.

[0007] According to a server power-on method provided by the present invention, the pheromone amount of the time difference of reaching the power peak during the startup process of each server in the server power-on sequence is updated according to the total time of the servers corresponding to the power-on sequence of each server reaching the power consumption peak, including: Determine the first pheromone increment according to the total time for the optimal server to reach the peak power consumption during off-peak hours; Determine the total pheromone increment according to the first pheromone increment and the second pheromone increment left by each ant during the construction of the power-on sequence on the server; According to the total pheromone increment, the pheromone amount of the time difference of reaching the power peak during the power-on process of each server in the server power-on sequence is updated to obtain an updated pheromone amount.

[0008] According to a server power-on method provided by the present invention, the server power-on sequence is continuously constructed by the ant colony algorithm according to the updated pheromone amount until the first preset condition is met to obtain the server target power-on sequence, including: The ants in the ant colony algorithm select the next server to be powered on according to the updated pheromone amount and the heuristic information to construct a server power-on sequence; Continue to update the pheromone amount of the time difference of reaching the power peak value during the startup process of each server in the server power-on sequence according to the reconstructed server power-on sequence until the first preset condition is met, stop updating, and obtain multiple groups of server power-on sequences; A target power-on sequence of servers in a power-on sequence of multiple groups of servers is determined according to a total time for the servers to reach a peak power consumption during off-peak hours.

[0009] According to a server power-on method provided by an embodiment of the present invention, the method for calculating the state transition probability specifically includes: ; Among them, ant k (k=1, 2, ..., n) in the ant algorithm uses the taboo table during the movement process finish k To record the currently powered on servers, use To record the servers that are allowed to start up in the next step, ={S-finish k ｝ ; yij(x) is the amount of information remaining at each time difference, is the inspiration information of each time difference.

[0010] According to a server power-on method provided by an embodiment of the present invention, the method for calculating the first pheromone increment includes: ; in, Indicates the known optimal server power-on sequence The total time for all servers to reach the peak power consumption when they are turned on at off-peak times. L Is a normal number.

[0011] According to a server power-on method provided by an embodiment of the present invention, the method for calculating the total pheromone increment includes: ; ; ; in, Indicates k The total time that all servers reach the peak power consumption during this server startup; Indicates the time difference in this iteration ( i , j ) on the pheromone increment, h is a coefficient, （1-h） express x arrive x+ d The pheromone volatilization rate at each moment.

[0012] The present invention also provides a server power-on device, comprising: A construction module is used to construct a server power-on sequence through an ant colony algorithm according to the pheromone amount of the time difference between each server in the server cluster to be powered on reaching the power peak during the startup process; An updating module, configured to update the pheromone amount of the time difference of reaching the power peak during the startup process of each server in the server power-on sequence according to the total time of the servers corresponding to the power-on sequence reaching the power consumption peak; The power-on module is used to continue to construct the server power-on sequence through the ant colony algorithm according to the updated pheromone amount until the first preset condition is met to obtain the server target power-on sequence.

[0013] According to a server power-on device provided by the present invention, the device is also used for: When the number of servers in the constructed server power-on sequence is less than a first preset threshold, the ants in the ant colony algorithm calculate the state transition probability according to the heuristic information and the pheromone amount, so as to select the next powered-on server according to the state transition probability; Writing the next powered-on server into the server power-on sequence in order, and further comparing the relationship between the number of servers in the server power-on sequence and the first preset threshold; When the number of servers in the server power-on sequence is still less than the first preset threshold, continue to select the next power-on server according to the ant colony algorithm; When the number of servers in the server power-on sequence is greater than or equal to the first preset threshold, each ant in the ant colony algorithm completes the traversal of the servers in the server cluster to be powered on and completes the construction of the server power-on sequence.

[0014] According to a server power-on device provided by the present invention, the device is also used for: Determine the first pheromone increment according to the total time for the optimal server to reach the peak power consumption during off-peak hours; Determine the total pheromone increment according to the first pheromone increment and the second pheromone increment left by each ant during the construction of the power-on sequence on the server; According to the total pheromone increment, the pheromone amount of the time difference of reaching the power peak during the power-on process of each server in the server power-on sequence is updated to obtain an updated pheromone amount.

[0015] According to a server power-on device provided by the present invention, the device is also used for: The ants in the ant colony algorithm select the next server to be powered on according to the updated pheromone amount and the heuristic information to construct a server power-on sequence; Continue to update the pheromone amount of the time difference of reaching the power peak value during the startup process of each server in the server power-on sequence according to the reconstructed server power-on sequence until the first preset condition is met, stop updating, and obtain multiple groups of server power-on sequences; A target power-on sequence of servers in a power-on sequence of multiple groups of servers is determined according to a total time for the servers to reach a peak power consumption during off-peak hours.

[0016] According to a server power-on device provided by the present invention, the method for calculating the state transition probability specifically includes: ; Among them, ant k (k=1, 2, ..., n) in the ant algorithm uses the taboo table during the movement process finish k To record the currently powered on servers, use To record the servers that are allowed to start up in the next step, ={S-finish k ｝ ; yij(x) is the amount of information remaining at each time difference, is the inspiration information of each time difference.

[0017] According to a server power-on device provided by the present invention, the method for calculating the first pheromone increment includes: ; in, Indicates the known optimal server power-on sequence The total time for all servers to reach the peak power consumption when they are turned on at off-peak times. L Is a normal number.

[0018] According to a server power-on device provided by the present invention, the method for calculating the total pheromone increment includes: ; ; ; in, Indicates k The total time that all servers reach the peak power consumption during this server startup; Indicates the time difference in this iteration ( i , j ) on the pheromone increment, h is a coefficient, （1-h） express x arrive x+ d The pheromone volatilization rate at each moment.

[0019] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned server power-on methods is implemented.

[0020] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the server power-on method described in any one of the above methods is implemented.

[0021] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the server power-on method described above is implemented.

[0022] The server power-on method, device, electronic device and storage medium provided by the present invention can effectively construct the server power-on sequence by simulating the group intelligence optimization algorithm of the foraging behavior of the ant colony, and effectively avoid the surge phenomenon caused by multiple servers reaching the power peak at the same time by staggered power-on, thereby reducing the energy consumption and operating costs of the data center. In addition, the time difference pheromone amount is used to guide the ant colony algorithm to search for the optimal server power-on sequence, and the pheromone amount is iteratively updated to approach the optimal solution, thereby solving the surge problem that may be caused by batch power-on of servers in the data center, and optimizing the server startup sequence to achieve fast and balanced power consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 Schematic diagram of the server staggered power-on system provided in an embodiment of the present application.

[0025] Figure 2 A schematic flow chart of a method for calculating the time to reach peak power during the startup process provided in an embodiment of the present application.

[0026] Figure 3 A schematic diagram of the server power-on method flow chart provided in an embodiment of the present application.

[0027] Figure 4 A schematic diagram of the flow chart of the server staggered power-on method provided in an embodiment of the present application.

[0028] Figure 5 A schematic diagram of the structure of a server power-on device provided in an embodiment of the present application.

[0029] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0031] Ant Colony Optimization (ACO) is a swarm intelligence optimization algorithm that simulates the collaboration process of real ant colonies based on the study of collective foraging behavior of real ant colonies in nature. The ant colony algorithm has been successfully applied to a series of combinatorial optimization problems such as the traveling salesman problem.

[0032] Traveling Salesman Problem (TSP): Given a set of n cities C = {c1, c2, ..., cn} and the length of the travel path between the cities dij (1≤i≤n, 1≤j≤n, i≠j), the traveling salesman starts from a certain city, traverses each city, and must visit each city once and only once, and finally returns to the original starting city. The goal of the TSP problem is to find a closed loop with the shortest path length.

[0033] The staggered power-on of servers in a data center can be transformed into a combinatorial optimization problem. Given a set of m servers S = {s1, s2, ..., sm} and the time difference tij (1≤i≤m, 1≤j≤m, i≠j) between the servers reaching the power peak during the startup process, the startup is then started from a certain server and all servers are started. Under the premise of staggered server power peaks, the startup time of all servers is minimized.

[0034] Figure 1 A schematic diagram of a server peak-shifting power-on system provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, it includes: a data center generally has multiple server cabinets, and a cabinet generally deploys multiple servers. A server in the data center can be selected as a control server, and the baseboard controller of the control server can be used to summarize the data of the data center servers and perform the calculation of the ant colony algorithm. The control workstation is optional. The control workstation is connected to all servers in the data center through the network and can be used to summarize the data of the data center servers and perform the calculation of the ant colony algorithm.

[0035] Figure 2 A schematic flow chart of a method for calculating the time to reach the power peak during the boot process provided in an embodiment of the present application includes: The control server or control workstation sends a query command to the baseboard management controllers of all servers to start the calculation of the power peak time.

[0036] Check whether each server has ever been powered on. If the server has been powered on, perform correction calculations on the historical power-on time; if it has not been powered on, perform time correction calculations on the same model.

[0037] For servers with a history of power-on, calculate the average time it takes to reach the power peak after the historical power-on. Send the calculation results to the control server or workstation to make time corrections to avoid duplication with other servers. If time duplication is found, add a random time accurate to milliseconds and record it to avoid future duplication.

[0038] If the server has not been powered on, set the historical power-on correction time to 0.

[0039] For the current server, query the average time it takes for the same model to reach peak power after startup. Check and correct the time to avoid duplication with the calculated time, and also add a random time accurate to milliseconds and record it.

[0040] If the server has been powered on, set the power-on correction time of the same model to 0.

[0041] The time ti for each server to reach the peak power during the startup process is calculated as follows: ; (1)

[0042] The calculation formula of the time difference tij between servers when they start up and reach the power peak is as follows: ; (2)

[0043] Through this calculation process, the time when each server reaches its power peak can be accurately calculated, as well as the time difference between servers. This helps to achieve staggered power-on of servers, optimize power management in data centers, reduce surge risks, and improve overall energy efficiency and system stability.

[0044] Figure 3 A schematic diagram of a server power-on method flow chart provided in an embodiment of the present application, such as Figure 3 As shown, including: Step 310, constructing a server power-on sequence by using an ant colony algorithm according to the pheromone amount of the time difference between each server in the server cluster to be powered on reaching the power peak during the startup process; In the embodiment of the present application, before the ant colony algorithm starts, it is necessary to first initialize the time difference pheromone quantity of each server in the server cluster to be powered on to reach the power peak. These pheromone quantities can be obtained based on historical data, simulation results or empirical estimates, indicating the time difference between different servers in reaching the power peak during the startup process.

[0045] Start the ant colony algorithm, where each ant represents a possible search path for the order in which servers are powered on. At the beginning of the algorithm, each ant randomly selects a server as the starting point.

[0046] Each ant decides which server to power on next based on the current pheromone amount and heuristic information (such as time difference). Paths with higher pheromone amounts indicate the power-on sequence that the ants considered to be better during their previous search, while heuristic information guides the ants to select servers that can further optimize the effect of staggered power-on.

[0047] When making decisions, ants calculate the probability of moving from the current server to another server, which is determined by the amount of pheromone and heuristic information. Usually, this probability calculation formula takes into account the relative importance of pheromones and the relative importance of heuristic information.

[0048] In the embodiment of the present application, each ant gradually builds a complete server power-on sequence according to the probability selection mechanism. Once an ant completes a complete traversal, a possible power-on sequence is built.

[0049] Step 320, updating the pheromone amount of the time difference of reaching the power peak during the startup process of each server in the server power-on sequence according to the total time of the servers corresponding to the power-on sequence reaching the power consumption peak; In an embodiment of the present application, after each ant has constructed a server power-on sequence, it calculates the total time for all servers in the sequence to reach the peak power consumption. This usually involves evaluating the power curve of each server when it is turned on, and calculating the power peak and its time distribution during the entire startup process. Based on the calculated total peak time, the quality of each power-on sequence is evaluated. This evaluation is the basis for pheromone update, because the shorter the total time, the more likely the power-on sequence is to be close to the optimal solution.

[0050] In the present application, firstly, the pheromone amount of the time difference reaching the power peak during the startup process of all servers is volatilized, that is, all pheromone amounts are reduced to avoid the solidification of the search space caused by the excessive accumulation of pheromones.

[0051] Then, according to the total staggered time of the power-on sequence found by each ant, the corresponding time difference pheromone amount is enhanced. Specifically, for each time difference between a pair of servers, if the time difference leads to a better staggered effect (i.e., a shorter total time) in a certain power-on sequence, the pheromone amount on the time difference is increased.

[0052] By continuously iterating the above process, the distribution of pheromones gradually tilts toward a more optimal server power-on sequence, thereby guiding the ants in subsequent iterations to be more likely to find a shorter total peak-shifting time.

[0053] Step 330 , based on the updated pheromone amount, continue to construct the server power-on sequence through the ant colony algorithm until the first preset condition is met to obtain the server target power-on sequence.

[0054] In the embodiment of the present application, in each iteration, each ant starts a new round of power-on sequence construction according to the pheromone amount updated in step 120. The update of the pheromone amount reflects the effective power-on sequence found in the previous iteration, so the updated pheromone amount will guide the ants to be more inclined to choose those power-on paths that have been proven to be effective before.

[0055] Each ant gradually builds a new server power-on sequence through a probabilistic selection mechanism based on the updated pheromone amount and heuristic information (such as the time difference between servers reaching power peak).

[0056] After each ant builds a power-on sequence, it calculates the total time it takes for all servers in the sequence to reach their peak power consumption. This total time is a key indicator for evaluating the quality of the new power-on sequence.

[0057] According to the quality of the newly constructed power-up sequence, the pheromone amount is updated again. This step further strengthens the pheromone of those power-up paths that lead to shorter total peak time, while weakening the pheromone of those paths that are not effective.

[0058] After each iteration, check whether the maximum number of iterations has been reached. Once the end condition is met, the algorithm terminates and outputs the currently found optimal server power-on sequence as the target power-on sequence. This sequence is the sequence that achieves the shortest server power consumption peak time while meeting the peak power-on requirements.

[0059] In the embodiment of the present application, by simulating the swarm intelligence optimization algorithm of the foraging behavior of ant colonies, the server power-on sequence can be effectively constructed, and the power-on peak is effectively avoided due to multiple servers reaching the power peak at the same time, thereby reducing the energy consumption and operating costs of the data center. In addition, the time difference pheromone amount is used to guide the ant colony algorithm to search for the optimal server power-on sequence. At the same time, the pheromone amount is iteratively updated to approach the optimal solution, thereby solving the power surge problem that may be caused by the batch power-on of servers in the data center, and optimizing the server startup sequence to achieve fast and balanced power consumption.

[0060] Optionally, the step of constructing a server power-on sequence by using an ant colony algorithm according to the initial pheromone amount of the time difference between each server in the server cluster to be powered on reaching a power peak during the power-on process includes: When the number of servers in the constructed server power-on sequence is less than a first preset threshold, the ants in the ant colony algorithm calculate the state transition probability according to the heuristic information and the pheromone amount, so as to select the next powered-on server according to the state transition probability; Writing the next powered-on server into the server power-on sequence in order, and further comparing the relationship between the number of servers in the server power-on sequence and the first preset threshold; When the number of servers in the server power-on sequence is still less than the first preset threshold, continue to select the next power-on server according to the ant colony algorithm; When the number of servers in the server power-on sequence is greater than or equal to the first preset threshold, each ant in the ant colony algorithm completes the traversal of the servers in the server cluster to be powered on and completes the construction of the server power-on sequence.

[0061] In the embodiment of the present application, the ants select the order in which the servers are powered on based on the heuristic information and the pheromone amount. This process begins with initializing the pheromone amount, i.e., the time difference between each server powering up and reaching the peak power. These initial pheromone amounts provide the ants with a preliminary guide to help them make choices in the search space.

[0062] As the algorithm progresses, the ant calculates the state transition probability based on the current pheromone amount and heuristic information (such as the time difference between servers). This probability determines which server the ant will choose to start up next. Each selection is based on a probabilistic model, where paths with higher pheromone amounts are more likely to be selected because they represent solutions that were considered better in previous iterations.

[0063] The ant selects the next server according to the calculated state transition probability and writes its order into the power-on order list. As the selection process proceeds, this list gradually grows until it reaches or exceeds a preset threshold. This threshold is an important parameter that defines the minimum number of servers that should be in the power-on order, ensuring the practicality and effectiveness of the power-on order.

[0064] If the number of servers in the power-on sequence has not reached this preset threshold, the ant will continue to select the next server to power on until this condition is met. This process is iterative, and each iteration may update the pheromone amount to reflect the newly discovered better or more feasible power-on sequence.

[0065] When the number of servers in the power-on sequence reaches or exceeds the preset threshold, the ants in the ant colony algorithm complete the traversal of the server cluster to be powered on, and the server power-on sequence is completed. This power-on sequence is designed to achieve peak power-on of servers to optimize the power consumption of the data center and avoid power surges.

[0066] Throughout the process, pheromone updates not only reflect the ants' findings during the search, but also guide the subsequent search direction. In this way, the ant colony algorithm can gradually approach the optimal server power-on sequence, thereby achieving efficient and balanced power management and improving the energy efficiency and stability of the data center.

[0067] Optionally, updating the pheromone amount of the time difference of reaching the power peak during the startup of each server in the server power-on sequence according to the total time of the servers corresponding to the power-on sequence of each server reaching the power consumption peak during the staggered peak, comprises: Determine the first pheromone increment according to the total time for the optimal server to reach the peak power consumption during off-peak hours; Determine the total pheromone increment according to the first pheromone increment and the second pheromone increment left by each ant during the construction of the power-on sequence on the server; According to the total pheromone increment, the pheromone amount of the time difference of reaching the power peak during the power-on process of each server in the server power-on sequence is updated to obtain an updated pheromone amount.

[0068] In the embodiment of the present application, the total time for an optimal server to reach the peak power consumption is determined. This time is obtained from the power-on sequence constructed by all ants and represents the best performance indicator found in the current iteration. Based on this optimal total time, the algorithm calculates the first pheromone increment, which reflects the contribution of the optimal solution to the pheromone update.

[0069] The method for calculating the first pheromone increment includes: ; in, Indicates the known optimal server power-on sequence The total time for all servers to reach the peak power consumption when they are turned on at off-peak times. L Is a normal number.

[0070] Each ant will also leave its own pheromone increment in the process of building the server power-on sequence. This is the second pheromone increment. This increment is determined based on the performance of the ant's own traversal path, reflecting the ant's exploration and evaluation of the solution space during the search process.

[0071] The algorithm determines the total pheromone increment by combining the first pheromone increment with the second pheromone increment left by each ant. This total increment is the basis for the algorithm to update the pheromone amount, which combines the influence of the global optimal solution and the local discoveries made by all ants during the search process.

[0072] The method for calculating the total pheromone increment includes: ; ; ; in, Indicates k The total time that all servers reach the peak power consumption during this server startup; Indicates the time difference in this iteration ( i , j ) is the pheromone increment on the second pheromone increment. h is a coefficient, （1-h） express x arrive x+d The pheromone volatilization rate at each moment.

[0073] Finally, the algorithm updates the pheromone amount of the time difference between each server reaching the power peak during the startup process in the server power-on sequence according to the total pheromone increment, guiding the ants to more likely choose server power-on sequences that help achieve a shorter total peak-shifting time in subsequent iterations.

[0074] Optionally, the step of continuing to construct the server power-on sequence by the ant colony algorithm according to the updated pheromone amount until a first preset condition is met to obtain a target server power-on sequence includes: The ants in the ant colony algorithm select the next server to be powered on according to the updated pheromone amount and the heuristic information to construct a server power-on sequence; Continue to update the pheromone amount of the time difference of reaching the power peak value during the startup process of each server in the server power-on sequence according to the reconstructed server power-on sequence until the first preset condition is met, stop updating, and obtain multiple groups of server power-on sequences; A target power-on sequence of servers in a power-on sequence of multiple groups of servers is determined according to a total time for the servers to reach a peak power consumption during off-peak hours.

[0075] In the embodiment of the present application, each ant in the ant colony algorithm calculates the state transition probability based on the updated pheromone amount and heuristic information (such as the time difference between servers reaching the power peak). The state transition probability guides the ants to select the next server to be powered on to build the server power-on sequence.

[0076] The ant selects a server based on the calculated probability and writes the selected servers into the power-on order list in order. This process is repeated until the complete server power-on order is constructed.

[0077] After each server power-on sequence is constructed, the algorithm will update the pheromone amount based on the total time it takes for the servers to reach the peak power consumption under the sequence. The purpose of updating the pheromone amount is to reflect the performance of the newly discovered power-on sequence and guide the subsequent search process.

[0078] The ants continue to select the next server to start based on the updated pheromone amount and heuristic information, and repeatedly build the power-on sequence. Each iteration may generate a new power-on sequence, which is used to update the pheromone amount. The iterative process continues until the first preset condition is met, such as reaching the maximum number of iterations, the change in pheromone updates is less than the preset threshold, or the quality of the solution has not been significantly improved in consecutive iterations. Once the preset condition is met, the algorithm stops iterating.

[0079] In the power-on sequence of multiple groups of servers, the optimal server power-on sequence is determined based on the total time it takes for the servers to reach the peak power consumption. This target power-on sequence is found in all iterations and can achieve the shortest peak power consumption time while ensuring the staggered power-on of the servers.

[0080] In the embodiment of the present application, the ant colony algorithm can effectively optimize the power-on sequence of the servers, reduce the peak power consumption of the data center when the servers are started in batches, and improve the overall energy efficiency and system stability. This method achieves effective management of the server power-on strategy by dynamically adjusting the pheromone amount and continuously optimizing the power-on sequence.

[0081] Figure 4 A flow chart of the method for staggered power-on of a server provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, including: Start the optimization process of staggered server power-on and prepare for iterative search using the ant colony algorithm.

[0082] The initial pheromone amount is set for the time difference between each server in the data center reaching the peak power. These pheromone amounts are the basis for the algorithm to start searching, and they will guide the ants' decisions when choosing the order in which to start the servers.

[0083] Before each iteration, check whether the preset end condition is met. Nc When the preset value is reached or exceeded, the algorithm stops iterating.

[0084] Each ant randomly selects a server as the starting point and begins to build a possible server startup sequence. This sequence is designed to achieve staggered power-on of the servers to reduce the peak power consumption.

[0085] Based on the heuristic information and pheromone concentration, the ants use the state transition probability model to select the next server that should be powered on. This process involves probability calculations to determine the likelihood of each server being selected.

[0086] The ants select servers one by one until the entire boot sequence is constructed. Each time a server is selected, the loop parameters are updated and a check is made to see if all servers have been selected.

[0087] For each startup sequence constructed by the ants, the total time it takes for the servers to reach the peak power consumption under this sequence is calculated. This total time is a key indicator for evaluating the quality of the startup sequence.

[0088] According to the startup sequence constructed by the ants and the corresponding total staggered time, the pheromone quantity is updated. This update process involves the volatilization and enhancement of pheromones to reflect the newly discovered better startup sequence.

[0089] If the end condition is not met, continue to iterate and construct the server power-on sequence. If the end condition is met, the algorithm ends and outputs the final server target power-on sequence.

[0090] In the embodiment of the present application, the ant colony algorithm can continuously explore and optimize the server power-on sequence, gradually reducing the total time for the server to reach the peak power consumption. Each iteration makes the pheromone distribution closer to the optimal solution, so that when the end condition is met, an efficient server power-on sequence can be obtained. This method not only improves the energy efficiency of the data center, but also enhances the stability and response speed of the system.

[0091] The server power-on device provided by the present invention is described below. The server power-on device described below and the server power-on method described above can be referenced to each other.

[0092] Figure 5 A schematic diagram of the structure of the server power-on device provided in the embodiment of the present application is shown in FIG. Figure 5 As shown, including: The construction module 510 is used to construct a server power-on sequence through an ant colony algorithm according to the pheromone amount of the time difference between each server in the server cluster to be powered on reaching the power peak during the startup process; The updating module 520 is used to update the pheromone amount of the time difference of reaching the power peak during the startup process of each server in the server power-on sequence according to the total time of the servers corresponding to the power-on sequence reaching the power consumption peak; The power-on module 530 is used to continue to construct the server power-on sequence through the ant colony algorithm according to the updated pheromone amount until the first preset condition is met to obtain the server target power-on sequence.

[0093] According to a server power-on device provided by the present invention, the device is also used for: When the number of servers in the constructed server power-on sequence is less than a first preset threshold, the ants in the ant colony algorithm calculate the state transition probability according to the heuristic information and the pheromone amount, so as to select the next powered-on server according to the state transition probability; Writing the next powered-on server into the server power-on sequence in order, and further comparing the relationship between the number of servers in the server power-on sequence and the first preset threshold; When the number of servers in the server power-on sequence is still less than the first preset threshold, continue to select the next power-on server according to the ant colony algorithm; When the number of servers in the server power-on sequence is greater than or equal to the first preset threshold, each ant in the ant colony algorithm completes the traversal of the servers in the server cluster to be powered on and completes the construction of the server power-on sequence.

[0094] According to a server power-on device provided by the present invention, the device is also used for: Determine the first pheromone increment according to the total time for the optimal server to reach the peak power consumption during off-peak hours; Determine the total pheromone increment according to the first pheromone increment and the second pheromone increment left by each ant during the construction of the power-on sequence on the server; According to the total pheromone increment, the pheromone amount of the time difference of reaching the power peak during the power-on process of each server in the server power-on sequence is updated to obtain an updated pheromone amount.

[0095] According to a server power-on device provided by the present invention, the device is also used for: The ants in the ant colony algorithm select the next server to be powered on according to the updated pheromone amount and the heuristic information to construct a server power-on sequence; Continue to update the pheromone amount of the time difference of reaching the power peak value during the startup process of each server in the server power-on sequence according to the reconstructed server power-on sequence until the first preset condition is met, stop updating, and obtain multiple groups of server power-on sequences; A target power-on sequence of servers in a power-on sequence of multiple groups of servers is determined according to a total time for the servers to reach a peak power consumption during off-peak hours.

[0096] According to a server power-on device provided by the present invention, the method for calculating the state transition probability specifically includes: ; Among them, ant k (k=1, 2, ..., n) in the ant algorithm uses the taboo table during the movement process finish k To record the currently powered on servers, use To record the servers that are allowed to start up in the next step, ={S-finish k ｝ ; yij(x) is the amount of information remaining at each time difference, is the inspiration information of each time difference.

[0097] According to a server power-on device provided by the present invention, the method for calculating the first pheromone increment includes: ; in, Indicates the known optimal server power-on sequence The total time for all servers to reach the peak power consumption when they are turned on at off-peak times. L Is a normal number.

[0098] According to a server power-on device provided by the present invention, the method for calculating the total pheromone increment includes: ; ; ; in, Indicates k The total time that all servers reach the peak power consumption during this server startup; Indicates the time difference in this iteration ( i , j ) on the pheromone increment, h is a coefficient, （1-h） express x arrive x+ d The pheromone volatilization rate at each moment.

[0099] The embodiment of the present application can effectively construct the server power-on sequence by simulating the swarm intelligence optimization algorithm of the foraging behavior of ant colonies, and effectively avoid the power surge caused by multiple servers reaching the power peak at the same time by staggered power-on, thereby reducing the energy consumption and operating costs of the data center. In addition, the time difference pheromone amount is used to guide the ant colony algorithm to search for the optimal server power-on sequence, and the optimal solution is approached by iteratively updating the pheromone amount, thereby solving the power surge problem that may be caused by batch power-on of servers in the data center, and optimizing the server startup sequence to achieve fast and balanced power consumption.

[0100] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the server power-on method, which includes: constructing a server power-on sequence through an ant colony algorithm according to the pheromone amount of the time difference between each server in the server cluster to be powered on reaching the power peak during the startup process; According to the total time for the servers corresponding to the power-on sequence of each server to reach the peak power consumption, the pheromone amount of the time difference for each server in the power-on sequence to reach the peak power consumption is updated; According to the updated pheromone amount, the server power-on sequence is continuously constructed by the ant colony algorithm until the first preset condition is met, thereby obtaining the server target power-on sequence.

[0101] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0102] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the server power-on method provided by the above methods, the method comprising: according to the pheromone amount of the time difference of each server in the server cluster to be powered on reaching the power peak during the startup process, constructing the server power-on sequence by using an ant colony algorithm; According to the total time for the servers corresponding to the power-on sequence of each server to reach the peak power consumption, the pheromone amount of the time difference for each server in the power-on sequence to reach the peak power consumption is updated; According to the updated pheromone amount, the server power-on sequence is continuously constructed by the ant colony algorithm until the first preset condition is met, thereby obtaining the server target power-on sequence.

[0103] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the server power-on method provided by the above methods, the method comprising: constructing a server power-on sequence by an ant colony algorithm according to the pheromone amount of the time difference between each server in the server cluster to be powered on reaching a power peak during the startup process; According to the total time for the servers corresponding to the power-on sequence of each server to reach the peak power consumption, the pheromone amount of the time difference for each server in the power-on sequence to reach the peak power consumption is updated; According to the updated pheromone amount, the server power-on sequence is continuously constructed by the ant colony algorithm until the first preset condition is met, thereby obtaining the server target power-on sequence.

[0104] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0105] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for powering on a server, characterized in that: include: According to the pheromone amount of the time difference between each server in the server cluster to be powered on reaching the power peak during the startup process, the server power-on sequence is constructed through the ant colony algorithm; According to the total time for the servers corresponding to the power-on sequence of each server to reach the peak power consumption, the pheromone amount of the time difference for each server in the power-on sequence to reach the peak power consumption is updated; According to the updated pheromone amount, the server power-on sequence is continuously constructed by the ant colony algorithm until the first preset condition is met, thereby obtaining the server target power-on sequence.

2. The server power-on method according to claim 1, characterized in that: The server power-on sequence is constructed by using an ant colony algorithm according to the initial pheromone amount of the time difference between each server in the server cluster to be powered on reaching the power peak during the startup process, including: When the number of servers in the constructed server power-on sequence is less than a first preset threshold, the ants in the ant colony algorithm calculate the state transition probability according to the heuristic information and the pheromone amount, so as to select the next powered-on server according to the state transition probability; Writing the next powered-on server into the server power-on sequence in order, and further comparing the relationship between the number of servers in the server power-on sequence and the first preset threshold; When the number of servers in the server power-on sequence is still less than the first preset threshold, continue to select the next power-on server according to the ant colony algorithm; When the number of servers in the server power-on sequence is greater than or equal to the first preset threshold, each ant in the ant colony algorithm completes the traversal of the servers in the server cluster to be powered on and completes the construction of the server power-on sequence.

3. The server power-on method according to claim 1, characterized in that: The updating of the pheromone amount of the time difference of reaching the power peak value during the startup process of each server in the server power-on sequence according to the total time of the servers corresponding to the power-on sequence of each server reaching the power consumption peak value comprises: Determine the first pheromone increment according to the total time for the optimal server to reach the peak power consumption during off-peak hours; Determine the total pheromone increment according to the first pheromone increment and the second pheromone increment left by each ant during the construction of the power-on sequence on the server; According to the total pheromone increment, the pheromone amount of the time difference of reaching the power peak during the power-on process of each server in the server power-on sequence is updated to obtain an updated pheromone amount.

4. The server power-on method according to claim 2, characterized in that: The method of continuing to construct the server power-on sequence by the ant colony algorithm according to the updated pheromone amount until the first preset condition is met to obtain the server target power-on sequence includes: The ants in the ant colony algorithm select the next server to be powered on according to the updated pheromone amount and the heuristic information to construct a server power-on sequence; Continue to update the pheromone amount of the time difference of reaching the power peak value during the startup process of each server in the server power-on sequence according to the reconstructed server power-on sequence until the first preset condition is met, stop updating, and obtain multiple groups of server power-on sequences; A target power-on sequence of servers in a power-on sequence of multiple groups of servers is determined according to a total time when the servers reach a peak power consumption during off-peak hours.

5. The server power-on method according to claim 2, characterized in that: The method for calculating the state transition probability specifically includes: ； Among them, ant k (k=1, 2, ..., n) in the ant algorithm uses the taboo table during the movement process finish k To record the currently powered on servers, use To record the servers that are allowed to start up in the next step, ={S-finish k ｝ ; yij(x) is the amount of information remaining at each time difference, is the inspiration information of each time difference.

6. The server power-on method according to claim 3, characterized in that: The method for calculating the first pheromone increment includes: ； in, Indicates the known optimal server power-on sequence The total time for all servers to reach the peak power consumption when they are turned on at off-peak times. L Is a normal number.

7. The server power-on method according to claim 6, characterized in that: The method for calculating the total pheromone increment includes: ； ； ； in, Indicates k The total time that all servers reach the peak power consumption during this server startup; Indicates the time difference in this iteration ( i , j ) is the pheromone increment on the second pheromone increment. h is a coefficient, （1-h） express x arrive x+d The pheromone volatilization rate at each moment.

8. A server power-on device, characterized in that: include: A construction module is used to construct a server power-on sequence through an ant colony algorithm according to the pheromone amount of the time difference between each server in the server cluster to be powered on reaching the power peak during the startup process; An updating module, configured to update the pheromone amount of the time difference of reaching the power peak during the startup process of each server in the server power-on sequence according to the total time of the servers corresponding to the power-on sequence reaching the power consumption peak; The power-on module is used to continue to construct the server power-on sequence through the ant colony algorithm according to the updated pheromone amount until the first preset condition is met to obtain the server target power-on sequence.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the server power-on method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the server power-on method according to any one of claims 1 to 7 is implemented.

Images