Methods for monitoring the operational status of solar streetlights and solar streetlights

Abstract

This application relates to the field of street light operation monitoring, and more particularly to a method for monitoring the operating status of solar street lights and a solar street light. The method includes the following steps: clustering street lights according to environmental parameters to obtain multiple clusters; calculating the outlier degree of power generation of a target street light; generating monitoring signal one in response to an outlier degree greater than a preset first threshold, and generating monitoring signal two otherwise; calculating the degree of change in the similarity of power generation between each cluster and its neighboring clusters; generating monitoring signal three in response to a change degree greater than a preset second threshold, and generating monitoring signal four otherwise; determining an abnormal operating status of the target street light in response to monitoring signals one and four; and determining a regional anomaly in the street lights within the corresponding cluster area in response to monitoring signals two and three. This application improves the accuracy of judging abnormal street light operating status.

Description

Technical Field

[0001] This application relates to the field of street light operation monitoring, and in particular to a method and system for monitoring the operation status of solar street lights. Background Technology

[0002] The core components of a solar street light include solar panels, batteries, and the lamp body. During the day, the solar panels convert sunlight into electrical energy and store it in the batteries. At night, the batteries power the street light. Solar street lights are typically installed outdoors, and the power output of the solar panels is related to the amount and intensity of sunlight received by the panels. If the solar panels are covered, for example, by dust, sand, or snow blocking direct sunlight from reaching the photovoltaic cells, this will cause a decrease in the photoelectric conversion efficiency of the solar panels, reducing power generation. The street light's batteries will not be fully charged, potentially leading to shorter nighttime illumination or even failure to light up at all.

[0003] By monitoring the power generation of solar panels, any abnormalities in power generation can be detected in a timely manner. Through Internet of Things (IoT) technology, the operating data of solar streetlights is uploaded to the cloud for remote monitoring and management. When an anomaly is detected (such as a decrease in power generation), the system automatically sends an alarm and provides maintenance suggestions.

[0004] However, the power generation of solar streetlights is affected by various factors, including seasonal changes, weather conditions, geographical location, and the duration of sunlight throughout the day. For example, in winter, due to shorter daylight hours and lower solar altitude angles, the power generation of solar panels is typically lower than in summer; and on cloudy, rainy, or foggy days, power generation also decreases significantly. Therefore, using a fixed threshold may not accurately reflect the actual operating conditions. Setting a fixed power generation threshold may lead to misjudgments or missed detections of abnormal situations. Summary of the Invention

[0005] To address the technical problem of low accuracy in determining abnormal power generation of solar streetlights, this application provides a method and system for monitoring the operating status of solar streetlights.

[0006] Firstly, this application provides a method for monitoring the operating status of solar streetlights, employing the following technical solution:

[0007] A method for monitoring the operational status of solar streetlights includes the following steps: Clustering streetlights into multiple clusters based on their environmental parameters; selecting any streetlight within a cluster as a target streetlight and calculating the outlier rate of its power generation; generating monitoring signal one if the outlier rate exceeds a preset first threshold, and generating monitoring signal two otherwise; calculating the degree of change in the similarity of power generation between each cluster and its neighboring clusters; generating monitoring signal three if the degree of change exceeds a preset second threshold, and generating monitoring signal four otherwise; determining that the individual operational status of the target streetlight is abnormal based on monitoring signals one and four; determining that there is a regional anomaly in the streetlights within the corresponding area of ​​the cluster based on monitoring signals two and three; determining that there is a regional anomaly in the streetlights within the corresponding area of ​​the cluster, and that the individual operational status of the target streetlight is abnormal based on monitoring signals one and three; otherwise, determining that the streetlight is in normal condition.

[0008] Optional parameters include snow cover and particulate matter. Particulate matter parameters include particulate matter concentration, wind speed, humidity, and rainfall. Snow cover parameters include temperature and snowfall.

[0009] Optionally, the outlier of power generation is the deviation of the real-time power generation of the target street light from the real-time power generation of the street lights in its cluster; or the outlier of power generation is the deviation of the real-time power generation of the target street light from its historical power generation.

[0010] Optionally, the expression for the outlier degree of power generation is: In the formula, L represents the outlier degree of the target street light's power generation, n represents the total number of street lights in the cluster to which the target street light belongs, and g i This represents the actual power generation of the target streetlight at time i. σ represents the average power generation of other streetlights in the cluster containing the target streetlight at time i, and σ represents the standard deviation of the power generation of other streetlights in the cluster containing the target streetlight.

[0011] Optionally, the expression for the outlier degree of power generation is: In the formula, L represents the outlier degree of the target street light's power generation, n represents the total number of street lights in the cluster to which the target street light belongs, and g i Let σ represent the actual power generation of the target streetlight at time i, G represent the average historical power generation of the target streetlight, and σ represent the actual power generation of the target streetlight at time i. ′ represents the standard deviation of the historical power generation of the target streetlight, and norm represents the standard normalization function.

[0012] Optionally, the calculation method for power generation similarity is as follows: for the average power generation sequence of each cluster, the normalized result of the cosine similarity of the power generation sequences corresponding to the two clusters is used as the power generation similarity.

[0013] Optionally, the formula for calculating the similarity of power generation is: Where S represents the similarity of power generation. Let i be the i-th value in the power generation sequence of the cluster-cluster center. is the i-th value in the power generation sequence of the binary cluster center of the cluster.

[0014] Optionally, the expression for the degree of change in power generation similarity is: Where D represents the degree of change in power generation similarity, S represents the power generation similarity sequence of two clusters at historical moments, max represents the maximum value function, min represents the minimum value function, and mean represents the average value function.

[0015] Optionally, the clustering algorithm can be DBSCAN clustering or K-Means clustering.

[0016] Secondly, this application provides a solar street light, which adopts the following technical solution:

[0017] The power generation of solar streetlights is monitored using the aforementioned solar streetlight operation status monitoring method.

[0018] This application has the following technical effects:

[0019] By clustering streetlights according to environmental parameters (such as snow cover and particulate matter parameters), streetlights with similar environmental conditions can be grouped into the same cluster. This clustering method can more accurately reflect the actual operating environment of the streetlights, thus avoiding misjudgments caused by environmental differences. For example, in dusty or snow-covered areas, even if power generation is low, it may be considered normal and not incorrectly marked as abnormal.

[0020] It supports dual monitoring of individual and regional anomalies, comparing the outlier degree of power generation of a street light with that of other street lights in the cluster. If the outlier degree is high, the street light may be malfunctioning; in this case, the street light may be faulty. However, if all the street lights in the cluster are covered by dust or snow, there may be a situation where the outlier degree of power generation of a single street light is low, and in this case, all the street lights in the cluster may be experiencing power generation failure.

[0021] Traditional monitoring methods may rely solely on the power generation data of a single streetlight, making them susceptible to false alarms due to environmental factors. This application, however, combines intra-cluster and inter-cluster comparisons to provide a more comprehensive assessment of streetlight status, thereby effectively reducing the false alarm rate. Attached Figure Description

[0022] Figure 1 This is a flowchart of the method for monitoring the operating status of solar streetlights according to an embodiment of this application. Detailed Implementation

[0023] This application discloses a method for monitoring the operating status of solar streetlights, referring to... Figure 1 The process includes steps S1-S4, as detailed below:

[0024] S1: Based on the environmental parameters of the streetlights, multiple clusters are obtained by clustering the streetlights.

[0025] Clustering is the process of grouping streetlights according to their environmental parameters. By grouping streetlights with similar environmental conditions into the same cluster, the operational status of the streetlights can be assessed more accurately.

[0026] Environmental parameters are crucial factors affecting the power generation of solar streetlights. To achieve accurate clustering, this application selects environmental parameters closely related to the operating status of the streetlights. In one embodiment, environmental parameters include snow accumulation parameters and particulate matter parameters, with particulate matter parameters including particulate matter concentration, wind speed, humidity, and rainfall. Environmental parameters can also reflect the location information of the streetlights. When environmental parameters within a region are similar, it indicates that the streetlights in that region are under similar environmental conditions, thus suggesting that these streetlights have similar location information or geographical distribution characteristics.

[0027] The clustering algorithm is either DBSCAN or K-Means clustering. While the K-means algorithm requires pre-specifying the number of clusters, in practical applications, the exact number of clusters cannot be determined, resulting in lower accuracy. Therefore, this application prefers the DBSCAN clustering algorithm, which can automatically identify the number of clusters. The clustering process is existing technology and will not be described in detail here. After clustering, multiple clusters are obtained.

[0028] S2: Take any street light in the cluster as the target street light and calculate the outlier degree of the target street light's power generation; if the outlier degree is greater than a preset first threshold, generate monitoring signal one, otherwise generate monitoring signal two.

[0029] After clustering, each cluster contains several streetlights. To assess whether the operating status of a particular streetlight (target streetlight) is abnormal, it is necessary to calculate the degree of deviation of its power generation from the power generation of other streetlights in the cluster, i.e., the power generation outlier. If the power generation outlier of the target streetlight exceeds a preset first threshold, the streetlight is considered to be possibly faulty or abnormal, and monitoring signal one is generated. If the power generation outlier of the target streetlight is lower than or equal to the first threshold, the streetlight is considered to be operating normally, and monitoring signal two is generated.

[0030] In one embodiment, the outlier of power generation is defined as the deviation of the real-time power generation of the target streetlight from the real-time power generation of the streetlights within its cluster. Since streetlights within the same cluster have similar environmental conditions, their power generation can be considered to be similar. If the power generation of the target streetlight deviates significantly from the average of other streetlights within the cluster, it may indicate that the streetlight is abnormal.

[0031] Specifically, the expression for the outlier degree of power generation is: In the formula, L represents the outlier degree of the target street light's power generation, n represents the total number of street lights in the cluster to which the target street light belongs, and g i This represents the actual power generation of the target streetlight at time i. σ represents the average power generation of other streetlights in the cluster containing the target streetlight at time i, and σ represents the standard deviation of the power generation of other streetlights in the cluster containing the target streetlight. If the power generation is significantly out of the range, it indicates that the power generation of the target streetlight deviates significantly from the average value of other streetlights in the cluster, which may indicate an anomaly. Conversely, it indicates that the power generation of the target streetlight is close to that of other streetlights in the cluster, and its operation is normal.

[0032] Besides intra-cluster comparison methods, the outlier degree of a target street light can also be assessed by comparing its real-time power generation with its historical power generation. In one embodiment, the outlier degree can also be the degree of deviation between the target street light's real-time power generation and its historical power generation.

[0033] Specifically, the expression for the outlier degree of power generation is: In the formula, L represents the outlier degree of the target street light's power generation, n represents the total number of street lights in the cluster to which the target street light belongs, and g i Let σ represent the actual power generation of the target streetlight at time i, G represent the average historical power generation of the target streetlight, and σ represent the actual power generation of the target streetlight at time i. ′ L represents the standard deviation of the target street light's historical power generation, and norm represents the standard normalization function. A large L indicates that the target street light's real-time power generation deviates significantly from its historical level, potentially indicating an anomaly. Conversely, a small L indicates that the target street light's real-time power generation is close to its historical level, and its operation is normal.

[0034] Intra-cluster comparison is suitable for assessing the relative condition of the target streetlight compared to surrounding streetlights, effectively eliminating the influence of environmental factors. Comparison with historical data is suitable for assessing the long-term change trend of the target streetlight itself, and can identify equipment aging or other systemic problems.

[0035] For example, the first threshold is set to 0.8. The first threshold is used to determine whether the power generation of the target street light deviates significantly from the historical power generation levels of other street lights in its cluster or its own.

[0036] In practical applications, it is generally assumed that the power generation differences among streetlights within a cluster are small (low standard deviation). Therefore, when the power generation outlier of a particular streetlight exceeds 0.8, its deviation can be considered significant. This indicates that the target streetlight's power generation deviates from the average power generation of other streetlights within the cluster by more than 0.8 times the cluster's standard deviation. This deviation may indicate that the streetlight has obstructions, damage, or other problems.

[0037] Historical power generation reflects the power generation level of streetlights under normal operating conditions. If the current power generation deviates from the historical average by more than 0.8 times the standard deviation, it may indicate that the streetlight's performance has deteriorated or that it has been affected by external factors (such as snow cover or dust accumulation).

[0038] S3: Calculate the degree of change in power generation similarity between each cluster and its neighboring clusters; if the degree of change is greater than a preset second threshold, generate monitoring signal three, otherwise generate monitoring signal four.

[0039] After clustering, each cluster contains several streetlights with similar environmental conditions. To assess whether there are significant changes in power generation between different clusters, the degree of change in power generation similarity needs to be calculated. If the degree of change exceeds a preset second threshold, a significant difference in power generation between the two clusters is considered to have occurred, and monitoring signal three is generated. If the degree of change is less than or equal to the second threshold, the power generation change between the two clusters is considered to be within the normal range, and monitoring signal four is generated.

[0040] In one embodiment, the similarity of power generation is calculated as follows: for the average power generation sequence of each cluster, the normalized result of the cosine similarity of the corresponding power generation sequences of two clusters is used as the power generation similarity. Cosine similarity is a commonly used similarity metric that measures the cosine value of the angle between two vectors. The smaller the angle, the higher the similarity. Here, the average power generation sequences of two clusters are considered as two vectors, and the similarity of their power generation is evaluated by calculating their cosine similarity. Since the result of cosine similarity is usually in the range of [-1, 1], it needs to be normalized (e.g., mapped to the range of [0, 1]) for consistent comparison with other indicators.

[0041] In one embodiment, the formula for calculating the similarity of power generation is: Where S represents the similarity of power generation. Let i be the i-th value in the power generation sequence of the cluster-cluster center. S represents the i-th value in the power generation sequence of the two cluster centers. If S is large (close to 1), it indicates that the power generation sequences of the two clusters are highly similar. If S is small (close to 0), it indicates that the power generation sequences of the two clusters are significantly different.

[0042] The expression for the degree of change in the similarity of power generation is: Where D represents the degree of change in power generation similarity, S represents the historical power generation similarity sequence of the two clusters, max represents the maximum value function, min represents the minimum value function, and mean represents the average value function. If D is large, it indicates that the power generation similarity between the two clusters has changed significantly, possibly indicating a regional anomaly. Conversely, if the change in power generation similarity between the two clusters is small, the operating state is relatively stable.

[0043] The nearest-neighbor clustering method defines and delineates clusters based on the distance between cluster centers being less than a distance threshold. The cluster center represents the average characteristic of all streetlights within the cluster in the environmental parameter space. If the DBSCAN clustering algorithm is used, the cluster center can be the mean point of the environmental parameters of all streetlights within the cluster. If the K-Means clustering algorithm is used, the cluster center is the centroid generated during the algorithm's iterations. In smaller regions (such as a district or city), a smaller distance threshold (such as 0.1 or 0.2) can be chosen. In larger regions (such as multiple cities or provinces), a larger distance threshold (such as 0.5 or 1.0) can be chosen.

[0044] The second threshold is used to determine whether the change in power generation similarity between different clusters is significant. For example, the second threshold can be set to 0.2. If the second threshold is greater than 0.2, it indicates that the power generation similarity between the two clusters has changed significantly, possibly due to changes in environmental conditions (such as snowfall) leading to a general decrease in power generation across the entire region. Conversely, it indicates that the change in power generation similarity exceeds 20% of its average. This magnitude of change can typically reflect the occurrence of regional anomalies.

[0045] In practical applications, the specific values ​​of the first and second thresholds can be adjusted based on the following factors:

[0046] In areas with high dust or particulate matter concentrations, power generation fluctuates significantly, so the first threshold can be appropriately increased to reduce false alarms. In cold or snowy areas, power generation is greatly affected by snow cover, so the first threshold can also be appropriately increased. If the power generation distribution of streetlights within a cluster is relatively uniform (small standard deviation), the first threshold can be set lower; if the power generation distribution of streetlights within a cluster is relatively dispersed (large standard deviation), the first threshold needs to be set higher.

[0047] Within a smaller region (such as a district or a city), where environmental conditions are relatively uniform, the second threshold can be set lower. Within a larger region (such as multiple cities or provinces), where environmental conditions may vary significantly, the second threshold can be set higher.

[0048] S4: In response to monitoring signal 1 and monitoring signal 4, determine that the individual operating status of the target street light is abnormal; in response to monitoring signal 2 and monitoring signal 3, determine that the street lights in the corresponding area of ​​the cluster have regional abnormalities; in response to monitoring signal 1 and monitoring signal 3, determine that the street lights in the corresponding area of ​​the cluster have regional abnormalities and the individual operating status of the target street light is abnormal; otherwise, determine that the street light status is normal.

[0049] When monitoring signal one and monitoring signal four are triggered simultaneously, the system will determine that a specific street light (the target street light individual) is malfunctioning. The simultaneous appearance of these two signals may indicate a problem with the power supply system or the light source itself of this street light.

[0050] When monitoring signal two and monitoring signal three are triggered simultaneously, the system will determine that multiple streetlights in a certain area (cluster) are experiencing regional anomalies. The simultaneous occurrence of these two signals may indicate that the solar panels in that area are blocked (e.g., due to continuous rainy days or tree obstruction), the batteries are aging, or there are other regional problems.

[0051] When monitoring signal one and monitoring signal three are triggered simultaneously, the system will not only determine that a specific street light (the target street light) is malfunctioning, but also that there is a regional malfunction affecting all street lights in the area (cluster) to which that street light belongs. This situation may indicate that a battery problem in the area has caused some street lights (including the target street light) to malfunction, and that the target street light also has an additional individual fault.

[0052] If none of the above conditions occur, the system determines that all streetlights are functioning normally. The solar panels are generating electricity normally, the batteries are fully charged, the streetlight bulbs are working properly, and no abnormal signals are triggered.

[0053] This application also discloses a method for monitoring the power generation of a solar street light. The solar street light is equipped with an environmental parameter acquisition module for real-time collection of environmental data related to its operating status. These environmental parameters include, but are not limited to, snow accumulation parameters (such as temperature and snowfall) and particulate matter parameters (such as particulate matter concentration, wind speed, humidity, and rainfall). By collecting these parameters, the actual operating environment of the street light can be more accurately assessed, thus providing basic data support for subsequent cluster analysis and anomaly detection. The solar street light has a built-in power generation monitoring module that can record the power generation data of each street light in real time. Simultaneously, outlier analysis and similarity change analysis are performed on the power generation data using embedded algorithms or a cloud computing platform.

[0054] Solar streetlights utilize built-in intelligent algorithms (such as DBSCAN clustering or K-Means clustering) to divide the streetlights into multiple clusters based on environmental parameters. Streetlights within each cluster share similar environmental conditions and operating characteristics. Based on the clustering results, the streetlights can automatically determine their own operational status and generate corresponding monitoring signals.

[0055] Solar streetlights can upload monitoring data to a cloud platform via wireless communication modules (such as LoRa and NB-IoT) for remote monitoring and centralized management. Maintenance personnel can view the real-time operating status of each streetlight through the cloud platform and quickly locate problematic streetlights or areas based on monitoring signals. Furthermore, the system supports generating maintenance work orders to guide maintenance personnel in performing targeted repairs or cleaning.

[0056] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A method for monitoring the operating status of solar streetlights, characterized in that, Including the following steps: Multiple clusters were obtained by clustering the streetlights based on their environmental parameters. Take any street light in the cluster as the target street light and calculate the outlier degree of the target street light's power generation; if the outlier degree is greater than a preset first threshold, generate monitoring signal one, otherwise generate monitoring signal two. Calculate the degree of change in power generation similarity between each cluster and its neighboring clusters; if the degree of change is greater than a preset second threshold, generate monitoring signal three, otherwise generate monitoring signal four; In response to monitoring signal one and monitoring signal four, it is determined that the individual target street light is in an abnormal operating state. In response to monitoring signal two and monitoring signal three, it was determined that there was a regional anomaly in the streetlights in the area corresponding to the cluster; In response to monitoring signal one and monitoring signal three, it is determined that the streetlights in the corresponding area of ​​the cluster have regional anomalies and that the individual target streetlights are in abnormal operating status; otherwise, it is determined that the streetlights are in normal status. Outlier in power generation is the deviation of the real-time power generation of the target street light from the real-time power generation of the street lights in its cluster; or outlier in power generation is the deviation of the real-time power generation of the target street light from its historical power generation. The expression for the outlier degree of power generation is: In the formula, This indicates the degree of outlierness in the power generation of the target streetlight. This represents the total number of streetlights in the cluster containing the target streetlight. Indicates the target street light is Actual power generation at any given moment. This indicates that other streetlights in the cluster containing the target streetlight are... Average power generation at time of day This represents the standard deviation of the power generation of other streetlights in the cluster containing the target streetlight. Or the expression for the degree of outlier in power generation is: In the formula, This indicates the degree of outlierness in the power generation of the target streetlight. This represents the total number of streetlights in the cluster containing the target streetlight. Indicates the target street light is Actual power generation at any given moment. This represents the average historical power generation of the target streetlights. This represents the standard deviation of the historical power generation of the target streetlights. This represents the standard normalization function.

2. The method for monitoring the operating status of solar streetlights according to claim 1, characterized in that, Environmental parameters include: snow cover parameters and particulate matter parameters. Particulate matter parameters include particulate matter concentration, wind speed, humidity and rainfall. Snow cover parameters include temperature and snowfall.

3. The method for monitoring the operating status of solar streetlights according to claim 1, characterized in that, The method for calculating the power generation similarity is as follows: for the average power generation sequence of each cluster, the normalized result of the cosine similarity of the power generation sequences corresponding to the two clusters is used as the power generation similarity.

4. The method for monitoring the operating status of solar streetlights according to claim 1, characterized in that, The formula for calculating the similarity of power generation is: ;in, This indicates a similarity in power generation. The first in the power generation sequence of cluster-cluster center One value, The first in the power generation sequence of the binary cluster centers of the cluster Values.

5. The method for monitoring the operating status of solar streetlights according to claim 1, characterized in that, The expression for the degree of change in the similarity of power generation is: ;in, This indicates the degree of change in the similarity of power generation. This represents the similarity sequence of power generation at historical moments between two clusters. `max` represents the maximum value function, and `min` represents the minimum value function. This represents the average value function.

6. The method for monitoring the operating status of solar streetlights according to any one of claims 1-5, characterized in that, The clustering algorithm is either DBSCAN clustering or K-Means clustering.

7. A solar street light, characterized in that, The power generation is monitored using the solar street light operation status monitoring method according to any one of claims 1-6.

Images