A load balancing method and related equipment for intelligent lighting collaborative management

Abstract

This application provides a load balancing method and related equipment for intelligent lighting collaborative management. The method includes: real-time acquisition of environmental parameters of each lighting area and preprocessing the environmental parameters; inputting the preprocessed environmental parameters into a preset deep neural network model to determine the load prediction sequence of each lighting area; judging the load status of each lighting area based on the load prediction sequence; generating a multi-area collaborative dimming rate set based on the load status and real-time environmental data through a regional hierarchical collaborative strategy; and controlling the lighting equipment in the target lighting area according to the multi-area collaborative dimming rate set. Through the implementation of this application's solution, cross-area, dynamic perception, and prediction-driven intelligent dimming control is achieved, improving the dynamic adaptability and load control accuracy of the lighting system.

Description

Technical Field

[0001] This application relates to the field of optical display, and more particularly to a load balancing method and related equipment for intelligent lighting collaborative management. Background Technology

[0002] Against the backdrop of the rapid development of smart cities and intelligent buildings, lighting systems, as a crucial component of building energy consumption, are gradually evolving towards intelligence and self-adaptability. This is especially true in complex, multi-functional spaces such as large office buildings, hospitals, schools, and transportation hubs, where different areas have varying lighting needs, frequent human activity, and significant challenges in energy consumption control. For example, in a large, multi-functional office building, different floors house meeting areas, open-plan offices, corridors, and rest areas, each exhibiting significantly different levels of occupancy and usage frequency throughout the day. Traditional lighting systems often employ timed control or simple strategies based on single sensors (such as light or human body sensors), making it difficult to achieve precise dimming based on multi-source environmental data. This leads to frequent instances of over-illumination or insufficient illumination in localized areas, resulting not only in energy waste but also negatively impacting user visual comfort and spatial experience. Summary of the Invention

[0003] This application provides a load balancing method and related equipment for intelligent lighting collaborative management, which solves the problem of lack of global optimization capability in the case of sudden load changes or resource conflicts in multiple areas in related technologies.

[0004] The first aspect of this application provides a load balancing method for intelligent lighting collaborative management, the load balancing method for intelligent lighting collaborative management comprising:

[0005] Real-time acquisition of environmental parameters for each lighting area, and preprocessing of the environmental parameters;

[0006] The preprocessed environmental parameters are input into a preset deep neural network model to determine the load prediction sequence for each lighting area;

[0007] The load status of each lighting area is determined based on the load prediction sequence;

[0008] Based on the load status and real-time environmental data, a multi-regional collaborative dimming rate set is generated through a regional hierarchical collaborative strategy.

[0009] Lighting control is performed on the lighting equipment in the target lighting area based on the multi-regional coordinated dimming rate set.

[0010] Optionally, in the first implementation of the first aspect of this application, the step of real-time acquisition of environmental parameters of each lighting area and preprocessing the environmental parameters includes:

[0011] Real-time collection of environmental parameters for each lighting area to generate a raw set of environmental parameters;

[0012] The original set of environmental parameters is traversed using a sliding window mechanism to remove outliers in the data offset and generate an anomaly-filtered data sequence.

[0013] By time-aligning the data sequence, a time-synchronized multi-data stream is generated;

[0014] The multivariate data stream is normalized, and the processed multivariate data stream is spatially aggregated to generate a standardized data matrix.

[0015] Optionally, in the second implementation of the first aspect of this application, the step of inputting the preprocessed environmental parameters into a preset deep neural network model to determine the load prediction sequence for each of the lighting areas includes:

[0016] The standardized data matrix is ​​input into a preset deep neural network model to determine the data to be predicted by the deep neural network model;

[0017] Historical data of each of the lighting areas within a preset time period are obtained through the sliding window mechanism.

[0018] The historical data is input into the deep neural network model, and the load prediction value of each lighting area is output.

[0019] Error correction judgment is performed on the predicted load value;

[0020] If the prediction error exceeds the error threshold within a preset number of time windows, the load prediction value will be dynamically corrected.

[0021] The load prediction value is overwritten by the prediction value corresponding to the corrected time window to generate a load prediction sequence for each lighting area.

[0022] Optionally, in the third implementation of the first aspect of this application, the step of determining the load state of each of the lighting areas based on the load prediction sequence includes:

[0023] Extract the peak load and average load values ​​of each lighting area within a preset future time period from the load prediction sequence;

[0024] The dynamic load index is calculated based on the difference between the peak load value and the average load value, and the historical load fluctuation range.

[0025] Dynamic correction factors are matched based on the regional function type and the current time period type;

[0026] The dynamic correction factor and the dynamic load index are weighted and fused to generate the corrected load index;

[0027] Compare the revised load index with the load baseline value of the same functional area in the historical database during the same period;

[0028] When the correction index continuously exceeds the load reference value, the corresponding lighting area is marked as overloaded, and a load state matrix is ​​generated by combining the area topology.

[0029] The overloaded lighting area is subjected to load diffusion constraints based on the spatial correlation between adjacent areas, and the final load state matrix is ​​generated by adjusting the weight values ​​of the adjacent areas.

[0030] Optionally, in the fourth implementation of the first aspect of this application, the step of generating a multi-regional collaborative dimming rate set based on the load status and real-time environmental data through a regional hierarchical collaborative strategy includes:

[0031] The initial dimming rate of each lighting area is generated based on the weight values ​​of the final load state matrix and the light intensity distribution in the real-time environmental data.

[0032] The initial dimming rate is used to perform inter-regional conflict detection, and a set of conflict-free dimming rates is generated by adjusting the dimming rate difference between conflicting regions.

[0033] Based on the dynamic change rate of personnel density in real-time environmental data, a dynamic attenuation factor is applied to the dimming rate of each region in the conflict-free dimming rate set.

[0034] Based on the regional topology, particle swarm optimization is performed on the attenuated set of conflict-free dimming rates to generate a dynamic weighted dimming rate set.

[0035] The dynamic weighted dimming rate set is hierarchically fused according to regional priority and spatial correlation to generate a multi-regional collaborative dimming rate set.

[0036] Optionally, in the fifth implementation of the first aspect of this application, the step of hierarchically fusing the dynamic weighted dimming rate set according to regional priority and spatial correlation to generate a multi-regional collaborative dimming rate set includes:

[0037] Priority labels are assigned to each lighting area based on the overload level weight values ​​of the final load state matrix.

[0038] Based on the priority labels, the dynamic weighted dimming rate set is divided into different priority subsets;

[0039] Based on the different priority subsets, the global dimming rate baseline value set generated from the conflict-free dimming rate set and the local dimming rate compensation value set calculated by the edge nodes are differentially weighted according to a preset ratio; wherein, the edge nodes are distributed decision-making units corresponding to each of the lighting areas;

[0040] The multi-region collaborative dimming rate set is generated by superimposing the differentiated global dimming rate and the local dimming rate through a hierarchical fusion strategy.

[0041] Optionally, in the sixth implementation of the first aspect of this application, the step of controlling the lighting of the target lighting area based on the multi-area coordinated dimming rate set includes:

[0042] The lighting area data information is obtained based on the multi-region coordinated dimming rate set and the final load state matrix, and a control data message is generated.

[0043] The control data message is processed by multi-layer convolution based on the set of global dimming rate baseline values ​​stored at the edge nodes to generate a joint prediction data structure that reflects the relationship between global and local dimming.

[0044] Based on the joint prediction data structure and the regional topology data, a hierarchical fusion operation is performed on the global dimming rate baseline and the local dimming rate compensation data within the lighting area, and an anti-conflict dimming instruction set is generated.

[0045] The anti-collision dimming instruction set is used to issue control commands to the lighting equipment in the target lighting area;

[0046] The lighting equipment is subjected to distributed dimming operation according to the control command.

[0047] A second aspect of this application provides a load balancing device for intelligent lighting collaborative management, the load balancing device for intelligent lighting collaborative management comprising:

[0048] The processing module is used to collect environmental parameters of each lighting area in real time and preprocess the environmental parameters.

[0049] The determination module is used to input the preprocessed environmental parameters into a preset deep neural network model to determine the load prediction sequence for each of the lighting areas;

[0050] The judgment module is used to determine the load status of each of the lighting areas based on the load prediction sequence;

[0051] The generation module is used to generate a set of multi-regional collaborative dimming rates based on the load status and real-time environmental data through a regional hierarchical collaborative strategy.

[0052] The control module is used to control the lighting equipment in the target lighting area according to the multi-area coordinated dimming rate set.

[0053] A third aspect of this application provides an electronic device, including a memory and a processor, wherein the processor is configured to execute a computer program stored in the memory, and when the processor executes the computer program, it implements the steps of the load balancing method for intelligent lighting collaborative management provided in the first aspect of this application.

[0054] The fourth aspect of this application provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the steps of the load balancing method for intelligent lighting collaborative management provided in the first aspect of this application.

[0055] In summary, the load balancing method and related equipment for intelligent lighting collaborative management provided in this application involve real-time acquisition of environmental parameters for each lighting area, preprocessing these parameters, inputting the preprocessed environmental parameters into a preset deep neural network model to determine the load prediction sequence for each lighting area, judging the load status of each lighting area based on the load prediction sequence, generating a multi-area collaborative dimming rate set based on the load status and real-time environmental data through a regional hierarchical collaborative strategy, and controlling the lighting equipment in the target lighting area according to the multi-area collaborative dimming rate set. Through the implementation of this application, intelligent dimming control driven by cross-area, dynamic perception and prediction is achieved, improving the dynamic adaptability and load control accuracy of the lighting system. Attached Figure Description

[0056] Figure 1 A flowchart illustrating the load balancing method for intelligent lighting collaborative management provided in this application embodiment;

[0057] Figure 2 A schematic diagram of the program modules of a load balancing device for intelligent lighting collaborative management provided in an embodiment of this application;

[0058] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0059] To make the inventive objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0060] To address the lack of global optimization capabilities in related technologies under conditions of sudden load changes or resource conflicts in multiple regions, embodiments of this application provide a load balancing method for intelligent lighting collaborative management, such as... Figure 1 This is a flowchart illustrating the load balancing method for intelligent lighting collaborative management provided in this embodiment. The load balancing method for intelligent lighting collaborative management includes the following steps:

[0061] Step 110: Collect environmental parameters of each lighting area in real time and preprocess the environmental parameters.

[0062] Specifically, a distributed sensor network is deployed across different functional areas within the building. Through light sensors, personnel sensors, and equipment power monitoring modules, multi-dimensional parameters such as light intensity, personnel density, and lighting equipment power are acquired in real time. To ensure data quality and consistency, the collected raw data undergoes outlier removal using a sliding window mechanism, and a time alignment algorithm is employed to correct sampling clock differences between different devices, ensuring data synchronization. Based on this, continuous variables such as light intensity and personnel density are normalized to unify the data scale, ultimately constructing a standardized data matrix suitable for modeling and analysis, providing data support for subsequent intelligent prediction models.

[0063] In one optional implementation of this embodiment, the steps of real-time acquisition of environmental parameters of each lighting area and preprocessing of the environmental parameters include: real-time acquisition of environmental parameters of each lighting area to generate an original set of environmental parameters; traversing the original set of environmental parameters through a sliding window mechanism, deleting outliers with data offsets, and generating an anomaly-filtered data sequence; time-aligning the data sequence to generate a time-synchronized multi-data stream; normalizing the multi-data stream, and spatially aggregating the processed multi-data stream to generate a standardized data matrix.

[0064] Specifically, real-time environmental parameters of each lighting area are collected through a distributed sensor network to obtain multi-dimensional data such as light intensity, personnel density, and equipment power. Sensors are electronic devices that can detect physical quantities and convert them into processable signals. This is significant in constructing a detailed set of raw environmental parameters. For example, in an office building, different areas output instantaneous light intensity and personnel density data through photosensitive elements and infrared sensors, respectively, thus providing a data foundation for subsequent predictions and helping the system reflect the real-time situation. Next, a sliding window mechanism is used to traverse the raw environmental parameter set. A sliding window is a technique that continuously updates the sampled data within a fixed time period to detect data offsets caused by acquisition errors or instantaneous interference. This method can dynamically identify and delete outliers, thereby generating a data sequence filtered for anomalies. For example, if a sudden spike in the acquired value is caused by equipment failure at a certain moment, the mechanism will remove the offset data, thus ensuring the stability and reliability of the data sequence. Furthermore, time alignment is performed on the filtered data sequence. Time alignment refers to correcting and matching the data from each sensor on the time axis. Its significance lies in overcoming time discrepancies caused by the asynchronous internal clocks of different sensors. The data stream is synchronized to allow for comparison and analysis of multivariate data on the same time frame. For example, aligning illumination data from different floors can accurately reflect the environmental conditions at the same moment, thus improving the accuracy of subsequent model predictions. Normalization is then applied to the synchronized multivariate data stream. Normalization maps various data points to a unified numerical range through mathematical transformations. Its importance lies in eliminating inconsistencies in different data units and numerical scales. For example, light intensity and personnel density are normalized to the range of 0 to 1, ensuring that the model treats each input feature fairly during training. Finally, spatial aggregation integrates the normalized multivariate data stream. Spatial aggregation merges adjacent areas or similar data based on the actual physical layout to form a unified data representation. Its purpose is to eliminate the noise impact of individual sensor fluctuations. For example, averaging illumination data from each corner of an office according to spatial weights outputs a standardized data matrix, providing stable and accurate input for subsequent deep learning models. The entire process ensures that the acquired data reflects the real dynamic state of the site while eliminating noise and time bias through processing techniques, thereby optimizing overall system performance and achieving precise matching of energy consumption control.

[0065] Step 120: Input the preprocessed environmental parameters into the preset deep neural network model to determine the load prediction sequence for each lighting area.

[0066] Specifically, preprocessed environmental parameters are input into a pre-defined deep neural network model to achieve temporal prediction of lighting load. This model consists of multiple neural network layers containing temporal memory units, enabling it to identify time-dependent features in the input data. The model receives a standardized data matrix as input, uses the historical environmental conditions of each region over the previous 24 hours as a time window, and employs a sliding prediction mechanism to output a lighting load trend sequence within a pre-defined future timeframe. A dynamic learning rate adjustment strategy is introduced during training to dynamically optimize network parameters based on prediction errors, improving prediction accuracy and generalization ability. This method allows for reliable estimates of future load trends before actual lighting demand occurs, providing crucial information for proactive lighting control adjustments.

[0067] In one optional implementation of this embodiment, the step of inputting preprocessed environmental parameters into a preset deep neural network model to determine the load prediction sequence for each lighting area includes: inputting a standardized data matrix into the preset deep neural network model to determine the data to be predicted by the deep neural network model; obtaining historical data for each lighting area within a preset time period through a sliding window mechanism; inputting the historical data into the deep neural network model to output the load prediction value for each lighting area; performing error correction judgment on the load prediction value; if the prediction error of a preset number of time windows exceeds the error threshold, dynamically correcting the load prediction value; and covering the load prediction value according to the prediction value corresponding to the corrected time window to generate the load prediction sequence for each lighting area.

[0068] Specifically, when inputting the standardized data matrix into the preset deep neural network model, the data matrix obtained after normalization and spatial aggregation is first used as the model input. This matrix has been numerically converted to a uniform scale, enabling the network to eliminate inconsistencies between different parameter dimensions. This allows for accurate identification of the temporal characteristics of the environmental state in each lighting area and determination of the model's prediction data, i.e., the future lighting load change trend to be predicted. Next, a sliding window mechanism is used to acquire historical data for each lighting area within a preset time period. The sliding window mechanism involves continuous sampling within a fixed time period and capturing information about data changes over time through continuous windows. Its significance lies in reflecting the historical dynamics of the lighting area over a period of time. For example, in an office building, the personnel density and light intensity data of a certain area over the past 24 hours are integrated into continuous time-series data, providing sufficient historical basis for load prediction. The collected historical data is then input into a deep neural network model. This model includes memory units and a nonlinear transformation module. Utilizing the temporal correlations inherent in the historical data, it outputs predicted load values ​​for each lighting area, thus obtaining lighting load forecasts for a future period. This process is similar to using neurons to learn historical patterns and obtaining expected load values ​​through feedforward computation. Its significance lies in providing a foundational predictive basis for subsequent load control decisions. After outputting the predicted values, error correction is performed. This error correction aims to identify potential deviations between the predicted and actual values ​​within a continuous time window, thereby quantifying the prediction error. If the prediction error exceeds a pre-set error threshold within a preset number of consecutive time windows, a dynamic correction mechanism is activated. This mechanism adjusts the original predicted values ​​using a set dynamic correction strategy to improve prediction accuracy. The dynamic correction formula can be expressed as:

[0069] ，

[0070] in, This represents the dynamically corrected load forecast value at time t. These are the initial predictions from the neural network. and These represent the historical actual load value and the predicted load value at time j, respectively. Here, k represents the number of continuous time windows involved in the calculation, and p is a parameter that adjusts for the impact of the prediction error. To correct the scaling factor, the expression comprehensively considers the magnitude and distribution characteristics of prediction errors over several past time periods, and derives a dynamic correction amount through power-law averaging, thereby ensuring that the predicted value more closely reflects actual load changes. For example, if a region experiences a significant prediction deviation within several consecutive time windows, the overall correction amount calculated in the formula will be larger, thus making the final output prediction value more reasonable through the superposition of correction terms. Finally, the original load prediction value is overlaid based on the predicted value corresponding to the corrected time window, forming a load prediction sequence for each lighting area. This operation, through dynamically corrected data, ensures that the final generated prediction sequence can better guide the control of lighting equipment in future applications, achieving load balancing and energy consumption optimization. Its practical significance lies in enabling the intelligent lighting control system to have the ability to self-correct and adapt to constantly changing environments, thereby effectively reducing energy consumption and improving lighting comfort in practical applications.

[0071] Step 130: Determine the load status of each lighting area based on the load prediction sequence.

[0072] Specifically, the load status of each lighting area is determined based on the load prediction sequence. This is achieved by analyzing the peak and average values ​​of each area within the prediction time period to construct a dynamic load index reflecting lighting intensity. A correction factor is introduced to weight and adjust the load index based on the area's spatial function and the current time period, thus more closely reflecting actual lighting needs. The corrected load index is then compared with a baseline value in the historical database. If the load exceeds a set threshold for a consecutive time period, the area is identified as being under high load. Simultaneously, load diffusion constraints are applied to adjacent areas based on their spatial topology to reflect the load transmission effect between areas, ultimately forming a complete load status matrix as the basis for dimming strategy formulation.

[0073] In an optional implementation of this embodiment, the step of determining the load status of each lighting area based on the load prediction sequence includes: extracting the peak load value and average load value of each lighting area within a preset future time period from the load prediction sequence; calculating a dynamic load index based on the difference between the peak load value and the average load value and the historical load fluctuation range; matching a dynamic correction factor according to the area function type and the current time period type; weighting and fusing the dynamic correction factor and the dynamic load index to generate a corrected load index; comparing the corrected load index with the load benchmark value of the same functional area in the same time period in the historical database; marking the corresponding lighting area as overloaded when the corrected index continuously exceeds the load benchmark value, and generating a load status matrix based on the area topology; applying load diffusion constraints to the overloaded lighting area according to the spatial correlation of adjacent areas, and generating the final load status matrix by adjusting the weight values ​​of adjacent areas.

[0074] Specifically, extracting the peak and average loads of each lighting area from the load forecast sequence within a preset future time period allows for an accurate description of the future load fluctuations in that area. Peak load reflects the highest energy consumption level that the area may encounter, while average load provides the overall energy consumption level over a period of time. This can be obtained through statistical calculations of forecast data within the future time period. For example, in an office area where forecast data fluctuates significantly, peak loads can reveal the risk of short-term high loads, while average loads reflect the overall trend. Then, based on the difference between peak and average loads and combined with historical load fluctuation ranges, the formula for calculating the dynamic load index can be expressed as:

[0075] ,

[0076] in, This represents the dynamic load index, where P represents the peak load within a preset future time period, and A represents the average load within the same time period. This represents the historical load fluctuation range. To avoid small constants with a denominator of zero, The coefficient used to adjust sensitivity is used in this formula to non-linearly amplify load fluctuations, thereby highlighting the sensitivity of the system to larger deviations. For example, when the load in a certain area suddenly exceeds the normal fluctuation range, the index value will increase rapidly, indicating potential risks. Subsequently, based on the area's functional type and the current time period, a dynamic correction factor is matched using preset rules. This factor reflects the tolerance of different functional areas or time periods to load fluctuations. For example, a conference area may require stricter load control during peak hours, while a corridor can be moderately relaxed. Matching is achieved through a functional relationship to ensure that the load prediction results are closer to the actual situation. Next, the dynamic correction factor is weighted and fused with the dynamic load index calculated above to form a corrected load index. This process adjusts the previously obtained index by multiplying it by the correction factor, which is significant in that it further compensates for the original index, ensuring that the load prediction has universality and accuracy under different functional and time periods.

[0077] Subsequently, the generated corrected load index is compared with the load benchmark value of the same functional area in the historical database during the corresponding time period. The historical load benchmark value is a standard energy consumption level obtained through long-term statistics, used to measure whether the current load deviates from the expected range. During the comparison process, when the corrected index continuously exceeds the benchmark value, the corresponding area can be marked as overloaded. Based on this, combined with the regional topology, a load state matrix is ​​constructed using the spatial connections between regions. Physically adjacent or functionally related regions are aggregated for analysis to further reflect the load transmission effect between regions. Finally, by introducing the spatial correlation of adjacent regions, load diffusion constraints are applied to the regions marked as overloaded. By adjusting the weight values ​​of adjacent regions, the overall load state is balanced and coordinated. Its significance lies in preventing the overload of a single region from evolving into the risk of system performance imbalance. For example, in a multi-region office building, adjacent regions can help each other alleviate local overload under load diffusion constraints, thereby forming the final load state matrix, providing a scientific decision-making basis and implementation guarantee for intelligent lighting systems.

[0078] Step 140: Based on load status and real-time environmental data, generate a multi-region collaborative dimming rate set through a regional hierarchical collaborative strategy.

[0079] Specifically, based on load status and real-time environmental data, a multi-regional collaborative dimming rate set is generated through a regional hierarchical collaborative strategy. Within a local area, an initial dimming rate is generated using fuzzy rule matching based on the current load status and environmental parameters (such as real-time light distribution and personnel density) to ensure that lighting adjustments are adapted to on-site needs. At the global level, swarm intelligence algorithms such as particle swarm optimization are used to jointly optimize the initial dimming rates of multiple areas. During the optimization process, search parameters are dynamically adjusted to balance local lighting needs with overall energy-saving goals. Finally, based on regional priority and spatial correlation, the dimming rates are differentiated and fused to generate a global multi-regional collaborative dimming rate set, providing an executable parameter set for lighting control.

[0080] In one optional implementation of this embodiment, the step of generating a multi-regional collaborative dimming rate set based on load status and real-time environmental data through a regional hierarchical collaborative strategy includes: generating an initial dimming rate for each lighting region according to the weight values ​​of the final load status matrix and the light intensity distribution in the real-time environmental data; performing inter-regional conflict detection on the initial dimming rate and generating a conflict-free dimming rate set by adjusting the dimming rate difference between conflicting regions; applying a dynamic attenuation factor to the dimming rate of each region in the conflict-free dimming rate set according to the dynamic change rate of personnel density in the real-time environmental data; performing particle swarm optimization on the attenuated conflict-free dimming rate set based on regional topology to generate a dynamic weighted dimming rate set; and hierarchically fusing the dynamic weighted dimming rate set according to regional priority and spatial correlation to generate a multi-regional collaborative dimming rate set.

[0081] Specifically, the system generates an initial dimming rate for each lighting area based on its current load status and ambient lighting conditions. The load status is derived from the final load status matrix generated by the preceding prediction module, which combines the topology between areas, overload identification logic, and spatial diffusion constraints. Ambient lighting data comes from a real-time light sensor network, reflecting the intensity and distribution of natural light. By fusing these two types of information, the system can calculate a preliminary dimming rate for each lighting area, reflecting a basic balance between illuminance demand and energy consumption. For example, in areas near large windows with ample natural light, the initial dimming rate will be lower to reduce energy waste; while in densely populated, high-load inner areas, the initial dimming rate may be higher. Subsequently, to avoid uneven lighting or sudden changes in light intensity at area boundaries caused by differences in dimming rates between areas, the system will perform conflict detection of dimming rates between areas. A conflict refers to an excessively large difference in dimming rates between two spatially adjacent areas, leading to a jarring perception or visual fatigue for the user. To resolve such conflicts, the system identifies conflicting areas and iteratively adjusts their dimming rates, buffering the differences and ultimately generating a dimming set without significant dimming rate abrupt changes in the global space. After conflict resolution, the system further applies an attenuation factor based on the dynamic rate of change in population density, thereby improving the dimming system's adaptability to changes in pedestrian flow. Changes in population density not only affect local illuminance requirements but also the overall system's load adjustment strategy. Therefore, the dimming rate of the corresponding area should be dynamically adjusted when the population rapidly increases or decreases. Specifically, the dimming rate in densely populated areas will be appropriately maintained or enhanced to ensure lighting quality. In vacant or low-frequency use areas, a certain attenuation will be applied to the dimming rate to further reduce unnecessary energy consumption. To achieve globally optimal dimming effects across regions, the system uses a particle swarm optimization algorithm to deeply optimize the dimming set that has resolved conflicts and undergone attenuation correction. Particle swarm optimization (PSO) is an optimization method that simulates the collaborative evolution of swarm intelligence. It simulates the iterative movement of multiple "dimming scheme particles" in the search space. In each iteration, each particle references its historical best value and the global best value of the swarm, gradually adjusting its solution. In this way, the dimming rate of each region is not only affected by its local state but also guided by the best solutions in the entire system, reflecting the intelligence of spatially global collaborative dimming. After PSO optimization, the system needs to perform hierarchical fusion based on region priority (e.g., conference areas are higher than aisles) and spatial topology (e.g., the tightness of connection between regions). The fusion process adjusts the contribution and response amplitude of the dimming rate according to the importance of different regions in the system, ultimately generating a multi-regional collaborative dimming rate set. High-priority regions have a larger dimming rate adjustment space, while low-priority regions act more as adjustment buffers, adapting to the overall lighting strategy. Furthermore, spatial correlation also affects the fusion weight; tightly connected regions tend to have synchronous and collaborative dimming behavior to avoid local discontinuities.Ultimately, the multi-zone coordinated dimming rate set output by the system represents the optimal response of the lighting system to global energy efficiency, comfort, and dynamic adaptability under the combined effects of multiple factors such as load prediction, lighting conditions, pedestrian flow, and spatial structure. This control result not only possesses high real-time performance and adaptive capabilities but also effectively supports the intelligent lighting control needs across zones and in dynamic environments within large building spaces, demonstrating the deep integration of intelligent sensing and coordinated control.

[0082] Furthermore, the step of hierarchically fusing the dynamic weighted dimming rate set according to regional priority and spatial correlation to generate a multi-regional collaborative dimming rate set includes: assigning priority labels to each lighting region based on the overload level weight values ​​of the final load state matrix; dividing the dynamic weighted dimming rate set into different priority subsets according to the priority labels; performing differentiated weight allocation on the global dimming rate baseline value set generated from the conflict-free dimming rate set and the local dimming rate compensation value set calculated by the edge nodes according to a preset ratio based on the different priority subsets; and superimposing the differentiated global dimming rate and local dimming rate through a hierarchical fusion strategy to generate a multi-regional collaborative dimming rate set.

[0083] Specifically, edge nodes correspond to distributed decision-making units for each lighting area. In this embodiment, the overload level weight value of each lighting area in the final load state matrix serves as a key indicator of the area's energy consumption load. Based on this weight value, priority labels are assigned to each area according to a preset mapping rule. The priority label characterizes the importance and urgency of the area in the system's dimming. For example, within the same building, meeting areas or temporary activity areas may be assigned higher priorities, while corridors or secondary functional areas may receive lower priorities, thus providing a basic criterion for dimming control. Subsequently, the dynamic weighted dimming rate set obtained through particle swarm optimization is divided into different priority subsets according to the priority labels, ensuring that areas in each priority subset follow similar dimming logic in energy allocation. Then, the system targets each... The priority subset extracts a global dimming rate baseline value set generated from the conflict-free dimming rate set. This baseline value set originates from large-scale data analysis, reflecting the overall energy consumption target and lighting demand of the region. Simultaneously, the local dimming rate compensation value set calculated by edge nodes utilizes real-time detection data from distributed decision units in the local environment, reflecting local characteristics and real-time response requirements. Here, edge nodes act as distributed controllers for each lighting area, achieving more refined dimming control through the synergy of local data and global strategies. Furthermore, based on a preset ratio, differentiated weight allocation is applied to the global dimming rate baseline value and the local dimming rate compensation value, ensuring that the allocated dimming rate maintains overall energy consumption balance while also satisfying the uneven characteristics of local lighting demand. This allows the system to respond promptly to the specific situations in different areas. The formula for generating multi-area collaborative dimming rates through a hierarchical fusion strategy can be expressed as:

[0084] ,

[0085] in, This represents the final multi-region collaborative dimming rate of region i. This represents the baseline value of the global dimming rate for region i. This represents the local dimming rate compensation value calculated at the edge node of region i. The priority label for region i. The priority mapping function, whose value fluctuates between 0 and 1, is used to adjust the contribution ratio of global and local dimming rates. The purpose of this function is to make high-priority areas rely more on the global dimming rate baseline, while low-priority areas focus more on local real-time correction. In implementation, for example, an office area with high energy consumption and high priority will have a larger priority mapping function value, so the final dimming rate will be mainly determined by the global strategy. In corridors with less traffic, the mapping function value will be lower, and local compensation will play a greater role. This fusion strategy, through hierarchical and differentiated weight allocation, combined with global planning and local intelligent response, ensures that the entire lighting system achieves the dual goals of energy consumption optimization and visual comfort in multi-area collaboration.

[0086] Step 150: Control the lighting of the target lighting area based on the multi-area coordinated dimming rate set.

[0087] Specifically, the system controls the lighting equipment in the target lighting area based on a multi-zone coordinated dimming rate set. It converts the dimming rate value corresponding to each zone into specific device control commands and sends them to the lighting controllers in each zone via an asynchronous communication protocol. The control commands not only include the target brightness value but also embed a gradient rate parameter to control the smoothness of the lighting intensity change process.

[0088] In one optional implementation of this embodiment, the step of controlling the lighting equipment in the target lighting area based on a multi-regional coordinated dimming rate set includes: obtaining lighting area data information based on the multi-regional coordinated dimming rate set and the final load state matrix, and generating a control data message; performing multi-layer convolution processing on the control data message based on the global dimming rate baseline value set data stored at the edge nodes to generate a joint prediction data structure reflecting the global and local dimming relationship; performing a layered fusion operation on the global dimming rate baseline and local dimming rate compensation data within the lighting area based on the joint prediction data structure and regional topology relationship data, and generating an anti-conflict dimming instruction set; issuing control commands to the lighting equipment in the target lighting area through the anti-conflict dimming instruction set; and performing distributed dimming operation on the lighting equipment according to the control commands.

[0089] Specifically, based on the multi-regional collaborative dimming rate set and the final load status matrix, the system obtains information such as real-time dimming rate, load status, historical energy consumption records, regional identity, and spatial location of each lighting area through the data interface. Data messages are constructed according to a predefined data format. The data messages contain dimming rate suggestions and load status identifiers for the lighting equipment, which are then transmitted to the distributed control module. The construction of the data messages can provide unified data input for subsequent modules. For example, in a large office building, the real-time dimming data, load fluctuations, and environmental parameters of each office, meeting room, and corridor are packaged and transmitted according to a predetermined protocol to ensure data format standardization and information integrity. Next, the set of global dimming rate baseline values ​​stored inside the edge node is invoked. This set represents the results of long-term data acquisition and global load regulation analysis. The control data message is then sent to the multi-layer convolutional processing module. Multi-layer convolutional processing refers to the extraction, dimensionality reduction, and fusion of features in the data message through a series of convolutional filtering operations. The convolutional layers in the convolutional neural network can capture the local and global correlations between dimming rates and load states in various regions. A joint prediction data structure is obtained through continuous filtering and activation function output. This data structure is stored in matrix form, and the global and local dimming relationships are clearly reflected in the joint prediction data. For example, comparing the commonalities and differences in dimming rates between the conference room and the corridor in adjacent areas provides a more detailed basis for prediction. Subsequently, the joint prediction data structure and regional topology relationship data—which describes the spatial connections, adjacency, and functional relevance between different areas within the building—are input into the hierarchical fusion module. The hierarchical fusion operation performs hierarchical weighted integration of the global dimming rate baseline and local dimming rate compensation data. By setting weights for each level, the data fusion results can reflect the hierarchical relationship between overall lighting balance and local demand compensation in the building. The generated anti-conflict dimming instruction set contains detailed parameters for dimming operations in each lighting area in the distributed network, such as target brightness, dimming change rate, and dimming time window. This ensures that there are no abrupt changes or conflicts in the dimming rates of different areas. For example, when inconsistencies occur between adjacent areas, the system can smoothly transition the dimming rate through fusion adjustment. Finally, the anti-conflict dimming command set is transmitted to the lighting equipment in the target lighting area via the network communication module. After receiving the command, the lighting equipment performs distributed dimming operation according to the parameters contained in the command. The control unit on the lighting equipment adjusts the output brightness and power according to the command to realize the gradual change of indoor lighting. This ensures that the entire lighting system can accurately transmit dimming commands based on coordinated, hierarchical data fusion and prediction in a distributed control environment, and complete load balancing and light environment regulation.

[0090] According to the load balancing method for intelligent lighting collaborative management provided in this application, environmental parameters of each lighting area are collected in real time and preprocessed. The preprocessed environmental parameters are then input into a preset deep neural network model to determine the load prediction sequence for each lighting area. The load status of each lighting area is determined based on the load prediction sequence. Based on the load status and real-time environmental data, a multi-area collaborative dimming rate set is generated through a regional hierarchical collaborative strategy. Lighting control is then performed on the lighting equipment in the target lighting area according to the multi-area collaborative dimming rate set. Through the implementation of this application, intelligent dimming control driven by cross-area dynamic perception and prediction is realized, improving the dynamic adaptability and load control accuracy of the lighting system.

[0091] Figure 2 This application provides a load balancing device for intelligent lighting collaborative management, which can be used to implement the load balancing method for intelligent lighting collaborative management in the aforementioned embodiments. Figure 2 As shown, the load balancing device for intelligent lighting collaborative management mainly includes:

[0092] The processing module 10 is used to collect environmental parameters of each lighting area in real time and preprocess the environmental parameters.

[0093] The determination module 20 is used to input the preprocessed environmental parameters into a preset deep neural network model to determine the load prediction sequence for each lighting area;

[0094] The judgment module 30 is used to determine the load status of each lighting area based on the load prediction sequence;

[0095] The generation module 40 is used to generate a set of multi-regional collaborative dimming rates based on load status and real-time environmental data through a regional hierarchical collaborative strategy.

[0096] The control module 50 is used to control the lighting equipment in the target lighting area based on the multi-area coordinated dimming rate set.

[0097] In one optional implementation of this embodiment, the processing module is specifically used to: collect environmental parameters of each lighting area in real time and generate an original set of environmental parameters; traverse the original set of environmental parameters through a sliding window mechanism, delete outliers with data offsets, and generate an anomaly-filtered data sequence; generate a time-synchronized multi-data stream by aligning the data sequence with time; normalize the multi-data stream and spatially aggregate the processed multi-data stream to generate a standardized data matrix.

[0098] Furthermore, in an optional implementation of this embodiment, the determining module is specifically used for: inputting a standardized data matrix into a preset deep neural network model to determine the data to be predicted by the deep neural network model; obtaining historical data of each lighting area within a preset time period through a sliding window mechanism; inputting the historical data into the deep neural network model and outputting the load prediction value of each lighting area; performing error correction judgment on the load prediction value; if the prediction error of a preset number of time windows exceeds the error threshold, then dynamically correcting the load prediction value; covering the load prediction value according to the prediction value corresponding to the corrected time window to generate a load prediction sequence for each lighting area.

[0099] In an optional implementation of this embodiment, the judgment module is specifically used to: extract the peak load value and average load value of each lighting area within a preset future time period from the load prediction sequence; calculate a dynamic load index based on the difference between the peak load value and the average load value and the historical load fluctuation range; match a dynamic correction factor according to the area function type and the current time period type; weight and fuse the dynamic correction factor and the dynamic load index to generate a corrected load index; compare the corrected load index with the load benchmark value of the same functional area in the same time period in the historical database; when the corrected index continuously exceeds the load benchmark value, mark the corresponding lighting area as overloaded, and generate a load state matrix based on the area topology; apply load diffusion constraints to the overloaded lighting area according to the spatial correlation of adjacent areas, and generate the final load state matrix by adjusting the weight values ​​of adjacent areas.

[0100] Furthermore, in an optional implementation of this embodiment, the generation module is specifically used to: generate the initial dimming rate of each lighting area based on the weight values ​​of the final load state matrix and the light intensity distribution in the real-time environmental data; perform inter-regional conflict detection on the initial dimming rate, and generate a conflict-free dimming rate set by adjusting the dimming rate difference of conflicting areas; apply a dynamic attenuation factor to the dimming rate of each area in the conflict-free dimming rate set based on the dynamic change rate of personnel density in the real-time environmental data; perform particle swarm optimization on the attenuated conflict-free dimming rate set based on the regional topology relationship to generate a dynamic weighted dimming rate set; and perform hierarchical fusion of the dynamic weighted dimming rate set according to regional priority and spatial correlation to generate a multi-regional collaborative dimming rate set.

[0101] Furthermore, in an optional implementation of this embodiment, when the generation module performs the function of hierarchically fusing the dynamic weighted dimming rate set according to regional priority and spatial correlation to generate a multi-regional collaborative dimming rate set, it is specifically used for: assigning priority labels to each lighting region based on the overload level weight value of the final load state matrix; dividing the dynamic weighted dimming rate set into different priority subsets according to the priority labels; and performing differentiated weight allocation on the global dimming rate baseline value set generated from the conflict-free dimming rate set and the local dimming rate compensation value set calculated by the edge nodes according to a preset ratio based on the different priority subsets; wherein, the edge nodes are distributed decision-making units corresponding to each lighting region; and superimposing the differentiated global dimming rate and local dimming rate through a hierarchical fusion strategy to generate a multi-regional collaborative dimming rate set.

[0102] In one optional implementation of this embodiment, the control module is used to: obtain lighting area data information based on the multi-region collaborative dimming rate set and the final load state matrix, and generate control data messages; perform multi-layer convolution processing on the control data messages based on the global dimming rate baseline value set data stored at the edge nodes, and generate a joint prediction data structure reflecting the global and local dimming relationship; perform a layered fusion operation on the global dimming rate baseline and local dimming rate compensation data within the lighting area based on the joint prediction data structure and the regional topology relationship data, and generate an anti-conflict dimming instruction set; issue control commands to the lighting equipment in the target lighting area through the anti-conflict dimming instruction set; and perform distributed dimming operation on the lighting equipment according to the control commands.

[0103] According to the load balancing device for intelligent lighting collaborative management provided in this application, environmental parameters of each lighting area are collected in real time and preprocessed. The preprocessed environmental parameters are then input into a preset deep neural network model to determine the load prediction sequence for each lighting area. The load status of each lighting area is determined based on the load prediction sequence. Based on the load status and real-time environmental data, a multi-area collaborative dimming rate set is generated through a regional hierarchical collaborative strategy. The lighting equipment in the target lighting area is then controlled according to the multi-area collaborative dimming rate set. Through the implementation of this application, intelligent dimming control driven by cross-area dynamic perception and prediction is realized, improving the dynamic adaptability and load control accuracy of the lighting system.

[0104] According to the scheme provided in this application Figure 3 An electronic device is provided as an embodiment of this application. This electronic device can be used to implement the load balancing method for intelligent lighting collaborative management in the foregoing embodiments, and mainly includes:

[0105] The system includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and executable on the processor 302. The memory 301 and the processor 302 are connected via communication. When the processor 302 executes the computer program 303, it implements the load balancing method for intelligent lighting collaborative management in the aforementioned embodiments. The number of processors can be one or more.

[0106] The memory 301 can be a high-speed random access memory (RAM) or a non-volatile memory, such as a disk storage device. The memory 301 is used to store executable program code, and the processor 302 is coupled to the memory 301.

[0107] Furthermore, embodiments of this application also provide a computer-readable storage medium, which may be disposed in the electronic device described in the above embodiments, and the computer-readable storage medium may be as described above. Figure 3 The memory in the illustrated embodiment.

[0108] The computer-readable storage medium stores a computer program that, when executed by a processor, implements the load balancing method for intelligent lighting collaborative management in the aforementioned embodiments. Furthermore, the computer-readable storage medium can also be a USB flash drive, external hard drive, read-only memory (ROM), RAM, magnetic disk, or optical disk, or any other medium capable of storing program code.

[0109] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0110] If the integrated unit is implemented as 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 this application, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0111] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A load balancing method for intelligent lighting collaborative management, characterized in that, include: Real-time acquisition of environmental parameters for each lighting area, and preprocessing of the environmental parameters; The preprocessed environmental parameters are input into a preset deep neural network model to determine the load prediction sequence for each lighting area; The load status of each lighting area is determined based on the load prediction sequence; Based on the load status and real-time environmental data, a multi-regional collaborative dimming rate set is generated through a regional hierarchical collaborative strategy. Lighting control is performed on the lighting equipment in the target lighting area based on the multi-regional coordinated dimming rate set; The step of determining the load status of each lighting area based on the load prediction sequence includes: Extract the peak load and average load values ​​of each lighting area within a preset future time period from the load prediction sequence; The dynamic load index is calculated based on the difference between the peak load value and the average load value, and the historical load fluctuation range. Dynamic correction factors are matched based on the regional function type and the current time period type; The dynamic correction factor and the dynamic load index are weighted and fused to generate the corrected load index; Compare the revised load index with the load baseline value of the same functional area in the historical database during the same period; When the correction index continuously exceeds the load reference value, the corresponding lighting area is marked as overloaded, and a load state matrix is ​​generated by combining the area topology. Based on the spatial correlation between adjacent regions, a load diffusion constraint is applied to the overloaded lighting area, and the final load state matrix is ​​generated by adjusting the weight values ​​of the adjacent regions. The step of generating a multi-regional collaborative dimming rate set based on the load status and real-time environmental data through a regional hierarchical collaborative strategy includes: The initial dimming rate of each lighting area is generated based on the weight values ​​of the final load state matrix and the light intensity distribution in the real-time environmental data. The initial dimming rate is used to perform inter-regional conflict detection, and a set of conflict-free dimming rates is generated by adjusting the dimming rate difference between conflicting regions. Based on the dynamic change rate of personnel density in real-time environmental data, a dynamic attenuation factor is applied to the dimming rate of each region in the conflict-free dimming rate set. Based on the regional topology, particle swarm optimization is performed on the attenuated set of conflict-free dimming rates to generate a dynamic weighted dimming rate set. The dynamic weighted dimming rate set is hierarchically fused according to regional priority and spatial correlation to generate a multi-regional collaborative dimming rate set.

2. The load balancing method for intelligent lighting collaborative management according to claim 1, characterized in that, The step of real-time acquisition of environmental parameters for each lighting area and preprocessing the environmental parameters includes: Real-time collection of environmental parameters for each lighting area to generate a raw set of environmental parameters; The original set of environmental parameters is traversed using a sliding window mechanism to remove outliers in the data offset and generate an anomaly-filtered data sequence. By time-aligning the data sequence, a time-synchronized multi-data stream is generated; The multivariate data stream is normalized, and the processed multivariate data stream is spatially aggregated to generate a standardized data matrix.

3. The load balancing method for intelligent lighting collaborative management according to claim 2, characterized in that, The step of inputting the preprocessed environmental parameters into a preset deep neural network model to determine the load prediction sequence for each of the lighting areas includes: The standardized data matrix is ​​input into a preset deep neural network model to determine the data to be predicted by the deep neural network model; Historical data of each of the lighting areas within a preset time period are obtained through the sliding window mechanism. The historical data is input into the deep neural network model, and the load prediction value of each lighting area is output. Error correction judgment is performed on the predicted load value; If the prediction error exceeds the error threshold within a preset number of time windows, the load prediction value will be dynamically corrected. The load prediction value is overwritten by the prediction value corresponding to the corrected time window to generate a load prediction sequence for each lighting area.

4. The load balancing method for intelligent lighting collaborative management according to claim 1, characterized in that, The step of hierarchically fusing the dynamic weighted dimming rate set according to regional priority and spatial correlation to generate a multi-regional collaborative dimming rate set includes: Priority labels are assigned to each lighting area based on the overload level weight values ​​of the final load state matrix. Based on the priority labels, the dynamic weighted dimming rate set is divided into different priority subsets; Based on the different priority subsets, the global dimming rate baseline value set generated from the conflict-free dimming rate set and the local dimming rate compensation value set calculated by the edge nodes are differentially weighted according to a preset ratio; wherein, the edge nodes are distributed decision-making units corresponding to each of the lighting areas; The multi-region collaborative dimming rate set is generated by superimposing the differentiated global dimming rate and the local dimming rate through a hierarchical fusion strategy.

5. The load balancing method for intelligent lighting collaborative management according to claim 4, characterized in that, The step of controlling the lighting of the target lighting area based on the multi-area coordinated dimming rate set includes: The lighting area data information is obtained based on the multi-region coordinated dimming rate set and the final load state matrix, and a control data message is generated. The control data message is processed by multi-layer convolution based on the set of global dimming rate baseline values ​​stored at the edge nodes to generate a joint prediction data structure that reflects the relationship between global and local dimming. Based on the joint prediction data structure and the regional topology data, a hierarchical fusion operation is performed on the global dimming rate baseline and the local dimming rate compensation data within the lighting area, and an anti-conflict dimming instruction set is generated. The anti-collision dimming instruction set is used to issue control commands to the lighting equipment in the target lighting area; The lighting equipment is subjected to distributed dimming operation according to the control command.

6. A load balancing device for intelligent lighting collaborative management, characterized in that, The load balancing device for intelligent lighting collaborative management includes: The processing module is used to collect environmental parameters of each lighting area in real time and preprocess the environmental parameters. The determination module is used to input the preprocessed environmental parameters into a preset deep neural network model to determine the load prediction sequence for each of the lighting areas; The judgment module is used to determine the load status of each of the lighting areas based on the load prediction sequence; The generation module is used to generate a set of multi-regional collaborative dimming rates based on the load status and real-time environmental data through a regional hierarchical collaborative strategy. The control module is used to control the lighting equipment in the target lighting area according to the multi-area coordinated dimming rate set; The judgment module is further configured to extract the peak load value and average load value of each lighting area within a preset future time period from the load prediction sequence. The dynamic load index is calculated based on the difference between the peak load value and the average load value, and the historical load fluctuation range. Dynamic correction factors are matched based on the regional function type and the current time period type; The dynamic correction factor and the dynamic load index are weighted and fused to generate the corrected load index; Compare the revised load index with the load baseline value of the same functional area in the historical database during the same period; When the correction index continuously exceeds the load reference value, the corresponding lighting area is marked as overloaded, and a load state matrix is ​​generated by combining the area topology. Based on the spatial correlation between adjacent regions, a load diffusion constraint is applied to the overloaded lighting area, and the final load state matrix is ​​generated by adjusting the weight values ​​of the adjacent regions. The generation module is also used to generate the initial dimming rate of each of the lighting areas based on the weight values ​​of the final load state matrix and the light intensity distribution in the real-time environmental data. The initial dimming rate is used to perform inter-regional conflict detection, and a set of conflict-free dimming rates is generated by adjusting the dimming rate difference between conflicting regions. Based on the dynamic change rate of personnel density in real-time environmental data, a dynamic attenuation factor is applied to the dimming rate of each region in the conflict-free dimming rate set. Based on the regional topology, particle swarm optimization is performed on the attenuated set of conflict-free dimming rates to generate a dynamic weighted dimming rate set. The dynamic weighted dimming rate set is hierarchically fused according to regional priority and spatial correlation to generate a multi-regional collaborative dimming rate set.

7. An electronic device, characterized in that, Includes memory and processor, of which: The processor is used to execute computer programs stored in the memory; When the processor executes the computer program, it implements the steps in the load balancing method for intelligent lighting collaborative management as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the load balancing method for intelligent lighting collaborative management as described in any one of claims 1 to 5.

Images