Air conditioning load control system

Abstract

The present application discloses an air-conditioning load control system, which relates to the technical field of air-conditioning load control. The system comprises: an initial overload detection module, which is used to obtain standard power load data of a target air-conditioning and obtain a preliminary overload analysis report; a deep detection module, which is used to obtain the preliminary overload analysis report and perform deep overload detection on the abnormal results in the preliminary overload analysis report through a timing monitoring mechanism; the timing monitoring mechanism performs deep overload detection on the time period marked as abnormal in the preliminary overload analysis report; the deep overload detection detects the time period marked as abnormal within the time window by pre-acquiring the time window size set in the time window module; a timing monitoring mechanism is set to merge the time periods in the previous and subsequent time periods that are also marked as abnormal, and re-mark them as continuous abnormal time periods; the continuous or continuous potential overload situation can be accurately identified, thereby improving the recognition accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning load regulation, and in particular to an air conditioning load regulation system. Background Art

[0002] The Chinese invention patent with publication number CN113218055B provides an air conditioning load control method, device and terminal equipment. The method includes: obtaining first power data of a target air conditioner, performing an initial overload detection on a distribution network line based on a preset power curve and the first power data of the target air conditioner, and obtaining a first detection result; performing data extraction on the first power data of the target air conditioner according to the first detection result to obtain second power data, and performing a secondary overload detection on the distribution network line based on a preset convolutional neural network model and the second power data to obtain a second detection result.

[0003] The existing technology only performs detection at one time point or time period, generates detection results and makes adjustments, and only focuses on the overload situation at a single time point or time period, while ignoring the continuity and persistence of the overload, increasing the number of missed reports and false alarms caused by the limitations of a single detection, and reducing the accuracy of the detection. Summary of the invention

[0004] The present application solves the problem of ignoring the continuity and persistence of overload in the prior art by providing an air-conditioning load control system, thereby achieving the technical effect of being able to accurately identify continuous or persistent potential overload conditions and improving recognition accuracy.

[0005] The present application provides an air conditioning load control system, the system comprising:

[0006] An initial overload detection module is used to obtain standard power load data of the target air conditioner, perform initial overload detection on the distribution network line based on a predetermined power load curve and the initial power load data of the target air conditioner, and obtain a preliminary overload analysis report;

[0007] A deep detection module is used to obtain a preliminary overload analysis report and perform a deep overload detection on the abnormal results in the preliminary overload analysis report through a timing monitoring mechanism to obtain a deep overload analysis report;

[0008] Time window module, used to set and adjust the size of the time window;

[0009] A control execution module is used to obtain air conditioning line information of a target air conditioner, generate a control instruction based on a preliminary overload analysis report and a deep overload analysis report, and control the load of the target air conditioner according to the control instruction;

[0010] Among them, the timing monitoring mechanism performs deep overload detection on the time periods marked as abnormal in the preliminary overload analysis report; the deep overload detection detects the time periods marked as abnormal within the time window by pre-acquiring the time window size set in the time window module. If multiple consecutive time periods are found to be marked as abnormal within the time window, the abnormal time periods are merged and re-marked as continuous abnormal time periods; statistical analysis is performed on the continuous abnormal time periods and the time series method is applied to obtain the trend changes of the continuous abnormal time periods; the association rule algorithm is used to mine the correlation factors of the overload anomaly and generate a deep overload analysis report.

[0011] Further, the initial power load data includes the actual power value corresponding to the target air conditioner at each time point; the distribution network line is initially overloaded based on the predetermined power load curve and the initial power load data of the target air conditioner to obtain a preliminary overload analysis report;

[0012] Among them, the standard power value of the air conditioner at that time point is determined according to the predetermined power load curve, and compared with the actual power value to obtain the difference value; the basic power data is grouped by time period, and the discreteness of the power difference at all time points in each time period is calculated; the discreteness is compared with the temporary limit value to obtain a preliminary overload analysis report.

[0013] Furthermore, the temporary limit value includes a low limit value and a high limit value. If the dispersion of a certain time period is lower than the low limit value, it is determined that the distribution network is not overloaded in the time period; if the dispersion is higher than the high limit value, it is determined that the distribution network is overloaded in the time period; if the dispersion is between the low limit value and the high limit value, the time period is marked as abnormal, indicating that deep overload detection is required;

[0014] The dispersion indicates the degree of difference between the actual power value and the standard power value, and is formed by comprehensive calculation using the range and the standard deviation.

[0015] Furthermore, the time window module initializes the time window and sets the step size of the window sliding, where the step size is the length of time each window moves; determines whether the size of the time window needs to be adjusted based on the system load and temporary limit value, and if adjustment is required, dynamically adjusts the size of the time window based on the step size.

[0016] Furthermore, each of the time windows calculates a load index, and the system load condition is determined based on the index value. When the system load is high, the window size is reduced; when the system load is low, the window size is increased. The load index includes the average load, peak load, and load distribution.

[0017] Furthermore, the system also includes a limit control module, which is used for real-time monitoring and dynamically adjusting the temporary limit value according to adjustment rules; the adjustment rule is based on the initial set temporary limit value and change range, and is automatically adjusted according to the load data collected in real time and the time window, and the temporary limit value is dynamically adjusted according to the change range; when the time window is reduced, the high limit value is lowered to improve the detection sensitivity; when the time window is expanded, the low limit value is increased to reduce false alarms.

[0018] Furthermore, the adjustment rules also include regular adjustment optimization based on historical overload records, obtaining historical overload records and adjustment records of temporary limit values, and comprehensively analyzing overload causes to continuously optimize the adjustment rules.

[0019] Furthermore, the limit control module is also used to monitor and adjust the long-term limit value in real time, and use a statistical analysis method to perform statistical analysis on the temporary limit value within a short period of time to obtain an initial long-term limit value; the initial long-term limit value produces a first impact value on the adjustment of the temporary limit value, and the temporary limit value produces a reverse impact value on the change of the initial long-term limit value.

[0020] Furthermore, the changing trends of the counter-influence value and the first impact value are opposite, the first impact value is from low to high, the counter-influence value is from high to low, and the sum of the counter-influence value and the first impact value is 100%; when the initial values ​​of the counter-influence value and the first impact value are the same, the change of the initial long-term boundary value tends to stabilize to form a long-term boundary value.

[0021] Furthermore, the long-term limit value is periodically verified and optimized based on the adjustment optimization record of the temporary limit value and the overall load change, and the values ​​of the reverse impact value and the first impact value are adjusted based on the verification result, and then the long-term limit value is adjusted through the temporary limit value.

[0022] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0023] By setting up a timing monitoring mechanism, the time periods in the previous and subsequent time periods that are also marked as abnormal are merged and re-marked as continuous abnormal time periods; thereby achieving the ability to accurately identify continuous or persistent potential overload situations and improving the recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 The present invention is an air conditioning load control system architecture diagram in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To facilitate the understanding of the present invention, the present application will be described more comprehensively below with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, but the present invention can be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, the purpose of providing these embodiments is to enable a more thorough and comprehensive understanding of the disclosed content of the present invention.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs; the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more related listed items.

[0027] In response to the problem of ignoring the continuity and persistence of overload in the prior art, the present application sets up a timing monitoring mechanism to merge the time periods in the previous and subsequent time periods that are also marked as abnormal, and re-mark them as continuous abnormal time periods; this achieves the ability to accurately identify continuous or persistent potential overload situations, thereby improving the recognition accuracy.

[0028] Embodiment 1: Figure 1 As shown, an air conditioning load control system, the system comprises:

[0029] An initial overload detection module is used to obtain standard power load data of the target air conditioner, perform initial overload detection on the distribution network line based on a predetermined power load curve and the initial power load data of the target air conditioner, and obtain a preliminary overload analysis report;

[0030] Specifically, the initial power load data includes the actual power value corresponding to the target air conditioner at each time point; the distribution network line is initially overloaded based on the predetermined power load curve and the initial power load data of the target air conditioner to obtain a preliminary overload analysis report;

[0031] Specifically, the standard power value of the air conditioner at that time point is determined according to the predetermined power load curve, and compared with the actual power value to obtain the difference value; the basic power data is grouped by time period, and the discreteness of the power difference at all time points in each time period is calculated; the discreteness is compared with the preset temporary limit value to obtain a preliminary overload analysis report. The preliminary overload analysis report records the preliminary detection results of multiple time periods, and marks the time periods with preliminary abnormal detection for subsequent deep overload detection.

[0032] A deep detection module is used to obtain a preliminary overload analysis report and perform a deep overload detection on the abnormal results in the preliminary overload analysis report through a timing monitoring mechanism to obtain a deep overload analysis report;

[0033] Specifically, the temporary limit value includes a lower limit value and an upper limit value. If the dispersion of a certain time period is lower than the lower limit value, it is determined that the distribution network is not overloaded during the time period; if the dispersion is higher than the upper limit value, it is determined that the distribution network is overloaded during the time period; if the dispersion is between the lower limit value and the upper limit value, the time period is marked as abnormal, indicating that a deep overload detection is required; the dispersion indicates the degree of difference between the actual power value and the standard power value, and the dispersion is formed by comprehensive calculation using the range and standard deviation.

[0034] Among them, the timing monitoring mechanism performs deep overload detection on the time periods marked as abnormal in the preliminary overload analysis report; the deep overload detection detects the time periods marked as abnormal within a pre-set time window, and if multiple consecutive time periods are found to be marked as abnormal within the time window, the abnormal time periods are merged and re-marked as continuous abnormal time periods; statistical analysis is performed on the continuous abnormal time periods and the time series method is applied to obtain the trend changes of the continuous abnormal time periods; the association rule algorithm is used to mine the correlation factors of the overload anomaly and generate a deep overload analysis report.

[0035] The time window module is used to set and adjust the size of the time window.

[0036] Specifically, the timing monitoring mechanism uses the time period marked as abnormal in the preliminary overload analysis report as the initial time period, takes the initial time period as the reference point, and extends the time before and after according to the size of the time window. The time window module can set the size of the time window according to the time distance of the initial time period. For example, the time window is set to one hour; then when extending, query one hour forward and one hour backward; perform in-depth detection in the contents of the two time periods before and after. If there are also time periods marked as abnormal in the time window, all time periods marked as abnormal are re-marked as continuous abnormal time periods; for example, first A time period T1 (14:00-15:00) is detected and initially marked as abnormal. The preset time window is one hour. Then, the status of the time periods one hour before and after T1 (i.e., 13:00-14:00 and 15:00-16:00) is checked according to the time window. It is found that these two adjacent time periods (T0:13:00-14:00 and T2:15:00-16:00) are also marked as abnormal. Therefore, the three time periods T0, T1 and T2 are merged into a longer time period T_merged (13:00-16:00) and re-marked as a continuous abnormal time period.

[0037] The control execution module is used to obtain the air-conditioning line information of the target air-conditioning, generate control instructions based on the preliminary overload analysis report and the deep overload analysis report, and control the load of the target air-conditioning according to the control instructions.

[0038] Specifically, a timing monitoring mechanism is set up, and the abnormal time period of the initial detection is used as the initial time period, and the status of the time periods before and after it is monitored. A time window module is set to control the time range of the previous and next detections, and the time periods in the previous and next time periods that are also marked as abnormal are merged and re-marked as continuous abnormal time periods; compared with the prior art that only detects overload conditions at a single time point or time period, the present application scheme can more accurately identify continuous or continuous potential overload conditions, fully consider the continuity and continuity of the overload, and reduce omissions and false alarms caused by the limitations of single-segment detection; the time periods that are continuously in a potential overload state are merged and marked as continuous abnormal time periods, which can improve the comprehensiveness of detection when performing secondary overload detection, and further improve the accuracy of regulation.

[0039] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0040] The present application sets up a timing monitoring mechanism to merge the time periods in the previous and subsequent time periods that are also marked as abnormal, and re-mark them as continuous abnormal time periods; this achieves the effect of being able to accurately identify continuous or persistent potential overload situations and improve recognition accuracy.

[0041] Embodiment 2: In embodiment 1, a time window is set to adjust the time before and after the abnormal time period. This embodiment is further limited on the basis of the above embodiment.

[0042] The time window is initialized and the step length of the window sliding is set, where the step length is the length of time each window moves; whether the size of the time window needs to be adjusted is determined based on the system load and the temporary limit value, and if adjustment is required, the size of the time window is dynamically adjusted based on the step length.

[0043] Each time window calculates a load index, and determines the system load condition based on the index value. When the system load is high, the window size is reduced; when the system load is low, the window size is increased. The load index includes the average load, peak load, and load distribution.

[0044] Specifically, when the time window is initialized, it is set based on historical data and system control conditions. At least one week to one month of historical data is collected, including system load, processing speed and overload conditions. The historical data is analyzed to calculate the average load, peak load and load distribution. Through historical data analysis, an initial and relatively reasonable sliding time window size is determined. This size can effectively detect overload conditions without triggering too many false alarms. Based on the results of data analysis, the initial sliding window size and sliding step size are set. When the average load of multiple consecutive windows exceeds the temporary limit value, it indicates that there is an overload risk. At this time, the window size can be reduced to improve the sensitivity of overload detection; when the average load of multiple consecutive windows is far below the temporary limit value, it indicates that the load is light. At this time, the window size can be increased to reduce false alarms and improve the stability of the system.

[0045] Statistics and analysis are performed on the data in each sliding window to calculate indicators such as average load and peak load. If multiple consecutive windows are overloaded, the window size is reduced according to the preset strategy; if the load of multiple consecutive windows is low, the window size is increased. When an overload is detected, the detailed information of the overload is recorded, including the time, duration, and degree of the overload; according to the severity and duration of the overload, the corresponding response mechanism is triggered, such as sending an alarm, adjusting resource allocation, or load diversion. After each adjustment of the sliding window size, the system should record the window size before and after the adjustment, the reason for the adjustment, and the effect after the adjustment, and continuously optimize the window adjustment strategy based on the effect after the adjustment.

[0046] Preferably, a feedback mechanism is set in the time window module to adjust the window size according to the results of overload detection and the actual performance of the system. If the current window size leads to too many false positives or false negatives, the window size should be adjusted appropriately to improve the accuracy of detection. According to the size records of the automatically adjusted time window and the corresponding load detection and control effects, the automatic adjustment strategy is optimized to continuously improve the accuracy of automatic adjustment.

[0047] In this embodiment, a step size is set in the time window module, and a load index is added. Whether the time window size needs to be adjusted is determined based on the system load situation and the temporary limit value. If adjustment is required, it is dynamically adjusted according to the set step size. At the same time, optimization feedback is set, and each adjustment and the effect after the adjustment are recorded. The adjustment and the corresponding detection effect and control effect are used to verify whether the adjustment has further improved the detection rate, and an analysis and summary are performed to continuously optimize the adjustment method.

[0048] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0049] This application sets the step size in the time window module and adds a load indicator. It determines whether the size of the time window needs to be adjusted based on the system load situation and temporary limit value, thereby realizing dynamic adjustment of the time window and further improving the detection accuracy and control precision.

[0050] Embodiment 3: In the above embodiments, the effect of dynamically adjusting the time window size is achieved, but in the above embodiments, a temporary limit value is used as a standard for verifying whether there is an overload. This embodiment makes further limitations on the above embodiments.

[0051] Continue reading Figure 1 The system further comprises a limit control module, which is used for real-time monitoring and dynamically adjusting the temporary limit value according to the adjustment rules; the adjustment rules are based on the initial set temporary limit value and the change amplitude, according to the load data collected in real time and the automatic adjustment of the time window, and dynamically adjusting the temporary limit value according to the change amplitude; when the time window is reduced, the high limit value is reduced to improve the detection sensitivity; when the time window is expanded, the low limit value is increased to reduce false alarms;

[0052] The adjustment rules also include regularly performing adjustment optimization based on historical overload records, obtaining historical overload records and adjustment records of temporary limit values, and comprehensively analyzing overload causes to continuously optimize the adjustment rules.

[0053] Specifically, the limit control module continuously monitors the load data of the entire system, and interacts with the time window module to track the changes in the time window and monitor the adjustment of the time window. Based on the initially set temporary limit value and the preset change range (for example, if the percentage of standard power is used as the temporary limit value, the high limit value is 115%, the low limit value is 95%, and the change range can be initially set to 3%), the limit control module will dynamically adjust the temporary limit value according to the real-time collected load data and the automatic adjustment of the time window. When an abnormal increase in load is detected or the time window is reduced, the high limit value is automatically lowered to increase the sensitivity of overload detection; on the contrary, if the load is relatively stable or the time window is expanded, the low limit value is appropriately increased to reduce false alarms.

[0054] The limit control module will collect and organize historical overload records and corresponding temporary limit value adjustment records regularly (such as weekly or monthly), conduct in-depth analysis of the collected historical overload records, and explore the main causes of overload. The analysis may include the time when the load peak occurs, external factors, and internal factors. Based on the comprehensive analysis results, the adjustment rules are optimized. For example, if it is found that overload events are mainly concentrated in the afternoon peak period, you can consider setting a stricter limit value during this period. If the analysis shows that the system is prone to overload under certain specific environmental conditions, the temporary limit value can be automatically adjusted under these conditions.

[0055] For example, in the air conditioning system of a shopping mall, the temporary limit values ​​are initially set, such as the upper limit is 115% of the rated power, the lower limit is 95% of the rated power, and the setting change range is ±5%. In a certain time period (15:00-19:00), the limit control module detects the load abnormality and automatically reduces the upper limit value to 105% of the rated power to improve the detection sensitivity. After the load returns to normal, it is automatically adjusted back to 115%. Collect and organize historical overload records and corresponding temporary limit value adjustment records every week, including the time, duration, and load data of the overload. Analysis shows that overload events are mainly concentrated in the afternoon peak hours on Mondays and Fridays. For the afternoon peak hours on Mondays and Fridays, the upper limit value is automatically adjusted to 105% of the rated power and the lower limit value is adjusted to 90% to improve the detection sensitivity and reduce false alarms; the optimized adjustment rules are updated to the limit control module to ensure that the limit value can be automatically adjusted during specific time periods.

[0056] In this embodiment, a limit control module is set to adjust the temporary limit value in real time according to the actual load situation, so that a corresponding response can be made quickly to sudden changes in the load, thereby improving the accuracy and efficiency of overload detection. By dynamically adjusting the limit value, energy consumption can be reduced and energy efficiency can be improved while ensuring stable operation. Compared with the fixed preset threshold in the prior art, the temporary limit value can be flexibly adjusted, and the accuracy can be adjusted according to the actual load situation, and the adjustment rules can be continuously optimized according to the adjustment records and situations.

[0057] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0058] The present application sets a limit control module to adjust the temporary limit value in real time according to the actual load conditions, thereby improving the accuracy and efficiency of overload detection. By dynamically adjusting the limit value, the effect of further improving the detection flexibility and control accuracy is achieved.

[0059] Embodiment 4: In the above embodiment, a limit control module is set up to dynamically adjust the temporary limit value according to the automatic adjustment of the time window. However, during the adjustment of the temporary limit value, the entire system cannot be adjusted for a long time to achieve a stable state. This embodiment makes further limitations on the above embodiment.

[0060] The limit control module is also used to monitor and adjust the long-term limit value in real time, and use a statistical analysis method to perform statistical analysis on the temporary limit value within a short period of time to obtain an initial long-term limit value; the initial long-term limit value produces a first impact value on the adjustment of the temporary limit value, and the temporary limit value produces a reverse impact value on the change of the initial long-term limit value.

[0061] Specifically, the short term refers to the statistical generation within a short period of time such as a week or a month. The statistical analysis method is to perform statistical analysis on the temporary boundary value data within a period of time, and calculate the mean and median of all data. The temporary boundary value data is recorded after each adjustment, and the median is selected as the benchmark. The median is fine-tuned in combination with the actual load data to form the initial long-term boundary value.

[0062] The reverse impact value and the first impact value have opposite change trends, the first impact value is from low to high, the reverse impact value is from high to low, and the sum of the reverse impact value and the first impact value is 100%; when the initial values ​​of the reverse impact value and the first impact value are the same, the change of the initial long-term boundary value tends to stabilize to form a long-term boundary value;

[0063] Specifically, the adjustment of the temporary boundary value and the initial long-term boundary value is determined by multiple factors. The first impact value refers to the proportion of the initial long-term boundary value when the temporary boundary value is adjusted. Similarly, the counter-impact value is the proportion of the temporary boundary value to the adjustment of the initial long-term boundary value. The first impact value has a relatively low proportion in the adjustment rule of the temporary boundary value, and is initially set to account for 20%; the counter-impact value accounts for 80% (1-first impact value) in the dynamic change of the initial long-term boundary value. Through mutual influence, continuous adjustment and optimization, the first impact value is set to increase (for example, 5%), and the counter-impact value is set to decrease (for example, 5%). After each load regulation, the first impact value and the counter-impact value are increased or decreased accordingly until the initial values ​​of the counter-impact value and the first impact value are the same, that is, when the first impact value is 80%, the change of the initial long-term boundary value tends to stabilize and form a long-term boundary value. After the initial long-term boundary value forms the long-term boundary value, the values ​​of the first impact value and the reverse impact value will only be fine-tuned in a short period of time. Through the first impact value, the long-term boundary value fine-tunes the temporary boundary value, so that the temporary boundary value continues to approach the long-term boundary value and finally reaches the optimal boundary value.

[0064] The long-term limit value is verified and optimized regularly according to the adjustment optimization record of the temporary limit value and the overall load change, and the values ​​of the reverse impact value and the first impact value are adjusted according to the verification result, and then the long-term limit value is adjusted through the temporary limit value.

[0065] Specifically, the long-term boundary value is verified and optimized regularly according to the adjustment optimization record of the temporary boundary value and the overall load change. The values ​​of the counter-impact value and the first impact value are adjusted according to the verification results. The long-term boundary value is not adjusted directly. Instead, the values ​​of the counter-impact value and the first impact value are adjusted to enhance the proportion of the counter-impact value. Then, the long-term boundary value is adjusted through the temporary boundary value. The adjustment requires a long time for verification and optimization. By adjusting the counter-impact value and the first impact value and optimizing over time, the accuracy of the long-term impact value adjustment is improved.

[0066] Specifically, an initial long-term boundary value is generated based on a small number of temporary boundary values ​​at the beginning, and the temporary boundary value is adjusted in turn according to the set long-term boundary value, so that the adjustment direction of the temporary boundary value is toward the direction of the initial long-term boundary value, that is, it is close to the range of the long-term boundary value. Here, the initial long-term boundary value has a lower impact on the adjustment of the temporary boundary value, and in the process of continuous adjustment and optimization, the temporary boundary value also affects the initial long-term boundary value, and the range of the initial long-term boundary value is continuously adjusted to make it a more accurate and long-term boundary value that conforms to the long-term usage rules. After optimization, the proportion of the long-term boundary value to the temporary boundary value adjustment is also increasing, tending to a more stable value. The long-term boundary value will be adjusted according to the optimization results after the adjustment rules are regularly optimized, and the proportion will also be adjusted. There is a dynamic interaction between the temporary boundary value and the long-term boundary value to maintain a benign dynamic balance.

[0067] The limit control module is designed to dynamically adjust the temporary limit value and the long-term limit value to ensure the stability and efficiency of the system operation. The limit control module monitors and adjusts the temporary limit value in real time so that the long-term limit value can gradually converge and stabilize within a reasonable range. In the limit control module, there is a dynamic interaction between the temporary limit value and the long-term limit value. A long-term limit value generated based on a standard value is preset as an initial reference, and a temporary limit value is generated to continuously monitor the effectiveness of the control process. By analyzing the detection data and the control results in real time, the setting range and specific value of the long-term limit value are gradually adjusted. The stable area of ​​the long-term limit value and its allowable error range are determined, and the long-term limit value is adjusted regularly within the error range according to the load data collected in real time. Through dynamic adjustment, it can be ensured that the long-term limit value is more in line with the needs of the actual operating environment. After the control and detection cycle, a long-term limit value that matches the actual operating situation will be finally determined, and its stable working area and reasonable error range will be obtained accordingly, and adaptive adjustment will be achieved within the error range.

[0068] In this embodiment, by real-time monitoring and adjustment of temporary boundary values, and gradual adjustment of long-term boundary values, the system can better adapt to changing load conditions, thereby reducing the risk of overload and improving the stability of overall operation; the dynamic adjustment of the boundary control module can maintain efficient operation under different load conditions, and by real-time analysis of detection data and control results, the optimal boundary value setting can be found, thereby improving energy utilization efficiency and work efficiency; according to the analysis of the system, a targeted long-term boundary value is formed, and the long-term boundary value is used to adjust the temporary boundary value, and at the same time, a reasonable error range is selected in the process of forming the long-term boundary value, and adaptive adjustment is performed within the reasonable error range. Temporary boundary values ​​and long-term boundary values ​​are added, and a dynamic interactive influence mode is set, so that more accurate boundary values ​​can be continuously selected according to changes in load conditions, and a more effective control scheme is generated.

[0069] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0070] The present application sets up a boundary control module to dynamically adjust temporary boundary values ​​and long-term boundary values. By real-time monitoring and adjustment of temporary boundary values, the long-term boundary values ​​can gradually converge and stabilize within a reasonable range, establishing a dynamic interactive influence mode, thereby achieving the effect of improving the stability of the overall operation.

[0071] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An air conditioning load control system, characterized in that: The system comprises: An initial overload detection module is used to obtain standard power load data of the target air conditioner, perform initial overload detection on the distribution network line based on a predetermined power load curve and the initial power load data of the target air conditioner, and obtain a preliminary overload analysis report; A deep detection module is used to obtain a preliminary overload analysis report and perform a deep overload detection on the abnormal results in the preliminary overload analysis report through a timing monitoring mechanism to obtain a deep overload analysis report; Time window module, used to set and adjust the size of the time window; A control execution module is used to obtain air conditioning line information of a target air conditioner, generate a control instruction based on a preliminary overload analysis report and a deep overload analysis report, and control the load of the target air conditioner according to the control instruction; Among them, the timing monitoring mechanism performs deep overload detection on the time period marked as abnormal in the preliminary overload analysis report; the deep overload detection detects the time period marked as abnormal within the time window by pre-acquiring the time window size set in the time window module. If multiple consecutive time periods are found to be marked as abnormal within the time window, the abnormal time periods are merged and re-marked as continuous abnormal time periods; statistical analysis is performed on the continuous abnormal time periods and the trend changes of the continuous abnormal time periods are obtained by applying the time series method; the association rule algorithm is used to mine the associated factors of the overload anomaly and generate a deep overload analysis report; the initial power load data includes the actual power value corresponding to the target air conditioner at each time point; Determine the standard power value of the air conditioner at that time point according to the predetermined power load curve, and compare it with the actual power value to obtain the difference value; group the basic power data by time period, and calculate the discreteness of the power difference at all time points in each time period; compare the discreteness with the temporary limit value to obtain a preliminary overload analysis report.

2. An air conditioning load control system according to claim 1, characterized in that: The temporary limit value includes a low limit value and a high limit value. If the dispersion of a certain time period is lower than the low limit value, it is determined that the distribution network is not overloaded in the time period; if the dispersion is higher than the high limit value, it is determined that the distribution network is overloaded in the time period; if the dispersion is between the low limit value and the high limit value, the time period is marked as abnormal, indicating that deep overload detection is required; The dispersion indicates the degree of difference between the actual power value and the standard power value, and is formed by comprehensive calculation using the range and the standard deviation.

3. The air conditioning load control system according to claim 1, characterized in that: The time window module initializes the time window and sets the step size of the window sliding, where the step size is the length of time each window moves; determines whether the size of the time window needs to be adjusted based on the system load and temporary limit value, and if adjustment is required, dynamically adjusts the size of the time window based on the step size.

4. An air conditioning load control system as claimed in claim 3, characterized in that: Calculate the load index for each time window, determine the system load according to the index value, and reduce the window size when the system load is high; When the system load is low, the window size is increased; the load indicators include average load, peak load and load distribution.

5. The air conditioning load control system according to claim 1, characterized in that: The system also includes a limit control module, which is used for real-time monitoring and dynamically adjusting the temporary limit value according to adjustment rules; the adjustment rule is based on the initial set temporary limit value and change range, and according to the automatic adjustment of the load data collected in real time and the time window, the temporary limit value is dynamically adjusted according to the change range; when the time window is reduced, the high limit value is reduced to improve the detection sensitivity; when the time window is expanded, the low limit value is increased to reduce false alarms.

6. An air conditioning load control system as claimed in claim 5, characterized in that: The adjustment rules also include regularly performing adjustment optimization based on historical overload records, obtaining historical overload records and adjustment records of temporary limit values, and comprehensively analyzing overload causes to continuously optimize the adjustment rules.

7. An air conditioning load control system as claimed in claim 5, characterized in that: The limit control module is also used to monitor and adjust the long-term limit value in real time, and use a statistical analysis method to perform statistical analysis on the temporary limit value within a short period of time to obtain an initial long-term limit value; the initial long-term limit value produces a first impact value on the adjustment of the temporary limit value, and the temporary limit value produces a reverse impact value on the change of the initial long-term limit value.

8. An air conditioning load control system as claimed in claim 7, characterized in that: The change trends of the counter-influence value and the first influence value are opposite, the first influence value is from low to high, the counter-influence value is from high to low, and the sum of the counter-influence value and the first influence value is 100%; when the initial values ​​of the counter-influence value and the first influence value are the same, the change of the initial long-term boundary value tends to stabilize to form a long-term boundary value.

9. An air conditioning load control system as claimed in claim 8, characterized in that: The long-term limit value is verified and optimized regularly according to the adjustment optimization record of the temporary limit value and the overall load change, and the values ​​of the reverse impact value and the first impact value are adjusted according to the verification result, and then the long-term limit value is adjusted through the temporary limit value.

Images