A distributed energy-saving control method and system for refrigeration equipment

Abstract

This invention proposes a distributed energy-saving control method and system for refrigeration equipment. The method includes: acquiring physical parameters in the environment; fusing preprocessed data through environmental thermodynamic field mapping to generate an environmental thermodynamic field model; acquiring corresponding temperature field time-series data based on the time-series input sequence of the environmental thermodynamic field model; correcting the temperature field time-series data to generate a corresponding future temperature distribution and constructing a predicted future thermodynamic field model; performing temperature deviation calculation and analysis on the future temperature distribution to obtain the cooling demand per unit volume of air and the global cooling demand, and designing an optimal refrigeration power allocation scheme to minimize total energy consumption and meet power allocation constraints; executing the optimal refrigeration power allocation scheme; determining the overall load balance of the system based on the current load ratio of each device; performing global optimization scheduling based on the overall load balance to generate the final refrigeration equipment power allocation scheme.

Description

Technical Field

[0001] This invention belongs to the field of distributed energy-saving control, and particularly relates to a distributed energy-saving control method and system for refrigeration equipment. Background Technology

[0002] Refrigeration systems are widely used in data centers, industrial cooling, shopping malls, office buildings, and cold chain logistics, with the core objective of maintaining a stable temperature environment with minimal energy consumption. However, existing refrigeration control technologies still have many problems, resulting in low overall energy efficiency. First, most refrigeration systems rely on local temperature sensors for adjustment, only acquiring temperature information at specific measuring points and failing to accurately perceive the temperature distribution of the entire space. This can lead to localized overcooling or overheating, resulting in energy waste. Second, current mainstream refrigeration control strategies typically employ a passive response mechanism, initiating adjustment only when the measured temperature exceeds a set threshold. This method has significant lag, cannot predict temperature change trends, and is prone to large temperature fluctuations, further increasing unnecessary energy consumption. Finally, in scenarios where multiple refrigeration devices operate collaboratively, each device is usually controlled independently, lacking a global optimization strategy. This can lead to some devices operating at high loads for extended periods while others operate at lower loads, resulting in uneven energy distribution and reduced overall system efficiency.

[0003] Therefore, how to introduce a more accurate environmental sensing mechanism into the refrigeration system, combine it with temperature trend prediction for proactive adjustment, and achieve global energy saving through multi-device collaborative optimization has become a key technical challenge for improving the energy efficiency of the refrigeration system. Summary of the Invention

[0004] The purpose of this invention is to propose a distributed energy-saving control method and system for refrigeration equipment, which effectively overcomes the defects of existing refrigeration control technology and achieves more precise and efficient energy-saving refrigeration control.

[0005] To achieve the above objectives, a first aspect of the present invention provides a distributed energy-saving control method for a refrigeration device, the method comprising the following steps:

[0006] The physical parameters in the environment are acquired, all physical parameters are preprocessed, and the preprocessed data are then fused together to generate an environmental thermal field model through environmental thermal field mapping.

[0007] Based on the time-series input sequence of the environmental thermal field model, the corresponding temperature field time-series data is obtained, the temperature field time-series data is corrected, the corresponding future temperature distribution is generated, and a predicted future thermal field model is constructed.

[0008] Temperature deviation calculation and analysis are performed on the future temperature distribution to obtain the cooling demand per unit volume of air and the global cooling demand. The optimal cooling power allocation scheme is designed to minimize total energy consumption and meet power allocation constraints. The total energy consumption is the total power of the system, and the total power must meet the global cooling demand.

[0009] Among them, satisfying the power allocation constraints includes equipment operation limits, temperature demand constraints, and load balancing constraints; the equipment operation limits are the maximum power of a single refrigeration unit; the temperature demand constraints are future cooling capacity demands; and the load balancing constraints are power difference constraints between devices, used to ensure that no individual device will operate under overload.

[0010] The optimal cooling power allocation scheme is executed. The overall load balance of the system is determined based on the current load ratio of each device. Global optimization scheduling is performed based on the overall load balance to generate the final cooling equipment power allocation scheme.

[0011] Preferably, the physical parameters include temperature, humidity, and air velocity; the preprocessing includes anomaly detection and correction operations.

[0012] Preferably, the fused preprocessed data is mapped through an environmental thermal field to generate an environmental thermal field model, including:

[0013] Obtain the space to be measured;

[0014] The measurement space is divided into M×N grid cells. The temperature at the center of each grid cell is calculated by weighting the temperature at the center of the grid cell at time t. The weighting coefficients used in the weighting calculation are calculated using exponential decay.

[0015] Calculate the gradient of adjacent grid points. If the gradient change is too large, adjust the temperature value of the grid center point at time t to smooth the temperature change, reduce noise interference, calculate the local variance of the measurement points, dynamically adjust the filtering parameters, remove high-frequency noise, and ensure the stability of the thermal field.

[0016] By combining the optimized temperature values ​​of all grid points, the final thermal field M is formed. t ={T(x,y,t)|(x,y)∈Ω}, where Ω is the region of measurement space and T(x,y,t) is the temperature value of point (x,y) at time t.

[0017] Preferably, the time-series input sequence is used to extract the main change patterns using adaptive dimensionality reduction mapping to generate a dimensionality-reduced feature matrix.

[0018] Preferably, the step of correcting the time-series temperature field data to generate the corresponding future temperature distribution and constructing a predicted future thermal field model includes:

[0019] Get the current thermal field M t An adaptive local smoothing term is used for smoothing to generate a prediction model. The adaptive local smoothing term is calculated through local gradient constraints to ensure that the predicted temperature change trend conforms to the thermal diffusion law.

[0020] Calculate prediction confidence based on uncertainty measures calculated from historical errors;

[0021] The prediction model is based on the prediction confidence level. Make adjustments to generate the adjusted prediction model.

[0022] By combining the predicted temperature values ​​of all grid points, the final future temperature distribution is constructed. in, Ω represents the predicted temperature value at time t+T′ in the future (x,y); Ω represents the area of ​​the measurement space.

[0023] Preferably, the prediction model is based on the prediction confidence level. Adjustments will be made, including:

[0024] A confidence weighting is introduced between the predicted value and the current temperature field. When the confidence of the prediction result is the highest, it relies most on the preliminary prediction value calculated based on the feature matrix after dimensionality reduction of the time series input. When the prediction confidence is the lowest, it tends to maintain the current temperature field to avoid excessive prediction deviation.

[0025] Preferably, the step of performing temperature deviation calculation and analysis on the future temperature distribution to obtain the cooling demand per unit volume of air and the global cooling demand, and designing the optimal cooling power allocation scheme to minimize total energy consumption and meet power allocation constraints, specifically involves:

[0026] Determine the temperature deviation between the predicted future temperature value and the set target temperature. The temperature deviation represents the amount of temperature change that needs to be adjusted at the current location. Combine this with air density, specific heat capacity, and air flow velocity to calculate the cooling demand per unit volume of air and the global cooling demand.

[0027] The total power of the system is obtained, which is provided by N refrigeration units. The refrigeration power optimization target is designed to minimize the total energy consumption while ensuring that the global cooling demand is met.

[0028] Design power allocation constraints;

[0029] Generate the optimal cooling power allocation scheme.

[0030] Preferably, the generation of the optimal cooling power allocation scheme includes at least one of the following:

[0031] A. Adopt a gradient adjustment strategy to initialize the power of each refrigeration device, calculate a preliminary allocation scheme based on the global cooling demand, and gradually adjust the power output of each device to ensure that the temperature demand is met while the overall energy consumption is minimized. Calculate the rate of change of the objective function, judge the convergence status, and output the final power scheme if the optimal conditions are met or the maximum number of iterations is reached.

[0032] B. Calculate the unit power consumption cooling contribution ratio of all devices by combining the power output of each device with the global cooling demand, and prioritize allocating a larger proportion of the load to devices with a high unit power consumption cooling contribution ratio, while setting a power limit for devices with a low unit power consumption cooling contribution ratio to avoid a decrease in overall energy efficiency. In the allocation process, a dynamic adjustment strategy is introduced so that devices with lower energy efficiency only need to supplement additional cooling demand when necessary.

[0033] C. If a device operates under high load for a long period of time, adjust the power of neighboring devices appropriately to balance the temperature distribution, and set a dynamic power adjustment window. Reassess the device status every cycle to adapt to environmental changes and improve the long-term stability of the refrigeration system.

[0034] Preferably, the step of executing the optimal cooling power allocation scheme involves determining the overall load balance of the system based on the current load ratio of each device, performing global optimization scheduling based on the overall load balance, and generating the final cooling equipment power allocation scheme, specifically including:

[0035] Calculate the current load ratio of each device, that is, the proportion of the current power output of the device to its maximum power, and calculate the overall load balance of the system to measure the distribution of the load of all devices.

[0036] Dynamically adjust equipment power based on the load distribution of all devices:

[0037] If the current load ratio of a certain device is much lower than the average load ratio of all devices, then the power of that device should be increased appropriately to reduce the pressure on the high-load devices.

[0038] If the current load ratio of a certain device is much higher than the average load ratio of all devices, then the power of that device should be reduced appropriately to prevent overload, and the excess load should be transferred to other devices.

[0039] If the temperature gradient between adjacent areas is large, increase the power of equipment near the high-temperature area to accelerate temperature equalization;

[0040] The operating status is adaptively optimized based on the distribution of load across all devices:

[0041] If a device operates at low load for an extended period, determine whether it can be temporarily shut down to reduce unnecessary energy consumption; if a device operates at high load for an extended period, prioritize scheduling other devices to increase their power and reduce the operating pressure on the device in question.

[0042] Set a time window, recalculate the load balancing degree in each time window, and adjust the power distribution strategy based on the latest data;

[0043] Generate the final power allocation scheme for the refrigeration equipment.

[0044] In another aspect of the present invention, a distributed energy-saving control system for a refrigeration device is provided, the system comprising:

[0045] The environmental thermal field model building unit acquires physical parameters in the environment, preprocesses all physical parameters, and then merges the preprocessed data through environmental thermal field mapping to generate an environmental thermal field model.

[0046] The future thermal field model construction unit is used to obtain the corresponding temperature field time series data according to the time series input sequence of the environmental thermal field model, perform correction processing on the temperature field time series data, generate the corresponding future temperature distribution, and constitute the predicted future thermal field model.

[0047] The cooling power allocation scheme initialization unit is used to perform temperature deviation calculation and analysis on the future temperature distribution, obtain the cooling capacity requirement per unit volume of air and the global cooling capacity requirement, and design the optimal cooling power allocation scheme to minimize total energy consumption and meet power allocation constraints; wherein, the total energy consumption is the total power of the system, and the total power must meet the global cooling capacity requirement;

[0048] Among them, satisfying the power allocation constraints includes equipment operation limits, temperature demand constraints, and load balancing constraints; the equipment operation limits are the maximum power of a single refrigeration unit; the temperature demand constraints are future cooling capacity demands; and the load balancing constraints are power difference constraints between devices, used to ensure that no individual device will operate under overload.

[0049] The cooling power allocation scheme optimization unit is used to execute the optimal cooling power allocation scheme. It determines the overall load balance of the system based on the current load ratio of each device, performs global optimization scheduling based on the overall load balance, and generates the final cooling equipment power allocation scheme.

[0050] The beneficial technical effects of the present invention are at least as follows:

[0051] This invention addresses the problems of limited sensing capabilities, control lag, and lack of collaborative optimization in existing refrigeration systems by proposing an adaptive energy-saving refrigeration control method and system based on environmental thermodynamic field mapping.

[0052] First, by integrating data from multiple sensors to construct an environmental thermal field mapping, accurate perception of the temperature distribution throughout the space is achieved, enabling the refrigeration system to optimize and regulate based on global thermal information, thus avoiding localized overcooling or overheating.

[0053] Secondly, by employing temperature trend prediction technology, historical temperature change data is analyzed to predict future temperature evolution trends, enabling the system to proactively adjust cooling power before temperature fluctuations occur, reducing response lag and improving energy efficiency.

[0054] Finally, in scenarios where multiple refrigeration devices operate simultaneously, a collaborative optimization mechanism is established. Based on environmental thermal field data and temperature prediction results, the cooling power of each device is dynamically adjusted to achieve load balancing, reduce overall energy consumption, and improve system stability and energy efficiency. Through these innovations, this invention effectively overcomes the shortcomings of existing refrigeration control technologies, achieving more precise and efficient energy-saving refrigeration control. Attached Figure Description

[0055] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0056] Figure 1 This is a flowchart of a distributed energy-saving control method for refrigeration equipment disclosed in an embodiment of the present invention. Detailed Implementation

[0057] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0058] Example 1

[0059] like Figure 1 As shown in the figure, an embodiment of the present invention provides a distributed energy-saving control method for refrigeration equipment, the method comprising the following steps:

[0060] S1. Obtain the physical parameters in the environment, preprocess all physical parameters, and then fuse the preprocessed data through environmental thermal field mapping to generate an environmental thermal field model.

[0061] Specifically, the goal of this step is to construct an environmental thermal field model M. tThis provides an accurate data foundation for subsequent temperature prediction, power optimization, and coordinated scheduling of refrigeration equipment. Traditional refrigeration systems rely on only a few fixed sensors, making it difficult to comprehensively perceive ambient temperature, leading to over- or under-cooling in local areas and affecting overall energy efficiency. To address this issue, this solution proposes a method combining multi-source sensor fusion, spatial dynamic modeling, and thermodynamic field interpolation optimization to construct a high-precision spatial temperature field and ensure the spatiotemporal consistency of the data.

[0062] Further, set the measurement points:

[0063] Define N measurement points in the environment, with the measurement point set S = {s1, s2, ..., s...} N}

[0064] Collect physical parameters such as temperature, humidity, and air velocity to form a data vector:

[0065]

[0066] in:

[0067] Measurement point s i Temperature value at time t

[0068] Measurement point s i Humidity value at time t

[0069] Measurement point s i air velocity at time t

[0070] Furthermore, anomaly detection and correction:

[0071] Calculate the measurement point s i temperature and its neighboring measurement point s j If the temperature difference exceeds a set threshold, it is considered abnormal.

[0072]

[0073] in:

[0074] Measurement point s i set of neighboring measurement points

[0075] Measurement point s i abnormality

[0076] For outlier data points, a combination of temporal and spatial interpolation is used for correction.

[0077]

[0078] in:

[0079] λ: Time regression factor (controls the weights of time interpolation)

[0080] w i,j : Measurement point s i With neighboring measuring point s j Weighting coefficients between

[0081] Furthermore, the thermal field is constructed:

[0082] Gridded region division:

[0083] The measurement space is divided into M×N grid cells, with each grid center point g. k temperature Calculated by weighting from surrounding measurement points:

[0084]

[0085] in:

[0086] Grid center point g k Temperature value at time t

[0087] W i,k : Measurement point s i For grid point g k Influence weight

[0088] Weighting coefficient W i,k Exponential decay is used:

[0089]

[0090] in:

[0091] d i,k : Measurement point s i With grid center g k Euclidean distance

[0092] α: Hyperparameter controlling the decay rate

[0093] Furthermore, thermal field optimization:

[0094] Local gradient optimization:

[0095] Calculate the gradient between adjacent grid points; if the gradient change is too large, adjust accordingly. It smooths out temperature changes and reduces noise interference.

[0096] Adaptive spatiotemporal filtering:

[0097] Calculate the local variance of the measurement points, dynamically adjust the filtering parameters, remove high-frequency noise, and ensure the stability of the thermal field.

[0098] Furthermore, the final thermal field model is generated:

[0099] Constructing a thermal field model:

[0100] By combining the optimized temperature values ​​of all grid points, the final thermal field is formed:

[0101] M t ={T(x,y,t)∣(x,y)∈Ω} (6)

[0102] in:

[0103] Ω: Measurement area

[0104] T(x,y,t): The temperature value of point (x,y) at time t.

[0105] S2. Based on the time-series input sequence of the environmental thermal field model, obtain the corresponding temperature field time-series data, perform correction processing on the temperature field time-series data, generate the corresponding future temperature distribution, and construct the predicted future thermal field model.

[0106] The goal of this step is to base it on the environmental thermal field model M. t Predict the temperature distribution at future time t+T′ This provides accurate input for subsequent dynamic cooling power calculations. Traditional refrigeration systems rely solely on current temperature feedback to adjust power, failing to predict cooling demand in advance, resulting in delayed adjustments. This step constructs an adaptive temperature prediction mechanism through time series modeling, spatial correlation correction, and prediction uncertainty compensation, improving prediction accuracy and stability.

[0107] Furthermore, thermal field data from the past T time points are selected to form a time-series input sequence:

[0108] X t ={M t-T M t-T+1 ,...,M t} (7)

[0109] in:

[0110] X t Time series data for predicting temperature fields

[0111] M t-T To M t The thermal field at the past T moments

[0112] Dimensionality Reduction Optimization: Due to the high dimensionality of the thermal field data, direct modeling and computation are costly. Therefore, an adaptive dimensionality reduction mapping Φ(·) is used to extract the main change patterns.

[0113] Z t =Φ(X t (8)

[0114] in:

[0115] Z t : Feature matrix after dimensionality reduction

[0116] Φ(·): Dimensionality reduction transformation mapping, combined with spatiotemporal correlation, to ensure that key temperature patterns are not lost.

[0117] Furthermore, spatiotemporal correlation correction:

[0118] Spatial correction items:

[0119] Traditional prediction methods typically assume that temperature changes between measurement points are independent. However, in real-world scenarios, temperature changes are influenced by factors such as airflow, equipment heat dissipation, and human activity, exhibiting strong spatial correlation.

[0120] Adaptive local smoothing term Ψ(M) t ), combined with the current thermal field M t Optimize the prediction model:

[0121]

[0122] in:

[0123] F(Z t ): Based on time series input Z t Preliminary predicted values ​​calculated

[0124] Ψ(M t Based on the current thermal field M t Calculated spatial correction term

[0125] Correction term calculation:

[0126] Ψ(M t By using local gradient constraint calculations, we ensure that the predicted temperature change trend conforms to the laws of thermal diffusion.

[0127]

[0128] in:

[0129] The Laplace transform of the current thermal field characterizes the diffusion trend of the temperature field.

[0130] β: Balance coefficient, controls the correction range, and avoids over-adjustment.

[0131] Further, the prediction confidence score is calculated:

[0132] Since temperature changes are influenced by various factors, the predicted values ​​are uncertain, and it is necessary to calculate the prediction confidence level σ. t Dynamically adjust prediction weights:

[0133]

[0134] in:

[0135] ω t Dynamic weights, ω t ∈[0,1]

[0136] σ t σ is an uncertainty measure calculated based on historical errors. t The larger the value, the higher the instability of the prediction result.

[0137] Adaptive compensation mechanism:

[0138] Introduce a confidence-weighted average between the predicted value and the current temperature field:

[0139]

[0140] When the confidence level of the prediction result is high (σ) t When the time is small, it mainly depends on F(Z). t );

[0141] When the prediction confidence is low (σ) t When the temperature field is large, it tends to maintain the current temperature field M. t To avoid excessive prediction bias.

[0142] Furthermore, the final model of the future thermal field is generated:

[0143] By combining the predicted temperature values ​​of all grid points, the final future temperature distribution is constructed:

[0144]

[0145] in:

[0146] Predicted temperature value at time t+T′ (x,y)

[0147] Ω: Measurement area

[0148] As input to step 3, it is used to calculate the optimal cooling power in the future.

[0149] S3. Perform temperature deviation calculation and analysis on the future temperature distribution to obtain the cooling demand per unit volume of air and the global cooling demand, and design the optimal cooling power allocation scheme to minimize total energy consumption and meet power allocation constraints; wherein, the total energy consumption is the total power of the system, and the total power must meet the global cooling demand.

[0150] The goal of this step is to build upon the future thermal field model predicted in Step 2. Calculate the optimal cooling power P that each refrigeration unit needs to allocate at the future time t+T′. t This solution ensures minimal overall energy consumption while meeting temperature requirements. Traditional refrigeration systems typically use fixed power or simple on / off control, which struggles to adapt to dynamic changes in temperature demand, easily leading to localized overcooling or overheating and increased energy waste. This solution, through cooling demand calculation, equipment energy efficiency optimization, and a load balancing mechanism, ensures the accuracy and stability of cooling power allocation.

[0151] Furthermore, calculate future cooling demand:

[0152] Calculate the temperature deviation at each spatial location (x, y) at a future time t+T′:

[0153]

[0154] in:

[0155] ΔT(x,y,t+T′): Temperature deviation, representing the amount of temperature change that needs to be adjusted at the current position (x,y).

[0156] Step 2: Predicted future temperature values.

[0157] T target : The set target temperature.

[0158] Calculate the cooling requirement per unit volume of air, considering air density ρ and specific heat capacity c. p And the airflow velocity V(x,y):

[0159] Q(x,y,t+T′)=ρc p V(x,y)ΔT(x,y,t+T′) (15)

[0160] in:

[0161] Q(x,y,t+T′): The amount of cooling required at the current position (x,y) at time t+T′ (in J).

[0162] ρ: Air density (unit: kg / m³) 3 ).

[0163] c pSpecific heat capacity of air (unit: J / kg·K).

[0164] V(x,y): Air velocity (unit: m / s).

[0165] Calculate the total cooling demand:

[0166]

[0167] Where Ω represents the entire region.

[0168] Furthermore, a cooling power optimization target is established:

[0169] Set the total power P of the system t Provided by N refrigeration units:

[0170]

[0171] in:

[0172] Cooling power of the i-th refrigeration unit at time t (unit: W).

[0173] The goal is to minimize total energy consumption while ensuring the global cooling demand Q. total (t+T′) is satisfied:

[0174]

[0175] in:

[0176] η i Coefficient of Performance (COP) of the i-th refrigeration unit.

[0177] Furthermore, optimize power allocation constraints:

[0178] Equipment operating limitations: The power output of each device is limited by its own capacity, ensuring that it will not exceed the device's maximum operating power.

[0179]

[0180] Where P max This is the maximum power of a single refrigeration unit.

[0181] Temperature requirement constraint: Total cooling capacity must meet future cooling demand.

[0182]

[0183] Load balancing constraint: Power output should be as balanced as possible among different devices.

[0184]

[0185] The δ control mechanism manages the power differences between devices to ensure that no individual device will be overloaded.

[0186] Furthermore, iterative optimization methods

[0187] A gradient adjustment strategy is adopted to initialize the power of each refrigeration unit, and based on the global cooling capacity demand Q. total (t+T′) Calculate the initial allocation scheme.

[0188] Gradual adjustment It ensures that temperature requirements are met while minimizing overall energy consumption.

[0189] Calculate the rate of change of the objective function, determine the convergence status, and output the final power scheme if the optimal conditions are met or the maximum number of iterations is reached.

[0190] Furthermore, calculate the unit power consumption cooling contribution ratio of all devices, i.e.:

[0191]

[0192] Where γ i It reflects the energy efficiency of the equipment under the current load; the higher the value, the stronger the cooling capacity per unit power.

[0193] Prioritize high γ i The equipment is allocated a larger proportion of the load, and is more sensitive to low gamma. i Set a power limit for the equipment to avoid a decrease in overall energy efficiency.

[0194] During the allocation process, a dynamic adjustment strategy is introduced so that less energy-efficient equipment only needs to supplement additional cooling capacity when necessary.

[0195] Furthermore, considering load balancing among devices, if a device operates at high load for an extended period, the power of neighboring devices is appropriately adjusted to balance temperature distribution. A dynamic power adjustment window is set, and the device status is reassessed each cycle to adapt to environmental changes and improve the long-term stability of the refrigeration system. The optimized refrigeration equipment power allocation scheme P... t As input to step 4, ensure stable system operation and optimize energy consumption globally.

[0196] S4. Execute the optimal cooling power allocation scheme, determine the overall load balance of the system based on the current load ratio of each device, perform global optimization scheduling based on the overall load balance, and generate the final cooling equipment power allocation scheme.

[0197] Specifically, the goal of this step is to determine the optimal cooling power allocation scheme P based on the calculation in step 3. tThis solution intelligently schedules multiple refrigeration devices to ensure the entire system meets temperature requirements with minimal energy consumption. Since the power of refrigeration devices is limited, directly implementing the optimal power scheme may lead to overload of some devices while others remain idle, thus affecting cooling efficiency and system stability. Therefore, this solution uses load balancing adjustment, device collaborative scheduling, and dynamic power correction to ensure reasonable energy distribution among devices, improving the overall efficiency and reliability of the refrigeration system.

[0198] Furthermore, calculate the current load ratio of each device, i.e., the current operating power of the device. It accounts for its maximum power P max Ratio:

[0199]

[0200] in:

[0201] The load ratio of the i-th device is in the range of [0,1], and the larger the value, the higher the load.

[0202] P max : The maximum operating power of a single device.

[0203] Calculate the overall load balance of the system, measuring the distribution of load across all devices:

[0204]

[0205] in:

[0206] This is the average load ratio of the system, ensuring that the load on all devices is even.

[0207] γ is the energy efficiency adjustment coefficient. The second term is used to penalize the power of low-efficiency equipment, prompting the system to prioritize the allocation of high-efficiency equipment.

[0208] The goal is to minimize Λ t This means that while meeting cooling needs, the equipment load is balanced and the overall energy consumption is reduced.

[0209] Furthermore, increase the power of low-load devices: if the load of a certain device is higher than... far below Then, appropriately increase the power of the equipment to reduce the pressure on high-load equipment:

[0210]

[0211] κ is an adjustment factor that ensures stable power changes and avoids frequent equipment start-ups and shutdowns.

[0212] Limit the power of high-load devices: If the load of a certain device is higher than that of a high-load device... Much higher Then, appropriately reduce the power of the device to prevent overload, and transfer the excess load to other devices:

[0213]

[0214] Temperature gradient correction: Considering the ambient temperature changes around the equipment, if the temperature gradient between adjacent areas is large, increase the power of equipment near the high-temperature area to accelerate temperature equalization.

[0215]

[0216] Where β is the environmental response coefficient. This indicates the rate of change of the temperature around the equipment.

[0217] Furthermore, intelligent control of equipment start-up and shutdown:

[0218] If a device is under low load for an extended period of time Determine whether the device can be temporarily shut down to reduce unnecessary energy consumption.

[0219] If a device is under high load for an extended period of time Then, other devices will be prioritized to increase their power, reducing the operating pressure on this device.

[0220] Dynamic power adjustment window:

[0221] Set a time window ΔT, and recalculate the load balancing degree Λ every ΔT. t And adjust the power allocation strategy based on the latest data.

[0222] This allows the system to adapt to changes in ambient temperature, ensuring it always operates at its optimal state.

[0223] Furthermore, the final refrigeration equipment operation plan is generated:

[0224] After the above optimizations, the final power allocation scheme for the refrigeration equipment is generated:

[0225]

[0226] This solution ensures balanced load across all devices, prevents individual devices from being overloaded for extended periods, and improves system stability.

[0227] By adjusting the load balance, unnecessary energy consumption is reduced, enabling the entire system to maintain optimal temperature control with minimal energy consumption.

[0228] This power distribution scheme is ultimately applied to the equipment control system to execute the final cooling strategy.

[0229] Example 2

[0230] In another embodiment of the present invention, a distributed energy-saving control system for a refrigeration device is disclosed, the system comprising:

[0231] The environmental thermal field model building unit acquires physical parameters in the environment, preprocesses all physical parameters, and then merges the preprocessed data through environmental thermal field mapping to generate an environmental thermal field model.

[0232] The future thermal field model construction unit is used to obtain the corresponding temperature field time series data according to the time series input sequence of the environmental thermal field model, perform correction processing on the temperature field time series data, generate the corresponding future temperature distribution, and constitute the predicted future thermal field model.

[0233] The cooling power allocation scheme initialization unit is used to perform temperature deviation calculation and analysis on the future temperature distribution, obtain the cooling capacity requirement per unit volume of air and the global cooling capacity requirement, and design the optimal cooling power allocation scheme to minimize total energy consumption and meet power allocation constraints; wherein, the total energy consumption is the total power of the system, and the total power must meet the global cooling capacity requirement;

[0234] Among them, satisfying the power allocation constraints includes equipment operation limits, temperature demand constraints, and load balancing constraints; the equipment operation limits are the maximum power of a single refrigeration unit; the temperature demand constraints are future cooling capacity demands; and the load balancing constraints are power difference constraints between devices, used to ensure that no individual device will operate under overload.

[0235] The cooling power allocation scheme optimization unit is used to execute the optimal cooling power allocation scheme. It determines the overall load balance of the system based on the current load ratio of each device, performs global optimization scheduling based on the overall load balance, and generates the final cooling equipment power allocation scheme.

[0236] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0237] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0238] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0239] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0240] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0241] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0242] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0243] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0244] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0245] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0246] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0247] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0248] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0249] Finally, it should be noted that the lithium battery pack chip equalization control platform disclosed in the embodiments of the present invention is only a preferred embodiment of the present invention and is only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A distributed energy-saving control method for refrigeration equipment, characterized in that, The method includes the following steps: The physical parameters in the environment are acquired, all physical parameters are preprocessed, and the preprocessed data are then fused together and mapped through the environmental thermal field to generate an environmental thermal field model. Based on the time-series input sequence of the environmental thermal field model, the corresponding temperature field time-series data is obtained, the temperature field time-series data is corrected, the corresponding future temperature distribution is generated, and a predicted future thermal field model is constructed. Temperature deviation calculation and analysis are performed on the future temperature distribution to obtain the cooling demand per unit volume of air and the global cooling demand. The optimal cooling power allocation scheme is designed to minimize total energy consumption and meet power allocation constraints. The total energy consumption is the total power of the system, and the total power must meet the global cooling demand. Among them, satisfying the power allocation constraints includes equipment operation limits, temperature demand constraints, and load balancing constraints; the equipment operation limits are the maximum power of a single refrigeration unit; the temperature demand constraints are future cooling capacity demands; and the load balancing constraints are power difference constraints between devices, used to ensure that no individual device will operate under overload. The optimal cooling power allocation scheme is executed. The overall load balance of the system is determined based on the current load ratio of each device. Global optimization scheduling is performed based on the overall load balance to generate the final cooling equipment power allocation scheme. The process of implementing the optimal cooling power allocation scheme involves determining the overall load balance of the system based on the current load ratio of each device, performing global optimization scheduling based on the overall load balance, and generating the final cooling equipment power allocation scheme. Specifically, this includes: Calculate the current load ratio of each device, that is, the proportion of the current power output of the device to its maximum power, and calculate the overall load balance of the system to measure the distribution of the load of all devices. Dynamically adjust equipment power based on the load distribution of all devices: If the current load ratio of a certain device is much lower than the average load ratio of all devices, then the power of that device should be increased appropriately to reduce the pressure on the high-load devices. If the current load ratio of a certain device is much higher than the average load ratio of all devices, then the power of that device should be reduced appropriately to prevent overload, and the excess load should be transferred to other devices. If the temperature gradient between adjacent areas is large, increase the power of equipment near the high-temperature area to accelerate temperature equalization; The operating status is adaptively optimized based on the distribution of load across all devices: If a device is under low load for an extended period, determine whether it can be temporarily shut down to reduce energy consumption; if a device is under high load for an extended period, prioritize scheduling other devices to increase their power and reduce the operating pressure on the device in question. Set a time window, recalculate the load balancing degree in each time window, and adjust the power distribution strategy based on the latest data; Generate the final power allocation scheme for the refrigeration equipment.

2. The distributed energy-saving control method for refrigeration equipment according to claim 1, characterized in that, The physical parameters include temperature, humidity, and air velocity; the preprocessing includes anomaly detection and correction operations.

3. The distributed energy-saving control method for refrigeration equipment according to claim 1, characterized in that, The fused preprocessed data is mapped through an environmental thermal field to generate an environmental thermal field model, including: Obtain the space to be measured; The measurement space is divided into Each grid cell has a temperature at its center point calculated by weighting the temperature of surrounding measurement points, generating the grid center point at time [time]. The temperature value; wherein the weighting coefficients for the weighted calculation are calculated using exponential decay; Calculate the gradient between adjacent grid points. If the gradient change is too large, adjust the grid center point at time t. The temperature values ​​smooth out temperature changes, reduce noise interference, calculate the local variance of the measurement points, dynamically adjust the filtering parameters, remove high-frequency noise, and ensure the stability of the thermal field. The final thermal field is formed by combining the optimized temperature values ​​of all grid points. ,in, To measure the area of ​​the space, For point At any moment Temperature value.

4. The distributed energy-saving control method for refrigeration equipment according to claim 1, characterized in that, The time-series input sequence is used to extract the main change patterns using adaptive dimensionality reduction mapping to generate a dimensionality-reduced feature matrix.

5. A distributed energy-saving control method for refrigeration equipment according to claim 3, characterized in that, The step of correcting the time-series temperature field data to generate the corresponding future temperature distribution and constructing a predicted future thermal field model includes: Get the current thermal field An adaptive local smoothing term is used for smoothing to generate a prediction model. The adaptive local smoothing term is calculated using local gradient constraints to ensure that the predicted temperature change trend conforms to the thermal diffusion law. Calculate prediction confidence based on uncertainty measures calculated from historical errors; The prediction model is based on the prediction confidence level. Make adjustments to generate the adjusted prediction model. ; By combining the predicted temperature values ​​of all grid points, the final future temperature distribution is constructed. ,in, For the future Time point The predicted temperature value; For: the area or range of the measurement space.

6. A distributed energy-saving control method for refrigeration equipment according to claim 5, characterized in that, The prediction model is based on the prediction confidence level. Adjustments will be made, including: A confidence weighting is introduced between the predicted value and the current temperature field. When the confidence of the prediction result is the highest, it relies most on the preliminary prediction value calculated based on the feature matrix after dimensionality reduction of the time series input. When the prediction confidence is the lowest, it tends to maintain the current temperature field to avoid excessive prediction deviation.

7. A distributed energy-saving control method for refrigeration equipment according to claim 1, characterized in that, The process involves calculating and analyzing the temperature deviation of the future temperature distribution to obtain the cooling demand per unit volume of air and the global cooling demand. The optimal cooling power allocation scheme is then designed to minimize total energy consumption and satisfy power allocation constraints. Specifically: Determine the temperature deviation between the predicted future temperature value and the set target temperature. The temperature deviation represents the amount of temperature change that needs to be adjusted at the current location. Combine this with air density, specific heat capacity, and air flow velocity to calculate the cooling demand per unit volume of air and the global cooling demand. Obtain the total power of the system from The refrigeration equipment was jointly provided by Taiwan and the design aimed to optimize the refrigeration power, with the goal of minimizing total energy consumption while ensuring that the overall cooling demand was met. Design power allocation constraints; Generate the optimal cooling power allocation scheme.

8. A distributed energy-saving control method for refrigeration equipment according to claim 1, characterized in that, The generation of the optimal cooling power allocation scheme includes at least one of the following: A. Adopt a gradient adjustment strategy to initialize the power of each refrigeration device, calculate a preliminary allocation scheme based on the global cooling demand, and gradually adjust the power output of each device to ensure that the temperature demand is met while the overall energy consumption is minimized. Calculate the rate of change of the objective function, judge the convergence status, and output the final power scheme if the optimal conditions are met or the maximum number of iterations is reached. B. Calculate the unit power consumption cooling contribution ratio of all devices by combining the power output of each device with the global cooling demand, and prioritize allocating a larger proportion of the load to devices with a high unit power consumption cooling contribution ratio, while setting a power limit for devices with a low unit power consumption cooling contribution ratio to avoid a decrease in overall energy efficiency. In the allocation process, a dynamic adjustment strategy is introduced so that devices with lower energy efficiency only need to supplement additional cooling demand when necessary. C. If a device operates under high load for a long period of time, adjust the power of neighboring devices appropriately to balance the temperature distribution, and set a dynamic power adjustment window. Reassess the device status every cycle to adapt to environmental changes and improve the long-term stability of the refrigeration system.

9. A system for implementing a distributed energy-saving control method for refrigeration equipment as described in claim 1, characterized in that, The system includes: The environmental thermal field model building unit acquires physical parameters in the environment, preprocesses all physical parameters, and then merges the preprocessed data through environmental thermal field mapping to generate an environmental thermal field model. The future thermal field model construction unit is used to obtain the corresponding temperature field time series data according to the time series input sequence of the environmental thermal field model, perform correction processing on the temperature field time series data, generate the corresponding future temperature distribution, and constitute the predicted future thermal field model. The cooling power allocation scheme initialization unit is used to perform temperature deviation calculation and analysis on the future temperature distribution, obtain the cooling capacity requirement per unit volume of air and the global cooling capacity requirement, and design the optimal cooling power allocation scheme to minimize total energy consumption and meet power allocation constraints; wherein, the total energy consumption is the total power of the system, and the total power must meet the global cooling capacity requirement; Among them, satisfying the power allocation constraints includes equipment operation limits, temperature demand constraints, and load balancing constraints; the equipment operation limits are the maximum power of a single refrigeration unit; the temperature demand constraints are future cooling capacity demands; and the load balancing constraints are power difference constraints between devices, used to ensure that no individual device will operate under overload. The cooling power allocation scheme optimization unit is used to execute the optimal cooling power allocation scheme. It determines the overall load balance of the system based on the current load ratio of each device, performs global optimization scheduling based on the overall load balance, and generates the final cooling equipment power allocation scheme.

Images