Machine room energy-saving regulation and control program evaluation method, system, equipment and medium

Abstract

The invention provides a machine room energy-saving regulation and control program evaluation method, system and device and a medium, and the method comprises the steps: obtaining a plurality of simulation data of a machine room environment, the simulation data comprising first simulation data defined in a preset scene and second simulation data generated based on a pre-constructed environment simulation model; based on a to-be-tested energy-saving regulation and control program, the multiple pieces of simulation data are processed, and a regulation and control strategy corresponding to each piece of simulation data is output; wherein the energy-saving regulation and control program is obtained by packaging a pre-constructed energy-saving regulation and control model; and obtaining an expected regulation and control result corresponding to each piece of simulation data, comparing each regulation and control strategy with the corresponding expected regulation and control result, and finally determining an evaluation result of the energy-saving regulation and control program. The evaluation accuracy of the energy-saving regulation and control program can be improved, and potential problems in the energy-saving regulation and control program can be found in time.

Description

Technical Field

[0001] The present invention relates to the field of big data AI energy-saving technology, and in particular to a method, system, device and medium for evaluating a computer room energy-saving control program. Background Art

[0002] In recent years, the attention paid to energy conservation and emission reduction in computer rooms has gradually increased, and with the development of big data and artificial intelligence technology, more and more computer rooms have begun to control air-conditioning equipment through energy-saving control programs based on AI models. These programs can automatically adjust the parameters of computer room equipment according to the real-time conditions of the computer room (such as ambient temperature, humidity, etc.), thereby achieving the goal of energy conservation and emission reduction. However, the current energy-saving control programs lack rigorous testing and evaluation, resulting in the inability to discover potential problems in the energy-saving control programs during the development phase, resulting in frequent failures of the computer room energy-saving control programs when they are put into actual application environments; and the environmental conditions in the computer room are varied and complex, and only simple simulation tests are performed on a small number of conditions. After the energy-saving control program is launched, it is still possible to encounter environmental conditions that will cause program interruptions and errors, which cannot improve the accuracy of energy-saving control, let alone ensure the safety of the computer room environment and the energy-saving effect that can be achieved. Summary of the invention

[0003] The embodiment of the present invention provides a method, system, device and medium for evaluating a computer room energy-saving control program to solve the problems existing in the related technologies. The technical solution is as follows:

[0004] In a first aspect, an embodiment of the present invention provides a method for evaluating a computer room energy-saving control program, comprising:

[0005] Acquire multiple simulation data of the computer room environment, the simulation data including first simulation data defined under a preset scenario and second simulation data generated based on a pre-built environment simulation model;

[0006] Based on the energy-saving control program to be tested, multiple simulation data are processed respectively, and the control strategy corresponding to each simulation data is output; wherein the energy-saving control program is obtained by encapsulating the pre-built energy-saving control model;

[0007] Obtain the expected control result corresponding to each simulation data, compare each control strategy with its corresponding expected control result, and finally determine the evaluation result of the energy-saving control program.

[0008] In one embodiment, the desired regulatory outcome includes:

[0009] a first expected control indicator defined by the target computer room when encountering a preset scenario with a specified problem, the first expected control indicator including an expected control operation and an expected response time; and,

[0010] The second expected indicator corresponding to the target computer room in the intelligent scenario includes the number of alarms, alarm duration, fault severity, equipment control frequency, and energy-saving effect.

[0011] In one embodiment, each control strategy is compared with its corresponding expected control result, and finally determining the evaluation result of the energy-saving control program to be tested includes:

[0012] Compare the first control strategy with the first expected control index and output a first evaluation result; the first control strategy is the result output by analyzing the first simulation data based on the energy-saving control model; and

[0013] Performing indicator statistics on the second control strategy to obtain indicator results; comparing the indicator results with the second expected indicators, and outputting a second evaluation result; wherein the second control strategy is the result output by analyzing the second simulation data based on the energy-saving control model.

[0014] In one embodiment, it further includes:

[0015] Acquire signal data from a specified data source, integrate the signal data, and obtain a first data set containing device signals at all time steps;

[0016] Based on the first data set, all device signals in the previous time step are used as input of the memory network model, and the device signals in the next time step are used as output of the memory network model. The memory network model is trained to obtain an environment simulation model.

[0017] In one embodiment, it further includes:

[0018] Acquire signal data from a specified data source, and integrate the signal data to obtain a second data set;

[0019] Based on the second data set, the device signals and environmental conditions are used as the input of the learning model, the optimized control strategy is used as the output of the learning model, the learning model is trained, and the learning model is optimized through a preset reward function to obtain an energy-saving control model.

[0020] In one embodiment, it further includes:

[0021] Determining data subsets in a plurality of different continuous time periods according to the second data set, and processing the plurality of data subsets to obtain initial state data for defining an initial state of a computer room environment;

[0022] The environment simulation model is initialized based on the initial state data, so that the environment simulation model simulates the dynamic changes of the computer room environment from the initial state.

[0023] In one embodiment, it further includes:

[0024] The simulation data is stored in a designated storage unit, and the stored simulation data is backed up regularly through the designated storage unit to obtain the backup data and store it in the designated storage unit.

[0025] In a second aspect, an embodiment of the present invention provides a computer room energy-saving control program evaluation system, which executes the computer room energy-saving control program evaluation method as described above.

[0026] In a third aspect, an embodiment of the present invention provides an electronic device, the device comprising: a memory and a processor. The memory and the processor communicate with each other through an internal connection path, the memory is used to store instructions, the processor is used to execute the instructions stored in the memory, and when the processor executes the instructions stored in the memory, the processor executes the method in any one of the above-mentioned embodiments.

[0027] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a computer, the method in any one of the above-mentioned embodiments is executed.

[0028] The advantages or beneficial effects of the above technical solution include at least:

[0029] The present invention predefines corresponding first simulation data for preset scenarios where environmental or data problems may occur, and simultaneously collects second simulation data generated based on a pre-built environmental simulation model, and generates corresponding control strategies for the first simulation data and the second simulation data respectively through the energy-saving control model, and then evaluates the control strategies, so as to improve the evaluation accuracy of the energy-saving control program and promptly discover potential problems in the energy-saving control program, so as to facilitate the subsequent reasonable optimization of the energy-saving control program and further improve the energy-saving control effect.

[0030] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in the present invention and should not be regarded as limiting the scope of the present invention.

[0032] Figure 1 It is a flow chart of the method for evaluating the energy-saving control program of a computer room of the present invention;

[0033] Figure 2 It is a schematic diagram of the execution steps of the method for evaluating the energy-saving control program of a computer room of the present invention;

[0034] Figure 3 A schematic diagram of the source of an example of the environmental simulation program of the present invention;

[0035] Figure 4 This is a schematic diagram of the unit connection of the computer room energy-saving control program evaluation system of the present invention;

[0036] Figure 5 A schematic diagram showing the relationship between an environment simulation program instance, an energy-saving control program instance and an evaluation instance of the present invention;

[0037] Figure 6 It is a schematic diagram of the interaction and logical time synchronization flow of each program instance of the present invention;

[0038] Figure 7 The structure block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0040] In recent years, with the increasing attention paid by the country to energy conservation and emission reduction in computer rooms, as well as the development of big data and artificial intelligence technologies, more and more computer rooms have begun to implement air conditioning equipment control through energy-saving control programs based on AI models. These programs can generate control strategies for air conditioning equipment based on the real-time conditions of the computer room (such as ambient temperature, humidity, etc.), and send them through the gateway interface to remotely control computer room equipment such as air conditioners. These programs need to reduce unnecessary refrigeration redundancy as much as possible within the safe range of the computer room environment to achieve the goal of energy conservation and emission reduction. In order to ensure the environmental safety of the computer room and the energy-saving effect that can be achieved, rigorous testing and evaluation must be carried out before the model is deployed online to discover and deal with potential problems. After the evaluation is passed, the computer room energy-saving control program can be put into the production environment.

[0041] At present, the evaluation methods of energy-saving control programs adopted by the industry mainly include code unit testing, integration testing, and manual evaluation. Although such methods can avoid problems such as program interruption caused by logic errors after the algorithm control program is launched to a certain extent, they also have the following shortcomings:

[0042] (1) Limited evaluation conditions. Unit testing and integration testing can only be performed on a small number of preset conditions. However, the environmental conditions in the computer room are varied and complex. After the energy-saving control program is launched, it is still possible to encounter environmental conditions that may cause program interruption or errors.

[0043] (2) It is difficult to evaluate the safety and energy-saving effects of the control. Unit testing and integration testing can only ensure that the program does not interrupt or report errors under the preset conditions, but cannot evaluate whether the control strategy generated by the program is reasonable. An unreasonable strategy may cause the computer room environment temperature to be too high or too low, affecting the safety and energy-saving effects of the computer room environment.

[0044] (3) There are potential safety hazards. When running energy-saving control programs and conducting evaluation tests in a real computer room environment, the computer room environment will be actually affected. If the computer room carries important business, the impact will be greater if problems occur.

[0045] (4) Long evaluation cycle. Due to factors such as signal acquisition frequency, equipment control interval, and environmental change lag, conducting a manual evaluation in a real environment often requires waiting for several hours or even dozens of hours, which seriously affects the efficiency of R&D iteration.

[0046] (5) It is difficult to achieve automated batch evaluation. The manual evaluation method is limited by human resources and cannot be automated or batched. When the energy-saving control program is frequently upgraded and iterated and the environmental conditions of the computer room to be evaluated are diverse, the labor cost required is very huge.

[0047] When the energy-saving control program is frequently upgraded and iterated and a large number of computer rooms are involved, the adverse effects of the above problems will be particularly obvious.

[0048] In order to solve the above problems, in the first aspect, an embodiment of the present invention provides a method for evaluating a computer room energy-saving control program, such as Figure 1 , Figure 2 As shown, the specific method includes the following steps:

[0049] Step S1: Acquire multiple simulation data of the computer room environment, where the simulation data includes first simulation data defined under a preset scenario and second simulation data generated based on a pre-built environment simulation model.

[0050] Before evaluating the effect of energy-saving control, various parameters need to be configured to specify the specific execution methods of various key operations in each execution unit. The configuration content includes the specific parameters and corresponding values ​​of each execution unit, among which the execution unit includes the signal acquisition unit, data storage unit, environment simulation unit, interface synchronization unit, control strategy unit, result evaluation unit, etc. These configurations will be saved in the data storage unit for other units to read and use.

[0051] After completing the parameter configuration, the signal acquisition unit collects signal data from the specified data source such as the room dynamic environment system and organizes it into relevant data sets. The organized data sets will be saved in the data storage unit and can be read by other execution units such as the environmental simulation unit, control strategy unit, and result evaluation unit for training models, evaluating energy-saving control programs, etc.

[0052] The data sets mainly include computer room information data sets, equipment information data sets, signal information data sets, historical signal data sets, etc. Among them, the computer room information, equipment information and signal information data sets provide the identification, characteristics and attached object lists of related objects, which can be regarded as static data; while the historical signal data set provides the values ​​of computer room equipment signals at multiple time points, which can be regarded as dynamic data.

[0053] In this embodiment, the collected signal data is integrated through feature engineering to obtain a first data set required for training the environmental simulation model of the target computer room and a second data set required for training the energy-saving control model of the target computer room, which are used to train the computer room environmental simulation model and the computer room energy-saving control model respectively.

[0054] Specifically, the first data set used to train the environmental simulation model contains static data of the equipment in the computer room and historical signal data (ambient temperature and humidity, air conditioning control parameters, energy consumption of electric meters, etc.). Using the long short-term memory network model architecture, the model input corresponding to each time step is all the device signals of that time step, and the model output is the device signal of the next time step. The model is trained using historical signal data to learn the dependencies between device signals and their evolution over time. After the training is completed, the environmental simulation model obtained can predict the values ​​of each device signal, such as temperature, humidity, energy consumption, etc., at each time interval (1 minute), forming a multivariate time series prediction task.

[0055] The second data set used to train the energy-saving control model contains static data of the equipment in the computer room and historical signal data (ambient temperature and humidity, air conditioning control parameters, meter energy consumption, etc.). The policy gradient method of the deep reinforcement learning architecture is used to process the input device signals and environmental conditions, and output the optimized control strategy. The control strategy refers to the air conditioning control signal (such as temperature and humidity set values, switches, etc.); all current device states and environmental conditions are used as the state space, and all controllable actions are used as the action space; and the model is optimized through a reward function related to the energy-saving effect, rewarding strategies with low energy consumption and stable environmental parameters, and punishing unreasonable control behaviors, and finally obtaining an energy-saving control model. The energy-saving control model continuously interacts with the simulated environment, selects actions and obtains feedback at each time step, and gradually optimizes the control strategy to maximize the cumulative reward.

[0056] For the energy-saving control model, the reward function used in this embodiment is expressed as follows:

[0057] Reward=-(α×EnergyConsumption+b×EnvironmentDeviation);

[0058] Wherein, EnergyConsumption: represents the air conditioning energy consumption value of the current time step, and the goal is to minimize energy consumption; in this embodiment, the time step length used is 1 minute, so this variable represents the energy consumption value within 1 minute;

[0059] EnvironmentDeviation: represents the deviation value of environmental parameters, which measures the deviation between parameters such as temperature and humidity and the target value. The goal is to minimize the deviation to keep the environment stable. In this embodiment, 28 degrees Celsius is taken as the target value of the environmental temperature. If the actual temperature is 30 degrees Celsius, the deviation is 2 degrees Celsius.

[0060] a, b: represent weight coefficients, which are used to balance the importance of energy saving effect and environmental stability; in this embodiment, a=1, b=0.5.

[0061] After completing the training of the above-mentioned environmental simulation model and energy-saving control model, the environmental simulation model is encapsulated into an environmental simulation program and integrated into the environmental simulation unit, and the energy-saving control model is encapsulated into an energy-saving control program and integrated into the control strategy unit in preparation for deployment in subsequent steps.

[0062] The environmental simulation unit provides static data about the computer room, equipment, and signals, as well as dynamic data of simulated environmental signals to the control strategy unit through the interface synchronization unit; at the same time, it can also receive control signals from the control strategy unit and influence changes in the simulated environment accordingly.

[0063] The static data provided by the environmental simulation unit can be preset manually, which describes the basic characteristics of a specific computer room and its ancillary equipment; while the dynamic data can be preset manually or generated by the environmental simulation model. Its source depends on the selected simulation method and describes the state changes of a given computer room and equipment. In addition to simulating data such as the computer room environment, the environmental simulation unit also supports the simulation of data-related problems, such as outliers, missing data, data delays, etc., by simulating one or more virtual computer rooms and problem conditions, so as to facilitate the subsequent comprehensive evaluation of the energy-saving control program.

[0064] It should be pointed out that the present invention is not limited to the specific algorithms and deep learning frameworks used in the environmental simulation model and the energy-saving control model; in other embodiments, different algorithms and frameworks may be used for training.

[0065] The environment simulation unit of this embodiment realizes the simulation of the computer room environment in two ways, that is, using the simulation data corresponding to the two different scenarios as the input of the energy-saving control program to obtain the corresponding control strategies under different scenarios. Specifically, the first simulation data is the first simulation data corresponding to the preset scenario, and the second simulation data is the second simulation data corresponding to the intelligent scenario.

[0066] The preset scenario simulation combines business experience to imagine typical problem scenarios (such as a sudden temperature rise in the local room, equipment failure, data problems, etc.), and manually constructs corresponding simulation data for evaluation based on the problem scenario. This method can be used as long as the simulation data is configured, and is suitable for evaluating the response of the algorithm under known problems.

[0067] Intelligent scenario simulation mainly generates room environment simulation data through environmental simulation models, which can create more complex or unpredictable scenarios for evaluation. This method requires the deployment of environmental simulation programs in environmental simulation units, which is suitable for evaluating the performance of algorithms in unpredictable scenarios.

[0068] Furthermore, before running the environment simulation program, it is also necessary to select data subsets in multiple different continuous time periods from the second data set according to actual needs, and after cleaning, formatting or converting the multiple data subsets, obtain initial state data that meets the input requirements of the environment simulation program. The initial state data is used to define the initial state of the computer room environment, including setting key parameters such as temperature, humidity, and equipment status at the initial moment; load the defined initial state data into the environment simulation program, start the environment simulation program, and then the environment simulation program will start to simulate the dynamic changes of the computer room environment according to the initial state. Through these steps, the initialization of the computer room environment simulation program can be achieved, ensuring that the simulation environment can start from the data subset representing the actual operating state of the computer room, so as to perform effective simulation and evaluation.

[0069] It should be noted that in addition to generating computer room environment simulation data through the environment simulation model, other models of machine learning or deep learning algorithms can also be used to generate computer room environment simulation data. The invention does not limit the specific machine learning or deep learning algorithm used in its model, but it must meet the following requirements to achieve docking with the interface synchronization unit and the control strategy unit:

[0070] ·Can be initialized using different data sets of the computer room status, which mainly include the signal values ​​of various equipment in the computer room;

[0071] Able to continuously predict and output various dynamic data composed of room environment signals to meet the use requirements of energy-saving control programs;

[0072] Able to receive control strategies from energy-saving control programs and change the direction of changes in the simulated environment accordingly;

[0073] Use logical time instead of physical time to implement internal operations, and take the logical time provided by external modules as the standard.

[0074] like Figure 3 As shown, for each environment simulation mode, multiple environment simulation program instances can exist simultaneously. An environment simulation program instance refers to a specific process of an environment simulation program started during the evaluation process. For preset scenario simulation, each environment simulation program instance comes from a preset scenario data set; for intelligent simulation, each environment simulation program instance comes from a combination of an initial state data set of a computer room and an environment simulation model.

[0075] Step S2: processing a plurality of simulation data respectively based on the energy-saving control program to be tested, and outputting the control strategy corresponding to each simulation data; wherein the energy-saving control program is obtained by encapsulating a pre-built energy-saving control model.

[0076] The energy-saving control model refers to a model that can generate energy-saving control strategies based on relevant input features. The energy-saving control model is simply encapsulated to form an energy-saving control program integrated in the control strategy unit. The energy-saving control program can collect the required signal data from the environmental simulation unit with the help of the energy-saving control unit and the interface docking unit, and output the generated control strategy to the environmental simulation unit through the interface docking unit.

[0077] The energy-saving control model can be trained by the data collected by the signal acquisition unit. It should be noted that the invention does not limit the specific machine learning or deep learning algorithm used by the model, but it must meet the following requirements to achieve docking with the interface synchronization unit and the environmental simulation unit:

[0078] Ability to generate control strategies based on simulation data provided by the environment simulation unit, and the control strategies can be received by the environment simulation unit;

[0079] Use logical time instead of physical time to implement internal operations, and take the logical time provided by external modules as the standard.

[0080] When conducting an assessment, there can be multiple instances of the energy-saving control program at the same time. An energy-saving control program instance refers to a specific energy-saving control program process that is started during the assessment process. Each energy-saving control program instance has only one corresponding environment simulation program instance, and the two constitute an assessment instance (e.g. Figure 5 shown).

[0081] In order to accelerate the control process and ensure the consistency of the order and interval of related events between the acceleration and the environment simulation unit, the control strategy unit needs to use the interface synchronization unit to obtain the logical time as the reference time of the internal program to achieve serial acceleration. At the same time, the control strategy unit can run multiple instances of the environment simulation program at the same time to achieve parallel acceleration. Through these two acceleration methods, the time required for evaluation can be reduced.

[0082] Step S3: Obtain the expected control result corresponding to each simulation data, compare each control strategy with its corresponding expected control result, and finally determine the evaluation result of the energy-saving control program.

[0083] In this embodiment, since there are two modes, namely, preset scene simulation and intelligent scene simulation, the control strategies generated according to the simulation data in different scenes are different, and correspondingly, the methods for evaluating the generated control strategies may also be different.

[0084] Specifically, for the preset scenario simulation, when defining the first simulation data corresponding to the preset scenario, since the simulation data is artificially constructed and is simulation data under a known problem, the expected control result corresponding to the preset scenario is also predictable, and the first expected control index corresponding to the preset scenario can also be manually defined. The first expected control index includes the expected control operation and the expected response time, which serves as the evaluation basis for the first control strategy generated under the preset scenario. That is, the first simulation data is analyzed based on the energy-saving control model to output the first control strategy, the first control strategy is compared with the first expected control index, and the first evaluation result is output.

[0085] For the intelligent scene simulation, the second expected indicator corresponding to the target computer room in the intelligent scene is preset. The second expected indicator includes the number of alarms, alarm duration, fault severity, equipment control frequency, and energy-saving effect. The control strategy generated in the intelligent scene is evaluated according to the second expected indicator. That is, the second simulation data is analyzed based on the energy-saving control model to output the second control strategy, and the indicator statistics of the second control strategy are performed to obtain the indicator result; the indicator result is compared with the second expected indicator, and the second evaluation result is output.

[0086] It should be noted that the method for evaluating the performance of the energy-saving control program in a given computer room simulation environment can be performed in the evaluation unit, wherein the result evaluation unit uses a statistical analysis method to evaluate the energy-saving control program from the following aspects:

[0087] Robustness: Mainly refers to the ability of the energy-saving control program to maintain normal operation and smoothly execute various functions. For example, program warnings, errors, and interruptions may occur during the operation of the energy-saving control program. Since the evaluation involves multiple simulation environments, the program will face more uncertain inputs, so this type of evaluation can serve as an effective supplement to general unit testing and integration testing.

[0088] ·Safety: Mainly refers to the ability of the energy-saving control program to promptly identify and handle environmental anomalies and maintain various computer room environmental indicators within a safe range under various computer room environmental conditions. For example, during the operation of the energy-saving control program, the alarm types (ambient temperature, humidity, etc.) and their frequency, duration, and degree that appear in the simulated computer room environment; for example, when encountering specific scenario conditions, whether the energy-saving control program can make the expected response, and the timeliness of the response. This type of assessment plays a vital role in ensuring the safety of the computer room environment after the energy-saving control program goes online, and cannot be replaced by general unit testing and integration testing.

[0089] Energy saving: mainly refers to the ability of the energy-saving control program to reduce the energy consumption of the air conditioner in the computer room. For example, after using the energy-saving control program, compared with not using the program, the amount of electricity saved and the rate of electricity saving can be achieved. This type of evaluation has a certain reference value for ensuring that the energy-saving control program can bring the expected benefits after it goes online.

[0090] It should be pointed out that the evaluation indicators that can be statistically analyzed are related to the simulation method in the environmental simulation unit. For example, indicators such as power saving and ambient temperature alarm duration, which involve the long-term interaction between the energy-saving control program and the simulated environment of the computer room, can only be evaluated through intelligent scene simulation; on the other hand, indicators such as expected operations and their response time that require pre-specified clear conditions must be evaluated through preset scene simulation; indicators for robustness evaluation (such as program error rate) are not limited by the simulation method.

[0091] After each evaluation, the evaluation results will be marked with the energy-saving control program version, computer room simulation environment and other information, and stored in the data storage unit. Users can query to understand the evaluation results, and make horizontal (same energy-saving control program version, different simulation environments) and vertical (same simulation environment, different energy-saving control program versions) comparisons.

[0092] In a second aspect, an embodiment of the present invention provides a computer room energy-saving control program evaluation system, such as Figure 4 As shown, the system includes a parameter configuration unit, a signal acquisition unit, a data storage unit, an environment simulation unit, a control strategy unit, an interface synchronization unit and a result evaluation unit.

[0093] Among them, the parameter configuration unit is used to configure various parameters to specify the specific execution methods of various key operations in the device. The configuration includes multiple parameters and corresponding values, involving the signal acquisition unit, data storage unit, environment simulation unit, interface synchronization unit, control strategy unit, result evaluation unit, etc. These configurations will be saved in the data storage unit for other units to read and use.

[0094] The signal acquisition unit is used to collect signal data from data sources such as the power environment system of the computer room, and organize them into relevant data sets. The data sets organized by the signal acquisition unit will be stored in the data storage unit and can be read by the environmental simulation unit, the control strategy unit, the result evaluation unit, etc., for training models, evaluating energy-saving control programs, etc.

[0095] The data storage unit is used to save and back up the relevant data configured, collected or generated by the device for reading and use by other units. The data storage unit of the device interacts with other units of the device that have data reading and writing requirements through an interface.

[0096] The data that the data storage unit needs to save includes configuration parameters, signal data, evaluation data, log data, etc. In addition to the data storage function, this unit also has a data backup function, which can back up data in various forms such as full backup and incremental backup to avoid data loss due to system failure.

[0097] The environment simulation unit is used to deploy environment simulation and output computer room programs, and collect environment simulation data as input for energy-saving control programs. The environment simulation unit provides static data about the computer room, equipment, and signals, as well as simulated dynamic data of environmental signals to the control strategy unit through the interface synchronization unit; at the same time, it can also receive control signals from the control strategy unit and exert influence on changes in the simulated environment accordingly.

[0098] The control strategy unit is used to deploy the energy-saving control program to be tested and output the control strategy. The energy-saving control model is a model that can generate energy-saving control strategies based on relevant input features; the energy-saving control program is a simple encapsulation of the energy-saving control model, providing the model with basic functions such as input and output processing and interface docking. The energy-saving control program can collect the required signal data from the environmental simulation unit with the help of this unit and the interface docking unit, and output the control strategy generated by it to the environmental simulation unit through the interface docking unit.

[0099] Combination Figure 5As shown, the interface synchronization unit is used to achieve the connection and time synchronization between the computer room simulation environment and the energy-saving control program, and intercept relevant data as the basis for evaluation. The interface synchronization unit establishes a one-to-one correspondence between multiple running instances in the environment simulation unit and the control strategy unit, forwards requests from different instances to the correct corresponding instances, and provides consistent logical time for paired instances; at the same time, the interface synchronization unit can also save the intercepted data in the data storage unit for the result evaluation unit to read and use.

[0100] The functions provided by the interface synchronization unit include:

[0101] ·Register and associate evaluation instances: When starting the evaluation process, the interface synchronization unit needs to register the environment simulation program instance and the energy-saving control program instance, assign unique identifiers to them, establish a one-to-one correspondence, and form an evaluation instance.

[0102] Define and synchronize logical time: For each evaluation instance, the interface synchronization unit needs to initialize and maintain a logical time so that the environment simulation program instance and the energy-saving control program instance can run and interact according to this time; this function is mainly completed through the logical time management module and the time coordinator.

[0103] ·Intercept and output evaluation data: While receiving and forwarding data from the energy-saving control program instance and the environmental simulation program instance, output it to the result evaluation unit to obtain the evaluation result.

[0104] The logical time management module and the time coordinator are the main components for realizing the acceleration based on logical time as described in the invention. Among them, the core responsibility of the logical time management module is to maintain and advance the logical time; and the task of the time coordinator is to ensure the data flow and interaction synchronization between programs at each step of the logical time advancement. This embodiment adopts an event-driven logical time synchronization method, which drives the advancement of the logical time step through the interaction time between the environment simulation program instance, the energy-saving control program instance and the time coordinator; each advancement makes the logical time advance by a preset step length.

[0105] In the above process, the speed of time step advancement is only limited by the program's operational interaction efficiency and the preset time step. Assuming that the average physical time consumed by the steps from "requesting to obtain simulation environment data" to "forwarding control strategy" is 60 milliseconds, and the preset advancement step is 60 seconds, it means that the time required for evaluation can be shortened to one thousandth of the original time.

[0106] The result evaluation unit is used to evaluate the performance of the energy-saving control program in a given computer room simulation environment. The data used for the evaluation include the simulated environment data output by the environment simulation program instance and the control strategy data output by the energy-saving control program instance. After the data is statistically analyzed and the evaluation results are obtained, these results will be labeled and stored in the data storage unit for future use.

[0107] The following is an explanation of the energy-saving control effect system of the computer room of this embodiment in combination with actual data:

[0108] The parameter configuration unit is used to complete the configuration of various parameters involved in the operation of the device. For example, the configuration related to the signal acquisition unit is shown in Table 1:

[0109] Table 1: Example of parameter configuration of embodiment

[0110]

[0111]

[0112] The signal acquisition unit collects signal data from the dynamic ring system and organizes it to form a computer room information data set, a device information data set, a signal information data set, and a historical signal data set. The samples are shown in Table 2, Table 3, Table 4, and Table 5 (desensitized). Since a computer room generally has multiple devices and each device can have one or more signals, the device list field of the computer room information data set and the signal list field of the device information data set store multiple corresponding devices or signal identifiers in a list. It should be pointed out that this embodiment only takes one computer room as an example, so the relevant data set only contains relevant data of a single computer room; but the system proposed in this embodiment supports the collection of data from multiple computer rooms at the same time.

[0113] Table 2: Data set of computer room information

[0114]

[0115] Table 3: Device information data set

[0116]

[0117]

[0118] Table 4: Signal information dataset

[0119]

[0120] Table 5: Historical signal dataset

[0121]

[0122]

[0123] This embodiment uses the relational database management system PostgreSQL to implement data storage, and combines the data backup tool pgdump and the scheduled task tool crontab that comes with the Unix-like operating system to implement regular data backup.

[0124] It should be pointed out that the invention is not limited to the relational database management system used for implementation; in other embodiments, a relational database management system different from that of this embodiment may be used for implementation.

[0125] In order to implement the preset scenario simulation method, this embodiment combines business experience and the characteristics of the target computer room to construct one or more simulated historical signal data sets, which are in a form similar to Table 5. The simulated signal data set needs to reflect the environmental or data problems that may occur during the energy-saving regulation of the computer room, such as an abnormal increase in temperature at a certain temperature in the computer room, missing air conditioning operation status signal, etc. After constructing the data set, it is also necessary to define the control operations and response times that the energy-saving regulation program of the expected computer room should take according to the problems reflected in the data set, and complete the configuration through the parameter configuration unit and associate it with the preset scene. This embodiment constructs 3 preset scenes, and the duration of each scene is 24 hours. The problems reflected and the corresponding expected operations and response times are as follows (in order to simplify the explanation, only the relevant equipment and signals that are more closely related to the scene are described):

[0126] The preset scene 1 is as follows:

[0127] Evaluation objective: To evaluate whether the energy-saving control program of the computer room can prevent the ambient temperature from rising continuously and avoid overheating.

[0128] Scenario description: The temperature signal of the temperature sensor device "Computer Room Ambient Temperature - 1" remains at 24.0 degrees Celsius from 00:00:00 to 23:00:00. Starting from 23:00:00, the temperature of "Computer Room Ambient Temperature - 1" rises at a rate of 0.1 degrees Celsius per minute and reaches 28.0 degrees Celsius at 23:40:00. The cooling device "Air Conditioner 1" closest to the temperature sensor "Computer Room Ambient Temperature - 1" is always in the off state.

[0129] · Expected response operation: Start "Air Conditioner 1" and set the temperature setting value of "Air Conditioner 1" to below 28.0 degrees Celsius.

[0130] ·Expected response time: before 23:43:00.

[0131] The preset scene 2 is as follows:

[0132] Evaluation objective: To evaluate whether the energy-saving control program of the computer room can prevent the ambient temperature from dropping continuously and reduce unnecessary energy consumption.

[0133] Scenario description: The temperature signal of the temperature sensor device "Computer Room Ambient Temperature - 1" remains at 26.0 degrees Celsius from 00:00:00 to 23:00:00. From 23:00:00, it decreases at a rate of 0.1 degrees Celsius per minute and drops to 22.0 degrees Celsius at 23:40:00. The cooling device "Air Conditioner 1" closest to the temperature sensor "Computer Room Ambient Temperature - 1" is always on, and the temperature setting value is 26.0 degrees Celsius. Another cooling device "Air Conditioner 2" closer to the temperature sensor "Computer Room Ambient Temperature - 1" is always on, and the temperature setting value is 22.0 degrees Celsius.

[0134] · Expected response action: Increase the temperature setting of "Air Conditioner 2" by 1-2 degrees Celsius.

[0135] ·Expected response time: before 23:45:00.

[0136] The preset scene 3 is as follows:

[0137] Evaluation objective: To evaluate whether the energy-saving control program of the computer room can handle the signal loss problem in a timely and reasonable manner.

[0138] Scenario description: The cooling device "Air Conditioner 1" is always on from 00:00:00 to 23:00:00, and the return air temperature and its set value signal remain at 25 degrees Celsius; the cooling device "Air Conditioner 2" near "Air Conditioner 1" is always off; starting from 23:00:00, the return air temperature signal of "Air Conditioner 1" is missing.

[0139] · Expected response operation: Start "Air Conditioner 2" and make the temperature setting value of "Air Conditioner 2" close to the temperature setting value of "Air Conditioner 1" (±1 degree Celsius); turn off "Air Conditioner 1".

[0140] ·Expected response time: before 23:50:00.

[0141] In order to implement the intelligent scene simulation method, in addition to training the computer room environment simulation model according to the aforementioned steps and encapsulating it into a program, it is also necessary to specify the initial state of the target computer room for the program to initialize the simulation program. Depending on the initial state, the simulation data output by the computer room environment simulation program will also be different, which can increase the scope of the test scenario to a certain extent. The initial state can be described by a subset of data in any continuous time period in the historical signal data set (Table 5). This embodiment selects data from three time periods for the initialization of the computer room environment simulation program. In addition, this embodiment also uses a parameter configuration unit to uniformly set the duration of the computer room environment simulation to 24 hours, and also configures the alarm thresholds of certain key signals (such as temperature, etc.) of equipment such as temperature sensors and air conditioners.

[0142] After completing the above configuration, you can start the environmental simulation program instance, energy-saving control program instance and evaluation instance, and start collecting evaluation data. After starting the environmental simulation program instance, the program begins to generate various types of computer room environmental signal data (such as temperature sensing temperature, air conditioning return air temperature, etc.). The energy-saving control program instance can request simulated signal data from the environmental simulation program instance through the interface synchronization unit, and based on these simulated signal data, generate appropriate control strategies (for example, adjust the temperature setting value of an air conditioner, or switch the air conditioner on and off, etc.), and pass the control strategy data to the environmental simulation unit through the interface synchronization unit, which in turn acts on the environmental simulation program instance (see the process). Figure 6 As shown). While the interface synchronization unit forwards the environmental simulation signal data and the control strategy data between the environmental simulation program instance and the energy-saving control program instance, it also forwards these data to the result evaluation unit for evaluation. Since this embodiment constructs 3 preset scenes and 3 initial states of the computer room environment simulation, a total of 6 computer room environment simulation program instances are formed. These 6 environmental simulation program instances will form evaluation instances with 6 corresponding computer room energy-saving control program instances.

[0143] In the logical time scale, this embodiment sets the duration of the six evaluation instances to 24 hours, with a time step of 1 minute, and the computer room environment simulation model and the computer room energy-saving control model both perform prediction output at a frequency of 1 minute / time (a total of 1440 times in 24 hours). This means that if the evaluation is performed in the aforementioned manner in a real environment, each evaluation will require 24 hours of physical time, and the total time consumed will reach 144 hours of physical time. However, due to the use of an acceleration method based on logical time, the physical time consumed by the actual operation of each evaluation instance has been greatly reduced, providing an acceleration of more than 1000 times; coupled with the fact that all instances are executed in parallel, the total physical time consumed is equivalent to the time consumed by the longest instance, rather than the sum of the time consumed by the six evaluation instances. The physical time consumed and the acceleration effect of running the aforementioned evaluation instances are shown in Table 6:

[0144] Table 6: Speed ​​improvement effect

[0145]

[0146] In addition, it should be pointed out that since the computer room environment simulation model and the computer room energy-saving control model of this embodiment use deep learning algorithms with large computational complexity, they are the main determinants of the running time, and the running time of the evaluation instance is approximately equal to the sum of the two. Since the preset scenario simulation method does not use the computer room environment simulation model, the time consumed by the environment simulation is approximately equal to 0, so the acceleration effect of the relevant evaluation instance is more obvious. In other embodiments, the acceleration effect will be different depending on the complexity of the algorithm used and the hardware specifications used.

[0147] The evaluation method and device proposed in this embodiment support the evaluation of the energy-saving control program of the computer room from the main aspects of robustness, security, energy-saving, etc.; however, depending on the environmental simulation method used in the evaluation example, the evaluation may focus on different aspects:

[0148] For the preset scenario simulation, this embodiment mainly evaluates whether the computer room energy-saving control program can make the expected control operation when encountering a specific problem scenario, and whether the response time is within the expected range. The main results are shown in Table 7.

[0149] For intelligent scenario simulation, this embodiment mainly evaluates the number, duration, severity, equipment control frequency, energy-saving effect, and number of program error interruptions of the computer room energy-saving control program during the evaluation period. The main evaluation results are shown in Table 8.

[0150] It can be seen from the relevant results that in this embodiment, the energy-saving control program of the computer room performed the expected operation within the expected time in the environment of the three preset scenarios evaluated and passed the evaluation. However, in the environment simulated by the three intelligent scenarios, problems such as program error interruption and excessive temperature in the computer room were found, indicating that there was a problem with the internal logic of the energy-saving control program.

[0151] Table 7: Preset scenario simulation evaluation results

[0152]

[0153]

[0154] Table 8: Intelligent scenario simulation evaluation results

[0155]

[0156]

[0157] Through the above steps, this embodiment completes the evaluation of the energy-saving control program of the computer room, and its beneficial effects are as follows:

[0158] 1. This embodiment proposes a more comprehensive evaluation system for the energy-saving control program of the computer room, which can discover potential problems of the program as much as possible and improve the safety and effectiveness of energy saving in the computer room; and proposes to evaluate the energy-saving control program of the computer room from three aspects: robustness, security, and energy saving, and proposes to provide an operating environment for the energy-saving control program by combining preset scene simulation and intelligent scene simulation, so as to ensure that the energy-saving control program can make the expected response in a timely manner under known conditions and can still output reasonable control strategies in unknown environments.

[0159] 2. In the system of this embodiment, through the cooperation of various units, it is possible to evaluate the energy-saving control program of the computer room in large quantities and automatically, which can significantly reduce the manual input in the research and development cycle.

[0160] 3. This embodiment uses logical time instead of physical time to implement the internal logic of the program to achieve serial acceleration of the evaluation, thereby reducing the time required for each evaluation; and coordinates the interaction between the computer room environment simulation program and the computer room energy-saving control program by synchronizing the program's external standard logical time to ensure the correctness of the relevant results; it also proposes to deploy environmental simulation program instances and energy-saving control program instances in an elastically scalable manner to achieve parallel acceleration of the evaluation, further reducing the time required to conduct evaluations on multiple evaluation instances.

[0161] In a third aspect, an embodiment of the present invention provides an electronic device, Figure 7 FIG. 2 shows a structural block diagram of an electronic device according to an embodiment of the present invention. Figure 7As shown, the electronic device includes: a memory 100 and a processor 200, wherein the memory 100 stores a computer program that can be run on the processor 200. When the processor 200 executes the computer program, the computer room energy-saving control program evaluation method in the above embodiment is implemented. The number of the memory 100 and the processor 200 can be one or more.

[0162] The electronic device also includes:

[0163] The communication interface 300 is used to communicate with external devices and perform data exchange transmission.

[0164] If the memory 100, the processor 200 and the communication interface 300 are implemented independently, the memory 100, the processor 200 and the communication interface 300 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0165] Optionally, in a specific implementation, if the memory 100, the processor 200 and the communication interface 300 are integrated on a chip, the memory 100, the processor 200 and the communication interface 300 can communicate with each other through an internal interface.

[0166] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present invention when executed by a processor.

[0167] An embodiment of the present invention further provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present invention.

[0168] An embodiment of the present invention also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided by the embodiment of the invention.

[0169] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced RISC machines (ARM) architecture.

[0170] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).

[0171] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0172] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0173] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0174] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for evaluating a computer room energy-saving control program, characterized in that: include: Acquire multiple simulation data of the computer room environment, wherein the simulation data includes first simulation data defined under a preset scenario and second simulation data generated based on a pre-built environment simulation model; Based on the energy-saving control program to be tested, the plurality of simulation data are processed respectively, and the control strategy corresponding to each simulation data is output; wherein the energy-saving control program is obtained by encapsulating the pre-built energy-saving control model; Obtain the expected control result corresponding to each simulation data, compare each control strategy with its corresponding expected control result, and finally determine the evaluation result of the energy-saving control program.

2. The method for evaluating the energy-saving control program of a computer room according to claim 1, characterized in that: The desired control results include: a first expected control indicator defined by the target computer room when encountering the preset scenario with a specified problem, wherein the first expected control indicator includes an expected control operation and an expected response time; and The target computer room corresponds to a second expected indicator in the intelligent scenario, wherein the second expected indicator includes the number of alarms, the alarm duration, the severity of the fault, the frequency of equipment control, and the energy-saving effect.

3. The method for evaluating the energy-saving control program of a computer room according to claim 2, characterized in that: The step of comparing each of the control strategies with the corresponding expected control result to finally determine the evaluation result of the energy-saving control program includes: Compare a first control strategy with the first expected control index and output a first evaluation result; the first control strategy is a result output by analyzing the first simulation data based on the energy-saving control model; and Performing indicator statistics on the second control strategy to obtain an indicator result; comparing the indicator result with the second expected indicator, and outputting a second evaluation result; wherein the second control strategy is a result output by analyzing the second simulation data based on the energy-saving control model.

4. The method for evaluating the energy-saving control program of a computer room according to claim 1, characterized in that: Also includes: Acquire signal data from a specified data source, and integrate the signal data to obtain a first data set containing device signals at all time steps; Based on the first data set, all device signals in the previous time step are used as input of the memory network model, and the device signals in the next time step are used as output of the memory network model. The memory network model is trained to obtain the environment simulation model.

5. The method for evaluating the energy-saving control program of a computer room according to claim 4, characterized in that: Also includes: Acquire signal data from a specified data source, and integrate the signal data to obtain a second data set; Based on the second data set, the device signals and environmental conditions are used as the input of the learning model, the optimized control strategy is used as the output of the learning model, the learning model is trained, and the learning model is optimized through a preset reward function to obtain the energy-saving control model.

6. The method for evaluating the energy-saving control program of a computer room according to claim 5, characterized in that: Also includes: Determining data subsets in a plurality of different continuous time periods according to the second data set, and processing the plurality of data subsets to obtain initial state data for defining an initial state of a computer room environment; The environment simulation model is initialized based on the initial state data, so that the environment simulation model simulates the dynamic changes of the computer room environment from the initial state.

7. The method for evaluating the energy-saving control program of a computer room according to claim 1, characterized in that: Also includes: The simulation data is stored in a designated storage unit, and the stored simulation data is backed up regularly through the designated storage unit to obtain backup data and store it in the designated storage unit.

8. A computer room energy-saving control program evaluation system, characterized in that: Execute the computer room energy-saving control program evaluation method as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the computer room energy-saving control program evaluation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for evaluating a computer room energy-saving control program according to any one of claims 1 to 7 is implemented.

Images