Method and device for automatically adjusting dehumidifier of ring main unit, medium and equipment

Abstract

The invention relates to the technical field of power systems, and particularly provides a method and device for automatically adjusting ring main unit dehumidifiers, a medium and equipment, and the method can comprise the steps: obtaining the total dehumidification power value of all dehumidifiers in the future time based on a pre-trained ring main unit power prediction model and historical data of a ring main unit; the dehumidification power of each dehumidifier is adjusted according to the power adjusting step length determined by the dehumidification demand weight of each dehumidifier; wherein the adjustment sum of the dehumidification power of all dehumidifiers does not exceed the total value of the dehumidification power; under the dehumidification power, the dehumidification efficiency of each dehumidifier in a preset time period is obtained; the dehumidification efficiency is compared with the expected efficiency, the dehumidification demand weight is optimized, and the optimized dehumidification demand weight is obtained; and the dehumidification power is automatically adjusted through the optimized dehumidification demand weight. According to the embodiment of the invention, power self-adjustment of the dehumidifier can be realized, and intelligent dehumidification of the ring main unit is realized.

Description

Technical Field

[0001] This application relates to the technical field of power systems. Specifically, it relates to a method, device, medium, and equipment for automatic adjustment of a dehumidifier in a ring main unit (RMU). Background Art

[0002] With the acceleration of the construction of smart grids, as a key equipment in the distribution system, the RMU is long-term in an outdoor or semi-closed environment, and the humidity inside the cabinet is likely to cause insulation aging, short circuit and other faults.

[0003] Currently, most of the traditional dehumidifiers supporting the existing RMUs adopt a fixed power design, which can neither dynamically adjust according to the total power limit of the DTU (distribution network terminal) and PT (voltage transformer) in the RMU (the total power limit of some small RMUs is ≤ 500W), nor has the ability to adjust the dehumidification power of a single device. In the current technology, it still operates at full power in low humidity, resulting in waste of electric energy; in high humidity, the power is significantly insufficient, affecting the dehumidification effect.

[0004] Therefore, how to provide a technical solution for an automatic adjustment method of an RMU dehumidifier with intelligent control has become an urgent technical problem to be solved. Summary of the Invention

[0005] Some embodiments of this application aim to provide a method, device, medium, and equipment for automatic adjustment of an RMU dehumidifier. Through the technical solutions of the embodiments of this application, the power of the dehumidifier can be automatically adjusted, without causing waste of electric energy while meeting the dehumidification requirements, and the degree of intelligence is relatively high.

[0006] In a first aspect, some embodiments of this application provide a method for automatic adjustment of an RMU dehumidifier, including: obtaining the total dehumidification power value of all dehumidifiers in the future based on a pre-trained power prediction model of the RMU and the historical data of the RMU; adjusting the dehumidification power of each dehumidifier according to the power adjustment step determined by the dehumidification demand weight of each dehumidifier, where the sum of the adjustments of the dehumidification power of all dehumidifiers does not exceed the total dehumidification power value; obtaining the dehumidification efficiency of each dehumidifier within a preset period at the dehumidification power; optimizing the dehumidification demand weight by comparing the dehumidification efficiency with the expected efficiency to obtain an optimized dehumidification demand weight; and automatically adjusting the dehumidification power through the optimized dehumidification demand weight.

[0007] Some embodiments of this application first determine the total dehumidification power of all dehumidifiers using a ring mains power prediction model and its historical data. Then, the dehumidification power of each dehumidifier is adjusted based on a power adjustment step size determined by the dehumidification demand weight of each dehumidifier. Afterwards, the dehumidification demand weight is optimized based on a comparison between the dehumidification efficiency and predicted efficiency of each dehumidifier to automatically adjust the dehumidification power. These embodiments of the application can achieve automatic power adjustment of the dehumidifiers, meeting dehumidification requirements without wasting energy, and incorporate unsupervised learning, resulting in a high degree of artificial intelligence.

[0008] In some embodiments, obtaining the total dehumidification power of all dehumidifiers in the future time based on a pre-trained ring main unit power prediction model and historical data of the ring main unit includes: inputting the historical data into the ring main unit power prediction model to obtain the total power limit of the ring main unit in the future time; and calculating the total dehumidification power based on the total power limit and the power consumption of other equipment.

[0009] Some embodiments of this application can obtain the total power limit of the ring main unit through a ring main unit power prediction model. Combined with the power consumption of other equipment, the total dehumidification power value is determined. This method can determine the upper limit of the dehumidifier's power to ensure the normal operation of the ring main unit.

[0010] In some embodiments, the power adjustment step size is calculated by weighting the dehumidification demand.

[0011] Some embodiments of this application calculate the power adjustment step size by weighting the dehumidification demand, providing a basis for automatic adjustment of the dehumidifier.

[0012] In some embodiments, obtaining the dehumidification efficiency of each dehumidifier within a preset time period includes: obtaining the humidity change and power consumption value of each dehumidifier within the preset time period; calculating the humidity change, the power consumption value, and other parameters to obtain the dehumidification efficiency; wherein the other parameters include the dehumidification demand weight, efficiency coefficient, constraint coefficient, indicator function, and dehumidification power.

[0013] Some embodiments of this application obtain dehumidification efficiency by measuring the temperature change and power consumption of each dehumidifier within a preset time period, as well as other parameters, in order to effectively determine the dehumidification effect.

[0014] In some embodiments, the step of optimizing the dehumidification demand weight by comparing the dehumidification efficiency with the expected efficiency to obtain the optimized dehumidification demand weight includes: if the dehumidification efficiency is greater than or equal to the expected efficiency, then reducing the dehumidification demand weight to the next weight level to obtain the optimized dehumidification demand weight; if the dehumidification efficiency is less than the expected efficiency, then increasing the dehumidification demand weight to obtain the optimized dehumidification demand weight.

[0015] Some embodiments of this application optimize the dehumidification demand weight by comparing the dehumidification efficiency with the expected efficiency, thereby obtaining the optimized dehumidification demand weight and providing support for the power self-adjustment of the dehumidifier.

[0016] In some embodiments, automatically adjusting the dehumidification power based on the optimized dehumidification demand weight includes: calculating a latest power step size based on the optimized dehumidification demand weight; and adjusting the dehumidification power according to the latest power step size so as to continue performing the dehumidification operation according to the adjusted dehumidification power.

[0017] Some embodiments of this application calculate the latest power step size by optimizing the dehumidification demand weight and then adjust the dehumidification power accordingly to perform dehumidification, thereby achieving intelligent control of dehumidification power and making it highly practical.

[0018] In some embodiments, each dehumidifier has a corresponding dehumidification model at the cloud platform layer; the dehumidification model is used to display the dehumidification power, temperature, humidity and operating status of each dehumidifier; the visualization interface of the cloud platform layer is used to display the layout of each dehumidifier in the ring network cabinet; the cloud platform layer is used to store the historical dehumidification data of each dehumidifier.

[0019] Some embodiments of this application display relevant data of the dehumidifier through a cloud platform layer and store historical dehumidification data, thereby realizing a visual display of dehumidification status and effective data storage.

[0020] Secondly, some embodiments of this application provide an automatic adjustment device for a ring main unit dehumidifier, comprising: a power limit module, used to obtain the total dehumidification power of all dehumidifiers within a future time period based on a pre-trained ring main unit power prediction model and historical data of the ring main unit; an adjustment module, used to adjust the dehumidification power of each dehumidifier according to a power adjustment step size determined by the dehumidification demand weight of each dehumidifier; wherein the sum of the adjustments of the dehumidification power of all dehumidifiers does not exceed the total dehumidification power; an efficiency acquisition module, used to obtain the dehumidification efficiency of each dehumidifier within a preset time period under the dehumidification power; and an automatic adjustment module, used to optimize the dehumidification demand weight by comparing the dehumidification efficiency with the expected efficiency to obtain an optimized dehumidification demand weight; and to automatically adjust the dehumidification power based on the optimized dehumidification demand weight.

[0021] Thirdly, some embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the method described in any embodiment of the first aspect.

[0022] Fourthly, some embodiments of this application provide an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, can implement the method as described in any embodiment of the first aspect.

[0023] Fifthly, some embodiments of this application provide a computer program product, the computer program product including a computer program, wherein the computer program, when executed by a processor, can implement the method described in any embodiment of the first aspect. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of some embodiments of this application, the accompanying drawings used in some embodiments of this application will be briefly described below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 System diagrams for automatic adjustment of ring main unit dehumidifiers provided for some embodiments of this application; Figure 2 One of the flowcharts for the automatic adjustment method of a ring main unit dehumidifier provided for some embodiments of this application; Figure 3 The second flowchart of the method for automatic adjustment of a ring main unit dehumidifier provided for some embodiments of this application; Figure 4 Block diagram of an automatic adjustment device for a ring main unit dehumidifier provided for some embodiments of this application; Figure 5 A schematic diagram of an electronic device provided for some embodiments of this application. Detailed Implementation

[0026] The technical solutions of some embodiments of this application will now be described with reference to the accompanying drawings.

[0027] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0028] In related technologies, from the perspective of the electrical system characteristics of ring main units (RNBs), their integrated core components such as DTUs (Distribution Terminal Units) and PTs (Voltage Transformers) have strict total power limits (most small RNBs have a total power limit of ≤500W, and medium-sized RNBs ≤800W). As an essential supporting device, the power consumption of the dehumidifier needs to dynamically adapt to the real-time power margin of the RNB to avoid overload of the internal electrical circuits and malfunction of protection devices due to power accumulation. Simultaneously, with the development of distribution network automation technology, RNB maintenance has shifted from "on-site inspection" to "remote monitoring," requiring dehumidifiers to have data uploading and remote control capabilities to improve maintenance efficiency.

[0029] Current dehumidifier solutions employ a "fixed-power dehumidifier + local status display" structure. At the power control level, a mechanical power setting is used, with fixed power levels such as 120W, 180W, and 240W, manually adjusted via a knob on-site. This solution lacks a dynamic power adjustment algorithm and cannot automatically adapt to the ring mains' real-time power reserve. At the cloud management level, only a simple LED local display module is installed, requiring maintenance personnel to bring testing equipment to the site to read operating parameters (such as current power and dehumidification capacity), equipment model, installation time, fault records, and other asset management information, relying on manual paper-based data entry. Other solutions address the "inconvenience of traditional dehumidifier maintenance" by using an external, electrically replaceable structure, but these do not involve dynamic power adjustment or cloud management, thus still employing a "fixed power, local maintenance" approach.

[0030] As can be seen from the above-mentioned technologies, the existing technologies have significant technical defects: First, fixed power settings cannot match the dynamic power requirements and stepless parameter adjustment of the ring main unit. In scenarios with low power margin, the total power may exceed the limit due to the fixed power of the dehumidifier, triggering overload protection. In scenarios with high power margin, full-power operation results in energy waste. Second, the lack of cloud management technology support makes it impossible to remotely monitor the power status and fault information of the dehumidifier in real time. After a fault occurs, manual investigation is required, resulting in a delayed response. Third, asset management relies on manual operation, which can easily lead to discrepancies between the ledger and the actual equipment parameters, as well as missing fault history records, failing to meet the technical requirements of distribution network automation.

[0031] In view of this, some embodiments of this application provide a method for automatic adjustment of dehumidifiers in a ring main unit. This method first determines the total dehumidification power of the dehumidifiers within a future timeframe. Using this as a limit, a power adjustment step size is determined according to the dehumidification demand weight of each dehumidifier to adjust its dehumidification power. Subsequently, the optimized dehumidification demand weight is determined by calculating and analyzing the dehumidification efficiency of each dehumidifier, and the dehumidification power is adjusted again. This application embodiment achieves automatic dehumidifier power adjustment without manual intervention throughout the process, and the total power of all dehumidifiers remains within a set limit, achieving automatic adaptation to the real-time power margin of the ring main unit. This not only avoids energy waste but also achieves a suitable dehumidification effect. It can be seen that this application achieves automatic dehumidifier power adjustment through the coordinated control of multiple dehumidifiers, and achieves a certain dehumidification effect. Furthermore, each dehumidifier in this application can be connected to a cloud platform layer, which can display the working status of each dehumidifier, allowing relevant personnel to view relevant data in a timely manner, achieve remote control, and provides a high degree of visualization.

[0032] The following is in conjunction with the appendix Figure 1 The overall composition and structure of the automatic adjustment system for the ring main unit dehumidifier provided by some embodiments of this application are illustrated by way of example.

[0033] like Figure 1 As shown, some embodiments of this application provide a system diagram for automatic adjustment of a ring main unit dehumidifier. This automatic adjustment system for the ring main unit dehumidifier may include: a sensing layer 110, a control layer 120, an execution layer 130, a communication layer 140, and a cloud platform layer 150.

[0034] The sensing layer 110 is used for environmental and equipment status acquisition. For example, it uses a high-precision SHT30 temperature and humidity sensor (error ±2%RH) to collect humidity and temperature data at the installation locations of each dehumidifier. Simultaneously, it integrates an NTCS0603 thermistor to collect the temperature of the dehumidifier's core components, preventing overheating damage. The sampling circuit employs a differential amplification design to suppress 3rd and 5th harmonic interference within the ring main unit, ensuring data acquisition accuracy reaches 0.5 level, providing reliable input for subsequent intelligent algorithms.

[0035] The control layer 120 is used to run the "Total Power Dynamic Adaptation Algorithm", which includes the LSTM ring main unit power load prediction algorithm (as a specific example of the ring main unit power prediction model) and the Q-learning power allocation optimization algorithm (Q algorithm for short) to achieve reasonable allocation of dehumidification power.

[0036] The execution layer 130 executes power adjustment commands for each dehumidifier based on the dehumidification power obtained from the control layer 120. Simultaneously, the PWM (Pulse Width Modulation) controller adjusts the duty cycle of the MOSFET according to this power command, achieving stepless adjustment of 0-50W for a single dehumidifier with an accuracy of ±2%. Each dehumidifier individually collects its actual power and humidity changes within 5 seconds, feeding this data back to the Q-algorithm. This data is used to update the Q-value and dehumidification demand weight corresponding to that dehumidifier, ensuring that the power adjustment of a single dehumidifier always adapts to its own dehumidification needs, thus strengthening the precise control of each device by the Q-algorithm.

[0037] The communication layer 140 adopts a low-power wide-area communication bus topology. Multiple dehumidifiers (e.g., up to 32 units, limited by the RS485 bus load) are connected in series via A / B differential signal lines. 120Ω terminating resistors are connected to both ends of the bus to reduce signal reflection. One end of the bus connects to the local controller of the ring main unit, which then accesses the local area network via an upstream module, ultimately uploading data to the cloud platform layer and timing logic. The anti-interference design uses an isolated RS485 chip to achieve dual isolation of power and signal, suppressing common-mode interference within the ring main unit (interference voltage ≤2500V) and ensuring a data transmission success rate ≥99.8%.

[0038] The cloud platform layer 150 enables intelligent management and control, building a 1:1 digital model for each dehumidifier (as a specific embodiment of the dehumidification model) to map the power, temperature, humidity, and operating time of the physical dehumidifier equipment in real time. A 3D visualization interface intuitively displays the layout and operation of the dehumidifiers within the ring network cabinet, allowing users to click on devices to view historical dehumidification data (e.g., power curves and dehumidification statistics for the past year), generate asset ledgers, and filter equipment by region and operating year, solving the problem of disorganized traditional manual ledgers. Maintenance personnel can issue commands such as "total power limit adjustment" and "dehumidifier priority modification" through the cloud platform layer 150. These commands are transmitted via the communication layer 140 to the control layer 120, enabling remote stepless power adjustment (e.g., increasing the total power limit of the dehumidifier to 500W during the high humidity period in summer and reducing it to 350W during the low humidity period in winter).

[0039] It is understood that the automatic adjustment system of the ring network cabinet dehumidifier provided above is a specific example provided by this application. In actual practice, its architecture and the execution process of each internal layer can be flexibly adjusted. This application does not make specific limitations on the embodiments.

[0040] In some embodiments of this application, the automatic adjustment system of the ring network cabinet dehumidifier described above can be deployed on a mobile terminal or a non-portable computer terminal. This application does not specifically limit the embodiments.

[0041] The following is in conjunction with the appendix Figure 2The present application provides an exemplary embodiment of the implementation process of automatic adjustment of the ring main unit dehumidifier by the control layer 120.

[0042] Please see the appendix Figure 2 , Figure 2 A flowchart illustrating a method for automatic adjustment of a ring main unit dehumidifier is provided for some embodiments of this application. The method for automatic adjustment of the ring main unit dehumidifier may include: S210, based on a pre-trained ring main unit power prediction model and historical data of the ring main unit, obtains the total dehumidification power of all dehumidifiers in the future.

[0043] For example, in a specific embodiment of this application, the ring main unit power prediction model is obtained by training an LSTM (Long Short-Term Memory) model using historical data from the ring main unit. During training, the Adam optimizer is used with a learning rate of 0.001 and 100 training epochs. Model parameters are updated through a sliding window to predict the power prediction value for each time interval in the future (as a specific example of the total power limit). For instance, the ring main unit power prediction model can predict the power prediction value of the ring main unit every 5 minutes (as a specific example of the time interval) within the next 1 hour (as a specific example of the future time). Using this trained ring main unit power prediction model and the current historical data, the total dehumidification power that all dehumidifiers can allocate in the future can be obtained.

[0044] In some embodiments of this application, S210 may include: inputting the historical data into the ring main unit power prediction model to obtain the total power limit of the ring main unit in the future time period; and calculating the total dehumidification power value based on the total power limit and the power consumption of other equipment.

[0045] For example, in a specific embodiment of this application, a trained LSTM model is used to predict the change in power limit every 5 minutes within the next hour. Historical power data of the ring main unit for the same period over the past 7 days, real-time temperature, and electricity consumption periods (such as morning peak 8:00-10:00 and evening peak 18:00-20:00) are input into the LSTM model, and the predicted power value is output. For example, if the current power of the ring main unit is 500W and the predicted power value is 400W, it can be known that the power of the ring main unit will decrease from 500W to 400W within 10 minutes, thereby generating a pre-load reduction signal to facilitate power allocation.

[0046] Specifically, obtain the current total power limit P(Φ) of the ring main unit obtained from the above prediction (issued in real time by the DTU via RS485), and the real-time power consumption P of the DTU, etc. α The current total power consumption P of all dehumidifiersH The allocatable power value (as a specific example of the total dehumidification power) is calculated using the following formula: ΔP = P(Φ) - (P α + P H -10% P(Φ), where 10% P(Φ) is a safety margin reserved to avoid exceeding the standard due to power fluctuations.

[0047] Furthermore, by collecting the temperature and humidity data for each dehumidifier, each dehumidifier can be classified to obtain an initial value for the dehumidification demand weight of each dehumidifier. For example, this initial value K... d It can include the following three levels: K d =1.5, indicating humidity > 85%RH and temperature T > 30℃, which is considered high-risk; K d =1.2, indicating a humidity level between 70%RH and 85%RH, which falls under the medium-risk category; K d =0.8 indicates that the humidity is ≤70%RH, which is considered low risk. It is understood that the classification method can be adjusted according to the actual application scenario, and this application embodiment does not impose specific limitations here.

[0048] In a specific embodiment of this application, a Q-learning power allocation optimization algorithm is used to achieve real-time dynamic adjustment of power. The Q value in this Q-learning algorithm is Q(S,a), which represents the dehumidification demand weight W of the i-th dehumidifier device in the current state S. i Below, the "quality" of adjusting the dehumidification power of device i is determined by selecting action a (as a specific example of power adjustment step size). A higher Q value indicates that the action is more likely to bring long-term benefits, and that it achieves efficient dehumidification without exceeding the limit. The Q value is iteratively optimized through "immediate reward + expected future reward," and its iterative formula is: Q t+1 (S,a)←Q t (s,a) +αE[R +γmax Q t+1 (S,a) - Q t [(S,a)]; where t is time, S is the current state space, and the quantified value of dehumidification demand is used as the core input feature S= {ΔP, P(Φ), (W1, P1), (W2, P2), ..., (W n , P n Let} represent the nth dehumidifier; R be the immediate reward after performing action a (i.e., the reward function); α be the learning rate (e.g., a dynamic value of 0.2~0.5 to control the influence of new experience on the old Q value); and γ be the discount factor (e.g., 0.9). The status of each dehumidifier is represented as a pair of "(demand weight, actual power)" values, allowing the system to directly obtain the correlation information of "how much power the device needs" and "how much power is currently being used" when sensing the environment.

[0049] S220, adjust the dehumidification power of each dehumidifier according to the power adjustment step size determined by the dehumidification demand weight of each dehumidifier; wherein the sum of the adjustment of the dehumidification power of all dehumidifiers does not exceed the total dehumidification power value. The power adjustment step size is calculated based on the dehumidification demand weight.

[0050] For example, in a specific embodiment of this application, the power adjustment step size a and the dehumidification demand weight W i They are positively correlated. The formula for calculating a is: a = L + L × (W i -0.8) / (1.5-0.8), where L is the correlation factor, and its value is 5. When W i When W = 1.5 (high demand), a = 5 + (0.7 / 0.7) × 5 = 10W, and the 10W step size only accounts for 2%-5% of the total power of 200-500W, which will not cause system power fluctuations; when W i When Wi = 1.2 (medium demand), a = 5 + (0.4 / 0.7) × 5 ≈ 8W; when Wi = 0.8 (low demand), a = 5 + (0 / 0.7) × 5 = 5W.

[0051] The above design ensures that high-demand devices have a larger power adjustment range and can quickly increase power to meet dehumidification needs, while low-demand devices are limited by small step sizes to avoid ineffective energy consumption.

[0052] S230, under the dehumidification power, obtain the dehumidification efficiency of each dehumidifier within a preset time period.

[0053] For example, in a specific embodiment of this application, by calculating the dehumidification efficiency, a basis can be provided for subsequent automatic adjustment of dehumidification power.

[0054] In some embodiments of this application, S230 may include obtaining the humidity change and power consumption value of each dehumidifier during the preset time period; calculating the humidity change, the power consumption value and other parameters to obtain the dehumidification efficiency; wherein the other parameters include the dehumidification demand weight, efficiency coefficient, constraint coefficient, indication function and the dehumidification power.

[0055] For example, in a specific embodiment of this application, dehumidification efficiency is characterized using a reward function R. The reward function R = W i ×η×ΔH i / ΔP i +β×IΣsum(P i <ΔP), where W i As the weight for dehumidification demand, ΔH i / ΔP iThe dehumidification rate per unit is ΔH. i Let ΔP be the change in humidity. i Here, η is the power consumption value, η is the efficiency coefficient (or scaling factor), initially set to 10, significantly widening the gap and reinforcing the priority of efficiency for high-demand equipment; β is the constraint coefficient, initially set to 1, which controls the weight of the "power compliance item" to ensure that "not exceeding the power limit" is the bottom-line constraint. I is the indicator function (5 for compliance, -10 for exceeding the limit), ensuring that not exceeding the power limit is still the bottom line, but its priority is lower than the efficient operation of high-demand equipment. If the high demand W n The higher the equipment efficiency, the double the reward (e.g., W). n When the equipment efficiency reaches 0.6%RH / W (e.g., 1.5), the reward is 1.5 × 10 × 0.6 = 9; if the efficiency is low (e.g., 0.2%RH / W), the penalty also increases accordingly. i enlarge.

[0056] The dehumidification efficiency of each dehumidifier within a preset time period (e.g., 30 minutes or 1 hour) can be calculated using the formula for R above.

[0057] S240, by comparing the dehumidification efficiency with the expected efficiency, the dehumidification demand weight is optimized to obtain the optimized dehumidification demand weight; and the dehumidification power is automatically adjusted based on the optimized dehumidification demand weight.

[0058] For example, in a specific embodiment of this application, by comparing the dehumidification efficiency with the set expected efficiency, the current W can be... i Optimization can be performed, which in turn can optimize 'a' to adjust the dehumidification power of each dehumidifier and achieve automatic adjustment.

[0059] Specifically, S240 may include: if the dehumidification efficiency is greater than or equal to the expected efficiency, then reduce the dehumidification demand weight to the next weight level to obtain the optimized dehumidification demand weight.

[0060] For example, taking high-demand equipment as an example, if its dehumidification efficiency R is greater than or equal to the expected efficiency, then the dehumidifier will be downgraded, and W will be reduced. i Adjust to the next level below the current level, i.e., W. i =1.5 adjusted to W i =1.2 (as a specific example of the optimized dehumidification demand weight).

[0061] Specifically, S240 may include: if the dehumidification efficiency is less than the expected efficiency, then increase the dehumidification demand weight to obtain the optimized dehumidification demand weight.

[0062] For example, taking high-demand equipment as an example, if its dehumidification efficiency R is less than the expected efficiency, then the dehumidifier should be upgraded, and W should be increased.i Adjusted to a temporary value, i.e., W i =1.5 adjusted to W i =1.6 or other values ​​higher than 1.5 (as a specific example of optimized dehumidification demand weighting) to enable the dehumidifier to dehumidify faster. And on the next Q-value update, a penalty is imposed on the action of "not allocating enough power to the device" (the corresponding Q-value is reduced).

[0063] Then, S240 may include: calculating the latest power step size based on the optimized dehumidification demand weight; adjusting the dehumidification power according to the latest power step size, so as to continue performing the dehumidification operation according to the adjusted dehumidification power.

[0064] For example, after obtaining the latest optimized dehumidification demand weight, the latest power step size is recalculated according to the calculation formula of a above, so as to adjust the dehumidification power and continue to perform dehumidification operation.

[0065] It should be noted that this step can also be performed by the execution layer. The execution layer collects the actual dehumidification amount of a single dehumidifier every 30 minutes, calculates the dehumidification efficiency of the previous and next 30 minutes through the microcontroller (MCU), and feeds it back to the control layer. If the dehumidification efficiency is <0.3%RH / W (the dehumidification efficiency is too low), the Q-learning algorithm is triggered to adjust the action space (such as reducing the power step size of the dehumidifier and prioritizing the allocation of power to high-efficiency devices), forming a closed loop of "prediction-allocation-execution-efficiency feedback-re-optimization".

[0066] As can be seen from the above description of automatic dehumidification power adjustment, this application can allocate power to devices with high dehumidification demands and enhance power adjustment capabilities for different demand scenarios; automatic power adjustment can be achieved by comparing the actual dehumidification effect with the expected effect. Ultimately, this application achieves "demand-oriented intelligent power allocation," which differs from traditional reinforcement learning that only focuses on the single objective of power compliance, and solves the technical pain point of "disconnect between dehumidification demand and power allocation."

[0067] In some embodiments of this application, each dehumidifier has a corresponding dehumidification model at the cloud platform layer; the dehumidification model is used to display the dehumidification power, temperature, humidity and operating status of each dehumidifier; the visualization interface of the cloud platform layer is used to display the layout of each dehumidifier in the ring network cabinet; the cloud platform layer is used to store the historical dehumidification data of each dehumidifier.

[0068] For example, in a specific embodiment of this application, the cloud platform layer constructs a 1:1 digital model for each dehumidifier, mapping the dehumidification power, temperature and humidity, and running time (i.e., operating status) of the physical equipment in real time. The layout and operation of the dehumidifiers in the ring network cabinet are displayed intuitively through a 3D visualization interface. It supports clicking on the equipment to view historical dehumidification data (e.g., power curves and dehumidification statistics for the past year), generating an asset ledger, and supporting the filtering of equipment by region and years of operation, thus solving the problem of chaotic traditional manual ledgers.

[0069] The following is in conjunction with the appendix Figure 3 The present application provides an exemplary description of the specific process of automatic adjustment of the ring main unit dehumidifier provided in some embodiments.

[0070] Please see the appendix Figure 3 , Figure 3 A flowchart illustrating an automatic adjustment method for a ring main unit dehumidifier, provided for some embodiments of this application.

[0071] The above process is illustrated below by example.

[0072] S310 inputs historical data into the ring main unit power prediction model to obtain the total power limit of the ring main unit in the future.

[0073] S320 calculates the total dehumidification power based on the total power limit and the power consumption of other equipment.

[0074] S330 adjusts the dehumidification power of each dehumidifier according to the power adjustment step size determined by the dehumidification demand weight of each dehumidifier.

[0075] S340, under dehumidification power, obtains the dehumidification efficiency of each dehumidifier within a preset time period.

[0076] S350: Determine if the dehumidification efficiency is less than the expected efficiency. If so, proceed to S360; otherwise, proceed to S370.

[0077] S360, increase the dehumidification demand weight to obtain the optimized dehumidification demand weight, and return to S330.

[0078] S370, reduce the dehumidification demand weight to the next weight level to obtain the optimized dehumidification demand weight, and return to S330.

[0079] It is understood that the specific implementation process of S310~S70 can refer to the method implementation examples provided above. To avoid repetition, detailed descriptions are omitted here.

[0080] As can be seen from the above embodiments of this application, this application quantifies the dehumidification requirement into a weight W. iIt deeply embeds Q-learning into the state space (sensing demand priority), reward function (high-demand equipment receives higher rewards for efficient operation), and action space (high-demand equipment has a larger upper limit for step size). Power allocation accurately matches the urgency of dehumidification and dynamically adapts to the adjustment range, thus achieving "demand-oriented precise power allocation" to solve the pain point of the disconnect between demand and decision-making. LSTM is introduced to predict the power limit changes of the ring main unit in the future, sending a pre-adjustment signal 5 seconds in advance. The state space of Q-learning includes the predicted value P(Φ), and by predicting and shrinking the upper limit of step size in advance, it can avoid exceeding the limit caused by power mutations, thus having "strong resistance to fluctuations and low overload risk". By designing a dehumidification efficiency feedback closed loop, ΔHi / ΔPi (dehumidification rate) is collected at preset intervals, the step size is reduced, high-efficiency equipment is given priority in power allocation, and the algorithm selects the "high demand + high efficiency" allocation strategy, self-optimizing energy saving and reducing ineffective energy consumption by more than 20%.

[0081] Please refer to Figure 4 , Figure 4 The diagram illustrates a block diagram of an automatic adjustment device for a ring main unit dehumidifier according to some embodiments of this application. It should be understood that this automatic adjustment device for the ring main unit dehumidifier corresponds to the method embodiments described above and is capable of performing the various steps involved in the method embodiments. The specific functions of this automatic adjustment device for the ring main unit dehumidifier can be found in the description above; detailed descriptions are omitted here to avoid repetition.

[0082] Figure 4 The automatic adjustment device for the ring main unit dehumidifier includes at least one software function module that can be stored in a memory or embedded in the device in the form of software or firmware. The device includes: a power limit module 410, used to obtain the total dehumidification power of all dehumidifiers within a future time period based on a pre-trained ring main unit power prediction model and historical data of the ring main unit; an adjustment module 420, used to adjust the dehumidification power of each dehumidifier according to a power adjustment step size determined by the dehumidification demand weight of each dehumidifier; wherein the sum of the adjustments to the dehumidification power of all dehumidifiers does not exceed the total dehumidification power value; an efficiency acquisition module 430, used to obtain the dehumidification efficiency of each dehumidifier within a preset time period under the dehumidification power; and an automatic adjustment module 440, used to optimize the dehumidification demand weight by comparing the dehumidification efficiency with the expected efficiency to obtain an optimized dehumidification demand weight; and to automatically adjust the dehumidification power based on the optimized dehumidification demand weight.

[0083] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the aforementioned method, and will not be elaborated further here.

[0084] Some embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can perform the operation of any of the methods corresponding to the methods provided in the above embodiments.

[0085] Some embodiments of this application also provide a computer program product, which includes a computer program, wherein when the computer program is executed by a processor, it can implement the operation of any of the methods corresponding to the above embodiments provided in the above embodiments.

[0086] like Figure 5 As shown, some embodiments of this application provide an electronic device 500, which includes a memory 510, a processor 520, and a computer program stored in the memory 510 and executable on the processor 520. When the processor 520 reads the program from the memory 510 via a bus 530 and executes the program, it can implement the methods of any of the above embodiments.

[0087] Processor 520 can process digital signals and can include various computing architectures. For example, it can be a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements multiple instruction set combinations. In some examples, processor 520 can be a microprocessor.

[0088] The memory 510 can be used to store instructions executed by the processor 520 or data related to the execution of instructions. These instructions and / or data may include code for implementing some or all of the functions of one or more modules described in the embodiments of this application. The processor 520 of this disclosure embodiment can be used to execute the instructions in the memory 510 to implement the methods shown above. The memory 510 includes dynamic random access memory, static random access memory, flash memory, optical memory, or other memories well known to those skilled in the art.

[0089] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0090] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0091] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, 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 limitations, 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.

Claims

1. A method for automatic adjustment of a ring main unit dehumidifier, characterized in that, include: Based on a pre-trained ring main unit power prediction model and historical data of the ring main unit, the total dehumidification power of all dehumidifiers in the future is obtained. The dehumidification power of each dehumidifier is adjusted according to the power adjustment step size determined by the dehumidification demand weight of each dehumidifier; wherein the sum of the adjustment of the dehumidification power of all dehumidifiers does not exceed the total value of the dehumidification power. Under the aforementioned dehumidification power, the dehumidification efficiency of each dehumidifier within a preset time period is obtained; By comparing the dehumidification efficiency with the expected efficiency, the dehumidification demand weight is optimized to obtain the optimized dehumidification demand weight; and the dehumidification power is automatically adjusted based on the optimized dehumidification demand weight.

2. The method as described in claim 1, characterized in that, The pre-trained ring main unit power prediction model and historical data of the ring main unit are used to obtain the total dehumidification power of all dehumidifiers in the future, including: The historical data is input into the ring main unit power prediction model to obtain the total power limit of the ring main unit in the future time period; The total dehumidification power is calculated based on the total power limit and the power consumption of other equipment.

3. The method as described in claim 1 or 2, characterized in that, The power adjustment step size is calculated by weighting the dehumidification demand.

4. The method as described in claim 1 or 2, characterized in that, The process of obtaining the dehumidification efficiency of each dehumidifier within a preset time period includes: Obtain the humidity change and power consumption of each dehumidifier during the preset time period; The dehumidification efficiency is obtained by calculating the humidity change, the power consumption value, and other parameters; wherein the other parameters include the dehumidification demand weight, efficiency coefficient, constraint coefficient, indicator function, and dehumidification power.

5. The method as described in claim 1 or 2, characterized in that, The process of optimizing the dehumidification demand weight by comparing the dehumidification efficiency with the expected efficiency to obtain the optimized dehumidification demand weight includes: If the dehumidification efficiency is greater than or equal to the expected efficiency, then the dehumidification demand weight is reduced to the next weight level to obtain the optimized dehumidification demand weight. If the dehumidification efficiency is less than the expected efficiency, then the dehumidification demand weight is increased to obtain the optimized dehumidification demand weight.

6. The method as described in claim 1 or 2, characterized in that, The automatic adjustment of the dehumidification power based on the optimized dehumidification demand weight includes: The latest power step size is calculated by weighting the optimized dehumidification demand. The dehumidification power is adjusted according to the latest power step size so that the dehumidification operation can continue to be performed according to the adjusted dehumidification power.

7. The method as described in claim 1 or 2, characterized in that, Each dehumidifier has a corresponding dehumidification model at the cloud platform layer; the dehumidification model is used to display the dehumidification power, temperature, humidity and operating status of each dehumidifier; the visualization interface of the cloud platform layer is used to display the layout of each dehumidifier in the ring network cabinet; the cloud platform layer is used to store the historical dehumidification data of each dehumidifier.

8. A device for automatic adjustment of a ring main unit dehumidifier, characterized in that, include: The power limit module is used to obtain the total dehumidification power of all dehumidifiers in the future based on the pre-trained power prediction model of the ring network cabinet and the historical data of the ring network cabinet. An adjustment module is used to adjust the dehumidification power of each dehumidifier according to a power adjustment step size determined by the dehumidification demand weight of each dehumidifier; wherein the sum of the adjustments to the dehumidification power of all dehumidifiers does not exceed the total value of the dehumidification power; An efficiency acquisition module is used to acquire the dehumidification efficiency of each dehumidifier within a preset time period under the dehumidification power. An automatic adjustment module is used to optimize the dehumidification demand weight by comparing the dehumidification efficiency with the expected efficiency, and obtain the optimized dehumidification demand weight; and to automatically adjust the dehumidification power based on the optimized dehumidification demand weight.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is executed by a processor to perform the method as described in any one of claims 1-7.

10. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and running on the processor, wherein the computer program is executed by the processor to perform the method as described in any one of claims 1-7.

Images