A smart city lighting energy efficiency management system based on the Internet of Things

Abstract

The present application relates to the technical field of lighting energy efficiency management, and particularly relates to a smart city lighting energy efficiency management system based on Internet of Things, which comprises a data acquisition and analysis module, an intelligent control module, a fault detection and early warning module, an energy management module and a report and statistical analysis module; the data acquisition and analysis module collects environmental data and traffic flow data in real time through illumination sensors, temperature sensors, humidity sensors, people flow sensors and vehicle flow sensors arranged in various regions of the city; the present application can accurately predict lighting demand through multi-sensor data acquisition and complex algorithms, realize individualized brightness adjustment and energy saving, efficiently detect and early warn faults to ensure stable operation of the system, optimize energy management, realize efficient energy utilization by combining a genetic algorithm and LSTM prediction, and provide intuitive display and decision support through the report and statistical analysis module to realize efficient energy utilization and optimization of lighting effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of lighting energy efficiency management, and particularly relates to a smart city lighting energy efficiency management system based on Internet of Things. BACKGROUND

[0002] In today's rapidly developing urban environment, city lighting system plays a vital role. The traditional city lighting control method mainly relies on fixed time table for switching operation. However, this method has many obvious disadvantages.

[0003] On the one hand, the fixed time table cannot adapt to the dynamic changes of actual demand. The weather conditions of the city are complex and changeable, and there are significant differences in different seasons. Only relying on the fixed time table, it is impossible to make accurate adjustment according to the sunrise and sunset time, cloud thickness and other key information in the weather forecast. For example, in overcast or thick cloud, the actual light intensity may be much lower than that in sunny day, if the lighting is still controlled according to the fixed time table, it may cause insufficient lighting, which brings safety hazards to pedestrians and vehicles. And in the process of seasonal change, the change of daylight length also makes the irrationality of fixed time table more prominent, which may cause waste of energy or poor lighting effect.

[0004] On the other hand, the traditional method cannot respond to the changes of people flow and vehicle flow in different areas in time. The functions of each area in the city are different, and the demand for lighting in commercial area, residential area and industrial area is quite different. The fluctuation of people flow and vehicle flow directly affects the lighting demand. In the area with large people flow and vehicle flow, high lighting brightness is needed to ensure safety and convenience; while in the area with small people flow and vehicle flow, high lighting brightness not only wastes energy, but also may cause light pollution. However, the traditional fixed time table control cannot be flexibly adjusted according to these actual conditions, and it is difficult to realize the efficient use of energy and the optimization of lighting effect.

[0005] In summary, the traditional city lighting adopts the fixed time table control method, which has been difficult to meet the needs of modern city development. The present application proposes a smart city lighting energy efficiency management system based on Internet of Things. SUMMARY

[0006] The purpose of the present application is to solve the problem that the traditional city lighting adopts fixed time table for switching control, and cannot be flexibly adjusted according to actual demand, and proposes a smart city lighting energy efficiency management system based on Internet of Things.

[0007] The technical scheme of the present application: a smart city lighting energy efficiency management system based on Internet of Things, comprising:

[0008] The data acquisition and analysis module collects environmental data and traffic flow data in real time through light intensity sensors, temperature sensors, humidity sensors, people flow sensors and vehicle flow sensors deployed in various areas of the city, and the environmental data includes light intensity, temperature, humidity, people flow and vehicle flow. The collected data is analyzed and processed using weighted average algorithm and trend analysis algorithm to extract useful information, including sunrise and sunset time, cloud thickness, people flow and vehicle flow trend. According to the analysis result, the regression analysis algorithm is used to predict the lighting demand in different areas and at different times.

[0009] The intelligent control module automatically adjusts the lighting on and off time according to the prediction result of the data acquisition and analysis module, gradually adjusts the lighting brightness using linear adjustment algorithm according to the change of light intensity after sunrise and before sunset, dynamically adjusts the lighting brightness using dynamic adjustment algorithm according to the change of people flow and vehicle flow at night, increases the lighting brightness in areas with large people flow and vehicle flow, reduces the lighting brightness in areas with small people flow and vehicle flow, and temporarily turns off the lighting in areas without people and vehicles. At the same time, it supports remote control function, and the management personnel can manually control the intelligent lamps through the management platform or mobile application.

[0010] The fault detection and early warning module monitors the running state of the intelligent lamps in real time, including current, voltage and power parameters. When a lamp failure is detected, the fault determination algorithm is used to automatically issue a warning message, and the fault information is sent to the management platform and mobile application to notify the maintenance personnel for processing and positioning of the faulty lamps.

[0011] The energy management module analyzes the energy consumption of the city lighting system, including power consumption and power consumption time. According to the energy consumption data, the energy saving strategy optimization algorithm is used to develop energy saving strategies, including optimizing lighting on and off time and adjusting lighting brightness.

[0012] The report and statistical analysis module generates reports, including daily, monthly and annual reports, to show the operation and energy consumption of the city lighting system, and statistically analyzes the historical data to provide decision support for the management personnel.

[0013] Optionally, the weighted average algorithm formula in the data acquisition and analysis module is: comprehensive index value = Σ(index value x weight).

[0014] Wherein, the light intensity weight calculation formula is W1 = a x (1-e^(-b x light intensity change rate)), the people flow weight calculation formula is W2 = c x (1-e^(-d x people flow standard deviation)), and the vehicle flow weight calculation formula is W3 = e x (1-e^(-f x vehicle flow peak to valley ratio)).

[0015] a, b, c, d, e, f are adjustment coefficients, by continuously adjusting these coefficients to adapt to different urban environments and needs, each sensor data index value is given different weights according to the actual situation, to obtain a comprehensive environmental data evaluation result.

[0016] Optionally, in the data acquisition and analysis module, the trend analysis algorithm is: by performing difference calculation on the traffic flow and vehicle flow data in a period of time, if the difference result presents an upward trend, it is judged that the traffic flow and vehicle flow have an increasing trend, otherwise it is a decreasing trend, and a self-regression integral sliding average model is further introduced to predict the long-term trend of the traffic flow and vehicle flow, the formula is:

[0017] ;

[0018] Where Yt is the current traffic flow or vehicle flow, μ is a constant term, , etc. are autoregressive coefficients, , etc. are sliding average coefficients, εt is an error term, and p and q are model parameters. The model parameters are determined by fitting historical data to more accurately predict the trend of traffic flow and vehicle flow.

[0019] Optionally, the regression analysis algorithm uses a multiple linear regression model:

[0020] Lighting demand = α + β1 x illumination + β2 x traffic flow + β3 x vehicle flow + β4 x seasonal factor + β5 x weather factor + ε;

[0021] Where α is a constant term, β1, β2, β3, etc. are regression coefficients, and ε is an error term. The seasonal factor is simulated by a sine function, the formula is , where A is the amplitude, ω is the angular frequency, t is the time (in seasons), is the phase;

[0022] The weather factor is quantified by fuzzy logic, and a value between 0 and 1 is obtained by comprehensive evaluation of cloud thickness, precipitation probability and other factors, representing the degree of influence of weather on lighting demand.

[0023] Optionally, in the intelligent control module, the linear adjustment algorithm is:

[0024] Lighting brightness = initial brightness x (1 - current illumination ÷ maximum illumination) x g^(-h x illumination change speed);

[0025] Where g and h are adjustment coefficients, gradually adjusting the lighting brightness as the illumination changes, while considering the influence of illumination change speed on lighting brightness adjustment. The faster the change speed, the relatively smaller the adjustment amplitude, to avoid frequent and large changes in brightness.

[0026] Optionally, the dynamic adjustment algorithm in the intelligent control module is:

[0027] illumination brightness = basic brightness + delta brightness;

[0028] wherein delta brightness = k x people flow ^ m x vehicle flow ^ n, k, m, n are adjustment coefficients, the greater the people flow and vehicle flow, the greater the delta brightness, and the adjustment coefficients are used to adapt to the traffic flow characteristics of different areas.

[0029] Optionally, in the fault detection and early warning module, the fault determination algorithm is: when the current, voltage and power parameters of the lamp exceed the normal range [lower limit value, upper limit value], it is determined that the lamp has a fault, and a principal component analysis algorithm is further introduced to reduce the dimension of the lamp operation state data.

[0030] Optionally, in the energy management module, the energy saving strategy optimization algorithm is: taking the minimization of energy consumption as the objective function, the objective function formula is Minimize E = Σ(Pi x ti), wherein E is the total energy consumption, Pi is the power of the i-th lamp, ti is the opening time of the i-th lamp, and the lighting demand and renewable energy supply are combined as constraint conditions, and the genetic algorithm is used to solve the optimal lighting opening and closing time and lighting brightness adjustment scheme; in the genetic algorithm, the chromosome is represented as a set of lighting control parameters, and the chromosome is continuously optimized through selection, crossover and mutation operations to find the optimal solution that meets the objective function and constraint conditions.

[0031] Optionally, the report and statistical analysis module includes a data mining unit, which performs in-depth analysis on historical data, uses an association rule algorithm to mine potential associations between different environmental factors and lighting demand, uses an Apriori algorithm, sets the minimum support as min sup and the minimum confidence as min conf, and finds out frequent item sets by continuously scanning the data set, and then generates strong association rules to provide more accurate decision basis for lighting energy efficiency management, which is expressed by the formula:

[0032] If the frequency of item set X in the data set is greater than or equal to min sup, then X is a frequent item set; if the confidence of rule X→Y Conf(X→Y) = P(Y|X) is greater than or equal to min_conf, then X→Y is a strong association rule, wherein P(Y|X) represents the probability of Y appearing under the condition that X appears.

[0033] Optionally, the energy management module combines long short-term memory network (LSTM) in deep learning to predict future energy demand, and the input sequence is X=(x1, x2,..., xt), wherein xt represents a feature vector at t time, including power consumption, illumination, and passenger flow; the LSTM unit updates cell state Ct and hidden state ht through forget gate, input gate and output gate;

[0034] The forget gate ft decides to discard the filtered information from the cell state ;

[0035] The input gate it decides which new information is stored in the cell state ,

[0036] The candidate cell state The cell state Ct=ftC t-1 +itCt~;

[0037] The output gate ot decides to output the filtered information, The hidden state ht=ot*tanh(Ct). By training the LSTM network, the future energy demand is predicted to better develop energy-saving strategies, wherein sigma is a sigmoid function, Wi, Wc and Wo are weight matrices, bi, bc and bo are bias terms.

[0038] Compared with the prior art, the present application has at least one of the following beneficial technical effects:

[0039] The present application precisely regulates lighting demand, collects a large amount of data through various sensors, and analyzes and processes the data using complex algorithms to accurately predict lighting demand in different areas and at different times. For example, the lighting on and off time and brightness are automatically adjusted according to weather conditions, seasonal changes, passenger flow, vehicle flow and other factors, which maximizes energy saving while ensuring lighting effect.

[0040] At the same time, individual adjustments are made according to the characteristics of different areas, the lighting brightness is increased in areas with large passenger flow and vehicle flow to ensure safety and convenience, the lighting brightness is reduced in areas with small passenger flow and vehicle flow to reduce energy waste and light pollution, and the lighting is temporarily turned off in areas without people and vehicles to further improve energy utilization efficiency.

[0041] Further, efficient fault detection and early warning technology is used to monitor the running state of intelligent lamps in real time, which can timely discover faults and automatically send warning information to notify maintenance personnel for processing. At the same time, the faulty lamps are located to facilitate maintenance personnel to quickly find the fault point, improve the maintenance efficiency, and ensure the stable operation of the urban lighting system.

[0042] Further optimize energy management, statistically analyze the energy consumption of the urban lighting system, use energy-saving strategy optimization algorithm to develop a reasonable energy-saving strategy, combine renewable energy supply, and realize the optimized use of energy. The optimal lighting on and off time and lighting brightness adjustment scheme are solved by a genetic algorithm, with the goal of minimizing energy consumption and reducing the energy cost of the urban lighting system.

[0043] In addition, the future energy demand is predicted using a long short-term memory network (LSTM), which can help develop energy-saving strategies in advance and better cope with changes in energy demand.

[0044] The report and statistical analysis module generates various reports to show the operation and energy consumption of the urban lighting system, providing intuitive data display for managers. At the same time, historical data are statistically analyzed and data-mined to mine the potential correlation between different environmental factors and lighting demand, providing more accurate decision support for managers and helping to optimize the layout and management of the urban lighting system.

[0045] In summary, the present application uses multiple sensors to collect data and complex algorithms to accurately predict lighting demand, achieve personalized brightness adjustment and energy saving, efficiently detect and warn of faults to ensure stable system operation, optimize energy management, and use genetic algorithms and LSTM prediction to achieve efficient energy use, and the report and statistical analysis module provides intuitive display and decision support. This system comprehensively improves the energy efficiency of urban lighting, reduces costs, helps sustainable urban development, and achieves efficient energy use and optimal lighting effects. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 A block diagram of a smart city lighting energy efficiency management system based on the Internet of Things. DETAILED DESCRIPTION

[0047] To make the purpose, technical solutions, and advantages of the present application clearer, the following will further describe the embodiments of the present application in conjunction with the drawings.

[0048] Embodiment:

[0049] As shown in Figure 1 The present application proposes a smart city lighting energy efficiency management system based on the Internet of Things, which includes a data collection and analysis module, an intelligent control module, a fault detection and warning module, an energy management module, and a report and statistical analysis module. Each module is described in detail below.

[0050] 1. Data collection and analysis module

[0051] The light intensity sensor, temperature sensor, humidity sensor, people flow sensor and vehicle flow sensor are deployed in various regions of the city to collect environmental data and traffic flow data in real time, including light intensity, temperature, humidity, people flow and vehicle flow.

[0052] The collected data is analyzed and processed using a weighted average algorithm, with the formula being Comprehensive Index Value = Σ(Index Value x Weight). The light intensity weight calculation formula is W1 = a x (1 - e^(-b x Light Intensity Change Rate), the people flow weight calculation formula is W2 = c x (1 - e^(-d x People Flow Standard Deviation), and the vehicle flow weight calculation formula is W3 = e x (1 - e^(-f x Vehicle Flow Peak Valley Ratio). By continuously adjusting the adjustment coefficients a, b, c, d, e and f to adapt to different urban environments and needs, and assigning different weights to each sensor data index value according to actual conditions, a comprehensive environmental data evaluation result is obtained.

[0053] A trend analysis algorithm is used to determine the trend by differentiating people flow and vehicle flow data over a period of time. If the difference result shows an upward trend, it is determined that people flow and vehicle flow have an increasing trend, and vice versa. A self-regression integral moving average model is further introduced to predict the long-term trend of people flow and vehicle flow, with the formula being . where Yt is the current time people flow or vehicle flow, μ is the constant term, are the self-regression coefficients, are the moving average coefficients, εt is the error term, and p and q are model parameters determined by fitting historical data to more accurately predict the trend of people flow and vehicle flow.

[0054] Useful information is extracted, including sunrise and sunset times, cloud thickness, people flow and vehicle flow trends. Based on the analysis results, a multiple linear regression model is used to predict lighting needs in different regions and at different times, with the formula being Lighting Needs = α + β1 x Light Intensity + β2 x People Flow + β3 x Vehicle Flow + β4 x Seasonal Factor + β5 x Weather Factor + ε. Where α is the constant term, β1, β2, β3, etc. are regression coefficients, and ε is the error term. The seasonal factor is simulated using a sine function, with the formula being where A is the amplitude, ω is the angular frequency, t is the time (in seasons), is the phase; the weather factor is quantified by fuzzy logic, with a comprehensive evaluation of cloud thickness, precipitation probability and other factors to obtain a value between 0 and 1, representing the degree of weather influence on lighting needs.

[0055] 2. Intelligent control module

[0056] According to the prediction results of the data acquisition and analysis module, the lighting on and off time is automatically adjusted. According to the change of illumination before sunrise and after sunset, the lighting brightness is gradually adjusted using linear adjustment algorithm, lighting brightness = initial brightness × (1 - current illumination ÷ maximum illumination) × g^(-h × illumination change speed). Wherein, g and h are adjustment coefficients, gradually adjust the lighting brightness with the change of illumination, at the same time consider the influence of illumination change speed on lighting brightness adjustment, the faster the change speed, the relatively reduced adjustment amplitude, to avoid frequent and large changes in brightness.

[0057] At night, according to the change of passenger flow and vehicle flow, the lighting brightness is dynamically adjusted using dynamic adjustment algorithm, lighting brightness = basic brightness + Δ brightness, where Δ brightness = k × passenger flow ^ m × vehicle flow ^ n, k, m, n are adjustment coefficients, the larger the passenger flow and vehicle flow, the larger the Δ brightness, through the adjustment coefficient to adapt to the traffic flow characteristics of different areas. Increase the lighting brightness in the area with large passenger flow and vehicle flow, reduce the lighting brightness in the area with small passenger flow and vehicle flow, and temporarily turn off the lighting in the area without people and vehicles.

[0058] Support remote control function, management personnel can manually control intelligent lamps through management platform or mobile application.

[0059] Through a variety of sensors to collect a large amount of data, and use complex algorithm for analysis and processing, can accurately predict the lighting demand of different areas and different time. For example, according to the weather conditions, seasonal changes, passenger flow, vehicle flow and other factors to automatically adjust the lighting on and off time and brightness, while ensuring the lighting effect, maximize energy saving. According to the characteristics of different areas, individual adjustment is made, the lighting brightness is increased in the area with large passenger flow and vehicle flow, to ensure safety and convenience; reduce the lighting brightness in the area with small passenger flow and vehicle flow, to reduce energy waste and light pollution; temporarily turn off the lighting in the area without people and vehicles, to further improve the energy utilization efficiency.

[0060] 3. Fault detection and early warning module

[0061] Real-time monitoring of the running state of intelligent lamps, including current, voltage, power and other parameters. When a lamp failure is detected, a fault determination algorithm is used to automatically send a warning message and send the fault information to the management platform and mobile application, notifying maintenance personnel to handle the fault lamp. The fault determination algorithm is: when the current, voltage, power and other parameters of the lamp exceed the normal range [lower limit value, upper limit value], it is determined that the lamp has a fault. Further introduce principal component analysis algorithm to reduce the dimension of the lamp running state data. Real-time monitoring of the running state of intelligent lamps can timely detect faults and automatically send warning messages to notify maintenance personnel to handle the fault. At the same time, the fault lamp is located, making it easy for maintenance personnel to quickly find the fault point, improving maintenance efficiency and ensuring the stable operation of the city lighting system.

[0062] 4. Energy management module

[0063] Statistical analysis of the energy consumption of the city lighting system, including power consumption and power consumption time. According to the energy consumption data, an energy-saving strategy optimization algorithm is used to develop an energy-saving strategy, including optimizing lighting on and off times, adjusting lighting brightness, etc. The energy-saving strategy optimization algorithm is: the objective function is to minimize energy consumption E =Σ(Pi×ti), where E is the total energy consumption, Pi is the power of the i-th lamp, and ti is the on time of the i-th lamp. Combined with lighting demand and renewable energy supply as a constraint condition, the optimal lighting on and off time and lighting brightness adjustment scheme is solved by genetic algorithm. In the genetic algorithm, the chromosome is represented as a set of lighting control parameters, and the chromosome is continuously optimized through selection, crossover and mutation operations to find the optimal solution that meets the objective function and constraint conditions. Statistical analysis of the energy consumption of the city lighting system, use of the energy-saving strategy optimization algorithm to develop a reasonable energy-saving strategy, combined with renewable energy supply, to achieve optimal use of energy. Through genetic algorithm to solve the optimal lighting on and off time and lighting brightness adjustment scheme, with the goal of minimizing energy consumption, to reduce the energy cost of the city lighting system.

[0064] Combined with the long short-term memory network (LSTM) in deep learning to predict future energy demand. Let the input sequence be X=(x1,x2,...,xt), where xt represents the feature vector at time t, including power consumption, illumination, and traffic flow. The LSTM unit updates the cell state Ct and the hidden state ht through the forget gate, the input gate and the output gate. The forget gate ft decides to discard the filtered information from the cell state, The input gate it decides which new information is stored in the cell state, The candidate cell state The cell state The output gate ot determines whether the filtered information is output, , hidden state where σ is the sigmoid function, Wi, Wc, Wo are weight matrices, bi, bc, bo are bias terms. By training the LSTM network, the future energy demand is predicted to better formulate energy-saving strategies. Using long short-term memory network (LSTM) to predict future energy demand can formulate energy-saving strategies in advance and better cope with changes in energy demand.

[0065] 5. Report and statistical analysis module

[0066] Daily, monthly, and annual reports are generated to show the operation and energy consumption of the city lighting system.

[0067] Statistical analysis of historical data is performed to provide decision support for managers. Set up data mining unit, deep analysis of historical data, use association rule algorithm to mine the potential association between different environmental factors and lighting demand, use Apriori algorithm, set the minimum support min_sup, the minimum confidence min_conf, through constantly scanning the data set to find out the frequent item set, and then generate strong association rules, provide more accurate decision basis for lighting energy efficiency management. The formula is expressed as: if the frequency of item set X in the data set is greater than or equal to min_sup, then X is a frequent item set; if the confidence of rule X→Y Conf (X→Y)=P (Y|X) is greater than or equal to min_conf, then X→Y is a strong association rule, where P (Y|X) represents the probability of Y appearing under the condition that X appears. The report and statistical analysis module generates various reports to show the operation and energy consumption of the city lighting system, providing managers with intuitive data display. At the same time, statistical analysis and data mining of historical data are performed to mine the potential association between different environmental factors and lighting demand, providing managers with more accurate decision support, which helps to optimize the layout and management of the city lighting system.

[0068] The above specific embodiments are only a few optional embodiments of the present application, based on the technical solutions of the present application and the related inspiration of the above embodiments, those skilled in the art can make various alternative improvements and combinations to the above specific embodiments.

Claims

1. An Internet of Things based smart city lighting energy efficiency management system, characterized in that, Comprise: Data acquisition and analysis module, through the deployment of light intensity sensor, temperature sensor, humidity sensor, passenger flow sensor, traffic flow sensor in various areas of the city, real-time collection of environmental data and traffic flow data, environmental data including light intensity, temperature, humidity, passenger flow, traffic flow; and the collected data using weighted average algorithm and trend analysis algorithm for analysis and processing, extracting useful information, including sunrise and sunset time, cloud thickness, passenger flow and traffic flow trend; according to the analysis results, using regression analysis algorithm to predict the lighting demand in different areas and different times; Intelligent control module, according to the prediction results of data acquisition and analysis module, automatically adjust the lighting on and off time, according to the change of light intensity after sunrise and before sunset, using linear adjustment algorithm to gradually adjust the lighting brightness, according to the change of passenger flow and traffic flow at night, using dynamic adjustment algorithm to dynamically adjust the lighting brightness, increasing the lighting brightness in areas with large passenger flow and traffic flow, reducing the lighting brightness in areas with small passenger flow and traffic flow, temporarily turning off the lighting in areas without people and vehicles, while supporting remote control function, management personnel manually control the intelligent lamps through management platform or mobile application; Fault detection and early warning module, real-time monitoring of the running state of intelligent lamps, including current, voltage, power parameters, when detecting lamp failure, using fault judgment algorithm to automatically send warning information, and sending fault information to management platform and mobile application, notifying maintenance personnel to handle, positioning the fault lamps; Energy management module, statistical analysis of the energy consumption of urban lighting system, including power consumption, power consumption time, according to the energy consumption data, using energy saving strategy optimization algorithm to develop energy saving strategy, including optimizing lighting on and off time, adjusting lighting brightness; Report and statistical analysis module, generate report, report including daily report, monthly report, annual report, show the running condition and energy consumption of urban lighting system, statistical analysis of historical data, provide decision support for management personnel; The energy management module, the energy saving strategy optimization algorithm is: with the minimum energy consumption as the objective function, the objective function formula is Wherein E is total energy consumption, Pi is the power of the i th lamp, ti is the opening time of the i th lamp, combining the lighting demand, renewable energy supply as constraint condition, through genetic algorithm to solve the optimal lighting opening and closing time, lighting brightness adjustment scheme; The energy management module combines long short-term memory network in deep learning to predict future energy demand, the input sequence is X=(x1,x2,...,xt), where xt represents the feature vector at time t, including power consumption, light intensity, passenger flow, LSTM unit updates cell state Ct and hidden state ht through forget gate, input gate and output gate; The forget gate ft decides which information to filter out from the cell state ; The input gate it determines that the screening information is stored into the cell state , Candidate cell states , cell states ; The output gate ot decides whether the screening information is output, , hidden state ; wherein, sigmoid function, Wi, Wc, Wo are weight matrices, bi, bc, bo are bias terms.

2. The smart city lighting energy efficiency management system based on the Internet of Things according to claim 1, characterized in that, The weighted average algorithm formula in the data acquisition and analysis module is: comprehensive index value ; Wherein, the light intensity weight calculation formula is W1=a×(1-e^(-b×light intensity change rate)), the passenger flow weight calculation formula is W2=c×(1-e^(-d×passenger flow standard deviation)), the traffic flow weight calculation formula is W3=e×(1-e^(-f×traffic flow peak valley ratio)); a, b, c, d, e, f are adjustment coefficients, by continuously adjusting these coefficients to adapt to different city environment and demand, each sensor data index value is given different weight according to actual situation, to obtain comprehensive environmental data evaluation results.

3. The smart city lighting energy efficiency management system based on the Internet of Things according to claim 1, characterized in that, The trend analysis algorithm in the data collection and analysis module is: through differential calculation on the people flow and vehicle flow data in a period of time, if the differential result shows an upward trend, it is judged that the people flow and vehicle flow have an increasing trend, otherwise, it is a decreasing trend, and a self-regression integral sliding average model is further introduced to predict the long-term trend of the people flow and vehicle flow, and the formula is: ； where Yt is the current time of people flow or traffic flow, is a constant term, is an autoregressive coefficient, is a moving average coefficient, is an error term, and p and q are model parameters determined by fitting historical data to more accurately predict the trend of people flow and traffic flow.

4. The smart city lighting energy efficiency management system based on the Internet of Things according to claim 1, characterized in that, The regression analysis algorithm adopts a multiple linear regression model: Lighting demand = α + β1×illuminance + β2×people flow + β3×vehicle flow + β4×seasonal factor + β5×weather factor + ε; where a is a constant term, β1, β2, β3, β4, β5 are regression coefficients, and ε is an error term. The seasonal factor is simulated by a sine function, and the formula is where A is the amplitude, is the angular frequency, and t is the time in seasons, is the phase; The weather factor is quantified through fuzzy logic, and a value between 0 and 1 is obtained through comprehensive evaluation of multiple factors such as cloud thickness and precipitation probability, representing the degree of influence of weather on lighting demand.

5. The smart city lighting energy efficiency management system based on the Internet of Things according to claim 1, characterized in that, In the intelligent control module, the linear adjustment algorithm is: Lighting brightness = initial brightness × (1-current illuminance ÷ maximum illuminance) × g^(-h×illuminance change speed); Wherein, g and h are adjustment coefficients, gradually adjusting the lighting brightness with the change of illuminance, and considering the influence of illuminance change speed on lighting brightness adjustment, the faster the change speed, the relatively smaller the adjustment amplitude.

6. The smart city lighting energy efficiency management system based on the Internet of Things according to claim 1, characterized in that, The dynamic adjustment algorithm in the intelligent control module is: Lighting brightness = basic brightness + Δbrightness; Wherein, Δbrightness = k×people flow^m×vehicle flow^n, k, m, n are adjustment coefficients, and the larger the people flow and vehicle flow, the larger the Δbrightness. 7.The smart city lighting energy efficiency management system based on Internet of Things according to claim 1, wherein, In the fault detection and early warning module, the fault determination algorithm is: when the current, voltage and power parameters of the lamp exceed the normal range [lower limit value, upper limit value], it is judged that the lamp has a fault, and a principal component analysis algorithm is further introduced to reduce the dimension of the lamp operation state data. 8.The smart city lighting energy efficiency management system based on Internet of Things according to claim 1, wherein, The report and statistical analysis module includes a data mining unit, which deeply analyzes historical data, uses an association rule algorithm to mine potential associations between different environmental factors and lighting demand, uses an Apriori algorithm, sets the minimum support min_sup and the minimum confidence min_conf, and finds out frequent item sets by continuously scanning the data set, and then generates strong association rules, providing more accurate decision basis for lighting energy efficiency management, and the formula is expressed as: If the frequency of item set X in the data set is greater than or equal to min_sup, X is a frequent item set; if the confidence of rule X→Y Conf(X→Y)=P(Y|X) is greater than or equal to min_conf, X→Y is a strong association rule, wherein P(Y|X) represents the probability of Y appearing under the condition that X appears.

Images