Machine room energy saving method and device, computing device and computer storage medium

Abstract

The application discloses a kind of computer room energy-saving method, device, computing equipment and computer storage medium.The method comprises: obtaining the refrigeration influence parameter data associated with the refrigeration of each refrigeration equipment of computer room, wherein the refrigeration influence parameter includes: computer room temperature, the internal and external temperature difference between computer room and environment, the first refrigeration equipment set working temperature;Refrigeration influence parameter data is input to pre-trained energy-saving model for energy-saving prediction, to obtain the computer room refrigeration equipment target combination and the first refrigeration equipment target working temperature of this time that meet the refrigeration energy efficiency condition, wherein the energy-saving model is obtained based on PSO-BP neural network training;According to the first refrigeration equipment target working temperature of this time, the switch-on temperature of each refrigeration equipment in computer room refrigeration equipment target combination is calculated, and the corresponding refrigeration equipment is controlled according to the switch-on temperature of each refrigeration equipment Start or shutdown, to realize computer room energy saving.In the meantime of guaranteeing the stable operation of computer room equipment, energy saving and power saving are carried out by intelligent means.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and specifically to a method, apparatus, computing device, and computer storage medium for energy saving in computer rooms. Background Technology

[0002] During the 24-hour uninterrupted operation of the equipment inside the computer room, heat is continuously released. If the temperature in the computer room is too high, it will trigger a high temperature alarm, causing equipment failure and business interruption. Therefore, the normal operation of the computer room cooling equipment can ensure the stability of the computer room environment and the orderly operation of the equipment.

[0003] The temperature in the computer room is controlled by cooling equipment, which generally consumes a lot of energy, and continuous operation 24 hours a day will result in huge energy consumption. At the same time, the cooling equipment in the computer room operates independently and always operates according to the set temperature. At times, there is overcooling, resulting in excessive energy consumption and additional electricity bills.

[0004] The existing operating mode of the computer room cooling equipment is as follows:

[0005] 1. Based on the space of the computer room, the number and power of the working equipment, the operating temperature is set according to the established rules, and the equipment operates 24 hours a day under autonomous and independent operation.

[0006] 2. Based on changes in the external environment, such as when the temperature is below 10℃, manually shut down the cooling equipment in the machine room. Once the temperature rises, turn the air conditioning back on, and repeat this cycle.

[0007] The "uniform" operation of the cooling equipment in the computer room, especially when the ambient temperature is low, can lead to overcooling, resulting in significant energy waste and a consistently low energy efficiency ratio. Conversely, indiscriminately shutting down equipment risks overheating the computer room, ultimately impacting the operation of business equipment.

[0008] The existing solution lacks systematic control over the cooling equipment in the computer room and cannot make real-time and accurate adjustments to changes in the external environment to ensure that the cooling capacity can guarantee the stable and normal operation of the computer room and that energy consumption can be reasonably controlled, thus achieving energy saving and power saving. Summary of the Invention

[0009] In view of the above problems, embodiments of the present invention are proposed to provide a method, apparatus, computing device and computer storage medium for energy saving in computer rooms that overcomes or at least partially solves the above problems.

[0010] According to one aspect of the present invention, a data center energy-saving method is provided, comprising:

[0011] Acquire cooling-related parameter data associated with the cooling of each cooling device in the computer room. These cooling-related parameters include: computer room air temperature, temperature difference between the computer room and the environment, and the set operating temperature of the first cooling device.

[0012] The cooling effect parameter data is input into the pre-trained energy-saving model to predict energy saving, and the target combination of computer room cooling equipment that meets the cooling energy efficiency conditions and the target operating temperature of the first cooling equipment are obtained. The energy-saving model is trained based on the PSO-BP neural network.

[0013] Based on the target operating temperature of the first refrigeration equipment, the corresponding start-up and shutdown temperatures of each refrigeration equipment in the target combination of computer room refrigeration equipment are controlled according to the corresponding start-up and shutdown temperatures of each refrigeration equipment to achieve energy saving in the computer room.

[0014] According to another aspect of the present invention, a data center energy-saving device is provided, comprising:

[0015] The acquisition module is suitable for acquiring cooling-influence parameter data related to the cooling of each cooling device in the computer room. The cooling-influence parameters include: computer room air temperature, temperature difference between the computer room and the environment, and the set operating temperature of the first cooling device.

[0016] The prediction module is suitable for inputting cooling impact parameter data into a pre-trained energy-saving model to predict energy saving, and to obtain the target combination of computer room cooling equipment that meets the cooling energy efficiency conditions and the target operating temperature of the first cooling equipment in this case. The energy-saving model is trained based on the PSO-BP neural network.

[0017] The control module is adapted to control the start-up or shutdown of the corresponding cooling equipment in the target combination of computer room cooling equipment according to the target operating temperature of the first cooling equipment, so as to achieve energy saving in the computer room.

[0018] According to another aspect of the present invention, a computing device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0019] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-mentioned data center energy-saving method.

[0020] According to another aspect of the present invention, a computer storage medium is provided, wherein at least one executable instruction is stored in the storage medium, the executable instruction causing a processor to perform an operation corresponding to the above-described data center energy-saving method.

[0021] According to the solution provided in the above embodiments of the present invention, the intelligent temperature control of the computer room is scientifically guided to improve the energy efficiency ratio while ensuring the stable operation of the computer room; the target combination of computer room cooling equipment that meets the cooling energy efficiency conditions and the target operating temperature of the first cooling equipment are predicted by the energy-saving model, which greatly improves the accuracy of control and the intelligence of energy saving.

[0022] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more obvious and understandable, specific implementation methods of the embodiments of the present invention are described below. Attached Figure Description

[0023] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0024] Figure 1A A flowchart of the data center energy-saving method provided in an embodiment of the present invention is shown;

[0025] Figure 1B This diagram illustrates the impact of temperature on the cooling power and energy efficiency ratio of an air conditioner.

[0026] Figure 1C A schematic diagram illustrating the impact of the set operating temperature of an air conditioner on its cooling power and energy efficiency ratio.

[0027] Figure 1D A schematic diagram illustrating the impact of the set operating temperature on the cooling power and energy efficiency ratio of air conditioners in different types of computer rooms;

[0028] Figure 1E This is a schematic diagram of a BP neural network;

[0029] Figure 1F Here is a flowchart of the particle swarm optimization algorithm;

[0030] Figure 1G A schematic diagram of the data fitting curve for the regression of model predictions and actual values;

[0031] Figure 2 A schematic diagram of the structure of the data center energy-saving device provided in an embodiment of the present invention is shown;

[0032] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present invention is shown. Detailed Implementation

[0033] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the invention and to fully convey the scope of the invention to those skilled in the art.

[0034] Figure 1A A flowchart of a data center energy-saving method provided in an embodiment of the present invention is shown. Figure 1A As shown, the method includes the following steps:

[0035] Step S101: Obtain cooling impact parameter data related to the cooling of each cooling device in the computer room. The cooling impact parameters include: computer room air temperature, temperature difference between the computer room and the environment, and the set operating temperature of the first cooling device.

[0036] Specifically, to ensure a stable computer room environment and orderly equipment operation, cooling equipment is typically installed inside the computer room. The temperature of the computer room is controlled by turning the cooling equipment on and off. To utilize energy rationally and avoid waste, energy-saving control of the computer room is necessary. This requires acquiring cooling-related parameter data associated with the cooling of each cooling device in the computer room. These cooling-related parameters include: the computer room air temperature, the temperature difference between the computer room and the surrounding environment, and the set operating temperature of the primary cooling device. The primary cooling device is an air conditioner, and its set operating temperature is the same as the air conditioner's set operating temperature.

[0037] Cooling impact parameters are parameters that affect the cooling of cooling equipment in a computer room, and cooling impact parameter data are the parameter data corresponding to the cooling impact parameters.

[0038] Specifically, the correlation between cooling impact parameters and the cooling of cooling equipment can be determined through testing experiments in different environments. The cooling equipment here includes air conditioners and fresh air systems. The energy consumption of the cooling equipment is mainly measured by cooling power and energy efficiency ratio.

[0039] (I) AI calculation of the relationship between air conditioning cooling power, energy efficiency ratio and temperature

[0040] (1) Design concept

[0041] We selected air conditioners with coil temperature monitoring but no generator room connection, and calculated the impact of temperature and sunlight on their cooling power and energy efficiency ratio. Then, we derived the coefficients for changes in cooling power and energy efficiency ratio of the air conditioners when the temperature increases or decreases by 1 degree Celsius.

[0042] (2) Temperature Relationship Analysis

[0043] The air conditioning cooling power and energy efficiency ratio change with the outdoor temperature and sunshine. The influence coefficient of each degree change in ambient temperature and sunshine on cooling power and energy efficiency ratio is calculated.

[0044] Identify server rooms without power supply: From 0:00 to 5:00, shut down all cooling equipment in each server room for approximately 3 minutes. Obtain the output power of the smart meters and the input power of each "virtual meter - power input" during this time. A server room with a smart meter output power equal to the sum of the input power of each "virtual meter - power input" multiplied by (1 ± 5%) is considered to have no power supply. Select server rooms without power supply that have only one air conditioner with coil temperature monitoring. Analyze the relationship between the air conditioner's cooling capacity, energy efficiency ratio, and air temperature. With the air conditioner's set operating temperature unchanged, calculate the relationship between the air conditioner's cooling power, energy efficiency ratio, air temperature, and sunlight in these server rooms.

[0045] Based on temperature changes, one data point is acquired for each 1-degree Celsius change in temperature (data taken while the air conditioner is running). Data is acquired for periods when the air conditioner is running and the indoor coil temperature is below 15 degrees Celsius (all data exceeding 15 degrees Celsius is considered invalid). This includes the indoor coil temperature, the air conditioner's set operating temperature (or average return air temperature), the ambient temperature and sunshine duration, the smart meter's output power, and the input power of the "Power Input - Virtual Meter." Data with an indoor coil temperature greater than 15 degrees Celsius (both indoor coil temperature and return air temperature data) are discarded. For data acquired on cloudy or rainy days, the relationship between indoor coil temperature, air conditioner power consumption, and ambient temperature can be derived. Similarly, for data acquired on sunny, cloudy, rainy, and nighttime conditions at the same ambient temperature, the relationship between indoor coil temperature, air conditioner power consumption, and sunshine duration can be derived. Since the air conditioning cooling power = K * (average return air temperature - indoor coil temperature) * air volume, and the energy efficiency ratio = air conditioning cooling power / air conditioning power consumption, the relationship between air conditioning cooling power, energy efficiency ratio and air temperature and sunshine, as well as the coefficient of variation, can be obtained.

[0046] Air conditioner cooling capacity (W) 冷 =(T 工 -T 管 )*Air volume*K, where T 工 Set the operating temperature of the air conditioner (which is also equal to the average return air temperature T during the air conditioner's operation). 回 The air volume * K is a fixed number. Air conditioner energy efficiency ratio = air conditioner cooling capacity (W) 冷 / Air conditioner power consumption = Air conditioner cooling power (W) 冷 / (Air conditioning cooling power - sum of power inputs of all power sources in the computer room). Figure 1B This diagram illustrates the impact of temperature and other factors on the cooling power and energy efficiency ratio of an air conditioner.

[0047] The coefficient of variation can be calculated by taking the average value of each data point for every 1 degree Celsius increase or decrease in temperature in each computer room, or by performing discrete distribution statistical calculations on multi-point data (only data that is approximately 50% closest to the median value).

[0048] Air temperature and sunshine affect the indoor coil temperature of the air conditioner (which in turn affects the air conditioner's cooling power) and its power consumption, thus affecting the air conditioner's cooling power and energy efficiency ratio. It is deduced that Δcooling capacity = S1 * ΔT, Δcooling capacity = S2 * sunshine conditions, Δenergy efficiency ratio = S3 * ΔT, Δenergy efficiency ratio = S4 * sunshine conditions. The values ​​of S1, S2, S3, and S4 are calculated. When calculating S1 and S3, ΔT is taken as 1 degree. When calculating S2 and S4, sunshine conditions are categorized as cloudy / rainy days and nights, partly cloudy days, and sunny days. On cloudy / rainy days and nights, S2 and S4 = 0.

[0049] Note: After each county and city installs sunshine monitoring instruments, the sunshine coefficient can be obtained, and calculations can be made based on the sunshine coefficient.

[0050] The coefficients that determine the impact of air temperature on the cooling capacity and energy efficiency ratio of each computer room's air conditioner are derived. After removing the highest and lowest 10% of data, the average value of the remaining data for each computer room's air conditioner is used as the coefficients for the impact of air temperature and sunshine on the cooling capacity and energy efficiency ratio of each air conditioner. These coefficients can also be applied to other air conditioners.

[0051] (II) The Relationship Between Air Conditioner Cooling Power, Energy Efficiency Ratio and Air Conditioner Set Operating Temperature

[0052] (1) Design concept

[0053] We selected air conditioners with coil temperature monitoring but no generator room connection, and calculated the impact of the air conditioner's operating temperature setpoint on their cooling power and energy efficiency ratio. Then, we derived the coefficients for the change in cooling power and energy efficiency ratio per unit area of ​​the generator room when the set operating temperature increases or decreases by 1 degree Celsius.

[0054] (2) Analysis of working temperature relationship

[0055] Select computer rooms without a generator set, with only one air conditioner and coil temperature monitoring, and conduct monitoring and analysis on the relationship between air conditioner cooling capacity, energy efficiency ratio, and air conditioner operating temperature setpoint. Set the air conditioner operating temperature between 25-30 degrees Celsius, and calculate the relationship between air conditioner cooling power, energy efficiency ratio, and air conditioner operating temperature setpoint for these computer rooms.

[0056] Selecting a time period from 1:00 AM to 6:00 AM when the temperature is between 20 and 30 degrees Celsius, the system first sets the air conditioner's operating temperature to 30 degrees Celsius between 1:00 AM and 4:00 AM. The system then acquires data on the indoor coil temperature, smart meter power, and power supply input power for each short period when the air conditioner is on and the indoor coil temperature is below 15 degrees Celsius (all coil temperatures exceeding 15 degrees Celsius are considered invalid data). Next, from 3:00 AM to 6:00 AM, the system sets the air conditioner's operating temperature to 25 degrees Celsius, again acquiring data on the indoor coil temperature for each short period when the air conditioner is on and the indoor coil temperature is below 15 degrees Celsius (all coil temperatures exceeding 15 degrees Celsius are considered invalid data). The system then calculates the impact coefficient of a 1-degree Celsius increase or decrease in the air conditioner's operating temperature setting on its cooling capacity and energy efficiency ratio. Figure 1C A schematic diagram illustrating the impact of the set operating temperature on the air conditioner's cooling power and energy efficiency ratio.

[0057] Each computer room was classified according to its type (brick-concrete, color steel, and integrated) and the indoor equipment load per unit area. The data of the largest 10% and smallest 10% of each computer room were removed to obtain the impact coefficient of increasing or decreasing the air conditioning operating temperature setpoint by 1 degree on the air conditioning cooling capacity and energy efficiency ratio of each type of computer room. Figure 1D A schematic diagram illustrating the impact of the set operating temperature on the cooling power and energy efficiency ratio of air conditioners in different types of computer rooms.

[0058] If it is found that some unit area data are missing, or that the data volume is too small and does not conform to the overall data change pattern, then corrections should be made according to the overall data change pattern.

[0059] (III) The relationship between the cooling power, energy efficiency ratio and indoor / outdoor temperature difference of the fresh air system

[0060] Sunlight has little impact on the cooling capacity and energy efficiency ratio of fresh air systems and fresh air coolers, so it can be disregarded for the time being.

[0061] When the computer room air conditioning is off or the fresh air unit or fresh air cooler is on, the system acquires the air temperature and humidity, as well as the average ambient temperature of the computer room when the fresh air unit is running. The operating power of the fresh air unit or fresh air cooler is directly retrieved from or imported from the asset management system (refer to the classic algorithm).

[0062] The cooling power of a fresh air cooler = indoor and outdoor temperature difference (room ambient temperature - supply air temperature) * air volume. The supply air temperature is based on a 90% wet-bulb temperature. The energy efficiency ratio (EER) = cooling power / power consumption. The rated cooling power of a fresh air cooler = 10-degree temperature difference * air volume. Since air volume and power consumption remain essentially constant, for every 1-degree increase or decrease in the 90% wet-bulb temperature, the cooling power and EER of the fresh air cooler increase or decrease by 10%. The cooling power of a fresh air cooler = indoor and outdoor temperature difference (room ambient temperature - 90% wet-bulb temperature) * air volume. The energy efficiency ratio (EER) = cooling power of the fresh air cooler / operating power of the fresh air unit.

[0063] Similarly, for every 1 degree Celsius increase or decrease in temperature, the cooling power and energy efficiency ratio of the fresh air system will increase or decrease by 10%. The cooling power of the fresh air system = indoor and outdoor temperature difference ΔT * air volume, and the energy efficiency ratio = cooling power of the fresh air system / operating power of the fresh air system. Δcooling capacity = 0.1 * ΔT, Δenergy efficiency ratio = 0.1 * ΔT, ΔT = ambient temperature of the computer room - air temperature.

[0064] Step S102: Input the cooling effect parameter data into the pre-trained energy-saving model to predict energy saving, and obtain the target combination of computer room cooling equipment that meets the cooling energy efficiency conditions and the target operating temperature of the first cooling equipment. The energy-saving model is trained based on the PSO-BP neural network.

[0065] After obtaining the cooling impact parameter data, the cooling impact parameter data is input into the pre-trained energy-saving model for energy-saving prediction, to obtain the target combination of computer room cooling equipment that meets the cooling energy efficiency conditions and the target operating temperature of the first cooling equipment. The energy-saving model is trained based on the PSO-BP neural network.

[0066] The energy-saving model training process includes: acquiring sample data, which includes: cooling influence parameter data, computer room cooling equipment combination, and actual operating temperature of the first cooling equipment;

[0067] The PSO-BP neural network is trained based on sample data to obtain an energy-saving model. The energy-saving model includes the corresponding relationships between cooling influence parameter data, cooling energy efficiency conditions, computer room cooling equipment combination, and the actual operating temperature of the first cooling equipment.

[0068] Because BP neural network prediction models suffer from slow convergence, low accuracy, and a tendency to get trapped in local minima, PSO (Particle Swarm Optimization) is used to optimize the initial weights and thresholds of the BP neural network prediction model before retraining and making predictions. This significantly improves the convergence speed and accuracy of the BP neural network prediction model.

[0069] (1) In the PSO algorithm, the solution to each optimization problem is regarded as a bird, or "particle", in the search space. The algorithm first generates an initial solution, randomly initializing N particles in the D-dimensional feasible solution space to form a population z = {z1, z2, z3, ..., z}. N Here, air temperature, the set operating temperature of the first refrigeration unit, and the temperature difference between the machine room and the environment are represented as particles. Each particle has a position and velocity vector, z. i ={z i1 ,z i2 ,z i3 ,…,z iN}, and v i ={v i1 ,vi2 ,v i3 ,…,v iN Then, the fitness value is calculated based on the objective function for iterative search. Each particle updates its velocity and position according to the following formula: v kl (t+1)=ωv kl (t)+c1r1[p id -z id (t)]+c2r2[p gd -z id (t)]

[0070] z id (t+1)=z id (t)+v id (t+1)

[0071] In this application scenario, ω is set to 0.75, the acceleration constants c1 = c2 = 2, and r1 and r2 are random numbers between 0 and 1.

[0072] (2) A BP neural network is a neural network with three or more layers, including an input layer, an output layer, and hidden layers, such as... Figure 1E As shown, its training algorithm includes two processes: forward propagation and backward propagation. Input information is passed to the output layer through the hidden layer. The output signal is compared with the predicted signal. If there is an error, the error backpropagation method is used to return the error information along the original network, correcting the connection weights of the network layer by layer from the output layer through the intermediate layers.

[0073] Based on the above analysis of the input variables of the PSO-BP neural network model, air temperature, the set operating temperature of the first refrigeration unit, and the temperature difference between the computer room and the environment are the key factors affecting the target combination of the computer room refrigeration equipment and the target operating temperature of the first refrigeration unit in this case. A 3-layer BP neural network structure is adopted, with 3 neurons in the input layer and the output layer containing the target combination of the computer room refrigeration equipment and the target operating temperature of the first refrigeration unit in this case. The number of hidden layer factors is calculated as 7 using the following formula:

[0074] m = 2n + 1

[0075] In the formula: m is the number of neurons in the hidden layer; n is the number of neurons in the input layer.

[0076] 1) The input parameters have different material meanings. To avoid large absolute errors for large numerical components and small absolute errors for small numerical components in the input or output vectors, normalization is performed on the input and output respectively:

[0077]

[0078] 2) Initialize the size of the particle swarm, including the number of particles N, the length of each particle D, the initial velocity of the particles, and their positions. In the experiment, the number of particles N is taken as 50, and the formula for calculating the length of each particle L is: L = g1g2 + g2g3 + g2 + g3, where g1, g2, and g3 are the factor numbers of the input layer, hidden layer, and output layer of the neural network, respectively. The above formula yields L = 44.

[0079] 3) The sum of the absolute values ​​of the errors between the predicted and observed values ​​is used as the particle fitness value. n is the number of samples, o i Let e ​​be the observed value of sample i. i Let be the predicted value for sample i.

[0080] 4) Compare particle fitness to determine the individual extreme point and the global optimal extreme point for each particle. The comparison rule is as follows:

[0081] If F p <P bf Then P bf =F p P b =X i Otherwise P b and P bf constant.

[0082] If F p <G bf Then G bf =F p G b =X i Otherwise G b and G bf constant.

[0083] F p It is the particle's current fitness value, P. bf It is the individual optimal fitness value of the particle, G. bf It is the global optimal fitness value of the population, P b It is the optimal value for an individual particle, G. b It is the global optimum of the population, X i For the currently calculated particle.

[0084] 5) The particle position and velocity are updated using the v-value in the PSO algorithm. kl (t), z id (t), the initial velocity and position are randomly assigned using the rand() function.

[0085] Determine if the cooling conditions are met. If yes, output the result; otherwise, jump to calculate the fitness value for each particle. Figure 1F As shown.

[0086] The model's training and testing samples both utilize data obtained from the three types of experimental analysis described above, totaling 180 sets of data: 150 sets for training and 30 sets for testing. Using air temperature, the set operating temperature of the primary cooling equipment, and the temperature difference between the computer room and the surrounding environment as key factors, and incorporating them as inputs to the PSO-BP neural network model, both prediction accuracy and convergence speed are significantly improved, meeting practical needs and demonstrating important application value for intelligent cooling and energy saving in computer room air conditioning systems. Figure 1G As shown.

[0087] Step S103: Based on the target operating temperature of the first cooling equipment, the corresponding start-up and shutdown temperatures of each cooling equipment in the target combination of computer room cooling equipment are controlled according to the start-up and shutdown temperatures of each cooling equipment to achieve energy saving in the computer room.

[0088] After determining the target operating temperature of the first cooling equipment and the target combination of cooling equipment in the computer room, the start-up or shutdown of the corresponding cooling equipment can be controlled according to the start-up and shutdown temperatures of each cooling equipment in the target combination of cooling equipment in the computer room based on the target operating temperature of the first cooling equipment, so as to achieve energy saving in the computer room.

[0089] In an optional embodiment of the present invention, the start-up and shutdown temperatures corresponding to each refrigeration device in the target combination of computer room refrigeration devices, based on the target operating temperature of the first refrigeration device, further include:

[0090] Calculate the temperature difference between the target operating temperature of the first refrigeration unit this time and the target operating temperature of the first refrigeration unit in the previous time;

[0091] If the temperature difference is within the preset temperature difference range, then the start-up and shutdown temperatures of each refrigeration device in the target combination of computer room refrigeration equipment are determined according to the target operating temperature of the first refrigeration device in the previous test.

[0092] If the temperature difference is not within the preset temperature difference range, then the start-up and shutdown temperatures of each refrigeration device in the target combination of computer room refrigeration equipment will be determined according to the target operating temperature of the first refrigeration device.

[0093] Specifically, to improve the energy efficiency of the computer room, after determining the target operating temperature of the first cooling equipment, the temperature difference between the current target operating temperature and the previous target operating temperature is calculated. It is then determined whether this temperature difference falls within a preset temperature difference range, which is ±0.5 degrees Celsius. If the temperature difference is within the preset range, the start-up and shutdown temperatures of each cooling device in the target combination of computer room cooling equipment are calculated based on the previous target operating temperature. If the temperature difference is not within the preset range, the start-up and shutdown temperatures of each cooling device in the target combination of computer room cooling equipment are calculated based on the current target operating temperature.

[0094] In addition, the energy efficiency ratio of the current target combination of computer room cooling equipment can be compared with that of the previous target combination of computer room cooling equipment. If the change in energy efficiency ratio is less than or equal to 2%, the on / off temperature of each cooling device in the target combination of computer room cooling equipment will be determined based on the target operating temperature of the first cooling equipment in the previous test. If the change in energy efficiency ratio is greater than 2%, the on / off temperature of each cooling device in the target combination of computer room cooling equipment will be determined based on the target operating temperature of the first cooling equipment in the current test.

[0095] The calculation methods for start-up and shutdown temperatures differ depending on the type of refrigeration equipment. Specifically, when the first refrigeration equipment includes air conditioning, the start-up and shutdown temperatures corresponding to each refrigeration device in the target combination of computer room refrigeration equipment are further included based on the target operating temperature of the first refrigeration equipment.

[0096] Calculate the sum of the target operating temperature of the first refrigeration equipment and the first temperature threshold, and determine the calculated temperature as the start-up temperature of the first refrigeration equipment;

[0097] Calculate the difference between the target operating temperature of the first refrigeration equipment and the second temperature threshold, and determine the calculated temperature as the shutdown temperature of the first refrigeration equipment.

[0098] The first and second temperature thresholds are set based on experience. For example, the first temperature threshold is 2.2 and the second temperature threshold is 1.8. The target operating temperature of the first refrigeration equipment is 28 degrees. The refrigeration equipment combination consists of two air conditioners. The start-up temperature of the two air conditioners is 28 degrees + t1 = 28 degrees + 2.2 = 30.2 degrees, that is, the air conditioners are turned on when the return air temperature reaches 30.2 degrees. The shutdown temperature is 28 degrees - t2 = 28 degrees - 1.8 = 26.2 degrees, that is, the air conditioners are turned off when the return air temperature drops to 26.2 degrees.

[0099] The computer room's cooling equipment includes: when the second cooling equipment is included, the second cooling equipment includes: a fresh air unit; based on the target operating temperature of the first cooling equipment, the corresponding start-up and shutdown temperatures of each cooling device in the target combination of computer room cooling equipment further include:

[0100] The target ambient temperature of the computer room is determined based on the target operating temperature of the first refrigeration equipment. For example, a temperature relationship table between the target operating temperature of the first refrigeration equipment and the target ambient temperature of the computer room can be set up, and the target ambient temperature of the computer room corresponding to the target operating temperature of the first refrigeration equipment can be determined by looking up the table.

[0101] The sum of the target ambient temperature of the computer room and the first temperature threshold is used to determine the start-up temperature of the second cooling equipment.

[0102] The difference between the target ambient temperature of the computer room and the second temperature threshold is used to determine the calculated temperature as the shutdown temperature of the second cooling device.

[0103] For example: If the target operating temperature of the first refrigeration unit is 28 degrees Celsius, and the refrigeration unit combination is one fresh air unit, then based on the temperature relationship table, the target ambient temperature of the computer room corresponding to the target operating temperature of this first refrigeration unit is calculated to be 29 degrees Celsius. Then the start-up temperature of the fresh air unit = 29 degrees Celsius + t1 = 29 degrees Celsius + 2.2 = 31.2 degrees Celsius, that is, the fresh air unit starts when the ambient temperature of the computer room rises to 31.2 degrees Celsius, and the shutdown temperature = 29 degrees Celsius - t2 = 29 degrees Celsius - 1.8 = 27.2 degrees Celsius, that is, the unit shuts down when the ambient temperature of the computer room drops to 27.2 degrees Celsius.

[0104] In an optional embodiment of the present invention, for different types of computer rooms, the start-up temperature of each cooling device in the target combination of computer room cooling devices, based on the target operating temperature of the first cooling device, further includes:

[0105] If the computer room is a type 1 computer room, determine whether the target operating temperature of the first cooling equipment is greater than the third temperature threshold; if not, determine the target operating temperature of the first cooling equipment as the start-up temperature of each cooling equipment in the target combination of computer room cooling equipment; if so, determine the third temperature threshold as the start-up temperature of each cooling equipment in the target combination of computer room cooling equipment.

[0106] If the computer room is a type 2 computer room, determine whether the target operating temperature of the first cooling equipment is greater than the fourth temperature threshold; if not, determine the target operating temperature of the first cooling equipment as the start-up temperature of each cooling equipment in the target combination of computer room cooling equipment; if so, determine the fourth temperature threshold as the start-up temperature of each cooling equipment in the target combination of computer room cooling equipment.

[0107] For aggregation server rooms and OLTs, if the target operating temperature of the first cooling equipment is below 28 degrees Celsius, then the system will be powered on at that target temperature. If the target operating temperature exceeds 28 degrees Celsius, then the system will be powered on at 28 degrees Celsius. For ordinary server rooms, if the target operating temperature of the first cooling equipment is below 30 degrees Celsius, then the system will be powered on at that target temperature. If the target operating temperature exceeds 30 degrees Celsius, then the system will be powered on at 30 degrees Celsius.

[0108] The system generates and issues energy-saving start-up commands to the refrigeration equipment in the refrigeration unit via the environmental monitoring system. If the command content changes, it is issued immediately; otherwise, it is issued every 20 minutes. Shutdown commands are issued to refrigeration equipment not included in the refrigeration unit, once per hour, until they are included in the refrigeration unit.

[0109] This invention fully analyzes the key factors affecting the cooling power and energy efficiency ratio of refrigeration equipment. Through experimental data, it calculates the impact of computer room air temperature, operating temperature, and internal / external temperature difference on cooling power, scientifically guiding intelligent temperature control of the computer room and ensuring stable operation while improving energy efficiency. This solution constructs a PSO-BP neural network algorithm prediction model. By training the model with data, it obtains the target combination of computer room refrigeration equipment and the target operating temperature of the first refrigeration equipment. This contrasts sharply with existing methods of manually adjusting temperature and switching air conditioners on and off, greatly improving the accuracy of control and intelligent energy saving. Besides its application in intelligent energy saving for computer room refrigeration, this solution based on the PSO-BP neural network prediction model is also applicable to power prediction in similar fields such as electricity and wind power, demonstrating good versatility and broad application prospects.

[0110] According to the solution provided in the above embodiments of the present invention, the intelligent temperature control of the computer room is scientifically guided to improve the energy efficiency ratio while ensuring the stable operation of the computer room; the target combination of computer room cooling equipment that meets the cooling energy efficiency conditions and the target operating temperature of the first cooling equipment are predicted by the energy-saving model, which greatly improves the accuracy of control and the intelligence of energy saving.

[0111] Figure 2 A schematic diagram of the structure of the data center energy-saving device provided in an embodiment of the present invention is shown. Figure 2 As shown, the device includes: an acquisition module 201, a prediction module 202, and a control module 203.

[0112] The acquisition module 201 is adapted to acquire cooling influence parameter data related to the cooling of each cooling device in the computer room. The cooling influence parameters include: computer room air temperature, temperature difference between the computer room and the environment, and the set operating temperature of the first cooling device.

[0113] Prediction module 202 is adapted to input cooling impact parameter data into a pre-trained energy-saving model for energy-saving prediction, and obtain the target combination of computer room cooling equipment that meets the cooling energy efficiency conditions and the target operating temperature of the first cooling equipment in this case. The energy-saving model is obtained by training a PSO-BP neural network.

[0114] The control module 203 is adapted to control the start-up or shutdown of the corresponding cooling equipment based on the start-up and shutdown temperatures of each cooling equipment in the target combination of computer room cooling equipment according to the target operating temperature of the first cooling equipment, so as to achieve energy saving in the computer room.

[0115] Optionally, the control module is further adapted to: calculate the temperature difference between the current target operating temperature of the first refrigeration equipment and the previous target operating temperature of the first refrigeration equipment;

[0116] If the temperature difference is within the preset temperature difference range, then the start-up and shutdown temperatures of each refrigeration device in the target combination of computer room refrigeration equipment are determined according to the target operating temperature of the first refrigeration device in the previous test.

[0117] If the temperature difference is not within the preset temperature difference range, then the start-up and shutdown temperatures of each refrigeration device in the target combination of computer room refrigeration equipment will be determined according to the target operating temperature of the first refrigeration device.

[0118] Optionally, the first refrigeration equipment includes: an air conditioner;

[0119] The control module is further adapted to: calculate the sum of the target operating temperature of the first refrigeration equipment and the first temperature threshold, and determine the calculated temperature as the start-up temperature of the first refrigeration equipment;

[0120] Calculate the difference between the target operating temperature of the first refrigeration equipment and the second temperature threshold, and determine the calculated temperature as the shutdown temperature of the first refrigeration equipment.

[0121] Optionally, each cooling device in the computer room includes: a second cooling device, wherein the second cooling device includes: a fresh air unit;

[0122] The control module is further adapted to: determine the target ambient temperature of the computer room based on the target operating temperature of the first refrigeration equipment;

[0123] The sum of the target ambient temperature of the computer room and the first temperature threshold is used to determine the start-up temperature of the second cooling equipment.

[0124] The difference between the target ambient temperature of the computer room and the second temperature threshold is used to determine the calculated temperature as the shutdown temperature of the second cooling device.

[0125] Optionally, the control module is further adapted to: if the computer room is a first type of computer room, determine whether the target operating temperature of the first cooling equipment is greater than the third temperature threshold.

[0126] If not, the target operating temperature of the first refrigeration equipment will be determined as the start-up temperature of each refrigeration equipment in the target combination of refrigeration equipment in the computer room;

[0127] If so, the third temperature threshold is determined as the start-up temperature of each cooling device in the target combination of computer room cooling equipment.

[0128] Optionally, the control module is further adapted to: if the computer room is a second type of computer room, determine whether the target operating temperature of the first cooling equipment is greater than the fourth temperature threshold.

[0129] If not, the target operating temperature of the first refrigeration equipment will be determined as the start-up temperature of each refrigeration equipment in the target combination of refrigeration equipment in the computer room;

[0130] If so, the fourth temperature threshold is determined as the start-up temperature of each cooling device in the target combination of computer room cooling equipment.

[0131] Optionally, the device further includes: an energy-saving model training module, suitable for acquiring sample data, wherein the sample data includes: cooling influence parameter data, computer room cooling equipment combination, and actual operating temperature of the first cooling equipment;

[0132] The PSO-BP neural network is trained based on sample data to obtain an energy-saving model. The energy-saving model includes the corresponding relationships between cooling influence parameter data, cooling energy efficiency conditions, computer room cooling equipment combination, and the actual operating temperature of the first cooling equipment.

[0133] According to the solution provided in the above embodiments of the present invention, the intelligent temperature control of the computer room is scientifically guided to improve the energy efficiency ratio while ensuring the stable operation of the computer room; the target combination of computer room cooling equipment that meets the cooling energy efficiency conditions and the target operating temperature of the first cooling equipment are predicted by the energy-saving model, which greatly improves the accuracy of control and the intelligence of energy saving.

[0134] This invention provides a non-volatile computer storage medium storing at least one executable instruction that can execute the data center energy-saving method in any of the above method embodiments.

[0135] Figure 3 The diagram shows a structural schematic of a computing device provided in an embodiment of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computing device.

[0136] like Figure 3As shown, the computing device may include a processor, a communications interface, memory, and a communications bus.

[0137] The processor, communication interface, and memory communicate with each other via a communication bus. The communication interface is used to communicate with other network elements, such as clients or other servers. The processor executes programs, specifically the relevant steps described in the above-described embodiment of the data center energy-saving method for computing devices.

[0138] Specifically, the program may include program code, which includes computer operation instructions.

[0139] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0140] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0141] Specifically, the program can be used to cause the processor to execute the data center energy-saving method in any of the above method embodiments. The specific implementation of each step in the program can be found in the corresponding descriptions of the steps and units in the above data center energy-saving embodiments, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0142] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the embodiments of the present invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the embodiments of the present invention.

[0143] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0144] Similarly, it should be understood that, in order to streamline the embodiments of the invention and aid in understanding one or more of the various inventive aspects, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0145] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0146] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0147] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The embodiments of the present invention can also be implemented as device or apparatus programs (e.g., computer programs and computer program products) for performing part or all of the methods described herein. Such programs implementing the embodiments of the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0148] It should be noted that the above embodiments are illustrative of the present invention and not restrictive of the invention, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the present invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for energy saving in a computer room, comprising: Acquire cooling-influencing parameter data related to the cooling of each cooling device in the computer room, wherein the cooling-influencing parameters include: computer room air temperature, temperature difference between the computer room and the environment, and the set operating temperature of the first cooling device; The cooling effect parameter data is input into a pre-trained energy-saving model for energy-saving prediction, to obtain the target combination of computer room cooling equipment that meets the cooling energy efficiency conditions and the target operating temperature of the first cooling equipment in this case. The energy-saving model is obtained by training a PSO-BP neural network. Based on the target operating temperature of the first refrigeration equipment, calculate the start-up and shutdown temperatures of each refrigeration equipment in the target combination of refrigeration equipment in the computer room, and control the start-up or shutdown of the corresponding refrigeration equipment according to the start-up and shutdown temperatures of each refrigeration equipment to achieve energy saving in the computer room. The first refrigeration equipment includes: an air conditioner; The step of calculating the start-up and shutdown temperatures of each refrigeration device in the target combination of computer room refrigeration equipment based on the target operating temperature of the first refrigeration equipment further includes: Calculate the sum of the target operating temperature of the first refrigeration equipment and the first temperature threshold, and determine the calculated temperature as the start-up temperature of the first refrigeration equipment; Calculate the difference between the target operating temperature of the first refrigeration equipment and the second temperature threshold, and determine the calculated temperature as the shutdown temperature of the first refrigeration equipment.

2. The method according to claim 1, wherein, The step of calculating the start-up and shutdown temperatures of each refrigeration device in the target combination of computer room refrigeration equipment based on the target operating temperature of the first refrigeration equipment further includes: Calculate the temperature difference between the target operating temperature of the first refrigeration unit this time and the target operating temperature of the first refrigeration unit in the previous time; If the temperature difference is within the preset temperature difference range, then the start-up and shutdown temperatures of each refrigeration device in the target combination of computer room refrigeration equipment are calculated based on the previous target operating temperature of the first refrigeration device. If the temperature difference is not within the preset temperature difference range, the start-up and shutdown temperatures of each refrigeration device in the target combination of computer room refrigeration equipment are calculated based on the target operating temperature of the first refrigeration equipment.

3. The method according to claim 1 or 2, wherein, The cooling equipment in the computer room includes: a second cooling unit, wherein the second cooling unit includes: a fresh air unit; The step of calculating the start-up and shutdown temperatures of each refrigeration device in the target combination of computer room refrigeration equipment based on the target operating temperature of the first refrigeration equipment further includes: The target ambient temperature of the computer room is determined based on the target operating temperature of the first refrigeration equipment. The sum of the target ambient temperature of the computer room and the first temperature threshold is used to determine the start-up temperature of the second cooling equipment. The difference between the target ambient temperature of the computer room and the second temperature threshold is used to determine the calculated temperature as the shutdown temperature of the second cooling device.

4. The method according to claim 1, wherein, Based on the target operating temperature of the first refrigeration equipment, the calculation of the start-up temperature of each refrigeration unit in the target combination of computer room refrigeration equipment further includes: If the computer room is a type 1 computer room, determine whether the target operating temperature of the first cooling equipment is greater than the third temperature threshold. If not, the target operating temperature of the first refrigeration equipment will be determined as the start-up temperature of each refrigeration equipment in the target combination of computer room refrigeration equipment; If so, the third temperature threshold is determined as the start-up temperature of each cooling device in the target combination of computer room cooling equipment.

5. The method according to claim 1 or 4, wherein, Based on the target operating temperature of the first refrigeration equipment, the calculation of the start-up temperature of each refrigeration unit in the target combination of computer room refrigeration equipment further includes: If the computer room is a type 2 computer room, determine whether the target operating temperature of the first cooling equipment is greater than the fourth temperature threshold. If not, the target operating temperature of the first refrigeration equipment will be determined as the start-up temperature of each refrigeration equipment in the target combination of computer room refrigeration equipment; If so, the fourth temperature threshold is determined as the start-up temperature of each cooling device in the target combination of computer room cooling equipment.

6. The method according to claim 1 or 2, wherein, The energy-saving model training process includes: Obtain sample data, wherein the sample data includes: cooling effect parameter data, computer room cooling equipment combination, and actual operating temperature of the first cooling equipment; The PSO-BP neural network is trained on the sample data to obtain an energy-saving model; wherein, the energy-saving model includes: the correspondence between cooling influence parameter data, cooling energy efficiency conditions, computer room cooling equipment combination, and the actual operating temperature of the first cooling equipment.

7. An energy-saving device for computer rooms, comprising: The acquisition module is adapted to acquire cooling influence parameter data related to the cooling of each cooling device in the computer room, wherein the cooling influence parameters include: computer room air temperature, temperature difference between the computer room and the environment, and the set operating temperature of the first cooling device; The prediction module is adapted to input the cooling impact parameter data into a pre-trained energy-saving model to perform energy-saving prediction, and obtain the target combination of computer room cooling equipment that meets the cooling energy efficiency conditions and the target operating temperature of the first cooling equipment in this case. The energy-saving model is obtained by training a PSO-BP neural network. The control module is adapted to calculate the start-up and shutdown temperatures of each refrigeration device in the target combination of computer room refrigeration equipment based on the target operating temperature of the first refrigeration equipment, and to control the start-up or shutdown of the corresponding refrigeration equipment according to the start-up and shutdown temperatures of each refrigeration device, so as to achieve energy saving in the computer room. The first refrigeration equipment includes: an air conditioner; The control module is further adapted to: calculate the sum of the target operating temperature of the first refrigeration equipment and the first temperature threshold, and determine the calculated temperature as the start-up temperature of the first refrigeration equipment; Calculate the difference between the target operating temperature of the first refrigeration equipment and the second temperature threshold, and determine the calculated temperature as the shutdown temperature of the first refrigeration equipment.

8. A computing device, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the data center energy-saving method as described in any one of claims 1-6.

9. A computer storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the data center energy-saving method as described in any one of claims 1-6.

Images