Energy Efficiency Management Method and System for Smart Street Lights

Abstract

The present invention provides an energy efficiency management method and system for intelligent street lights. The method includes: collecting the operating environment data, historical operating data, and real-time battery status data of the intelligent street lights, and respectively obtaining the lighting demand prediction result and the energy consumption prediction result based on predictive analysis. According to these prediction results and the battery status data, calculate the charge and discharge parameters of the battery and the deep discharge limit, and generate a battery management strategy. Combining with the virtual energy pool data of the street light network where the intelligent street lights are located, perform priority energy allocation according to the battery management strategy and the lighting demand prediction result to generate a dynamic energy allocation plan. On this basis, execute energy management and real-time monitor the energy consumption data of the intelligent street lights, and dynamically adjust the battery management strategy and the energy allocation plan according to the monitoring results. The present invention can efficiently allocate energy in a complex environment, achieve global optimization of the street light network, extend the battery life, and improve the energy management efficiency of the intelligent street lights.

Description

Technical Field

[0001] The present invention relates to the technical field of energy efficiency management, and particularly to an energy efficiency management method and system for intelligent street lights. Background Art

[0002] As an important part of the construction of smart cities, intelligent street lights not only have basic lighting functions, but also integrate various intelligent functions such as monitoring, communication, and environmental monitoring, providing comprehensive services for urban operation. In practical applications, intelligent street lights usually rely on battery power supply and cooperate with a virtual energy pool in the street light network to achieve efficient energy management. However, due to the wide distribution range and complex usage environment of street lights, their energy utilization and management have always been the key to the optimization of intelligent street light systems. Especially in scenarios of extreme weather or peak lighting demand, the energy management efficiency of street lights directly affects the stable operation of the street light network and the service life of equipment.

[0003] Currently, traditional energy efficiency management methods for intelligent street lights usually adopt fixed lighting strategies and single battery management methods. This method lacks in-depth analysis of operating environment data, historical operating data, and real-time battery status, and cannot accurately predict lighting demand and energy consumption changes. Summary of the Invention

[0004] The main objective of the present invention is to solve the technical problem in the energy efficiency management method of intelligent street lights that there is a lack of in-depth analysis of the operating environment and historical data, and it is impossible to make dynamic adjustments according to lighting demand, energy consumption changes, and battery status;

[0005] The first aspect of the present invention provides an energy efficiency management method for intelligent street lights, and the energy efficiency management method for intelligent street lights includes:

[0006] Collect the operating environment data, historical operating data of the intelligent street lights, and the real-time status data of the battery corresponding to the intelligent street lights, and perform predictive analysis based on the operating environment data and historical operating data to obtain a lighting demand prediction result and an energy consumption prediction result respectively;

[0007] Based on the lighting demand prediction result, the energy consumption prediction result, and the real-time status data of the battery, calculate the battery charge and discharge parameters and the deep discharge limit of the battery, and generate a battery management strategy based on the battery charge and discharge parameters and the deep discharge limit;

[0008] Obtain the virtual energy pool data of the virtual energy pool preset in the street light network where the intelligent street lights are located, and perform priority energy allocation based on the virtual energy pool data, the battery management strategy, and the lighting demand prediction result to obtain a dynamic energy allocation plan within the street light network;

[0009] Execute energy management for the intelligent street lights based on the dynamic energy allocation scheme, monitor the energy consumption data of the intelligent street lights in real time, and dynamically adjust the battery management strategy and the dynamic energy allocation scheme according to the energy consumption data to optimize the energy usage efficiency of the intelligent street lights.

[0010] Optionally, in the first implementation manner of the first aspect of the present invention, the operating environment data includes a light intensity data set, an activity detection data set, and a weather condition data set;

[0011] Collect the operating environment data and historical operating data of the intelligent street lights, and perform predictive analysis based on the operating environment data and historical operating data to obtain a lighting demand prediction result and an energy consumption prediction result respectively, including:

[0012] Perform time series decomposition on the historical operating data to obtain a lighting demand trend component, a lighting demand seasonal component, and a lighting demand random component, and input the light intensity data set and the activity detection data set into a preset multi-factor regression model for lighting demand to obtain a preliminary lighting demand prediction value;

[0013] Perform weighted fusion operation on the preliminary lighting demand prediction value, the lighting demand trend component, and the lighting demand seasonal component to obtain a corrected lighting demand prediction value, and input the corrected lighting demand prediction value and the lighting demand random component into a preset combined prediction algorithm to obtain a lighting demand prediction result;

[0014] Input the lighting demand prediction result and the weather condition data set into a preset energy consumption estimation neural network to obtain a preliminary energy consumption prediction value, and perform time series decomposition on the energy consumption data in the historical operating data to obtain an energy consumption trend component, an energy consumption seasonal component, and an energy consumption random component;

[0015] Perform weighted fusion operation on the preliminary energy consumption prediction value, the energy consumption trend component, and the energy consumption seasonal component to obtain a corrected energy consumption prediction value, and input the corrected energy consumption prediction value and the energy consumption random component into a preset combined prediction algorithm to obtain an energy consumption prediction result.

[0016] Optionally, in the second implementation manner of the first aspect of the present invention, calculating the battery charge and discharge parameters and the deep discharge limit of the battery based on the lighting demand prediction result, the energy consumption prediction result, and the real-time state data of the battery, and generating a battery management strategy based on the battery charge and discharge parameters and the deep discharge limit includes:

[0017] Divide the lighting demand prediction result and the energy consumption prediction result into time periods to obtain peak demand periods and low demand periods;

[0018] Based on the real-time status data of the battery, establish a battery health state assessment model to obtain an estimated remaining battery life;

[0019] Based on the peak demand period, valley demand period, and the estimated remaining battery life, calculate the optimal charge and discharge rates and charge and discharge time windows to obtain battery charge and discharge parameters;

[0020] According to the battery charge and discharge parameters and the estimated remaining battery life, set a dynamic deep discharge limit threshold to obtain a deep discharge limit;

[0021] Input the battery charge and discharge parameters and the deep discharge limit into a preset battery management algorithm to generate a battery management strategy including charge and discharge strategies, balanced charging strategies, and temperature control strategies.

[0022] Optionally, in the third implementation manner of the first aspect of the present invention, the setting a dynamic deep discharge limit threshold according to the battery charge and discharge parameters and the estimated remaining battery life to obtain a deep discharge limit includes:

[0023] Perform normalization processing on the estimated remaining battery life to obtain a life impact factor, and calculate a battery stress coefficient according to the charge and discharge rate in the battery charge and discharge parameters to obtain a stress impact factor;

[0024] Input the life impact factor and the stress impact factor into a preset fuzzy logic controller to obtain an initial deep discharge limit value;

[0025] Use an adaptive adjustment algorithm to correct the initial deep discharge limit value according to historical deep discharge data to obtain a corrected deep discharge limit value;

[0026] Compare the corrected deep discharge limit value with a preset safety threshold, and select the smaller value between the corrected deep discharge limit value and the preset safety threshold as the deep discharge limit.

[0027] Optionally, in the fourth implementation manner of the first aspect of the present invention, before obtaining the virtual energy pool data of the virtual energy pool preset in the street lamp network where the smart street lamp is located, and performing priority energy allocation based on the virtual energy pool data, the battery management strategy, and the lighting demand prediction result to obtain a dynamic energy allocation plan within the street lamp network, it further includes:

[0028] Collect the power generation capacity data, energy storage capacity data, and real-time energy status data of each smart street lamp in the street lamp network, and perform normalization processing on the power generation capacity data and the energy storage capacity data to obtain a standardized energy resource assessment result;

[0029] Calculate the relative energy levels of each smart street lamp based on the standardized energy resource assessment results and the real-time energy status data, obtain a network energy distribution map, and divide the surplus and shortage areas of the street lamp network according to the network energy distribution map to obtain a regional division result;

[0030] Based on the regional division result, generate an energy allocation strategy within the street lamp network and an energy exchange strategy with the smart grid, and integrate the energy allocation strategy and the energy exchange strategy to obtain a virtual energy pool.

[0031] Optionally, in the fifth implementation manner of the first aspect of the present invention, the obtaining the virtual energy pool data of the virtual energy pool preset for the street lamp network where the smart street lamp is located, and performing priority energy allocation based on the virtual energy pool data, the battery management strategy, and the lighting demand prediction result to obtain a dynamic energy allocation plan within the street lamp network includes:

[0032] Obtain the virtual energy pool data of the virtual energy pool preset for the street lamp network where the smart street lamp is located, and input the virtual energy pool data, the battery management strategy, and the lighting demand prediction result into a multi-objective optimization algorithm to obtain a preliminary energy allocation plan;

[0033] According to the preliminary energy allocation plan, execute a network load balancing algorithm to obtain an energy allocation plan after load balancing;

[0034] Apply an emergency response strategy to the energy allocation plan after load balancing, set an energy reserve threshold, and obtain an energy allocation plan with emergency response capabilities;

[0035] Combine the energy allocation plan with emergency response capabilities with the real-time data of the smart grid, execute a dynamic adjustment algorithm, and obtain a dynamic energy allocation plan.

[0036] Optionally, in the sixth implementation manner of the first aspect of the present invention, the performing energy management of the smart street lamp based on the dynamic energy allocation plan, real-time monitoring the energy consumption data of the smart street lamp, and dynamically adjusting the battery management strategy and the dynamic energy allocation plan according to the energy consumption data to optimize the energy use efficiency of the smart street lamp includes:

[0037] According to the dynamic energy allocation plan, execute individual energy control instructions for each smart street lamp and collect energy consumption data in real time;

[0038] Compare the energy consumption data with a preset energy efficiency benchmark, calculate an energy efficiency deviation value, and execute an adaptive PID control algorithm according to the energy efficiency deviation value to obtain an adjustment parameter of the battery management strategy;

[0039] Apply the adjustment parameters to the battery management strategy to generate an updated battery management strategy;

[0040] Based on the updated battery management strategy and the energy consumption data, re - execute the virtual energy pool optimization algorithm to obtain an optimized dynamic energy allocation plan.

[0041] A second aspect of the present invention provides an energy efficiency management system for smart street lights. The energy efficiency management system for smart street lights includes:

[0042] A prediction module, configured to collect the operating environment data, historical operating data of the smart street lights, and the real - time status data of the battery corresponding to the smart street lights, and perform predictive analysis based on the operating environment data and the historical operating data to obtain a lighting demand prediction result and an energy consumption prediction result respectively;

[0043] A strategy generation module, configured to calculate the battery charge - discharge parameters and the deep - discharge limit of the battery based on the lighting demand prediction result, the energy consumption prediction result, and the real - time status data of the battery, and generate a battery management strategy based on the battery charge - discharge parameters and the deep - discharge limit;

[0044] A deployment module, configured to obtain the virtual energy pool data of the virtual energy pool preset in the street light network where the smart street lights are located, and perform priority energy allocation based on the virtual energy pool data, the battery management strategy, and the lighting demand prediction result to obtain a dynamic energy allocation plan within the street light network;

[0045] An optimization module, configured to perform energy management of the smart street lights based on the dynamic energy allocation plan, monitor the energy consumption data of the smart street lights in real - time, and dynamically adjust the battery management strategy and the dynamic energy allocation plan according to the energy consumption data to optimize the energy use efficiency of the smart street lights.

[0046] The above - mentioned energy efficiency management method and system for smart street lights collect the operating environment data, historical operating data, and real - time status data of the battery of the smart street lights, and respectively obtain a lighting demand prediction result and an energy consumption prediction result based on predictive analysis. According to these prediction results and the battery status data, calculate the battery charge - discharge parameters and the deep - discharge limit, and generate a battery management strategy. Combine the virtual energy pool data of the street light network where the smart street lights are located, and perform priority energy allocation according to the battery management strategy and the lighting demand prediction result to generate a dynamic energy allocation plan. On this basis, perform energy management and monitor the energy consumption data of the smart street lights in real - time, and dynamically adjust the battery management strategy and the energy allocation plan according to the monitoring results. The present invention can efficiently allocate energy in a complex environment, achieve global optimization of the street light network, extend the battery life, and improve the energy management efficiency of smart street lights.

[0047] Other features and advantages of the present invention will be set forth in the following description, and in part will be obvious from the description, or may be learned by practice of the present invention. The objectives and other advantages of the present invention are realized and attained by the structure particularly pointed out in the specification, claims, and drawings.

[0048] To make the above objectives, features, and advantages of the present invention more comprehensible, the following specific preferred embodiments are given in conjunction with the accompanying drawings and are described in detail as follows. Description of the Drawings

[0049] Figure 1 Schematic diagram of the first embodiment of the energy efficiency management method for smart street lights in the embodiments of the present invention;

[0050] Figure 2 Schematic diagram of an embodiment of the energy efficiency management system for smart street lights in the embodiments of the present invention. Detailed Description of the Embodiments

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0052] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes other unlisted steps or units, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0053] To facilitate the understanding of this embodiment, a detailed introduction to an energy efficiency management method for smart street lights disclosed in the embodiments of the present invention will be given first. As Figure 1 shown, the method includes the following steps:

[0054] 101. Collect the operating environment data, historical operating data of the smart street lights, and the real-time status data of the battery corresponding to the smart street lights, and perform predictive analysis based on the operating environment data and historical operating data to obtain a lighting demand prediction result and an energy consumption prediction result respectively;

[0055] In an embodiment of the present invention, the operating environment data includes a light intensity data set, an activity detection data set, and a weather condition data set; collecting the operating environment data and historical operating data of the intelligent street lamp, and performing predictive analysis based on the operating environment data and historical operating data to obtain a lighting demand prediction result and an energy consumption prediction result respectively, including: decomposing the historical operating data by time series to obtain a lighting demand trend component, a lighting demand seasonal component, and a lighting demand random component, and inputting the light intensity data set and the activity detection data set into a preset multi-factor regression model for lighting demand to obtain a preliminary lighting demand prediction value; performing a weighted fusion operation on the preliminary lighting demand prediction value, the lighting demand trend component, and the lighting demand seasonal component to obtain a corrected lighting demand prediction value, and inputting the corrected lighting demand prediction value and the lighting demand random component into a preset combined prediction algorithm to obtain a lighting demand prediction result; inputting the lighting demand prediction result and the weather condition data set into a preset energy consumption estimation neural network to obtain a preliminary energy consumption prediction value, and decomposing the energy consumption data in the historical operating data by time series to obtain an energy consumption trend component, an energy consumption seasonal component, and an energy consumption random component; performing a weighted fusion operation on the preliminary energy consumption prediction value, the energy consumption trend component, and the energy consumption seasonal component to obtain a corrected energy consumption prediction value, and inputting the corrected energy consumption prediction value and the energy consumption random component into a preset combined prediction algorithm to obtain an energy consumption prediction result.

[0056] Specifically, the intelligent street lamp system collects light intensity data, activity detection data, and weather condition data through built-in light sensors, motion detectors, and weather sensors respectively. These data are recorded and stored in the system's database in real time, forming a historical operation dataset. The light intensity data reflects the natural light level of the environment and directly affects the turning-on time and lighting intensity requirements of the street lamps. The activity detection data includes the passing frequency and time distribution of pedestrians and vehicles, reflecting the usage of the road section. The weather condition data includes information such as temperature, humidity, and precipitation, and these factors will affect the energy consumption and lighting requirements of the street lamps. The system preprocesses these raw data, including denoising, standardization, and outlier processing, to ensure data quality. Next, the system performs time series decomposition on the historical operation data. This step uses algorithms such as STL (Seasonal and Trend decomposition using Loess) to decompose the time series data into a trend component, a seasonal component, and a random component. The trend component reflects the long-term change trend of lighting requirements, such as the basic lighting requirements that may increase year by year with the development of the city. The seasonal component captures the periodic change patterns, such as the difference in lighting requirements between weekdays and weekends, or the change in lighting duration between summer and winter. The random component contains irregular fluctuations, which may be caused by special events or unknown factors. This decomposition enables the system to understand the composition of lighting requirements more deeply and provides a basis for subsequent prediction. Then, the system inputs the preprocessed light intensity dataset and activity detection dataset into a preset multi-factor regression model for lighting requirements. This model can be a complex machine learning model, such as a random forest or a gradient boosting tree, which learns the non-linear relationship between light intensity and activity level and lighting requirements. The inputs of the model include the light intensity at the current time point, the activity detection data in the recent period, and other potentially relevant features. The model outputs a preliminary lighting requirement prediction value, which reflects the immediate lighting requirement estimate based on the current environmental conditions. The system then corrects the preliminary lighting requirement prediction value. It performs weighted fusion of the preliminary prediction value with the trend component and seasonal component obtained from the previous decomposition. The fusion process uses a predefined weight allocation scheme, which determines the importance of each component based on the analysis results of historical data. For example, during the season alternation period when the lighting requirements change drastically, the seasonal component may be assigned a higher weight. The fusion operation usually adopts weighted average or more complex non-linear combination methods. The purpose of this step is to combine the immediate prediction of the model with the long-term trend and periodic pattern to improve the accuracy and stability of the prediction. Then, the system inputs the corrected lighting requirement prediction value and the random component into a preset combined prediction algorithm. This algorithm can be an ensemble learning model, such as the Bagging or Boosting algorithm, which comprehensively considers the deterministic prediction (the corrected prediction value) and the uncertainty factor (the random component).The purpose of the combined prediction algorithm is to further improve the robustness of the prediction and reduce the bias that may be brought by a single model. The algorithm outputs the final prediction result of the lighting demand, which not only includes the point prediction value but may also include the prediction interval to represent the uncertainty range of the prediction. After obtaining the lighting demand prediction result, the system inputs it together with the weather condition dataset into a preset energy consumption estimation neural network. This neural network is a deep learning model that can adopt architectures such as LSTM (Long Short-Term Memory Network) or Transformer, and is capable of processing time series data and capturing complex non-linear relationships. The model learns the complex mapping relationship between lighting demand, weather conditions, and energy consumption. The output of the neural network is a preliminary energy consumption prediction value, which reflects the energy consumption estimation based on the predicted lighting demand and weather conditions. At the same time, the system performs time series decomposition on the energy consumption data in the historical operation data, and the method is similar to the previous processing of lighting demand data. This step also uses STL or similar algorithms to decompose the energy consumption data into trend components, seasonal components, and random components. This decomposition helps to understand the long-term trend, periodic changes, and random fluctuations of the energy consumption pattern, providing richer information for subsequent energy consumption prediction. Finally, the system corrects and combines the preliminary energy consumption prediction value. The correction process is similar to the correction of the lighting demand prediction, and the preliminary prediction value is weighted and fused with the energy consumption trend component and seasonal component. The weights used for fusion can be optimized based on the characteristics of the energy consumption data. Then, the corrected energy consumption prediction value and the energy consumption random component are input into the combined prediction algorithm. This algorithm can be another ensemble learning model that is optimized specifically for energy consumption prediction. The final output energy consumption prediction result includes the point prediction value and a possible prediction interval, providing comprehensive prediction information for the energy management of the smart street lamp system.

[0057] 102. Calculate the battery charge and discharge parameters and the deep discharge limit of the battery based on the lighting demand prediction result, the energy consumption prediction result, and the real-time status data of the battery, and generate a battery management strategy based on the battery charge and discharge parameters and the deep discharge limit;

[0058] In one embodiment of the present invention, calculating the battery charge and discharge parameters and the deep discharge limit of the battery based on the lighting demand prediction result, the energy consumption prediction result, and the real-time state data of the battery, and generating a battery management strategy based on the battery charge and discharge parameters and the deep discharge limit includes: dividing the lighting demand prediction result and the energy consumption prediction result into time periods to obtain peak demand periods and low demand periods; establishing a battery health state evaluation model according to the real-time state data of the battery to obtain an estimated value of the remaining battery life; calculating the optimal charge and discharge rate and the charge and discharge time window based on the peak demand period, the low demand period, and the estimated value of the remaining battery life to obtain the battery charge and discharge parameters; setting a dynamic deep discharge limit threshold according to the battery charge and discharge parameters and the estimated value of the remaining battery life to obtain the deep discharge limit; and inputting the battery charge and discharge parameters and the deep discharge limit into a preset battery management algorithm to generate a battery management strategy including a charge and discharge strategy, an equalization charging strategy, and a temperature control strategy.

[0059] Specifically, first, the lighting demand prediction result and the energy consumption prediction result are divided into time periods. The system uses a time series clustering algorithm, such as K-means or hierarchical clustering, to analyze the prediction data. The algorithm considers the absolute values and change rates of the lighting demand and the energy consumption, and divides 24 hours of a day into several time periods. By setting thresholds, the peak demand periods and the low demand periods are identified. The peak demand periods usually correspond to the morning and evening rush hours, when the lighting demand and the energy consumption are high; while the low demand periods may be late at night or early in the morning, when the system load is low. This division of time periods provides an important basis for formulating subsequent battery management strategies, enabling the system to adopt differentiated energy management measures at different time periods.

[0060] Specifically, the system establishes a battery health state evaluation model according to the real-time state data of the battery. This model uses a machine learning algorithm, such as support vector regression (SVR) or random forest, and the inputs include the charge and discharge times of the battery, the deep discharge times, the temperature history, the voltage and current characteristics, etc. The model analyzes the relationship between these parameters and the battery life, and outputs an estimated value of the remaining battery life. This estimated value is expressed in terms of the number of cycles or time units, reflecting the current health status and the expected available time of the battery. An accurate estimate of the remaining life is crucial for optimizing the battery usage strategy, extending the battery life, and planning maintenance.

[0061] Specifically, the system calculates the optimal charge and discharge rates and charge and discharge time windows based on the peak demand period, valley demand period, and estimated remaining battery life. This step uses a dynamic programming algorithm that takes into account multiple constraints: peak-to-valley electricity price differences, predicted energy demand, battery health, etc. The goal of the algorithm is to maximize economic benefits while ensuring that the battery life does not decay too quickly. During peak periods, the system tends to use the stored energy for power supply, while during valley periods, it gives priority to charging. The algorithm outputs a detailed charge and discharge plan, including the charge and discharge rates and durations for each time period, and these parameters constitute the battery charge and discharge parameter set.

[0062] Specifically, based on the calculated battery charge and discharge parameters and the estimated remaining battery life, the system further sets a dynamic deep discharge limit threshold. This process uses a fuzzy logic controller, and the input variables include the remaining battery life, current charge and discharge parameters, and historical usage patterns. The controller dynamically adjusts the deep discharge limit according to a predefined rule set. For example, when the remaining battery life is long, deeper discharges can be allowed to improve energy utilization; while when the battery is approaching the end of its life, a more conservative strategy is adopted to delay decay. The output deep discharge limit is a percentage value representing the maximum depth of discharge allowed. This limit ensures that the battery does not accelerate aging due to over-discharge and is flexibly adjusted in different situations, balancing the requirements of performance and life.

[0063] Specifically, the system inputs the battery charge and discharge parameters and the deep discharge limit into a preset battery management algorithm. This algorithm is a comprehensive decision-making system that can be based on a reinforcement learning or model predictive control (MPC) framework. The algorithm comprehensively considers the outputs of the previous steps and also incorporates real-time system status and external environment information. Through optimization calculations, the algorithm generates a comprehensive battery management strategy, including three main parts: charge and discharge strategy, equalization charging strategy, and temperature control strategy. The charge and discharge strategy details the charge and discharge operations for each time period, including the power magnitude and duration. The equalization charging strategy aims to extend the battery life by controlling the charging process of each battery cell to ensure that all cells maintain similar charge states. The temperature control strategy adjusts the working mode of the cooling system according to the ambient temperature and the battery operating status to maintain the optimal working temperature range. This comprehensive battery management strategy ensures that the intelligent street lamp system can operate efficiently, safely, and long-term, maximizing the battery's usage efficiency and life.

[0064] Further, setting a dynamic deep discharge limit threshold according to the battery charge and discharge parameters and the estimated remaining battery life, and obtaining the deep discharge limit includes: normalizing the estimated remaining battery life to obtain a life impact factor, and calculating a battery stress coefficient according to the charge and discharge rate in the battery charge and discharge parameters to obtain a stress impact factor; inputting the life impact factor and the stress impact factor into a preset fuzzy logic controller to obtain an initial deep discharge limit value; correcting the initial deep discharge limit value by applying an adaptive adjustment algorithm according to historical deep discharge data to obtain a corrected deep discharge limit value; comparing the corrected deep discharge limit value with a preset safety threshold, and selecting the smaller value of the corrected deep discharge limit value and the preset safety threshold as the deep discharge limit.

[0065] Specifically, first normalize the estimated remaining battery life to obtain a life impact factor. This step uses the Min-Max normalization method to map the estimated remaining life to the range of 0 to 1. Specifically, the system sets a maximum life threshold (such as 80% of the design life) and a minimum life threshold (such as 20% of the design life), and then calculates the normalized value according to the position of the current estimated remaining life within this range. This life impact factor reflects the degree of influence of the battery health status on the deep discharge limit. The closer the value is to 1, the newer the battery is and the deeper the discharge it can withstand. At the same time, the system calculates a battery stress coefficient according to the charge and discharge rate in the battery charge and discharge parameters to obtain a stress impact factor. This calculation process considers the ratio of the charge and discharge rate to the rated power of the battery, as well as the charge and discharge duration. For example, an exponential function is used to map the rate ratio to the range of 0 to 1. The higher the rate, the closer the stress impact factor is to 1, indicating a greater stress on the battery. The introduction of these two factors enables the system to comprehensively consider the battery health status and the current usage intensity, providing a quantitative basis for the subsequent setting of the deep discharge limit.

[0066] Specifically, the system inputs the life impact factor and the stress impact factor into a preset fuzzy logic controller to obtain the initial deep discharge limit value. The fuzzy logic controller contains a series of predefined IF-THEN rules, which are formulated based on expert knowledge and historical data analysis results. The controller first fuzzifies the two input impact factors and maps them to linguistic variables (such as "low", "medium", "high"). Then, based on fuzzy rule inference, it obtains the linguistic description of the deep discharge limit. For example, a rule might be "IF the life impact factor is high AND the stress impact factor is low THEN the deep discharge limit is high". Finally, through the defuzzification process, the linguistic description is converted into a specific numerical value, that is, the initial deep discharge limit value. This value is usually expressed as a percentage of the battery capacity. For example, 80% means that the battery is allowed to discharge until the remaining capacity is 20%. The use of the fuzzy logic controller enables the system to simulate the decision-making process of human experts, handle imprecise and uncertain information, and provides flexibility and robustness for setting the deep discharge limit.

[0067] Specifically, the system applies an adaptive adjustment algorithm to the initial deep discharge limit value according to historical deep discharge data to obtain the corrected deep discharge limit value. This step uses online learning algorithms, such as recursive least squares (RLS) or online gradient descent, to continuously update the relationship model between the deep discharge limit and battery performance. The algorithm inputs include the deep discharge limit setting values, the actual discharge depth, and the corresponding battery performance indicators (such as capacity attenuation rate, internal resistance change, etc.) over a past period of time. By analyzing this historical data, the algorithm learns the optimal deep discharge limit setting strategy and adjusts the current initial limit value accordingly. For example, if the historical data shows that the current limit value causes the battery to decay too quickly, the algorithm will appropriately lower the limit value; conversely, if the battery performs well, the limit can be moderately relaxed to improve energy utilization efficiency. This adaptive adjustment mechanism ensures that the deep discharge limit can be dynamically optimized as the battery usage situation and environment change, achieving a balance between extending battery life and improving energy utilization efficiency.

[0068] Specifically, the system compares the corrected deep discharge limit value with a preset safety threshold and selects the smaller value of the two as the final deep discharge limit. The preset safety threshold is a hard limit set based on battery technical specifications and safety considerations, usually provided by the battery manufacturer or determined according to industry standards. The purpose of this step is to establish a dual mechanism between dynamic optimization and safety guarantee. Even in extreme cases, such as algorithm anomalies or inaccurate input data, the system can ensure that the safety threshold is not exceeded, thus preventing irreversible damage caused by over-discharging of the battery. The comparison process uses a simple conditional judgment. If the corrected limit value is less than the safety threshold, the corrected value is directly adopted; otherwise, the safety threshold is adopted. The finally obtained deep discharge limit will be used to guide the actual battery management operation to ensure that the battery works in a safe and efficient state. This multi-level limit setting method takes into account both the dynamic characteristics and usage history of the battery and ensures the safety of the system, providing a reliable guarantee for the long-term stable operation of the intelligent street lamp system.

[0069] Further, before obtaining the virtual energy pool data of the virtual energy pool preset in the street lamp network where the intelligent street lamp is located and performing priority energy allocation based on the virtual energy pool data, battery management strategy, and lighting demand prediction result to obtain a dynamic energy allocation plan within the street lamp network, it further includes: collecting the power generation capacity data, energy storage capacity data, and real-time energy status data of each intelligent street lamp in the street lamp network, and performing normalization processing on the power generation capacity data and energy storage capacity data to obtain a standardized energy resource evaluation result; calculating the relative energy level of each intelligent street lamp based on the standardized energy resource evaluation result and the real-time energy status data to obtain a network energy distribution map, and dividing the surplus and shortage areas of the street lamp network according to the network energy distribution map to obtain a regional division result; generating an energy allocation strategy within the street lamp network and an energy exchange strategy with the smart grid based on the regional division result, and integrating the energy allocation strategy and the energy exchange strategy to obtain a virtual energy pool.

[0070] Specifically, it starts with data collection. The system collects data on the power generation capacity, energy storage capacity, and real-time energy status of each smart streetlight in the streetlight network through an intelligent sensor network. The power generation capacity data mainly comes from the photovoltaic panels installed on the streetlights, including information such as the rated power of the panels, the actual power generation efficiency, and the historical power generation. The energy storage capacity data reflects the capacity size, charge-discharge efficiency, and current health status of the battery system equipped for each streetlight. The real-time energy status data includes the current battery charge level, real-time power generation, and power consumption, etc. After preliminary data cleaning and preprocessing, these raw data enter the normalization processing stage. The normalization processing uses the Min-Max standardization method to map data with different dimensions to a unified interval from 0 to 1. The purpose of this step is to eliminate the incomparability of data caused by differences in hardware configurations between different streetlights, enabling subsequent analysis and decision-making processes to be carried out under a unified standard. The standardized energy resource assessment result obtained after normalization assigns a comparable energy resource index to each streetlight, which comprehensively reflects the power generation potential and energy storage capacity of the streetlight.

[0071] Specifically, next, the system calculates the relative energy level of each smart streetlight based on the standardized energy resource assessment result and the real-time energy status data, thereby obtaining an energy distribution map of the entire network. The calculation process uses the weighted average method, where the energy resource assessment result is used as a long-term potential indicator, and the real-time energy status data is used as a short-term status indicator, and the two are fused according to the preset weights. The relative energy level is a dynamically changing indicator that reflects the energy abundance of each streetlight in the entire network. The network energy distribution map is presented in the form of a heat map, visually showing the spatial characteristics of the energy distribution in the network. Based on this distribution map, the system uses clustering algorithms (such as K-means or DBSCAN) to divide the streetlight network into surplus and shortage regions. The algorithm groups streetlights with similar relative energy levels and adjacent geographical locations into one group, and finally divides the entire network into several regions with similar energy characteristics. The result of this regional division provides an important basis for formulating subsequent energy allocation strategies, enabling the system to balance and optimize energy at the macro level.

[0072] Specifically, based on the regional division results, the system generates an internal energy allocation strategy within the streetlight network and an energy exchange strategy with the smart grid. The internal energy allocation strategy uses a network flow algorithm to redistribute the excess electricity in the energy surplus areas to the energy shortage areas through virtual channels. The algorithm takes into account the virtual costs of energy transmission (such as transmission losses) and the demand priorities of each area to minimize the overall allocation cost. The energy exchange strategy with the smart grid is formulated based on the predicted overall energy surplus or shortage of the network. When there is an energy surplus, the system calculates the amount of electricity that can be fed back to the smart grid and determines the optimal feedback timing based on the current electricity price; when there is an energy shortage, it calculates the amount of electricity that needs to be purchased from the smart grid and formulates the most economical power purchase plan in combination with the time-of-use electricity price. These two strategies are integrated through a unified optimization model, which aims to minimize the overall operating cost and maximize the energy utilization efficiency, while considering constraints such as grid stability and user demand satisfaction. The integrated strategy constitutes the core operation mechanism of the virtual energy pool, enabling the entire streetlight network to interact intelligently with the external power grid as a unified energy entity and simultaneously achieving optimal internal energy allocation.

[0073] 103. Obtain the virtual energy pool data of the virtual energy pool preset for the streetlight network where the smart streetlight is located, and perform priority energy allocation based on the virtual energy pool data, battery management strategy, and lighting demand prediction results to obtain a dynamic energy allocation plan within the streetlight network;

[0074] In an embodiment of the present invention, the obtaining the virtual energy pool data of the virtual energy pool preset for the streetlight network where the smart streetlight is located, and performing priority energy allocation based on the virtual energy pool data, battery management strategy, and lighting demand prediction results to obtain a dynamic energy allocation plan within the streetlight network includes: obtaining the virtual energy pool data of the virtual energy pool preset for the streetlight network where the smart streetlight is located, and inputting the virtual energy pool data, battery management strategy, and lighting demand prediction results into a multi-objective optimization algorithm to obtain a preliminary energy allocation plan; according to the preliminary energy allocation plan, execute a network load balancing algorithm to obtain an energy allocation plan after load balancing; apply an emergency response strategy to the energy allocation plan after load balancing, set an energy reserve threshold, and obtain an energy allocation plan with emergency response capabilities; combine the energy allocation plan with emergency response capabilities with the real-time data of the smart grid and execute a dynamic adjustment algorithm to obtain a dynamic energy allocation plan.

[0075] Specifically, it starts with obtaining virtual energy pool data. The system obtains the status information of the virtual energy pool in real time through a preset data interface, including the current energy level, energy storage capacity, power generation capacity, etc. of each street lamp node. These data reflect the energy distribution and available resources of the entire street lamp network. Then, the system inputs these virtual energy pool data, together with the previously generated battery management strategy and lighting demand prediction results, into a multi-objective optimization algorithm. This algorithm uses evolutionary computing methods such as genetic algorithms or particle swarm optimization, with the objective functions of minimizing energy consumption, maximizing lighting effects, and extending battery life. Through iterative optimization, on the premise of meeting various constraint conditions (such as the minimum lighting requirements, the safe operating range of the battery, etc.), a preliminary energy allocation plan is generated. This plan assigns specific energy usage quotas and working modes to each street lamp node, but does not yet consider the overall balance of the network.

[0076] Specifically, subsequently, the system executes a network load balancing algorithm according to the preliminary energy allocation plan. This algorithm uses the minimum spanning tree or network flow algorithm in graph theory, regarding the entire street lamp network as an interconnected energy system. The algorithm first identifies the energy surplus nodes and energy shortage nodes in the network, and then calculates the optimal flow path of energy between the nodes. During this process, the algorithm considers the losses of virtual energy transmission, the network topology structure, and the energy demand priorities of each node. Through repeated iteration and adjustment, the algorithm finally obtains an energy allocation plan after load balancing. This plan not only meets the energy requirements of each node, but also ensures the balanced energy use of the entire network, avoiding local overload or resource waste.

[0077] Specifically, next, the system applies an emergency response strategy to the energy allocation plan after load balancing. This step aims to improve the emergency response ability and reliability of the street lamp network. The system first sets an energy reserve threshold based on historical data and expert knowledge. This threshold is usually expressed as the percentage of the minimum energy level that each node should maintain. Then, the system uses the Monte Carlo simulation method to simulate various possible emergency situations (such as local power outages, sudden large-scale lighting demands, etc.) and evaluate the emergency response ability of the current plan. Based on the simulation results, the system adjusts the energy allocation to ensure that each node retains sufficient energy reserves to cope with emergency situations. This process may involve reallocating the energy usage quotas of some nodes or adjusting the working modes of certain nodes. The finally obtained energy allocation plan with emergency response ability provides additional safety guarantees for the network while ensuring daily operations.

[0078] Specifically, finally, the system combines the energy distribution plan with emergency response capabilities with the real-time data of the smart grid and executes a dynamic adjustment algorithm. The purpose of this step is to enable the streetlight network to flexibly adjust its operation strategy according to the real-time conditions of the external power grid. The system first obtains the real-time information of the smart grid through a preset data interface, including power supply and demand conditions, real-time electricity prices, grid stability indicators, etc. Then, a dynamic decision-making model is constructed using reinforcement learning algorithms (such as Q-learning or Deep Q Network). This model takes the current state of the streetlight network, the energy distribution plan, and the real-time grid data as inputs and outputs a series of fine-tuning instructions. These instructions may include adjusting the power consumption time of certain nodes, changing the charge and discharge strategies of energy storage devices, or performing real-time energy exchange with the grid. Through continuous learning and optimization, the system can maximize the use of favorable opportunities of the grid (such as low valley electricity price periods) while ensuring the normal operation of the streetlight network, and provide auxiliary services to the grid (such as demand response) when necessary. The final dynamic energy allocation plan not only optimizes the energy use of the streetlight network itself but also realizes the coordinated operation with a larger-scale smart grid, reflecting the overall optimization concept of the smart city energy system.

[0079] 104. Execute the energy management of smart streetlights based on the dynamic energy allocation plan, monitor the energy consumption data of smart streetlights in real time, and dynamically adjust the battery management strategy and the dynamic energy allocation plan according to the energy consumption data to optimize the energy use efficiency of smart streetlights.

[0080] In one embodiment of the present invention, the execution of the energy management of smart streetlights based on the dynamic energy allocation plan, the real-time monitoring of the energy consumption data of smart streetlights, and the dynamic adjustment of the battery management strategy and the dynamic energy allocation plan according to the energy consumption data to optimize the energy use efficiency of smart streetlights includes: according to the dynamic energy allocation plan, execute individual energy control instructions for each smart streetlight and collect energy consumption data in real time; compare the energy consumption data with a preset energy efficiency benchmark, calculate the energy efficiency deviation value, and execute an adaptive PID control algorithm according to the energy efficiency deviation value to obtain the adjustment parameters of the battery management strategy; apply the adjustment parameters to the battery management strategy to generate an updated battery management strategy; based on the updated battery management strategy and the energy consumption data, re-execute the virtual energy pool optimization algorithm to obtain an optimized dynamic energy allocation plan.

[0081] Specifically, first, according to the dynamic energy allocation plan, individual energy control instructions are executed for each smart street lamp. The system sends specific control instructions to each smart street lamp through the central control unit. These instructions include the brightness adjustment of the lamp, the battery charge and discharge strategy, and the energy interaction method with surrounding devices. At the same time, the system activates the real-time monitoring module to continuously collect the energy consumption data of each street lamp. This data includes real-time power consumption, cumulative energy consumption, battery charge and discharge status, etc. The data collection uses high-precision energy metering devices, and the sampling frequency can reach multiple times per second to ensure capturing the subtle trends of energy consumption changes. The collected raw data undergoes preliminary filtering and outlier detection processing to form a standardized energy consumption dataset. This dataset not only reflects the real-time energy usage of each street lamp but also provides a basis for subsequent energy efficiency analysis and strategy adjustment.

[0082] Specifically, the system compares the collected energy consumption data with the pre-set energy efficiency benchmark. The energy efficiency benchmark is an ideal energy consumption standard formulated based on factors such as historical data, device specifications, and operating environment. The comparison process uses the sliding time window method to calculate the difference between the actual energy consumption and the benchmark value, obtaining the energy efficiency deviation value. This deviation value is a dynamically changing indicator that reflects the gap between the current operating state and the ideal state. Subsequently, the system inputs the energy efficiency deviation value into the adaptive PID (Proportional-Integral-Derivative) control algorithm. The three parameters (proportional coefficient, integral time, and derivative time) of the PID controller are adjusted in real time through an adaptive mechanism to adapt to different operating conditions and external environment changes. The algorithm calculates a set of optimal control parameters by minimizing the cumulative error of the energy efficiency deviation. These parameters constitute the adjustment instructions for the battery management strategy, including fine-tuning of the charge and discharge rate, dynamic adjustment of the deep discharge limit, etc. The use of adaptive PID control ensures that the system can quickly respond to energy efficiency changes while maintaining stability.

[0083] Specifically, the system applies the obtained adjustment parameters to the current battery management strategy to generate an updated battery management strategy. This process involves the dynamic update and verification of strategy parameters. The system first checks whether the new parameters are within the safe operating range to prevent risks that may be brought by excessive adjustment. After passing the security check, the new parameters are gradually applied to the battery management system. The update process adopts a smooth transition mechanism to avoid system instability caused by mutations. The updated battery management strategy may include a new charge and discharge curve, adjusted battery usage cycle, optimized temperature control parameters, etc. This dynamic adjustment mechanism enables the battery management strategy to continuously adapt to the actual operating conditions, achieving a balance between extending battery life and improving energy utilization efficiency.

[0084] Specifically, the system re-executes the virtual energy pool optimization algorithm based on the updated battery management strategy and the latest energy consumption data. This algorithm regards the entire streetlight network as a virtual energy pool, with the goal of optimizing the overall energy distribution and usage. The algorithm adopts distributed optimization methods such as distributed model predictive control (DMPC) or consensus-based distributed optimization. Each streetlight node acts as an independent optimization unit, exchanges information with neighboring nodes, and conducts local optimization. The central controller is responsible for coordinating the global optimization goal. The optimization process takes into account multiple factors, including the new battery management strategy of each node, the real-time energy consumption status, the predicted lighting demand, and possible environmental changes (such as weather forecasts). Through multiple rounds of iterative calculations, the algorithm finally generates an optimized dynamic energy allocation plan. This new plan not only reflects the performance improvement of individual streetlights but also demonstrates the collaborative optimization effect of the entire network. It assigns updated energy usage quotas to each streetlight, adjusts the energy exchange strategy between nodes, and may re-plan the interaction mode with the external power grid. This continuous optimization cycle ensures that the intelligent streetlight system can always operate in the most efficient manner, adapting to changing environments and demands.

[0085] In this embodiment, by collecting the operating environment data, historical operating data, and real-time battery status data of the intelligent streetlights, the lighting demand prediction result and the energy consumption prediction result are respectively obtained based on predictive analysis. According to these prediction results and the battery status data, the charge and discharge parameters and the deep discharge limit of the battery are calculated to generate a battery management strategy. Combining with the virtual energy pool data of the streetlight network where the intelligent streetlights are located, priority energy allocation is performed according to the battery management strategy and the lighting demand prediction result to generate a dynamic energy allocation plan. On this basis, energy management is executed and the energy consumption data of the intelligent streetlights is monitored in real time, and the battery management strategy and the energy allocation plan are dynamically adjusted according to the monitoring results. The present invention can efficiently allocate energy in a complex environment, achieve global optimization of the streetlight network, extend the battery life, and improve the energy management efficiency of the intelligent streetlights.

[0086] The energy efficiency management method of the intelligent streetlights in the embodiments of the present invention has been described above. Next, the energy efficiency management system of the intelligent streetlights in the embodiments of the present invention will be described. Please refer to Figure 2 , an embodiment of the energy efficiency management system of the intelligent streetlights in the embodiments of the present invention includes:

[0087] A prediction module 201, configured to collect the operating environment data, historical operating data of the intelligent streetlights, and the real-time status data of the battery corresponding to the intelligent streetlights, and perform predictive analysis based on the operating environment data and the historical operating data to respectively obtain a lighting demand prediction result and an energy consumption prediction result;

[0088] A strategy generation module 202, configured to calculate battery charge and discharge parameters and deep discharge limits of the battery based on the lighting demand prediction result, the energy consumption prediction result, and the real-time status data of the battery, and generate a battery management strategy based on the battery charge and discharge parameters and the deep discharge limits;

[0089] A deployment module 203, configured to obtain virtual energy pool data of a virtual energy pool preset in a street lamp network where the smart street lamp is located, and perform priority energy allocation based on the virtual energy pool data, the battery management strategy, and the lighting demand prediction result to obtain a dynamic energy deployment plan within the street lamp network;

[0090] An optimization module 204, configured to perform energy management of the smart street lamp based on the dynamic energy deployment plan, monitor the energy consumption data of the smart street lamp in real time, and dynamically adjust the battery management strategy and the dynamic energy deployment plan according to the energy consumption data to optimize the energy usage efficiency of the smart street lamp.

[0091] In an embodiment of the present invention, the energy efficiency management system of the smart street lamp runs the energy efficiency management method of the smart street lamp. The energy efficiency management system of the smart street lamp collects the operating environment data, historical operating data, and real-time battery status data of the smart street lamp, and respectively obtains a lighting demand prediction result and an energy consumption prediction result based on predictive analysis. According to these prediction results and the battery status data, the charge and discharge parameters and deep discharge limits of the battery are calculated, and a battery management strategy is generated. Combining the virtual energy pool data of the street lamp network where the smart street lamp is located, priority energy allocation is performed according to the battery management strategy and the lighting demand prediction result to generate a dynamic energy deployment plan. On this basis, energy management is performed and the energy consumption data of the smart street lamp is monitored in real time, and the battery management strategy and the energy deployment plan are dynamically adjusted according to the monitoring results. The present invention can efficiently allocate energy in a complex environment, achieve global optimization of the street lamp network, extend the battery life, and improve the energy management efficiency of the smart street lamp.

[0092] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system or device and unit can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0093] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0094] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for energy efficiency management of smart street lamps, characterized in that: The energy efficiency management method of the smart street lamp includes: Collecting the operating environment data, historical operating data and real-time status data of the battery corresponding to the smart street lamp, and performing prediction analysis based on the operating environment data and historical operating data to obtain lighting demand prediction results and energy consumption prediction results respectively; Calculating battery charge and discharge parameters and a depth of discharge limit of the battery based on the lighting demand prediction result, the energy consumption prediction result and the real-time status data of the battery, and generating a battery management strategy based on the battery charge and discharge parameters and the depth of discharge limit; Acquire virtual energy pool data of a virtual energy pool preset in a street light network where the smart street light is located, and perform priority energy allocation based on the virtual energy pool data, battery management strategy, and lighting demand forecast results to obtain a dynamic energy allocation plan within the street light network; The method of obtaining virtual energy pool data of a virtual energy pool preset in the street light network where the smart street light is located, and performing priority energy allocation based on the virtual energy pool data, battery management strategy and lighting demand forecast results to obtain a dynamic energy allocation plan within the street light network includes: obtaining virtual energy pool data of a virtual energy pool preset in the street light network where the smart street light is located, and inputting the virtual energy pool data, battery management strategy and lighting demand forecast results into a multi-objective optimization algorithm to obtain a preliminary energy allocation plan; executing a network load balancing algorithm according to the preliminary energy allocation plan to obtain a load-balanced energy allocation plan; applying an emergency response strategy to the load-balanced energy allocation plan, setting an energy reserve threshold, and obtaining an energy allocation plan with emergency response capabilities; combining the energy allocation plan with emergency response capabilities with real-time data of the smart grid, executing a dynamic adjustment algorithm, and obtaining a dynamic energy allocation plan; Before obtaining the virtual energy pool data of the virtual energy pool preset in the street light network where the smart street light is located, and performing priority energy allocation based on the virtual energy pool data, battery management strategy and lighting demand forecast results to obtain a dynamic energy allocation plan within the street light network, it also includes: collecting the power generation capacity data, energy storage capacity data and real-time energy status data of each smart street light in the street light network, and normalizing the power generation capacity data and energy storage capacity data to obtain a standardized energy resource assessment result; calculating the relative energy level of each smart street light based on the standardized energy resource assessment result and the real-time energy status data to obtain a network energy distribution map, and dividing the street light network into surplus and shortage areas according to the network energy distribution map to obtain a regional division result; based on the regional division result, generating an energy allocation strategy within the street light network and an energy exchange strategy with the smart grid, and integrating the energy allocation strategy and the energy exchange strategy to obtain a virtual energy pool; Based on the dynamic energy allocation scheme, energy management of smart street lights is performed, energy consumption data of smart street lights is monitored in real time, and the battery management strategy and dynamic energy allocation scheme are dynamically adjusted according to the energy consumption data to optimize the energy utilization efficiency of smart street lights.

2. The energy efficiency management method of smart street lamps according to claim 1, characterized in that: The operating environment data includes a light intensity data set, an activity detection data set, and a weather condition data set; The collecting of the operating environment data and the historical operating data of the smart street lamp, and performing prediction analysis based on the operating environment data and the historical operating data, respectively obtaining the lighting demand prediction results and the energy consumption prediction results include: Performing time series decomposition on the historical operation data to obtain a lighting demand trend component, a lighting demand seasonal component, and a lighting demand random component, and inputting the light intensity data set and the activity detection data set into a preset lighting demand multi-factor regression model to obtain a preliminary lighting demand forecast value; Performing a weighted fusion operation on the preliminary lighting demand forecast value, the lighting demand trend component and the lighting demand seasonal component to obtain a revised lighting demand forecast value, and inputting the revised lighting demand forecast value and the lighting demand random component into a preset combined forecasting algorithm to obtain a lighting demand forecast result; Input the lighting demand forecast result and the weather condition data set into a preset energy consumption estimation neural network to obtain a preliminary energy consumption forecast value, and perform time series decomposition on the energy consumption data in the historical operation data to obtain an energy consumption trend component, an energy consumption seasonal component, and an energy consumption random component; The preliminary energy consumption forecast value, the energy consumption trend component and the energy consumption seasonal component are weighted and fused to obtain a revised energy consumption forecast value, and the revised energy consumption forecast value and the energy consumption random component are input into a preset combined prediction algorithm to obtain an energy consumption forecast result.

3. The energy efficiency management method of the smart street lamp according to claim 1, characterized in that: The calculating the battery charge and discharge parameters and the depth discharge limit of the battery based on the lighting demand prediction result, the energy consumption prediction result and the real-time status data of the battery, and generating a battery management strategy based on the battery charge and discharge parameters and the depth discharge limit includes: Dividing the lighting demand forecast results and the energy consumption forecast results into time periods to obtain peak demand periods and valley demand periods; Establishing a battery health status assessment model based on the real-time status data of the battery to obtain an estimated value of the remaining battery life; Based on the peak demand period, the valley demand period and the estimated value of the remaining battery life, the optimal charge and discharge rate and the charge and discharge time window are calculated to obtain the battery charge and discharge parameters; According to the battery charge and discharge parameters and the estimated value of the remaining battery life, a dynamic deep discharge limit threshold is set to obtain a deep discharge limit; The battery charge and discharge parameters and the depth of discharge limit are input into a preset battery management algorithm to generate a battery management strategy including a charge and discharge strategy, a balanced charging strategy and a temperature control strategy.

4. The energy efficiency management method of the smart street lamp according to claim 3 is characterized in that: The step of setting a dynamic deep discharge limit threshold according to the battery charge and discharge parameters and the estimated value of the remaining battery life to obtain a deep discharge limit comprises: Normalizing the estimated value of the remaining life of the battery to obtain a life influence factor, and calculating the battery stress coefficient according to the charge and discharge rate in the battery charge and discharge parameters to obtain a stress influence factor; Inputting the life influence factor and the stress influence factor into a preset fuzzy logic controller to obtain an initial depth discharge limit value; Applying an adaptive adjustment algorithm to correct the initial depth discharge limit value according to historical depth discharge data to obtain a corrected depth discharge limit value; The modified deep discharge limit value is compared with a preset safety threshold, and a smaller value between the modified deep discharge limit value and the preset safety threshold is selected as the deep discharge limit.

5. The energy efficiency management method of a smart street lamp according to claim 1, characterized in that: The energy management of the smart street lamp is performed based on the dynamic energy allocation scheme, the energy consumption data of the smart street lamp is monitored in real time, and the battery management strategy and the dynamic energy allocation scheme are dynamically adjusted according to the energy consumption data to optimize the energy efficiency of the smart street lamp, including: According to the dynamic energy allocation scheme, individual energy control instructions are executed on each smart street lamp, and energy consumption data is collected in real time; Comparing the energy consumption data with a preset energy efficiency benchmark, calculating an energy efficiency deviation value, and executing an adaptive PID control algorithm according to the energy efficiency deviation value to obtain adjustment parameters of a battery management strategy; Applying the adjustment parameter to the battery management strategy to generate an updated battery management strategy; Based on the updated battery management strategy and energy consumption data, the virtual energy pool optimization algorithm is re-executed to obtain an optimized dynamic energy allocation solution.

6. An energy efficiency management system for smart street lamps, characterized in that: The energy efficiency management system of the smart street lamp includes: A prediction module, which is used to collect operating environment data, historical operating data and real-time status data of the battery corresponding to the smart street lamp, and perform prediction analysis based on the operating environment data and historical operating data to obtain lighting demand prediction results and energy consumption prediction results respectively; A strategy generation module is used to calculate the battery charge and discharge parameters and deep discharge limit of the battery based on the lighting demand prediction result, the energy consumption prediction result and the real-time status data of the battery, and generate a battery management strategy based on the battery charge and discharge parameters and the deep discharge limit; obtain the virtual energy pool data of the virtual energy pool preset in the street light network where the smart street light is located, and perform priority energy allocation based on the virtual energy pool data, the battery management strategy and the lighting demand prediction result to obtain a dynamic energy allocation plan in the street light network, including: obtaining the virtual energy pool data of the virtual energy pool preset in the street light network where the smart street light is located, and inputting the virtual energy pool data, the battery management strategy and the lighting demand prediction result into a multi-objective optimization algorithm to obtain a preliminary energy allocation plan; according to the preliminary energy allocation plan, executing a network load balancing algorithm to obtain a load-balanced energy allocation plan; applying an emergency response strategy to the load-balanced energy allocation plan, setting an energy reserve threshold, and obtaining an energy allocation plan with emergency capabilities; combining the energy allocation plan with emergency capabilities with the real-time data of the smart grid, executing a dynamic adjustment algorithm, and obtaining a dynamic energy allocation plan; Before obtaining the virtual energy pool data of the virtual energy pool preset in the street light network where the smart street light is located, and performing priority energy allocation based on the virtual energy pool data, battery management strategy and lighting demand forecast results to obtain a dynamic energy allocation plan within the street light network, it also includes: collecting the power generation capacity data, energy storage capacity data and real-time energy status data of each smart street light in the street light network, and normalizing the power generation capacity data and energy storage capacity data to obtain a standardized energy resource assessment result; calculating the relative energy level of each smart street light based on the standardized energy resource assessment result and the real-time energy status data to obtain a network energy distribution map, and dividing the street light network into surplus and shortage areas according to the network energy distribution map to obtain a regional division result; based on the regional division result, generating an energy allocation strategy within the street light network and an energy exchange strategy with the smart grid, and integrating the energy allocation strategy and the energy exchange strategy to obtain a virtual energy pool; A deployment module, used to obtain virtual energy pool data of a virtual energy pool preset in a street light network where the smart street light is located, and to perform priority energy allocation based on the virtual energy pool data, battery management strategy and lighting demand forecast results to obtain a dynamic energy deployment plan within the street light network; The optimization module is used to perform energy management of the smart street lamp based on the dynamic energy allocation plan, monitor the energy consumption data of the smart street lamp in real time, and dynamically adjust the battery management strategy and the dynamic energy allocation plan according to the energy consumption data to optimize the energy utilization efficiency of the smart street lamp.

Images