Multi-stage equipment energy efficiency optimization control system and method for efficient machine room

Abstract

The invention discloses a multi-stage equipment energy efficiency optimization control system and method for an efficient machine room, and relates to the technical field of equipment optimizing.The method comprises the steps that environment parameter data and design parameter data of a refrigerating machine room are obtained, an environment correction factor is analyzed, and the cold load rate is dynamically corrected based on the environment correction factor; on the basis of preset delay time, phase-space reconstruction is carried out on the historical corrected cold load rate sequence, the final embedded dimension is analyzed, and a hybrid prediction model is constructed on the basis of the final embedded dimension; matching optimal operation parameters based on physical resonance characteristics of equipment in combination with comprehensive energy efficiency indexes of the machine room; and performing data structure compression on the optimal operation parameters and the comprehensive energy efficiency indexes of the corresponding machine room, performing screening analysis on data points, and updating a parameter library. And invalid data interference is reduced, so that the system can realize self-adaptive optimization in long-term operation, and the data storage and calculation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment optimization, and specifically to a multi-level equipment energy efficiency optimization control system and method for an efficient computer room. Background Art

[0002] According to relevant statistics, building energy consumption in China accounts for about 30% of the total social energy consumption. Among the existing 21.5 billion square meters of public buildings in China, the energy-saving compliance rate is less than 10%. Among the nearly 2 billion square meters of newly built buildings each year, the proportion of high-energy-consuming buildings exceeds 90%. As a major energy consumer in buildings, the air-conditioning system accounts for about 47% of the total building energy consumption, and the energy consumption of the refrigeration machine room accounts for as high as 75% of the air-conditioning energy consumption, reaching 11% of the total social energy consumption. In the industrial field, which accounts for 65% of the total social energy consumption, the energy consumption of the refrigeration machine room also occupies a relatively high proportion. The energy conservation of efficient computer rooms is the top priority of building and industrial energy conservation and emission reduction work.

[0003] Traditional control methods for refrigeration machine rooms are currently only limited to controlling individual equipment, with separate adjustment of the chiller, chilled water pump, cooling water pump, and cooling tower. The control strategies for chilled water pumps, cooling water pumps, and cooling tower fans are only the start-stop control and interlock of the equipment itself, without paying attention to the high energy efficiency of the chiller unit, and lacking the optimization control of the overall energy efficiency of the refrigeration system. Refrigeration machine rooms often operate without stopping, generating a large amount of operation data, which is prone to data accumulation and reduced calculation efficiency.

[0004] Therefore, the present invention discloses a multi-level equipment energy efficiency optimization control system and method for an efficient computer room to solve the above problems. Summary of the Invention

[0005] [[ID=,19]]The purpose of the present invention is to provide a multi-level equipment energy efficiency optimization control system and method for an efficient computer room to solve the problems raised in the prior art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A multi-level equipment energy efficiency optimization control method for an efficient computer room, the method comprising the following steps:

[0007] S1: Obtain the environmental parameter data and design parameter data of the refrigeration machine room, analyze the environmental correction factor, and dynamically correct the cooling load rate based on the environmental correction factor;

[0008] S2: Based on a preset delay time, perform phase space reconstruction on the historical corrected cooling load rate sequence, analyze the final embedding dimension, and construct a hybrid prediction model based on the final embedding dimension;

[0009] S3: Match the optimal operating parameters based on the physical resonance characteristics of the equipment and the comprehensive energy efficiency index of the computer room;

[0010] S4: Compress the optimal operating parameters and the corresponding comprehensive energy efficiency index of the computer room in a data structure, screen and analyze the data points, and update the parameter library.

[0011] According to the above solution, in S1, it includes the following:

[0012] S101: Obtain the environmental parameter data and design parameter data of the refrigeration computer room. The environmental parameter data includes the supply water pipe temperature T in , the return water pipe temperature T out , the water flow rate Q, the solar radiation intensity S, the surface wind speed V, the environmental humidity H, and the equipment power consumption; analyze the environmental correction factor α based on the environmental parameter data; α = (S / S d ) × (V d / V) β × exp[-k H (H - H d )] × cos[π(T wet - T wetd ) / 6]; where S d , V d , H d , and T wetd respectively represent the solar radiation intensity, surface wind speed, environmental humidity, and wet bulb temperature under the design condition; β represents the preset surface wind speed correction coefficient; k H represents the preset humidity attenuation coefficient;

[0013] S102: Dynamically correct the cooling load rate L' based on the environmental correction factor; L' = Q × (T in - T out ) × α ÷

[0014] (Q d × △T d ); where Q d and △T d represent the flow rate and the temperature difference between the supply water pipe and the return water pipe under the design condition; Integrate the corrected cooling load rates according to the time sequence to generate a historical corrected cooling load rate sequence {L'(t)|t ∈ [1, T]}; where T represents the total number of moments.

[0015] This application improves the accuracy of cooling load calculation and the adaptability to dynamic environmental changes by introducing environmental variables such as solar radiation, wind speed, humidity, and wet bulb temperature; uses a cosine function and an exponential decay term for humidity and temperature correction to make the calculation results smoother and more in line with the actual situation, and avoids excessive calculation deviation caused by the fluctuation of a single factor. By introducing a correction factor, it compensates for the system load requirements under different meteorological conditions and optimizes the stability and energy efficiency of the system operation.

[0016] According to the above solution, in S2, it includes the following:

[0017] S201: Based on the preset delay time τ, embed the historical corrected cooling load rate sequence into the j-dimensional phase space for phase space reconstruction, and denote the i-th phase space vector as X i j =(L’(i), L’(i + τ), …, L’(i+(j - 1)τ)); Analyze the corresponding embedding degree coefficient where i ∈ [1, I], I represents the total number of phase space vectors; X i j +1 represents the phase space vector X i j corresponding to the phase space vector in the (j + 1)-dimensional phase space; ||X i j - X i j+1 || represents the Euclidean distance between the phase space vector X i j and the phase space vector X i j+1 ; R represents the preset distance threshold; A() represents the indicator function. If ||X i j - X i j+1 || > R, then A(||X i j - X i j+1 || > R) = 1, otherwise 0; If the embedding degree coefficient EDC is less than the corresponding threshold, take the corresponding dimension as the final embedding dimension;

[0018] S202: Based on the final embedding dimension, construct a hybrid prediction model. The hybrid prediction model includes a main system model and a slave system model. The expression of the main system model is: dL / dt = θ[L’(t - τ) - L’(t)]; The expression of the slave system model is: dL* / dt = θ[L’(t - τ) - L*(t)] + K[L’(t) - L*(t)]; Based on the historical corrected cooling load rate sequence, use the least squares method to fit the hybrid coefficient θ, and use the gradient descent method to optimize the coupling strength coefficient K.

[0019] Through the design of the master-slave system, use historical data to dynamically adjust the synchronous coupling strength, reduce the prediction error, and improve the accuracy of short-term load prediction; better adapt to the non-linear complex system and enhance the stability of prediction;

[0020] According to the above solution, in S3, it includes the following content:

[0021] S301: Analyze the resonance frequency f of the device based on the equivalent stiffness and equivalent mass of the devicer ; f r = 1 / (2π) × (ke / je) 1 / 2 ; where ke represents the equivalent stiffness of the device, and the equivalent stiffness of the device is inversely proportional to the real-time power consumption; je represents the equivalent mass, and the equivalent mass is proportional to the cumulative operation time;

[0022] Analyze the comprehensive energy efficiency index of the computer room, and the comprehensive energy efficiency index of the computer room is equal to the total cooling capacity provided by the refrigeration system at time t divided by the sum of the power consumptions of the chilled water host, chilled water pump, cooling water pump and cooling tower fan corresponding to time t;

[0023] S302: Construct the equipment operation frequency constraint condition and the chilled water supply and return temperature difference constraint condition corresponding to the comprehensive energy efficiency index of the computer room. The equipment operation frequency constraint condition is that the difference between the actual operation frequency of the equipment and the resonance frequency is less than the corresponding preset threshold, and the chilled water supply and return temperature difference constraint condition is that the chilled water supply and return temperature difference is greater than the corresponding preset threshold; Map the optimization problem of the comprehensive energy efficiency index of the computer room into the Hamiltonian form of the Ising model, and according to the start-stop state of the equipment and the energy efficiency coupling coefficient between the equipment, solve the ground state of the Ising model through the quantum annealing algorithm to obtain the optimal parameter combination {Nch, ffp, fcp, fct} corresponding to time t; where Nch represents the number of chilled water hosts, ffp represents the operation frequency of the chilled water pump, fcp represents the operation frequency of the cooling water pump, and fct represents the operation frequency of the cooling tower fan.

[0024] Use the binary spin variable σ to represent the start-stop or operation state of each device m ∈{-1, +1}; where σ m = +1 indicates that device m is in the operation state, and σ m = -1 indicates that device m is in the off state. Maximizing the comprehensive energy efficiency of the computer room is equivalent to minimizing the Hamiltonian HM;

[0025]

[0026] where, J (m，n) represents the collaborative energy efficiency relationship between device m and device n; h ... m represents the energy efficiency contribution of the device operating independently;

[0027] J (m，n) = [SCOP pair (m, n) - SCOP single (m)] ÷ SCOP max ;

[0028] h m = SCOP single (m) ÷ SCOP max ;

[0029] Among them, SCOP pair (m, n) represents the energy efficiency value of the collaborative operation of device m and device n, and SCOP single (m) represents the system comprehensive energy efficiency when device m operates independently; the system comprehensive energy efficiency when device m operates independently is equal to the cooling capacity provided by device m alone divided by the power consumption of device m alone; SCOP max represents the maximum value of the computer room comprehensive energy efficiency index;

[0030] Randomly generate an initial spin parameter combination {σ m |m ∈ [1, M]}; M represents the total number of devices; through the initial transverse magnetic field of the quantum annealing machine, the system is in a superposition state of all possible states; gradually reduce the transverse magnetic field strength to make the system evolve from the quantum superposition state to the classical state. When the time approaches the annealing time, the system collapses to the ground state with the lowest energy, corresponding to the optimal spin parameter combination. Check the device operation frequency constraint condition and the chilled water supply and return water temperature difference constraint condition. If not satisfied, trigger the penalty mechanism and solve again; according to the decoded optimal spin parameter combination, obtain the optimal parameter combination corresponding to time t.

[0031] This application realizes the dynamic calculation of the resonance frequency of the device by establishing an equivalent stiffness and equivalent mass model, combined with the device operation time and power consumption data, improving the accuracy of the device operation state evaluation; adopts resonance matching control to ensure that the device operation frequency is as close as possible to the resonance frequency, reducing mechanical losses and energy consumption, and improving the device operation life; by preferentially adjusting the device with the smallest frequency deviation, optimizing the coordinated operation strategy of the device group, and enhancing the stability and operation efficiency of the overall system.

[0032] Construct the resonance frequency using the device physical parameters, and characterize the dynamic characteristics of the device during operation through a physical model; combined with operation constraints, convert the optimization problem into an Ising model, and solve to obtain the optimal device parameter combination per hour through the quantum annealing algorithm. This application considers both the physical resonance effect of the device and global coordination in energy efficiency optimization.

[0033] According to the above solution, in S4, it includes the following content:

[0034] S401: Obtain the optimal parameter combination at each moment and the corresponding computer room comprehensive energy efficiency index to generate a parameter vector, and analyze the corresponding optimal linear reconstruction weight within the local domain based on the parameter vector: Among them, y r represents the parameter vector corresponding to time r; y q represents the parameter vector corresponding to time q; w (r，q) represents the linear reconstruction weight between the parameter vector y r and the parameter vector y q ; N(r) represents the parameter vector y rthe n nearest neighbors, where n is a preset constant; construct a low-dimensional embedding based on the obtained optimal linear reconstruction weights, map the parameter vector to a two-dimensional manifold to generate data points;

[0035] S402: preset neighborhood radius and minimum number of samples; for each data point, calculate the number of data points within its neighborhood; if the number is not less than the minimum number of samples, mark the data point as a core point; otherwise, if the data point falls within the neighborhood of a core point, mark it as a boundary point; otherwise, mark the data point as a noise point; group the core points directly or indirectly connected starting from a core point and the boundary points within their neighborhoods into the same cluster; mark each data point with the corresponding cluster label, and mark the data points that do not belong to any cluster as noise points;

[0036] S403: calculate the mean vector for each cluster, analyze the Euclidean distance from each data point in the cluster to the cluster center based on the mean vector, and analyze the standard deviation of the corresponding Euclidean distances of all data points; delete the data points whose Euclidean distance to the cluster center is greater than a preset number of times the standard deviation;

[0037] Generate a lightweight database, where the lightweight database includes a load rate interval, a device parameter combination, a predicted energy efficiency index, a parameter confidence level, and an index table; the load rate interval is divided into intervals based on the distribution of the predicted load rate; the device parameter combination represents the optimal device parameter combination corresponding to each cluster center; the predicted energy efficiency index represents the energy efficiency index predicted for each device parameter combination during the optimization process; the parameter confidence level is equal to the probability of achieving or exceeding the predicted energy efficiency during actual operation; sort the database according to the load rate and generate an index table.

[0038] This application improves the visualization and interpretability of data analysis by performing dimensionality reduction on the high-dimensional parameter space, extracts key operating modes, identifies different categories in the device operating mode, automatically eliminates outliers, and improves the robustness of the model; only retains the parameter combinations of the cluster centers for update, reduces interference from invalid data, enables the system to achieve adaptive optimization during long-term operation, and improves data storage and calculation efficiency.

[0039] In another aspect of this application, a multi-level device energy efficiency optimization control system for an efficient computer room, the system is implemented by applying the above-mentioned multi-level device energy efficiency optimization control system for an efficient computer room, and the system includes a data acquisition and correction module, a prediction model construction module, an operating parameter optimization module, and a data screening and optimization module;

[0040] The data acquisition and correction module is used to obtain the environmental parameter data and design parameter data of the refrigeration computer room, analyze the environmental correction factor, and dynamically correct the cooling load rate based on the environmental correction factor;

[0041] The prediction model construction module performs phase space reconstruction on the historical corrected cooling load rate sequence based on a preset delay time, analyzes the final embedding dimension, and constructs a hybrid prediction model based on the final embedding dimension;

[0042] The operating parameter optimization module matches the optimal operating parameters based on the physical resonance characteristics of the equipment and the comprehensive energy efficiency index of the computer room;

[0043] The data screening and optimization module compresses the data structure of the optimal operating parameters and the corresponding comprehensive energy efficiency index of the computer room, screens and analyzes the data points, and updates the parameter library.

[0044] According to the above solution, the data acquisition and correction module includes a correction factor analysis unit and a dynamic correction unit;

[0045] The correction factor analysis unit analyzes the environmental correction factor based on the environmental parameter data and design parameter data of the refrigeration computer room;

[0046] The dynamic correction unit dynamically corrects the cooling load rate based on the environmental correction factor, and integrates the corrected cooling load rate according to the time sequence to generate a historical corrected cooling load rate sequence.

[0047] According to the above solution, the prediction model construction module includes an embedding dimension analysis unit and a prediction model construction unit;

[0048] The embedding dimension analysis unit is used to perform phase space reconstruction on the historical corrected cooling load rate sequence based on a preset delay time; analyze the corresponding embedding degree coefficient, and confirm the final embedding dimension based on the embedding degree coefficient;

[0049] The prediction model construction unit is used to construct a hybrid prediction model based on the final embedding dimension; fit the hybrid coefficient by the least squares method, and optimize the coupling strength coefficient by the gradient descent method.

[0050] According to the above solution, the operating parameter optimization module is used for the index analysis unit and the optimal parameter analysis unit;

[0051] The index analysis unit analyzes the resonance frequency of the equipment based on the equivalent stiffness and equivalent mass of the equipment, and analyzes the comprehensive energy efficiency index of the computer room;

[0052] The optimal parameter analysis unit is used to construct the constraint conditions corresponding to the comprehensive energy efficiency index of the computer room; map the optimization problem of the comprehensive energy efficiency index of the computer room into the Hamiltonian form of the Ising model, and solve the ground state of the Ising model through the quantum annealing algorithm according to the start-stop state of the equipment and the energy efficiency coupling coefficient between the equipment to obtain the optimal parameter combination.

[0053] According to the above solution, the data screening and optimization module includes a data dimensionality reduction unit and a data screening unit;

[0054] The data dimensionality reduction unit is used to obtain the optimal parameter combination at each moment and the corresponding comprehensive energy efficiency index of the computer room to generate a parameter vector, analyze the corresponding optimal linear reconstruction weight in the local domain based on the parameter vector; construct a low-dimensional embedding based on the obtained optimal linear reconstruction weight, map the parameter vector to a two-dimensional manifold to generate data points;

[0055] The data screening unit is used to gather the data points to generate clusters, and further analyze and screen the data points within the clusters to generate a lightweight database.

[0056] Compared with the prior art, the beneficial effects of the present invention are as follows: By introducing environmental variables such as solar radiation, wind speed, humidity, and wet-bulb temperature, the accuracy of cold load calculation is improved, and the adaptability to dynamic environmental changes is enhanced; The cosine function and exponential decay term are used for humidity and temperature correction, making the calculation results smoother and more in line with the actual situation, and avoiding excessive calculation deviation caused by the fluctuation of a single factor. By introducing a correction factor, the demand for system load under different meteorological conditions is compensated, and the stability and energy efficiency of system operation are optimized; Through the master-slave system design, the synchronous coupling strength is dynamically adjusted using historical data, reducing the prediction error and improving the accuracy of short-term load prediction; It better adapts to non-linear complex systems and improves the stability of prediction; By establishing an equivalent stiffness and equivalent mass model, combined with equipment operation time and power consumption data, the dynamic calculation of the equipment resonance frequency is realized, improving the accuracy of equipment operation state evaluation; Resonance matching control is adopted to ensure that the equipment operation frequency is as close as possible to the resonance frequency, reducing mechanical loss and energy consumption, and improving the equipment operation life; By preferentially adjusting the equipment with the smallest frequency deviation, the coordinated operation strategy of the equipment group is optimized, and the stability and operation efficiency of the overall system are improved; By performing dimensionality reduction processing on the high-dimensional parameter space, key operation modes are extracted, improving the visualization and interpretability of data analysis, identifying different categories in the equipment operation mode, automatically eliminating abnormal points, and improving the robustness of the model; Only the parameter combinations of the clustering centers are retained for update, reducing the interference of invalid data, enabling the system to achieve adaptive optimization during long-term operation, and improving data storage and calculation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0058] Figure 1 is a schematic flowchart of a multi-level equipment energy efficiency optimization control method for an efficient computer room according to the present invention;

[0059] Figure 2 is a schematic structural diagram of a multi-level equipment energy efficiency optimization control system for an efficient computer room according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0061] Please refer to Figure 1 , the present invention provides a technical solution: a multi-level equipment energy efficiency optimization control system and method for an efficient computer room to solve the problems proposed in the prior art.

[0062] To achieve the above object, the present invention provides the following technical solution: a multi-level equipment energy efficiency optimization control method for an efficient computer room, the method includes the following steps:

[0063] S1: Obtain the environmental parameter data and design parameter data of the refrigeration machine room, analyze the environmental correction factor, and dynamically correct the cooling load rate based on the environmental correction factor;

[0064] In S1, it includes the following content:

[0065] S101: Obtain the environmental parameter data and design parameter data of the refrigeration machine room. The environmental parameter data includes the supply water temperature T in , the return water temperature T out , the water flow rate Q, the solar radiation intensity S, the surface wind speed V, the environmental humidity H, and the equipment power consumption; analyze the environmental correction factor α based on the environmental parameter data; α = (S / S d ) × (V d / V) β × exp[-k H (H - H d )] × cos[π(T wet - T wetd ) / 6]; where S d , V d , H d and T wetd respectively represent the solar radiation intensity, surface wind speed, environmental humidity, and wet bulb temperature under the design conditions; β represents the preset surface wind speed correction coefficient; k H represents the preset humidity attenuation coefficient;

[0066] S102: Dynamically correct the cooling load rate L' based on the environmental correction factor; L' = Q × (T in - T out ) × α ÷

[0067] (Q d × △Td ); where Q d and △T d represent the flow rate under the design condition and the temperature difference between the supply water pipe temperature and the return water pipe temperature; Integrate the corrected cooling load ratios according to the time sequence to generate a historical corrected cooling load ratio sequence {L’(t)|t∈[1, T]}; where T represents the total number of time moments.

[0068] S2: Based on a preset delay time, perform phase space reconstruction on the historical corrected cooling load ratio sequence, analyze the final embedding dimension, and construct a hybrid prediction model based on the final embedding dimension;

[0069] In S2, it includes the following content:

[0070] S201: Based on a preset delay time τ, embed the historical corrected cooling load ratio sequence into the j-dimensional phase space for phase space reconstruction, and denote the i-th phase space vector as X i j =(L’(i), L’(i + τ), …, L’(i + (j - 1)τ)); Analyze the corresponding embedding degree coefficient where i∈[1, I], I represents the total number of phase space vectors; X i j +1 represents the phase space vector X i j corresponding to the phase space vector in the j + 1-dimensional phase space; ||X i j -X i j+1 || represents the Euclidean distance between the phase space vector X i j and the phase space vector X i j+1 ; R represents a preset distance threshold; A() represents an indicator function. If ||X i j -X i j+1 ||>R, then A(||X i j -X i j+1 ||>R)=1, otherwise 0; If the embedding degree coefficient EDC is less than the corresponding threshold, take the corresponding dimension as the final embedding dimension;

[0071] S202: Construct a hybrid prediction model based on the final embedding dimension. The hybrid prediction model includes a main system model and a slave system model. The expression of the main system model is: dL / dt = θ[L’(t - τ) - L’(t)]; the expression of the slave system model is: dL* / dt = θ[L’(t - τ) - L*(t)] + K[L’(t) - L*(t)]; Based on the historical corrected cooling load rate sequence, the hybrid coefficient θ is fitted by the least squares method, and the coupling strength coefficient K is optimized by the gradient descent method.

[0072] S3: Match the optimal operating parameters based on the physical resonance characteristics of the equipment and the comprehensive energy efficiency index of the computer room;

[0073] In S3, the following content is included:

[0074] S301: Analyze the resonance frequency f of the equipment based on the equivalent stiffness and equivalent mass of the equipment r ; f r = 1 / (2π)×(ke / je) 1 / 2 ; where ke represents the equivalent stiffness of the equipment, and the equivalent stiffness of the equipment is inversely proportional to the real-time power consumption; je represents the equivalent mass, and the equivalent mass is proportional to the cumulative operating time; Analyze the comprehensive energy efficiency index of the computer room. The comprehensive energy efficiency index of the computer room is equal to the total cooling capacity provided by the refrigeration system at time t divided by the sum of the power consumption of the chilled water host, chilled water pump, cooling water pump and cooling tower fan at time t.

[0075] S302: Construct the equipment operating frequency constraint condition and the chilled water supply and return water temperature difference constraint condition corresponding to the comprehensive energy efficiency index of the computer room. The equipment operating frequency constraint condition is that the difference between the actual operating frequency of the equipment and the resonance frequency is less than the corresponding preset threshold, and the chilled water supply and return water temperature difference constraint condition is that the chilled water supply and return water temperature difference is greater than the corresponding preset threshold; Map the optimization problem of the comprehensive energy efficiency index of the computer room into the Hamiltonian form of the Ising model, and according to the equipment start-stop state and the energy efficiency coupling coefficient between equipment, solve the ground state of the Ising model through the quantum annealing algorithm to obtain the optimal parameter combination {Nch, ffp, fcp, fct} corresponding to time t; where Nch represents the number of chilled water hosts, ffp represents the operating frequency of the chilled water pump, fcp represents the operating frequency of the cooling water pump, and fct represents the operating frequency of the cooling tower fan.

[0076] S4: Compress the data structure of the optimal operating parameters and the corresponding comprehensive energy efficiency index of the computer room, screen and analyze the data points, and update the parameter library.

[0077] In S4, the following content is included:

[0078] S401: Obtain the optimal parameter combination and the corresponding comprehensive energy efficiency index of the computer room at each moment to generate a parameter vector, and analyze the optimal linear reconstruction weight corresponding to the local domain based on the parameter vector: Among them, y r represents the parameter vector corresponding to time r; y q represents the parameter vector corresponding to time q; w (r，q) represents the linear reconstruction weight between the parameter vector y r and the parameter vector y q ; N(r) represents the n nearest neighbors of the parameter vector y r , where n is a preset constant; construct a low-dimensional embedding based on the obtained optimal linear reconstruction weight, map the parameter vector to a two-dimensional manifold to generate data points;

[0079] S402: Preset the neighborhood radius and the minimum number of samples; for each data point, calculate the number of data points in its neighborhood; if the number is not less than the minimum number of samples, mark the data point as a core point; otherwise, if the data point falls within the neighborhood of a core point, mark it as a boundary point; otherwise, mark the data point as a noise point; group the core points directly or indirectly connected starting from a core point and the boundary points in their neighborhoods into the same cluster; mark each data point with the corresponding cluster label, and mark the data points that do not belong to any cluster as noise points;

[0080] S403: Calculate the mean vector for each cluster, analyze the Euclidean distance from each data point in the cluster to the cluster center based on the mean vector, and analyze the standard deviation of the Euclidean distances corresponding to all data points; delete the data points whose Euclidean distance to the cluster center is greater than a preset number of multiples of the standard deviation;

[0081] Embodiment 1: For any two data points, if data point 1 is a core point and data point 2 falls within the neighborhood of data point 1, then data point 1 is directly connected to data point 2;

[0082] There exists a chain of a series of data points DP1, DP2,..., DP N , where DP1 is a core point; and for any n, DP n+1 is directly connected to DP n , if DQ is the last point in this chain, then DQ is indirectly connected to DP1.

[0083] Generate a lightweight database, which includes a load rate interval, a device parameter combination, a predicted energy efficiency index, a parameter confidence level, and an index table; the load rate interval is divided into intervals based on the distribution of the predicted load rate; the device parameter combination represents the optimal device parameter combination corresponding to the center of each cluster; the predicted energy efficiency index represents the energy efficiency index predicted for each device parameter combination during the optimization process; the parameter confidence level is equal to the probability of achieving or exceeding the predicted energy efficiency during actual operation; sort the database according to the load rate and generate an index table.

[0084] Please refer to Figure 2, the present invention provides a technical solution: a multi-level equipment energy efficiency optimization control system for an efficient computer room, the system includes a data acquisition and correction module, a prediction model construction module, an operating parameter optimization module, and a data screening and optimization module;

[0085] The data acquisition and correction module is used to acquire the environmental parameter data and design parameter data of the refrigeration computer room, analyze the environmental correction factor, and dynamically correct the cooling load rate based on the environmental correction factor;

[0086] The prediction model construction module is based on a preset delay time, performs phase space reconstruction on the historical corrected cooling load rate sequence, analyzes the final embedding dimension, and constructs a hybrid prediction model based on the final embedding dimension;

[0087] The operating parameter optimization module matches the optimal operating parameters based on the physical resonance characteristics of the equipment and the comprehensive energy efficiency index of the computer room;

[0088] The data screening and optimization module compresses the data structure of the optimal operating parameters and the corresponding comprehensive energy efficiency index of the computer room, screens and analyzes the data points, and updates the parameter library.

[0089] The data acquisition and correction module includes a correction factor analysis unit and a dynamic correction unit;

[0090] The correction factor analysis unit analyzes the environmental correction factor based on the environmental parameter data and design parameter data of the refrigeration computer room;

[0091] The dynamic correction unit dynamically corrects the cooling load rate based on the environmental correction factor, and integrates the corrected cooling load rate according to the time sequence to generate a historical corrected cooling load rate sequence.

[0092] The prediction model construction module includes an embedding dimension analysis unit and a prediction model construction unit;

[0093] The embedding dimension analysis unit is used to perform phase space reconstruction on the historical corrected cooling load rate sequence based on a preset delay time; analyze the corresponding embedding degree coefficient, and confirm the final embedding dimension based on the embedding degree coefficient;

[0094] The prediction model construction unit is used to construct a hybrid prediction model based on the final embedding dimension; use the least squares method to fit the hybrid coefficient, and use the gradient descent method to optimize the coupling strength coefficient.

[0095] The operating parameter optimization module is used for the index analysis unit and the optimal parameter analysis unit;

[0096] The index analysis unit analyzes the resonance frequency of the equipment based on the equivalent stiffness and equivalent mass of the equipment, and analyzes the comprehensive energy efficiency index of the computer room;

[0097] The optimal parameter analysis unit is used to construct the constraint conditions corresponding to the comprehensive energy efficiency index of the computer room; map the optimization problem of the comprehensive energy efficiency index of the computer room into the form of the Hamiltonian of the Ising model, and solve the ground state of the Ising model through the quantum annealing algorithm according to the equipment start-stop state and the energy efficiency coupling coefficient between equipment to obtain the optimal parameter combination.

[0098] The data screening and optimization module includes a data dimensionality reduction unit and a data screening unit;

[0099] The data dimensionality reduction unit is used to obtain the optimal parameter combination at each moment and generate a parameter vector corresponding to the comprehensive energy efficiency index of the computer room, analyze the corresponding optimal linear reconstruction weight in the local domain based on the parameter vector; construct a low-dimensional embedding based on the obtained optimal linear reconstruction weight, and map the parameter vector to a two-dimensional manifold to generate data points;

[0100] The data screening unit is used to gather the data points to generate clusters, and further analyze and screen the data points within the clusters to generate a lightweight database.

[0101] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprises", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0102] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, in any aspect, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

Claims

1. A multi-level equipment energy efficiency optimization control method for an efficient computer room, characterized in that, The method includes the following steps: S1: Obtain the environmental parameter data and design parameter data of the refrigeration machine room to analyze the environmental correction factor, and dynamically correct the cooling load rate based on the environmental correction factor; S2: Based on a preset delay time, perform phase space reconstruction on the historical corrected cooling load rate sequence, analyze the final embedding dimension, and construct a hybrid prediction model based on the final embedding dimension; S3: Match the optimal operating parameters based on the equipment physical resonance characteristics combined with the comprehensive energy efficiency index of the machine room; S4: Compress the data structure of the optimal operating parameters and the corresponding comprehensive energy efficiency index of the machine room, screen and analyze the data points, and update the parameter library.

2. The multi - level equipment energy efficiency optimization control method for an efficient computer room according to claim 1, characterized in that: In S1, it includes the following: S101: Obtain the environmental parameter data and design parameter data of the refrigeration machine room. The environmental parameter data includes the temperature T of the water supply pipe in , the temperature T of the water return pipe out , the water flow rate Q, the solar radiation intensity S, the surface wind speed V, the environmental humidity H, and the equipment power consumption; Analyze the environmental correction factor α based on the environmental parameter data; S102: Dynamically correct the cooling load rate L' based on the environmental correction factor; L' = Q × (T in - T out ) × α ÷ (Q d ×△T d ); where Q d and △T d represent the flow rate under the design conditions and the temperature difference between the supply water pipe temperature and the return water pipe temperature; the historical corrected cooling load rate sequence {L’(t)|t∈[1, T]} is generated by integrating the corrected cooling load rates according to the time sequence; where T represents the total number of moments.

3. The multi-level equipment energy efficiency optimization control method for an efficient computer room according to claim 2, characterized in that: In S2, it includes the following: S201: Based on the preset delay time τ, embed the historical corrected cooling load rate sequence into the j-dimensional phase space for phase space reconstruction, and denote the i-th phase space vector as X i j =(L’(i), L’(i + τ), …, L’(i + (j - 1)τ)); Analyze the corresponding embedding degree coefficient EDC; if the embedding degree coefficient EDC is less than the corresponding threshold, use the corresponding dimension as the final embedding dimension; S202: Construct a hybrid prediction model based on the final embedding dimension. The hybrid prediction model includes a main system model and a slave system model; use the least squares method to fit the hybrid coefficient based on the historical corrected cooling load rate sequence, and use the gradient descent method to optimize the coupling strength coefficient.

4. The multi-level equipment energy efficiency optimization control method for an efficient computer room according to claim 3, characterized in that: In S3, it includes the following: S301: Analyze the resonance frequency f of the device based on the equivalent stiffness and equivalent mass of the device r ; Analyze the comprehensive energy efficiency index of the computer room, where the comprehensive energy efficiency index of the computer room is equal to the total cooling capacity provided by the refrigeration system at time t divided by the sum of the power consumptions of the chilled water host, chilled water pump, cooling water pump, and cooling tower fan corresponding to time t; S302: Construct the equipment operation frequency constraint condition and the chilled water supply and return water temperature difference constraint condition corresponding to the comprehensive energy efficiency index of the machine room. The equipment operation frequency constraint condition is that the difference between the actual operation frequency of the equipment and the resonance frequency is less than the corresponding preset threshold, and the chilled water supply and return water temperature difference constraint condition is that the chilled water supply and return water temperature difference is greater than the corresponding preset threshold; Map the optimization problem of the comprehensive energy efficiency index of the machine room into the Hamiltonian form of the Ising model. According to the equipment start-stop state and the energy efficiency coupling coefficient between equipment, solve the ground state of the Ising model through the quantum annealing algorithm to obtain the optimal parameter combination {Nch, ffp, fcp, fct} corresponding to time t; where Nch represents the number of chiller units, ffp represents the operation frequency of the chilled water pump, fcp represents the operation frequency of the cooling water pump, and fct represents the operation frequency of the cooling tower fan.

5. A multi-level equipment energy efficiency optimization control method for an efficient computer room according to claim 4, characterized in that: In S4, it includes the following: S401: Obtain the optimal parameter combination and the corresponding comprehensive energy efficiency index of the machine room at each moment to generate a parameter vector, analyze the corresponding optimal linear reconstruction weight in the local domain based on the parameter vector; construct a low-dimensional embedding based on the obtained optimal linear reconstruction weight, and map the parameter vector to a two-dimensional manifold to generate data points; S402: Preset the neighborhood radius and the minimum number of samples; For each data point, calculate the number of data points in its neighborhood; If the number is not less than the minimum number of samples, mark the data point as a core point; Otherwise, if the data point falls within the neighborhood of a core point, mark it as a boundary point; Otherwise, mark the data point as a noise point; Group the core points directly or indirectly connected starting from a core point and the boundary points within their neighborhoods into the same cluster; Mark the corresponding cluster label for each data point, and mark the data points that do not belong to any cluster as noise points; S403: Calculate the mean vector for each cluster, analyze the Euclidean distance from each data point in the cluster to the cluster center based on the mean vector, and analyze the standard deviation of the Euclidean distances corresponding to all data points; delete the data points whose Euclidean distance to the cluster center is greater than a preset number of times the standard deviation. Generate a lightweight database, where the lightweight database includes a load rate interval, a device parameter combination, a predicted energy efficiency index, a parameter confidence level, and an index table; the load rate interval is divided into intervals based on the distribution of the predicted load rate; the device parameter combination represents the optimal device parameter combination corresponding to the center of each cluster; the predicted energy efficiency index represents the energy efficiency index predicted for each device parameter combination during the optimization process; the parameter confidence level is equal to the probability of achieving or exceeding the predicted energy efficiency during actual operation; sort the database according to the load rate and generate an index table.

6. A multi-level equipment energy efficiency optimization control system for an efficient computer room, which is implemented by applying the multi-level equipment energy efficiency optimization control system for an efficient computer room described in any one of claims 1-5, and is characterized in that The system includes a data acquisition and correction module, a prediction model construction module, an operating parameter optimization module, and a data screening and optimization module; The data acquisition and correction module is used to obtain the environmental parameter data and design parameter data of the refrigeration machine room to analyze the environmental correction factor, and dynamically correct the cooling load rate based on the environmental correction factor; The prediction model construction module performs phase space reconstruction on the historical corrected cooling load rate sequence based on a preset delay time, analyzes the final embedding dimension, and constructs a hybrid prediction model based on the final embedding dimension; The operating parameter optimization module matches the optimal operating parameters based on the physical resonance characteristics of the equipment and the comprehensive energy efficiency index of the machine room; The data screening and optimization module compresses the data structure of the optimal operating parameters and the corresponding comprehensive energy efficiency index of the machine room, screens and analyzes the data points, and updates the parameter library.

7. A multi-level equipment energy efficiency optimization control system for an efficient computer room according to claim 6, characterized in that: The data acquisition and correction module includes a correction factor analysis unit and a dynamic correction unit; The correction factor analysis unit analyzes the environmental correction factor based on the environmental parameter data and design parameter data of the refrigeration machine room; The dynamic correction unit dynamically corrects the cooling load rate based on the environmental correction factor, and integrates the corrected cooling load rates according to the time sequence to generate a historical corrected cooling load rate sequence.

8. The multi-level equipment energy efficiency optimization control system for an efficient computer room according to claim 6, characterized in that: The prediction model construction module includes an embedding dimension analysis unit and a prediction model construction unit; The embedding dimension analysis unit is used to perform phase space reconstruction on the historical corrected cooling load rate sequence based on a preset delay time; Analyze the corresponding embedding degree coefficient, and confirm the final embedding dimension based on the embedding degree coefficient; The prediction model construction unit is used to construct a hybrid prediction model based on the final embedding dimension; use the least squares method to fit the hybrid coefficient, and use the gradient descent method to optimize the coupling strength coefficient.

9. The multi-level equipment energy efficiency optimization control system for an efficient computer room according to claim 6, wherein: The operating parameter optimization module is used for an index analysis unit and an optimal parameter analysis unit; The index analysis unit analyzes the resonance frequency of the equipment based on the equivalent stiffness and equivalent mass of the equipment, and analyzes the comprehensive energy efficiency index of the machine room; The optimal parameter analysis unit is used to construct the constraint conditions corresponding to the comprehensive energy efficiency index of the machine room; map the optimization problem of the comprehensive energy efficiency index of the machine room into the form of the Hamiltonian of the Ising model, and solve the ground state of the Ising model through the quantum annealing algorithm according to the equipment start-stop state and the energy efficiency coupling coefficient between equipment to obtain the optimal parameter combination.

10. A multi-level equipment energy efficiency optimization control system for an efficient computer room according to claim 6, characterized in that: The data screening and optimization module includes a data dimensionality reduction unit and a data screening unit; The data dimensionality reduction unit is used to obtain the optimal parameter combination at each moment and the corresponding comprehensive energy efficiency index of the computer room to generate a parameter vector, analyze the corresponding optimal linear reconstruction weight in the local domain based on the parameter vector; construct a low-dimensional embedding based on the obtained optimal linear reconstruction weight, and map the parameter vector to a two-dimensional manifold to generate data points; The data screening unit is used to gather the data points to generate clusters, and further analyze and screen the data points within the clusters to generate a lightweight database.

Images