Power load monitoring method and system for tourist scenic areas

By using the attraction function and generator to generate monitoring strength in the power load monitoring system of tourist attractions, dynamically adjusting the monitoring strength, the subjective problem of manually setting monitoring strength in the existing technology is solved, and the monitoring effect and resource utilization efficiency are improved .

CN118589499BActive Publication Date: 2024-11-12CRUITE SOFTWARE GRP CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411062933.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-12
Estimated Expiration
2044-08-05

AI Technical Summary

Technical Problem

The power load monitoring system in existing tourist scenic areas relies on manual settings, which is highly subjective and cannot achieve optimal monitoring efforts, resulting in untimely or missed monitoring, and may increase operating costs and equipment burden.

Method used

By obtaining historical data of tourist attractions, using the generator to randomly generate monitoring force, and calculate the attraction value through the attraction function, dynamically adjust the monitoring force, select the solution with the largest attraction value as the monitoring force, and predict the power load based on multi-source data in real time. Changes are dynamically adjusted.

Benefits of technology

It has achieved the selection of the optimal monitoring force based on the operating data of different tourist attractions, dynamically adjust the monitoring force, improve the monitoring effect, optimize resource allocation efficiency and reduce operating costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118589499B_ABST
    Figure CN118589499B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for monitoring electric load in tourist scenic areas, and relates to the technical field of electric monitoring. The method calculates the attractiveness value of each monitoring intensity, calculates the attractiveness of other monitoring intensity to the current monitoring intensity according to the attractiveness value, and updates the current monitoring intensity content value according to the attractiveness, and repeats the iterative update of the monitoring intensity after the content value is updated. When the convergence condition is met, all monitoring intensity is output, and the monitoring intensity with the largest attractiveness value is selected as the monitoring intensity scheme of the electric load of the tourist scenic area. After analyzing multi-source data through a prediction model, the change of the electric load of the tourist scenic area is predicted, and the content value of the monitoring intensity scheme is dynamically adjusted according to the prediction result of the electric load change. The monitoring system can select the optimal monitoring intensity according to the operation data of different tourist scenic areas, and dynamically adjust the monitoring intensity during the real-time operation of the tourist scenic area, so as to ensure the monitoring effect of the monitoring system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electric power monitoring, and in particular to a method and system for monitoring electric power load in tourist scenic areas. Background Art

[0002] With the development of tourism, the demand for electricity in tourist attractions is increasing, especially during the peak tourist season, when the power load increases significantly, which puts higher demands on the stability of the power system. Power load monitoring is an important measure to ensure the stability and safety of power supply in these tourist attractions.

[0003] In order to effectively monitor the power load in tourist scenic areas, the existing power load monitoring system in tourist scenic areas usually adopts the monitoring intensity preset manually. This monitoring method has the following defects:

[0004] 1. The monitoring intensity that is manually set is usually set based on expert knowledge and experience, which is subject to strong human subjectivity, so that the monitoring system may not be able to monitor the power load of the tourist attraction with the optimal monitoring intensity;

[0005] 2. Due to factors such as the environment, passenger flow and equipment in tourist attractions, the power load may vary greatly at different times. When the pre-set monitoring intensity is adopted, firstly, the monitoring intensity may be insufficient, resulting in untimely or missed monitoring. Secondly, excessive monitoring intensity may increase the operating costs of the scenic area and the workload of the monitoring equipment.

[0006] Based on this, the present invention proposes a method and system for monitoring power load in tourist scenic areas, which can select the optimal monitoring intensity according to the operating data of different tourist attractions, and dynamically adjust the monitoring intensity during the real-time operation of the tourist attractions, thereby ensuring the monitoring effect of the monitoring system. Summary of the invention

[0007] The purpose of the present invention is to provide a method and system for monitoring power load in tourist scenic areas to overcome the shortcomings of the background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a method for monitoring power load in a tourist scenic area, the monitoring method comprising the following steps:

[0009] The monitoring system obtains historical data of tourist attractions, randomly generates several monitoring strengths through a generator combined with historical data, calculates the attractiveness value of each monitoring strength through an attractiveness function, and calculates the attractiveness of other monitoring strengths to the current monitoring strength based on the attractiveness value;

[0010] Update the current monitoring intensity content value according to the attraction, repeat the iterative update of the monitoring intensity after the content value is updated, output all monitoring intensities when the convergence condition is met, and select the monitoring intensity with the largest attraction value as the monitoring intensity plan for the power load of the tourist attraction;

[0011] During the operation of tourist attractions, the monitoring system monitors the real-time multi-source data of the tourist attractions, analyzes the multi-source data through the prediction model, predicts the changes in the power load of the tourist attractions, and dynamically adjusts the content of the monitoring intensity plan based on the prediction results of the power load changes.

[0012] In a preferred embodiment, the content of each monitoring intensity includes coverage, sampling frequency and response speed, but the coverage, sampling frequency and response speed of different monitoring intensities are completely different or partially different.

[0013] In a preferred embodiment, the monitoring system obtains historical data of the tourist attraction, and randomly generates a number of monitoring strengths by combining the historical data with a generator, including the following steps:

[0014] Collect historical data of scenic area power load, including peak-period power consumption, average power consumption, maximum and minimum power consumption, and generate constraints for monitoring intensity based on peak-period power consumption, average power consumption, maximum and minimum power consumption. Use a generator to randomly generate monitoring intensity based on the constraints. When the number of generated monitoring intensities is equal to the quantity threshold, stop generating monitoring intensity.

[0015] In a preferred embodiment, the attraction of other monitoring forces to the current monitoring force is calculated according to the attraction value, including the following steps:

[0016] The attractiveness of monitoring intensity i A ij The calculation expression is:

[0017] In the formula, A ij represents the attraction of monitoring intensity j to monitoring intensity i, ε 0 represents the initial strength of the new gravity, is the distance influence factor, d ij represents the distance between monitoring intensity i and monitoring intensity j, G j is the attractiveness value of monitoring force j.

[0018] In a preferred embodiment, updating the current monitoring intensity content value according to the attraction includes the following steps:

[0019] Update the current monitoring intensity content value according to the attraction, the expression is:

[0020] In the formula, Indicates the updated value of the monitoring intensity i. Indicates the value of the content before the monitoring intensity i is updated, x j Indicates the value of the content of monitoring intensity j, is the step factor, and rand is a random number.

[0021] In a preferred embodiment, the monitoring intensity after the content value is updated is repeatedly iteratively updated, and all monitoring intensity is output when the convergence condition is met, including the following steps:

[0022] The monitoring intensity after the content value is updated is iteratively updated repeatedly. When the preset number of iterations is reached or there is a monitoring intensity with an attraction value greater than or equal to the attraction threshold after a certain iteration, it is judged that the convergence condition is met. The monitoring system outputs all monitoring intensities and selects the monitoring intensity with the largest attraction value as the monitoring intensity plan for the power load of the tourist attraction.

[0023] In a preferred embodiment, predicting the change of power load in a tourist attraction after analyzing multi-source data through a prediction model includes the following steps:

[0024] Substitute the temperature rise rate, the cumulative coefficient of human flow, the rate of increase of power consumption, and the current fluctuation amplitude into the prediction model to calculate the load factor. The function expression is:

[0025] In the formula, fh x is the load factor, T, D, L, and P are the temperature rise rate, the cumulative coefficient of human flow, the power consumption rise rate, and the current fluctuation amplitude, respectively. 1 ,ω 2 ,ω 3 ,ω 4 is the regression coefficient, and ω 1 ,ω 2 ,ω 3 ,ω 4 Both are greater than 0.

[0026] In a preferred embodiment, during the operation of a tourist attraction, the monitoring system monitors real-time multi-source data of the tourist attraction, including the following steps:

[0027] The monitoring system monitors real-time multi-source data of tourist attractions, including environmental data, regional data and equipment data. Environmental data includes the temperature rise rate, regional data includes the cumulative coefficient of human flow, and equipment data includes the power consumption rise rate and current fluctuation amplitude;

[0028] The calculation logic of the temperature rise rate is as follows: obtain the current temperature of the environment and the temperature of the previous moment, subtract the current temperature from the previous moment to obtain the temperature difference, subtract the current moment from the previous moment to obtain the monitoring time, and obtain the temperature rise rate by dividing the temperature difference by the monitoring time.

[0029] The calculation expression of the cumulative coefficient of human flow is: Where D is the cumulative coefficient of human traffic, t start is the starting time of monitoring, t end is the end of monitoring time point, N(t) is the flow of people at time t;

[0030] The calculation logic of the power consumption increase rate is as follows: obtain the power consumption of the device at the current moment and the power consumption at the previous moment, subtract the power consumption at the current moment from the power consumption at the previous moment to obtain the power consumption difference, subtract the current moment from the previous moment to obtain the monitoring time, and obtain the power consumption increase rate by dividing the power consumption difference by the previous monitoring time;

[0031] The calculation expression of the current fluctuation amplitude is: Where P is the current fluctuation amplitude, τ i is the total current value at the i-th monitoring time point, τ avg is the average current value, and M is the number of monitoring time points.

[0032] In a preferred embodiment, the constraint conditions for monitoring intensity are generated by combining the peak power consumption, average power consumption, maximum and minimum power consumption, and the generation steps are:

[0033] The coverage range is defined as the area proportional to the power consumption during peak hours. The maximum coverage area of ​​the tourist attraction is obtained, and the constraints satisfied by the coverage range are: [min_c, max_c], where min_c is the minimum coverage area, and max_c is the maximum coverage area, h_p is the peak power consumption, and max_l is the maximum power consumption;

[0034] The sampling frequency is defined as the ratio between the average power consumption and the maximum power consumption: Then the constraint satisfied by the sampling frequency is: [min_s, max_s], where min_s is the minimum sampling interval,, max_s is the maximum sampling interval, and μ_l is the average power consumption;

[0035] The response speed is defined as the ratio between the peak power consumption and the minimum power consumption: Then the constraint satisfied by the response speed is: [min_r, max_r], where min_r is the minimum response time interval, and max_r is the maximum response time interval, and min_l is the minimum power consumption.

[0036] The power load monitoring system for tourist scenic areas includes a monitoring intensity generation module, a monitoring intensity update module, a scheme output module, and a scheme dynamic adjustment module;

[0037] Monitoring intensity generation module: obtain historical data of tourist attractions, and randomly generate several monitoring intensities through the generator combined with historical data. The content of each monitoring intensity includes coverage, sampling frequency and response speed;

[0038] Monitoring strength update module: calculate the attraction value of each monitoring strength through the attraction function, calculate the attraction of other monitoring strengths to the current monitoring strength based on the attraction value, and update the current monitoring strength content value based on the attraction, and repeatedly iterate and update the monitoring strength after the content value is updated;

[0039] Scheme output module: when the convergence conditions are met, all monitoring intensities are output, and the monitoring intensity with the largest attraction value is selected as the monitoring intensity scheme for the power load of the tourist scenic spot;

[0040] Dynamic adjustment module of the plan: During the operation of the tourist attraction, the real-time multi-source data of the tourist attraction is monitored, and the power load changes of the tourist attraction are predicted after analyzing the multi-source data through the prediction model. The content of the monitoring intensity plan is dynamically adjusted according to the prediction results of the power load changes.

[0041] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0042] 1. The present invention calculates the attraction value of each monitoring intensity through an attraction function, calculates the attraction of other monitoring intensity to the current monitoring intensity based on the attraction value, and updates the current monitoring intensity content value based on the attraction, and repeats the iterative update of the monitoring intensity after the content value is updated. When the convergence condition is met, all monitoring intensities are output, and the monitoring intensity with the largest attraction value is selected as the monitoring intensity plan for the power load of the tourist attraction. The power load change of the tourist attraction is predicted after analyzing multi-source data through a prediction model, and the content value of the monitoring intensity plan is dynamically adjusted according to the prediction result of the power load change. The monitoring system can select the optimal monitoring intensity based on the operating data of different tourist attractions, and dynamically adjust the monitoring intensity during the real-time operation of the tourist attraction, thereby ensuring the monitoring effect of the monitoring system;

[0043] 2. The coverage scope in this application usually gives priority to covering the more important areas in the tourist attractions, that is, the tourist attractions can be divided into several sub-areas according to the power load, and then all the sub-areas are sorted from large to small according to the average power consumption to generate a regional sorting table, and the sub-areas to be monitored in the coverage scope are selected in positive order according to the regional sorting table. Through this method, the sub-areas with high power consumption are always in a monitored state, and some sub-areas with low power consumption can choose whether to be monitored according to the operating conditions of the tourist attractions, which can effectively improve the allocation efficiency of monitoring resources and reduce monitoring costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0045] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Example 1: Please refer to Figure 1 As shown, the power load monitoring method for tourist scenic areas described in this embodiment includes the following steps:

[0048] The monitoring system obtains the historical data of the tourist attraction, and randomly generates several monitoring intensities through a generator combined with the historical data. The content of each monitoring intensity includes coverage, sampling frequency and response speed, but the coverage, sampling frequency and response speed of different monitoring intensities are completely different or partially different. The attraction value of each monitoring intensity is calculated through the attraction function, and the attraction of other monitoring intensities to the current monitoring intensity is calculated based on the attraction value, and the current monitoring intensity content value is updated according to the attraction. The monitoring intensity after the content value is updated is iteratively updated repeatedly. When the convergence condition is met, all monitoring intensities are output, and the monitoring intensity with the largest attraction value is selected as the monitoring intensity plan for the power load of the tourist attraction. During the operation of the tourist attraction, the monitoring system monitors the real-time multi-source data of the tourist attraction, and predicts the power load change of the tourist attraction after analyzing the multi-source data through the prediction model, and dynamically adjusts the content value of the monitoring intensity plan according to the prediction result of the power load change.

[0049] This application calculates the attraction value of each monitoring intensity through an attraction function, calculates the attraction of other monitoring intensity to the current monitoring intensity based on the attraction value, and updates the current monitoring intensity content value based on the attraction, repeats the iterative update of the monitoring intensity after the content value is updated, and outputs all monitoring intensity after the convergence condition is met. The monitoring intensity with the largest attraction value is selected as the monitoring intensity plan for the power load of the tourist attraction, and the power load change of the tourist attraction is predicted after analyzing multi-source data through a prediction model, and the content value of the monitoring intensity plan is dynamically adjusted according to the prediction result of the power load change. The monitoring system can select the optimal monitoring intensity based on the operating data of different tourist attractions, and dynamically adjust the monitoring intensity during the real-time operation of the tourist attraction, thereby ensuring the monitoring effect of the monitoring system.

[0050] Embodiment 2: The monitoring system obtains historical data of a tourist attraction, and randomly generates a number of monitoring strengths by combining the historical data with a generator. The content of each monitoring strength includes coverage, sampling frequency, and response speed, but the coverage, sampling frequency, and response speed of different monitoring strengths are completely different or partially different, including the following steps:

[0051] Collect historical data of scenic area power load, including peak-time power consumption, average power consumption, maximum and minimum power consumption, etc., combine peak-time power consumption, average power consumption, maximum and minimum power consumption to generate monitoring intensity constraints, and use a generator to randomly generate monitoring intensity based on the constraints. When the number of generated monitoring intensities is equal to the quantity threshold, stop generating monitoring intensity;

[0052] Combine the peak power consumption, average power consumption, maximum and minimum power consumption to generate the monitoring intensity constraints. The generation steps are as follows:

[0053] The coverage range can be defined as the area proportional to the power consumption during peak hours. The maximum coverage area of ​​the tourist attraction is obtained, and the constraints satisfied by the coverage range are: [min_c, max_c], where min_c is the minimum coverage area, and max_c is the maximum coverage area, h_p is the peak power consumption, max_l is the maximum power consumption, and the unit of coverage is area;

[0054] The sampling frequency can be defined as a certain ratio between the average power consumption and the maximum power consumption: Then the constraint satisfied by the sampling frequency is: [min_s, max_s], where min_s is the minimum sampling interval, and max_s is the maximum sampling interval, and max_l is the maximum power consumption, μ_l is the average power consumption, and the sampling frequency is in seconds;

[0055] The response speed can be defined as a certain ratio between the peak power consumption and the minimum power consumption: Then the constraint satisfied by the response speed is: [min_r, max_r], where min_r is the minimum response time interval, and max_r is the maximum response time interval, and h_p is the peak power consumption, min_l is the minimum power consumption, and the unit of response speed is minute.

[0056] The monitoring intensity is randomly generated by the generator according to the constraints. When the number of generated monitoring intensity is equal to the quantity threshold, the generation of monitoring intensity is stopped. The relevant code examples are as follows:

[0057] Import_random

[0058] #Historical data statistics

[0059] high_peak_load=1200#Power consumption during peak hours (kW)

[0060] avg_load=800#Average power consumption (kW)

[0061] max_load=1500#Maximum power consumption (kW)

[0062] min_load=500#Minimum power consumption (kW)

[0063] #Automatically generated constraints

[0064] max_coverage_area = 5000 # Maximum coverage area (square meters)

[0065] min_coverage_area=high_peak_load*0.8*max_coverage_area / max_load# minimum coverage area (square meters)

[0066] min_sampling_frequency = (max_load - avg_load) / 10 # minimum sampling frequency (seconds)

[0067] max_sampling_frequency = (max_load - avg_load) / 5 # Maximum sampling frequency (seconds)

[0068] min_response_time = (high_peak_load - min_load) / 300 # minimum response speed (minutes)

[0069] max_response_time = (high_peak_load - min_load) / 150 # Maximum response speed (minutes)

[0070] #Quantity threshold

[0071] threshold=5#Generated monitoring intensity threshold

[0072] #Generate monitoring strength

[0073] monitoring_schemes = []

[0074] While_len(monitoring_schemes) <threshold:

[0075] coverage_area=random.uniform(min_coverage_area,max_coverage_area)

[0076] sampling_frequency=random.uniform(min_sampling_frequency,max_sampling_frequency)

[0077] response_time=random.uniform(min_response_time,max_response_time)

[0078] monitoring_scheme = {

[0079] 'coverage_area':coverage_area,

[0080] 'sampling_frequency':sampling_frequency,

[0081] 'response_time':response_time

[0082] }

[0083] monitoring_schemes.append(monitoring_scheme)

[0084] #Output the generated monitoring intensity plan

[0085] for_idx,scheme_in_enumerate(monitoring_schemes):

[0086] print(f"Scheme {idx+1}: coverage = {scheme['coverage_area']:.2f} square meters, sampling frequency = {scheme['sampling_frequency']:.2f} seconds, response speed = {scheme['respo nse_time']:.2f} minutes");

[0087] The randomly generated monitoring intensity content example is as follows:

[0088] Monitoring intensity 1: Coverage = 4200.23 square meters, sampling frequency = 108.45 seconds, response speed = 4.13 minutes;

[0089] Monitoring intensity 2: Coverage area = 4500.87 square meters, sampling frequency = 130.76 seconds, response speed = 4.32 minutes;

[0090] Monitoring intensity 3: Coverage = 3700.32 square meters, sampling frequency = 120.12 seconds, response speed = 3.75 minutes;

[0091] Monitoring intensity 4: Coverage = 4300.65 square meters, sampling frequency = 90.38 seconds, response speed = 3.02 minutes;

[0092] Monitoring intensity 5: Coverage = 5000.00 square meters, sampling frequency = 70.12 seconds, response speed = 2.92 minutes;

[0093] The above is only an example of generating five monitoring intensities. In actual applications, in order to improve the global optimization effect of the monitoring system, hundreds to thousands of monitoring intensities can be generated.

[0094] Furthermore, it should be noted that the coverage range described in the present application usually gives priority to covering more important areas in tourist attractions, that is, the tourist attractions can be divided into several sub-areas based on the power load, and then all the sub-areas are sorted from large to small according to the average power consumption to generate a regional sorting table, and the sub-areas to be monitored in the coverage range are selected in positive order according to the regional sorting table. Through this method, sub-areas with high power consumption are always in a monitored state, while some sub-areas with low power consumption can choose whether to be monitored according to the operating conditions of the tourist attractions, which can effectively improve the allocation efficiency of monitoring resources and reduce monitoring costs.

[0095] The attraction value of each monitoring force is calculated by the attraction function, including the following steps:

[0096] For tourist attractions, different monitoring efforts bring different monitoring costs, monitoring efficiencies, and monitoring system loads. In this application, the attractiveness value of each monitoring effort is calculated by minimizing the monitoring cost, maximizing the monitoring efficiency, and minimizing the monitoring system load. The expression is:

[0097] In the formula, G is the attraction value, δ is the monitoring efficiency, and σ is the monitoring cost. is the monitoring system load, α, β, and γ are the proportional coefficients of monitoring efficiency, monitoring cost, and monitoring system load, respectively, and α, β, and γ are all greater than 0. The larger the attractiveness value, the higher the applicability of monitoring intensity in tourist attractions;

[0098] The logic for obtaining monitoring efficiency is as follows: during the historical operation of obtaining monitoring intensity, when the monitoring system monitors the power load of the tourist scenic spot according to the monitoring intensity, the number of power failures detected under the monitoring intensity and the total number of power failures are obtained, and the number of power failures detected is divided by the total number of power failures to obtain the monitoring efficiency. The greater the monitoring efficiency, the smaller the omission rate under the monitoring intensity.

[0099] The acquisition logic of the monitoring system load is as follows: the CPU usage rate and content occupancy rate of the monitoring system when it is running are obtained through computer monitoring tools, and the CPU usage rate and content occupancy rate are summed to obtain the monitoring system load. The greater the monitoring system load, the more likely it is to cause the monitoring system to crash or the computer to fail during the monitoring process;

[0100] The logic for obtaining the monitoring cost is: obtain the energy consumption and operation and maintenance costs generated when the monitoring system is running, and sum the energy consumption and operation and maintenance costs to obtain the monitoring cost. The monitoring cost needs to be minimized.

[0101] The attraction of other monitoring strengths to the current monitoring strength is calculated based on the attraction value, and the current monitoring strength content value is updated based on the attraction, including the following steps:

[0102] The attraction of monitoring intensity j to monitoring intensity i A ij The calculation expression is:

[0103] In the formula, A ij represents the attraction of monitoring intensity j to monitoring intensity i, ε 0 represents the initial strength of the new gravity, is the distance influence factor, and d ij represents the distance between monitoring intensity i and monitoring intensity j, G j is the attractiveness value of monitoring force j;

[0104] The distance calculation expression between monitoring intensity i and monitoring intensity j is:

[0105] Where, d ij represents the distance between monitoring intensity i and monitoring intensity j, (R i ,F i ,S i ) is the coverage, sampling frequency and response speed of the monitoring intensity i, (R j ,F j ,S j ) is the coverage, sampling frequency and response speed of the monitoring intensity j.

[0106] Update the current monitoring intensity content value according to the attraction, the expression is:

[0107] In the formula, Indicates the updated value of the monitoring intensity i. Indicates the value of the content before the monitoring intensity i is updated, x j Indicates the value of the content of monitoring intensity j, is the step size factor, and rand is a random number, and the value range of rand is [0,1).

[0108] Repeat the iterative update of the monitoring intensity after the content value is updated. When the convergence condition is met, all monitoring intensities are output, and the monitoring intensity with the largest attraction value is selected as the monitoring intensity scheme of the power load of the tourist attraction, including the following steps:

[0109] The attraction value of the monitoring intensity after the content value is updated is recalculated, and the updated content value is iterated. When the preset number of iterations is reached or there is a monitoring intensity with an attraction value greater than or equal to the attraction threshold after a certain iteration, it is judged that the convergence condition is met, and the monitoring system outputs all monitoring intensities and selects the monitoring intensity with the largest attraction value as the monitoring intensity plan for the power load of the tourist attraction.

[0110] During the operation of tourist attractions, the monitoring system monitors the real-time multi-source data of tourist attractions, including the following steps:

[0111] The monitoring system monitors real-time multi-source data of tourist attractions, including environmental data, regional data, and equipment data;

[0112] Among them, environmental data includes the temperature rise rate, regional data includes the cumulative coefficient of human flow, and equipment data includes the power consumption rise rate and current fluctuation amplitude;

[0113] The calculation logic of the temperature rise rate is as follows: obtain the current temperature of the environment and the temperature of the previous moment, subtract the current temperature from the previous moment to obtain the temperature difference, subtract the current moment from the previous moment to obtain the monitoring time, and obtain the temperature rise rate by dividing the temperature difference by the monitoring time. The greater the temperature rise rate, the greater the air conditioning power in the tourist attraction, and the greater the power loss of the electrical equipment. At this time, the power load of the tourist attraction will increase, so it is necessary to increase the monitoring intensity;

[0114] The calculation expression of the cumulative coefficient of human flow is: Where D is the cumulative coefficient of human traffic, t start is the starting time of monitoring, t end is the end of monitoring time point, N(t) is the flow of people at time t, the larger the cumulative coefficient of the flow of people in the tourist attraction, the more frequent the use of internal power-consuming recreational facilities and other power-consuming equipment will be, and the power load of the tourist attraction will increase, so it is necessary to increase the monitoring intensity;

[0115] The calculation logic of the power consumption increase rate is as follows: obtain the power consumption of the device at the current moment and the power consumption at the previous moment, subtract the power consumption at the current moment from the power consumption at the previous moment to obtain the power consumption difference, subtract the current moment from the previous moment to obtain the monitoring time, and obtain the power consumption increase rate by dividing the power consumption difference by the monitoring time. The greater the power consumption increase rate, the greater the power loss in the tourist attraction. At this time, the power load of the tourist attraction will increase, so it is necessary to increase the monitoring intensity;

[0116] The calculation expression of the current fluctuation amplitude is: Where P is the current fluctuation amplitude, τ i is the total current value at the i-th monitoring time point, τ avgis the average current value, M is the number of monitoring time points, and the larger the current fluctuation amplitude, the greater the current fluctuation of all electrical equipment in the tourist scenic area within a period of time, which may indicate abnormalities and faults, so it is necessary to increase monitoring efforts.

[0117] After analyzing multi-source data through the prediction model, the power load changes of tourist attractions are predicted, including the following steps:

[0118] Substitute the temperature rise rate, the cumulative coefficient of human flow, the rate of increase of power consumption, and the current fluctuation amplitude into the prediction model to calculate the load factor. The function expression is:

[0119]

[0120] , where fh x is the load factor, T, D, L, and P are the temperature rise rate, the cumulative coefficient of human flow, the power consumption rise rate, and the current fluctuation amplitude, respectively. 1 ,ω 2 ,ω 3 ,ω 4 is the regression coefficient, and ω 1 ,ω 2 ,ω 3 ,ω 4 They are all greater than 0. From the function expression of the load coefficient, we can see that the larger the load coefficient, the more it is necessary to increase the content value of the monitoring intensity plan.

[0121] Dynamically adjust the content and value of the monitoring intensity plan according to the prediction results of power load changes, including the following steps:

[0122] After obtaining the load factor, the load factor is compared with the preset interval threshold, and the content value of the monitoring intensity plan is dynamically adjusted according to the comparison result between the load factor and the interval area. The dynamic adjustment method is shown in Table 1:

[0123]

[0124] Table 1

[0125] As can be seen from Table 1, the interval threshold includes the threshold fh 1 , threshold fh 2 , threshold fh 3 , threshold fh 4 , threshold fh 5 , and the threshold fh 1 <Threshold fh 2 <Threshold fh 3 <Threshold fh 4 <Threshold fh 5 , when the load factor fh x ≤Threshold fh 1When the load factor fh x >Threshold fh 5 When it is detected, it indicates that the power load in the tourist area is predicted to change greatly, and warnings and management are needed.

[0126] Embodiment 3: The power load monitoring system for tourist scenic areas described in this embodiment includes a monitoring intensity generation module, a monitoring intensity update module, a scheme output module, and a scheme dynamic adjustment module;

[0127] Monitoring intensity generation module: obtain historical data of tourist attractions, and randomly generate several monitoring intensities through the generator combined with historical data. The content of each monitoring intensity includes coverage, sampling frequency and response speed, but the coverage, sampling frequency and response speed of different monitoring intensities are completely different or partially different. A set of plans is established for several monitoring intensities, and the set of plans is sent to the monitoring intensity update module;

[0128] Monitoring strength update module: calculate the attraction value of each monitoring strength through the attraction function, calculate the attraction of other monitoring strengths to the current monitoring strength based on the attraction value, and update the current monitoring strength content value according to the attraction, repeatedly iterate and update the monitoring strength after the content value is updated, and send the iterative update result to the solution output module;

[0129] Scheme output module: when the convergence conditions are met, all monitoring intensities are output, and the monitoring intensity with the largest attraction value is selected as the monitoring intensity scheme for the power load of the tourist scenic spot. The monitoring intensity scheme is sent to the scheme dynamic adjustment module;

[0130] Dynamic adjustment module of the plan: During the operation of the tourist attraction, the real-time multi-source data of the tourist attraction is monitored, and the power load changes of the tourist attraction are predicted after analyzing the multi-source data through the prediction model. The content of the monitoring intensity plan is dynamically adjusted according to the prediction results of the power load changes.

[0131] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0132] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0133] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for monitoring power load in a tourist scenic area, characterized by: The monitoring method comprises the following steps: The monitoring system obtains historical data of tourist attractions, randomly generates several monitoring strengths through a generator combined with historical data, calculates the attractiveness value of each monitoring strength through an attractiveness function, and calculates the attractiveness of other monitoring strengths to the current monitoring strength based on the attractiveness value; Update the current monitoring intensity content value according to the attraction, repeat the iterative update of the monitoring intensity after the content value is updated, output all monitoring intensities when the convergence condition is met, and select the monitoring intensity with the largest attraction value as the monitoring intensity plan for the power load of the tourist attraction; During the operation of tourist attractions, the monitoring system monitors the real-time multi-source data of tourist attractions, analyzes the multi-source data through the prediction model, and predicts the changes in the power load of the tourist attractions. According to the prediction results of the power load changes, the content and value of the monitoring intensity plan are dynamically adjusted; The content of each monitoring intensity includes coverage, sampling frequency and response speed, but the coverage, sampling frequency and response speed of different monitoring intensity are completely different or partially different; The monitoring system obtains historical data of tourist attractions and randomly generates several monitoring intensities by combining historical data through a generator, including the following steps: Collect historical data of scenic area power load, including peak-time power consumption, average power consumption, maximum and minimum power consumption, and generate monitoring intensity constraints based on peak-time power consumption, average power consumption, maximum and minimum power consumption. Generate monitoring intensity randomly through the generator according to the constraints. When the number of generated monitoring intensity is equal to the quantity threshold, stop generating monitoring intensity. Calculating the attractiveness of other monitoring efforts to the current monitoring effort based on the attractiveness value includes the following steps: Monitoring intensity Monitoring efforts The attraction The calculation expression is: , where Indicates monitoring intensity Monitoring efforts The attraction represents the initial strength of the new gravity, is the distance influence factor, Indicates monitoring intensity And monitoring efforts The distance between To monitor the intensity The attractiveness value of Updating the current monitoring intensity content value according to the attraction includes the following steps: Update the current monitoring intensity content value according to the attraction, the expression is: , where Indicates monitoring intensity The updated content value, Indicates monitoring intensity The value of the content before updating. Indicates monitoring intensity Content value, is the step size factor, is a random number; Repeat the iterative update of the monitoring intensity after the content value is updated, and output all monitoring intensity when the convergence condition is met, including the following steps: When the preset number of iterations is reached or after a certain iteration, there is a monitoring intensity with an attraction value greater than or equal to the attraction threshold, it is judged that the convergence condition is met, the monitoring system outputs all monitoring intensities, and selects the monitoring intensity with the largest attraction value as the monitoring intensity plan for the power load of the tourist attraction; After analyzing multi-source data through the prediction model, the power load changes of tourist attractions are predicted, including the following steps: Substitute the temperature rise rate, the cumulative coefficient of human flow, the rate of increase of power consumption, and the current fluctuation amplitude into the prediction model to calculate the load factor. The function expression is: , where is the load factor, , , , They are respectively the temperature rising rate, the accumulation coefficient of human flow, the rising rate of power consumption, and the current fluctuation amplitude. , , , is the regression coefficient, and , , , Both are greater than 0.

2. The method for monitoring power load in a tourist scenic area according to claim 1, characterized in that: During the operation of tourist attractions, the monitoring system monitors the real-time multi-source data of tourist attractions, including the following steps: The monitoring system monitors real-time multi-source data of tourist attractions, including environmental data, regional data and equipment data. Environmental data includes the temperature rise rate, regional data includes the cumulative coefficient of human flow, and equipment data includes the power consumption rise rate and current fluctuation amplitude; The calculation logic of the temperature rise rate is as follows: obtain the current temperature of the environment and the temperature of the previous moment, subtract the current temperature from the previous moment to obtain the temperature difference, subtract the current moment from the previous moment to obtain the monitoring time, and obtain the temperature rise rate by dividing the temperature difference by the monitoring time. The calculation expression of the cumulative coefficient of human flow is: , where is the cumulative coefficient of human traffic, To start monitoring time point, To end the monitoring time point, For time The flow of people at any given moment; The calculation logic of the power consumption increase rate is as follows: obtain the power consumption of the device at the current moment and the power consumption at the previous moment, subtract the power consumption at the current moment from the power consumption at the previous moment to obtain the power consumption difference, subtract the current moment from the previous moment to obtain the monitoring time, and obtain the power consumption increase rate by dividing the power consumption difference by the previous monitoring time; The calculation expression of the current fluctuation amplitude is: , where is the current fluctuation amplitude, For the The total current value at each monitoring time point, is the average current value, is the number of monitoring time points.

3. The method for monitoring power load in a tourist scenic area according to claim 2, characterized in that: Combine the peak power consumption, average power consumption, maximum and minimum power consumption to generate the monitoring intensity constraints. The generation steps are: The coverage range is defined as the area proportional to the power consumption during peak hours. The maximum coverage area of ​​the tourist attraction is obtained, and the constraints satisfied by the coverage range are: , where is the minimum coverage area, and , is the maximum coverage area, For peak hours of electricity consumption, is the maximum power consumption; The sampling frequency is defined as the ratio between the average power consumption and the maximum power consumption: Then the constraints satisfied by the sampling frequency are: , where is the minimum sampling interval, and , is the maximum sampling interval, and , is the average electricity consumption; The response speed is defined as the ratio between the peak power consumption and the minimum power consumption: Then the constraint satisfied by the response speed is: , where is the minimum response time interval, and , Maximum response time, and , Minimum power consumption.

4. A power load monitoring system for tourist scenic areas, used to implement the monitoring method according to any one of claims 1 to 3, characterized in that: It includes a monitoring intensity generation module, a monitoring intensity update module, a plan output module, and a plan dynamic adjustment module; Monitoring intensity generation module: obtain historical data of tourist attractions, and randomly generate several monitoring intensities through the generator combined with historical data. The content of each monitoring intensity includes coverage, sampling frequency and response speed; Monitoring strength update module: calculate the attraction value of each monitoring strength through the attraction function, calculate the attraction of other monitoring strengths to the current monitoring strength based on the attraction value, and update the current monitoring strength content value based on the attraction, and repeatedly iterate and update the monitoring strength after the content value is updated; Scheme output module: when the convergence conditions are met, all monitoring intensities are output, and the monitoring intensity with the largest attraction value is selected as the monitoring intensity scheme for the power load of the tourist scenic spot; Dynamic adjustment module of the plan: During the operation of the tourist attraction, the real-time multi-source data of the tourist attraction is monitored, and the power load changes of the tourist attraction are predicted after analyzing the multi-source data through the prediction model. The content of the monitoring intensity plan is dynamically adjusted according to the prediction results of the power load changes.

Citation Information

Patent Citations

  • Monitoring method and system suitable for unattended low-voltage cabinet

    CN111884334A

  • Multi-level load management system and method based on power grid

    CN117578706A

  • Multi-source power dispatching method and system based on big data

    CN117767446A

  • System and apparatus for monitoring electricity supply system

    GB201914291D0

  • Device for monitoring reliability of electric power system

    JP1995227040A