Energy efficiency management system for stadium

Abstract

According to the intelligent stadium energy efficiency management system provided by the invention, activity data in the stadium are accurately captured through the real-time monitoring module, air conditioning and illumination are automatically adjusted by using the environment self-adaptive adjustment module, and optimization of energy consumption is realized. The system adopts an advanced sensor network, a data processing algorithm and a machine learning model, including ARIMA and LSTM, to predict an energy consumption trend and formulate an intelligent scheduling strategy. In addition, the system comprises functions of dynamic data acquisition frequency adjustment and energy consumption monitoring and recording, and a user-friendly interface control and intelligent energy-saving unit. Green energy integration and carbon footprint estimation enhance the environmental protection characteristics of the system. The system not only improves the energy use efficiency, but also supports the goals of sustainability and environmental protection.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent building management systems, and particularly to an energy efficiency management system applied to stadiums. Background Art

[0002] Existing energy efficiency management systems for stadiums mostly adopt simple automation control strategies and lack the ability to respond in real time to the usage situation of the stadium and environmental changes. For example, many systems are unable to dynamically adjust the operating parameters of energy-intensive equipment such as air conditioners and lighting according to the real-time game process, changes in the number of spectators, or indoor and outdoor environmental conditions, resulting in energy waste and poor environmental control effects. In addition, existing systems have limited capabilities in energy consumption prediction and scheduling and are difficult to achieve refined and personalized energy management. Summary of the Invention

[0003] To solve the above problems, the present invention provides an intelligent stadium energy efficiency management system, and its central feature is a real-time activity monitoring module. This module can accurately capture and analyze the real-time data of various activities in the stadium, including activity types, the number of participants, activity intensity, etc., providing an accurate basis for the system to adjust energy consumption.

[0004] To achieve the above object, the present application adopts the following technical solutions:

[0005] An energy efficiency management system for a stadium, comprising:

[0006] - A real-time activity monitoring module, using a macro-layer and a micro-layer sensor network, which are respectively deployed in different areas of the stadium to achieve full coverage;

[0007] - An environment adaptive adjustment module, which automatically adjusts the operating parameters of air conditioners and lighting equipment according to real-time monitoring data and preset thresholds through a PID control algorithm;

[0008] - An energy consumption prediction and intelligent scheduling module, which uses time series analysis and machine learning models to predict energy consumption trends and optimize energy usage strategies.

[0009] The real-time activity monitoring module further includes: an infrared imaging monitoring unit, which is deployed in the spectator stands, the competition venue, and the rest area and has a time resolution of at least 0.1 second; a video analysis and processing unit, which uses a deep learning-based pedestrian flow calculation algorithm with an accuracy of not less than 95%.

[0010] The environment adaptive adjustment module further includes: a temperature and humidity sensing unit, which is deployed in key areas and has a temperature measurement accuracy of at least ±0.5°C and a humidity measurement accuracy of ±2%; a light intensity sensing unit, which uses lux units and automatically adjusts the brightness according to a preset light intensity threshold, and the threshold range is 300 lx to 1000 lx.

[0011] The energy consumption prediction and intelligent scheduling module further includes: an energy consumption prediction algorithm processing unit that implements energy consumption prediction based on the ARIMA model, where the autoregressive (AR) order p ranges from 1 to 3, the differencing (I) order d is 0 or 1, and the moving average (MA) order q ranges from 1 to 2; a deep learning energy consumption analysis unit that analyzes time series data based on the LSTM model to identify at least 3 different energy consumption patterns.

[0012] The energy efficiency management system further includes: a data collection frequency dynamic adjustment unit that automatically adjusts the data collection frequency according to the activity type and the change in the number of audiences, and the frequency range is from 1 time per second to 1 time per minute; an energy consumption monitoring and recording unit that real-time records the total energy consumption and sub-item energy consumption of the venue, such as lighting, air conditioning, and equipment operation, etc., and the recording accuracy is ±1%.

[0013] The method of the energy efficiency management system includes the following steps: using the data collection and processing unit, adopting the Kalman filter and fuzzy logic algorithms to remove the noise in the sensor data and improve the data quality; using the data processing and analysis unit, adopting a distributed database system to store and retrieve data, and using the consistent hashing algorithm for data storage, and the total number of nodes is a power of 2.

[0014] The system further includes: a user interface control unit that provides at least two language options and supports at least 10 different environmental control parameter settings; an intelligent energy-saving control unit that is automatically activated according to real-time data and prediction results, and the energy-saving ratio is adjustable, with a range of 5% to 30%.

[0015] A computer-readable storage medium stores a computer program thereon, and the program is designed to perform the following operations: implementing a real-time monitoring and data analysis display unit that displays at least 5 different energy consumption indicators; - implementing an environment adaptive adjustment and energy consumption prediction unit that provides at least 3 different prediction models and scheduling strategies.

[0016] A computer device includes a processor and a memory. A computer program is stored on the memory, and the program is designed to implement the functions of the energy efficiency management system. Moreover, the processor and the memory further optimize the real-time performance and data processing ability of the system, where the processing speed of the processor is not lower than 2 GHz, and the capacity of the memory is not less than 4 GB.

[0017] The system or method further includes: a green energy utilization control unit that integrates solar photovoltaic panels and wind turbines, the energy conversion efficiency of the photovoltaic panels is not lower than 15%, and the power coefficient of the wind turbines is not lower than 0.3; a energy storage device management unit that uses a battery energy storage system to store energy not less than the total energy consumption of the venue for one day; a carbon footprint estimation unit that calculates the carbon emissions of the venue, supports carbon emission reduction strategies, and the reduction ratio is not less than 20%.

[0018] Through the above technical solutions, an energy efficiency management system for stadiums according to the present invention is provided. The system utilizes advanced sensor technologies, data processing algorithms, machine learning models, and automated control technologies to achieve real-time monitoring, analysis, and optimized management of the energy consumption within the stadium. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] To make the embodiments, technical solutions, and technical advantages of this application clearer, the following drawings provide non-limiting views of this application:

[0020] Figure 1 It shows a schematic diagram of the overall architecture of the stadium energy efficiency management system.

[0021] Figure 2 It shows the working principle diagram of the real-time activity monitoring module.

[0022] Figure 3 It shows the control flow chart of the environment adaptive adjustment module.

[0023] Figure 4 It shows the data processing flow chart of the energy consumption prediction and intelligent scheduling module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] To elaborate in detail the embodiments, technical solutions, and their technical advantages of this application, the following will provide a detailed and complete description in conjunction with the drawings. It should be clear that the described embodiments only represent some application scenarios of this application, rather than all possibilities. According to the embodiments of this disclosure, those skilled in the art can obviously obtain other possible embodiments without creative efforts, and these embodiments also fall within the protection scope of this application.

[0025] I. DATA COLLECTION

[0026] To ensure comprehensive monitoring of the environment and activities within the stadium, a multi-level and high-density sensor network is designed. These sensors are optimally arranged according to the structure and functional areas of the stadium to ensure seamless coverage. The sensor network adopts a hierarchical design, including a macro layer and a micro layer. The macro layer sensors are responsible for monitoring the environmental parameters of the entire stadium, while the micro layer sensors are deployed in key areas such as the spectator stands, playing field, and rest areas to provide more refined data.

[0027] Using infrared imaging technology and video analysis software, the real-time monitoring of the flow of spectators in and out and the seat occupancy situation is carried out. Through the sensors set at the entrances and exits, the system can accurately count the number of people and predict peak hours. Using video analysis software, the spectator flow is calculated through the following formula:

[0028]

[0029] Where Ft is the number of audience flow within time Δt, N in is the number of audiences entering, N out is the number of audiences leaving.

[0030] The temperature and humidity sensor array is distributed in each area of the venue, monitoring and recording temperature and humidity data in real time. These data are crucial for adjusting the air conditioning system to maintain the comfort of audiences and athletes. The temperature and humidity sensors use the following formula to define the comfort range:

[0031] T comfort = T base + a·RH + b

[0032] Here, T comfort is the comfortable temperature, T base is the base temperature, RH is the relative humidity, and a and b are coefficients determined based on ergonomic research.

[0033] The illuminance sensor monitors the illumination level in the venue, and the intelligent lighting system adjusts the brightness accordingly to meet visual needs and save energy. The sound sensor analyzes background noise and audience reactions to assist in adjusting the audio system. The illuminance sensor uses lux (lx) as the unit, and the sound intensity uses decibel (dB) as the unit. The system sets thresholds according to the activity type and automatically adjusts the lighting and sound systems.

[0034] All sensor data are transmitted through a synchronous network to ensure data consistency and accuracy. Each data point is timestamped for time series analysis and historical data comparison. The network time protocol (NTP) is used for data synchronization to ensure time consistency for all sensors. The timestamp format follows the ISO 8601 standard.

[0035] To ensure data quality, the system implements a multiple data verification mechanism, including sensor self - calibration, data cross - verification, and outlier removal. These measures ensure data reliability and analysis accuracy. Outlier removal uses the standard deviation method:

[0036] Remove outliers if / xi - μ / > k·σ

[0037] where, x i is a single data point, μ is the average value, σ is the standard deviation, and k is the threshold coefficient, usually taking 3 or higher.

[0038] An energy consumption monitoring module is specially designed to record the total energy consumption and sub - item energy consumption of the venue in real time, such as lighting, air conditioning, and equipment operation, etc. These data are crucial for energy consumption prediction and energy - saving strategies.

[0039] Dynamically adjust the data collection frequency according to the usage pattern of the venue and the type of event. For example, increase the collection frequency during large-scale events to capture the rapidly changing environment and event status.

[0040] To further enhance the intelligence and accuracy of data collection, the system adopts the following mathematical models and algorithms:

[0041] Adopt algorithms such as Kalman filtering to remove noise in sensor data and improve data quality. The Kalman filter uses the following formulas for state estimation and error covariance update:

[0042]

[0043] P k|k =(I-K k H)P k|k-1

[0044] Here, is the optimal state estimate at time k, P k|k is the estimated covariance, K k is the Kalman gain, Z k is the observation value, and H is the observation model.

[0045] Use algorithms such as fuzzy logic and neural networks to fuse data from different sensors to provide a more comprehensive understanding of the scenario. Data fusion uses the weighted average method:

[0046]

[0047] where s is the fused data, s i is the data of the i-th sensor, and ω i is the corresponding weight.

[0048] Based on time series analysis and machine learning models such as ARIMA, random forest, and gradient boosting machine, predict future environmental parameters and energy consumption trends. Time series prediction uses the ARIMA model, whose parameters include the autoregressive (AR) order p, the differencing (I) order d, and the moving average (MA) order q.

[0049] Implement an anomaly detection algorithm based on statistics and clustering analysis to timely detect abnormal patterns in the data and provide support for fault diagnosis and maintenance. Anomaly detection uses the Z-Score-based algorithm:

[0050]

[0051] If the absolute value of Z exceeds a certain threshold (usually 3), then x is considered an outlier.

[0052] II. Data Transmission and Processing

[0053] The collected data is transmitted to the central processing unit through an encrypted wireless communication network to ensure data security and privacy protection during the transmission process. An efficient data transmission protocol is adopted to reduce packet loss and latency and ensure data real-time performance. To ensure the security of data during transmission, the Advanced Encryption Standard (AES) algorithm is used to encrypt the data: E(k,m)→c where E represents the encryption function, k is the encryption key, m is the original data (plaintext), and c is the encrypted data (ciphertext).

[0054] The data transmission efficiency is achieved by optimizing the packet size and transmission frequency to reduce latency and packet loss rate. The sliding window protocol is used to control data transmission, where the window size W can be dynamically adjusted according to network conditions: W=min(W max , W network ) Here, W max is the theoretically maximum window size, and W network is the window size allowed by the current network conditions.

[0055] At the central processing unit, the received data is first subjected to fusion processing to integrate data streams from different sensors. Timestamps are used to synchronize the data to ensure data consistency. The data fusion algorithm can process multi-source data and provide a more accurate description of the environment and activity status. The data fusion algorithm uses the weighted average method to integrate data from different sensors:

[0056]

[0057] where S fused is the fused data value, S i is the data value of the i-th sensor, ω i is the corresponding weight, and n is the total number of sensors.

[0058] Data storage adopts a distributed database system to support the storage and rapid retrieval of large-scale data. The database management system (RDBMS) and non-relational database (NoSQL) are used in combination to meet the storage requirements of structured and unstructured data. The distributed database system uses the consistent hashing algorithm to allocate data to different nodes: node_id=hash(key)modN Here, key is the key value of the data, hash is the hash function, N is the total number of nodes, and node_id is the node number where the data is stored.

[0059] Before data analysis, data preprocessing is carried out, including data cleaning, normalization, denoising, and feature extraction. Data cleaning removes invalid or incorrect data records, normalization processes data with different formats and dimensions, denoising uses filtering techniques to reduce random fluctuations in the data, and feature extraction extracts useful information from the original data. Data normalization uses the Z-Score normalization method:

[0060]

[0061] where z i is the normalized data value, x i is the original data value, μ is the mean of the data, and σ is the standard deviation of the data.

[0062] Data analysis uses statistical analysis and machine learning techniques to mine patterns and associations in the data. Methods such as clustering analysis and principal component analysis (PCA) are used for data dimensionality reduction to simplify the model and extract key features. Association rule learning discovers the associations between different parameters, such as the relationship between temperature and audience flow. Principal component analysis (PCA) uses eigenvalue decomposition of the covariance matrix for dimensionality reduction:

[0063] C = QΛQ T

[0064] Here, C is the covariance matrix, Λ is the eigenvalue matrix, and Q is the eigenvector matrix.

[0065] To meet the real-time requirements, the system uses stream data processing technology to perform real-time analysis and processing of the data. Tools such as Apache Kafka and Apache Storm are used to achieve real-time data collection, transmission, and processing. Stream data processing uses the concept of time windows to process events in the data stream: window = {e ∣ t - Δt ≤ e.timestamp < t} Here, window is the set of events in the time window, e is the event, t is the current time, and Δt is the size of the time window.

[0066] Data visualization is an important means to help users understand the results of data analysis. The system provides a dynamic data visualization interface, including real-time data charts, historical data trend analysis, energy consumption distribution maps, etc., enabling users to intuitively understand the energy efficiency status of the venue. Data visualization uses dynamic charts and color coding to display real-time data and trends:

[0067] color = f(data_value, min_value, max_value)

[0068] Here, color is the color calculated based on the data value, f is the color mapping function, data_value is the data value, and min_value and max_value are the minimum and maximum values of the data.

[0069] The system implements a comprehensive data security policy, including data encryption, access control, network security, etc. Data is regularly backed up to prevent data loss or damage. During the data backup process, an incremental backup and full backup combination strategy is adopted to ensure data integrity and recoverability. The data backup strategy uses a combination of incremental backup and full backup:

[0070] backup_type = {'full', 'incremental'}

[0071] Here, backup_type represents the backup type, and full backup or incremental backup is selected according to a predefined backup plan or the amount of data change.

[0072] III. Intelligent Analysis

[0073] The core of the intelligent analysis module is a series of prediction models, which are trained through machine learning algorithms based on historical data and real-time data. The models include but are not limited to:

[0074] Time series prediction models: such as ARIMA, Seasonal-Trend decomposition using Loess (STL), used to predict energy consumption trends and audience flow. The ARIMA model combines autoregression (AR), differencing (I), and moving average (MA) to predict future values:

[0075]

[0076] where, Y t is the value of the time series at time t, φ i and θ j are model parameters, B is the backshift operator, d is the order of differencing, ∈ t is the error term.

[0077] Classification models: such as Support Vector Machine (SVM), Random Forest, used to identify and classify different types of activity patterns. Support Vector Machine (SVM) uses the following optimization problem to find the optimal separating hyperplane:

[0078]

[0079] s.t.y i (w·x i +b)≥1 - ξ i , ξ i ≥0

[0080] Among them, w is the weight vector, b is the bias term, C is the regularization parameter, and ξ i is the slack variable.

[0081] The system uses deep learning techniques, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), to process image and time series data. Deep learning models can learn from complex data patterns and provide highly accurate predictions. The convolutional neural network (CNN) uses the following forward propagation formula:

[0082] h i = f(W i * x + b i )

[0083] Among them, h i is the i-th feature map, W i is the convolutional kernel, * represents the convolution operation, b i is the bias term, and f is the activation function.

[0084] The RNN unit updates the hidden state using the following recurrence formula:

[0085] h t = tanh(W hh h t-1 + W xh x t + b h )

[0086] Among them, h t is the hidden state at time t, x t is the input, W hh and W xh are the weight matrices, and b h is the bias term.

[0087] Feature engineering is a key step in intelligent analysis. The system automatically identifies and selects the features that are most useful for the prediction task, including environmental parameters, audience behavior patterns, device status, etc. Feature selection can use mutual information to measure the relationship between features and target variables:

[0088]

[0089] Here, I represents mutual information, X and Y are random variables, p(x,y) is the joint probability distribution, and p(x) and p(y) are the marginal probability distributions.

[0090] Techniques such as cross-validation and grid search are used to optimize the model parameters and improve the generalization ability of the model. During the model training process, metrics such as accuracy, recall, and F1 score are used to evaluate the model performance. Cross-validation can reduce the risk of overfitting of the model:

[0091]

[0092] Among them, CV is the result of cross-validation, k is the number of folds, and MSE i is the mean squared error of the i-th fold.

[0093] The intelligent analysis module provides real-time analysis capabilities and quickly responds to changes in the venue. The analysis results are used for decision support to help managers formulate energy efficiency optimization strategies. Real-time analysis can adopt online learning algorithms such as Stochastic Gradient Descent (SGD):

[0094]

[0095] Here, wt is the parameter of the model at time t, η is the learning rate, is the gradient, Loss is the loss function, x t and y t are the input and target at time t, respectively.

[0096] IV. Environment Adaptive Regulation

[0097] Based on the prediction data and real-time monitoring data provided by the intelligent analysis module, the air conditioning system can automatically adjust the temperature and humidity to meet the needs of the audience and athletes. Advanced PID control algorithms and fuzzy logic are adopted to achieve smoother and more accurate temperature and humidity control. The PID controller calculates the control signal through the following formula:

[0098]

[0099] Among them, u(t) is the control signal, K p , K i and K d are the proportional, integral, and derivative gains respectively, e(t) is the deviation signal, ∫e(t)dt is the integral of the deviation, is the derivative of the deviation.

[0100] The fuzzy logic controller uses fuzzy sets and fuzzy rules to handle uncertainties and nonlinear problems. The general form of fuzzy logic is:

[0101] IF X IS A THEN Y IS B

[0102] Here, X and Y are the input and output variables, A and B are fuzzy sets, and IS and THEN are the connectives of fuzzy logic.

[0103] The lighting system automatically adjusts the brightness and color temperature according to the activity type in the venue and the illuminance sensor data. During off-peak hours, the system can reduce the lighting intensity to save energy; during large events, the lighting is enhanced to meet the visual needs. The lighting system uses the following formula to adjust the brightness:

[0104] I new =I old ×α

[0105] Wherein, I new is the new brightness value, I old is the old brightness value, and α is the adjustment coefficient.

[0106] The color temperature adjustment can be achieved by adjusting the brightness of different color LED lights:

[0107] T new =f(R new , G new , B new )

[0108] Wherein, T new is the new color temperature value, R new , G new and B new are the new brightness values of the red, green, and blue LED lights respectively, and f is the color temperature calculation function.

[0109] Using the data collected by the sound sensor, intelligently analyze the audience's reaction and the background noise level in the venue. The audio system automatically adjusts the volume and sound quality accordingly to ensure that the audience can clearly hear the game and broadcast information. The volume adjustment of the audio system can use the following formula:

[0110] V new =V old +ΔV

[0111] Wherein, V new is the new volume value, V old is the old volume value, and ΔV is the volume change amount.

[0112] The system monitors the air quality in the venue, including indicators such as carbon dioxide concentration and VOCs. According to the monitoring results, intelligently turn on or adjust the fresh air system and air purification equipment to keep the indoor air fresh. The turning on and adjustment of the fresh air system can be determined according to the carbon dioxide concentration:

[0113]

[0114] Here, CO 2 is the current carbon dioxide concentration, and CO 2，set is the set carbon dioxide concentration threshold.

[0115] The environment adaptive adjustment is not only based on real-time data, but also takes into account the usage pattern of the venue and the expected experience of the audience. The system formulates personalized environment control strategies according to the activity type, the number of audiences, and the environmental conditions. The environment control strategy can be achieved using multi-objective optimization:

[0116] min x f(x) s.t. g i (x) ≤ 0, h j (x) = 0

[0117] where f(x) is the objective function, x is the decision variable, and g i (x) and are the inequality and equality constraints respectively.

[0118] On the premise of ensuring comfort, the system gives priority to energy conservation. For example, the temperature is appropriately increased in areas with fewer audiences, and the brightness is reduced while ensuring lighting requirements. Energy conservation adjustment can be achieved through the following formula: E new = E old × (1 - ∈)

[0119] where E new is the new energy consumption value, E old is the old energy consumption value, and ∈ is the energy conservation ratio.

[0120] The system provides a user interface that allows managers to adjust environmental control parameters according to specific requirements. Users can set the thresholds of temperature, humidity, lighting, and sound to meet the requirements of special events. User-defined settings can be adjusted through the following formula:

[0121] x new = x old + Δx

[0122] where x new is the new parameter value, x old is the old parameter value, and Δx is the parameter change amount set by the user.

[0123] The environment adaptive adjustment module is linked with other system modules (such as the energy consumption prediction and scheduling module) to achieve overall optimization. For example, according to the energy consumption prediction results, the environmental settings are adjusted in advance to reduce energy waste. Intelligent linkage control can be achieved through the following formula:

[0124] y new = F(x old , Z)

[0125] where y new is the new state after linkage control, F is the linkage function, x old is the old state, and z is the input of other modules.

[0126] V. Energy Consumption Prediction and Scheduling

[0127] The system uses a variety of prediction models to analyze energy consumption data, including but not limited to:

[0128] Statistical models: such as linear regression and exponential smoothing, are used for short-term energy consumption prediction. The linear regression model is used to predict the relationship between energy consumption and time:

[0129]

[0130] where, is the predicted energy consumption value, X 1 ,..., X n are explanatory variables, β 0 is the intercept term, β 1 ,..., β n are regression coefficients.

[0131] The exponential smoothing model is used for short-term energy consumption prediction:

[0132] Y t+1 = αY t + (1 - α)Y t-1

[0133] where, Y t+1 is the predicted value at the next time point, Y t and Y t-1 are the actual values at the current and previous time points, and α is the smoothing coefficient.

[0134] Machine learning models: such as decision trees and gradient boosting machines (GBMs), are used for medium- and long-term energy consumption trend prediction. Decision trees split data into different branches through a series of questions for classification or regression:

[0135]

[0136] where, is the predicted energy consumption value, w i is the weight of the i-th branch, and Y i is the average energy consumption value of this branch.

[0137] Gradient boosting machines minimize the loss function by iteratively adding weak prediction models (usually decision trees):

[0138]

[0139] where, is the predicted energy consumption value, M is the number of iterations, v m is the weight of the m-th weak prediction model, is the prediction function of the m-th weak prediction model.

[0140] Deep learning models: such as long short-term memory networks (LSTMs), are used to capture long-term dependencies in time series data. LSTMs are used to capture long-term dependencies in time series data:

[0141]

[0142] Among them, is the hidden state at time t, X t is the input data, is the hidden state at the previous time point.

[0143] Energy consumption prediction is based on real-time monitoring data and historical energy consumption data, combined with the usage patterns of the venue and external environmental factors such as weather conditions and seasonal changes. The training of the prediction model can use cross-validation to evaluate the model performance:

[0144]

[0145] Among them, CV is the result of cross-validation, k is the number of folds, and MSE i is the mean squared error of the i-th fold.

[0146] The prediction results are used to guide the energy scheduling and management of the venue. The system optimizes the energy usage strategy according to the predicted energy consumption demand, such as adjusting the operation plan of the equipment, to achieve the reasonable distribution of energy. According to the prediction results, the system can optimize the operation plan of the equipment:

[0147] Energy optimized =Energy predicted ×η

[0148] Among them, Energy optimized is the optimized energy consumption, Energy predicted is the predicted energy consumption, and η is the adjustment coefficient.

[0149] The system automatically adjusts the energy supply and distribution according to the energy consumption prediction results. By adopting optimization algorithms such as genetic algorithms and particle swarm optimization, considering factors such as energy cost, supply reliability, and environmental impact, the optimization of energy usage is achieved. The optimization algorithm can adopt multi-objective optimization methods such as particle swarm optimization:

[0150] Fitness(x)=w 1 f 1 (x)+w 2 f 2 (x)+…

[0151] Among them, Fitness is the fitness function, x is the solution vector, f 1 , f 2 ,... are multiple objective functions, and w 1 , w 2 ,... are the weights corresponding to the objectives.

[0152] In intelligent scheduling, the system preferentially uses green energy sources such as solar and wind energy to reduce dependence on traditional energy sources and lower carbon emissions. Green energy scheduling can be adjusted according to energy supply and demand:

[0153] E green =min(E available ,E demand )

[0154] where E green is the amount of green energy scheduled, E available is the available amount of green energy, and E demand is the amount of energy demanded.

[0155] The system supports the demand response function and automatically adjusts the energy consumption of the venue according to the demand of the power grid and the electricity price signal, such as reducing the use of non-critical loads when the electricity price is high. Demand response can adjust energy consumption according to the electricity price signal: E DR =E base ×(1-γ·P t ) where E DR is the energy consumption under demand response, E base is the base energy consumption, γ is the response coefficient, and P t is the electricity price at time t.

[0156] The system has the ability of real-time scheduling and can quickly respond to changes in energy consumption demand in the venue, such as a sudden increase in the number of spectators or overtime in a game. Real-time scheduling can adjust energy supply according to real-time data:

[0157] E real-time =E current +ΔE

[0158] where E real-time is the amount of energy for real-time scheduling, E current is the current amount of energy, and ΔE is the adjusted amount of energy.

[0159] The user interface provides scheduling control functions, allowing managers to adjust the energy scheduling strategy according to the actual situation, such as manually preferentially using a certain type of energy or adjusting the operating parameters of equipment. Users can manually adjust energy scheduling through the user interface:

[0160] E user =E default +ΔE user

[0161] where E user is the amount of energy after user adjustment, E default is the default amount of energy, and ΔE user is the amount of energy adjusted by the user.

[0162] VI. Intelligent Energy Saving Mode

[0163] The intelligent energy saving mode is automatically activated based on real-time data and prediction results. When the activities in the venue decrease or during off-peak hours, the system will automatically adjust to the energy saving mode to reduce energy consumption. The activation of the energy saving mode can be expressed by the following logic:

[0164]

[0165] where EnergySavingMode is the status of the energy saving mode, ActivityLevel is the activity level in the venue, and Threshold is the preset threshold of the activity level.

[0166] In the energy saving mode, the system will automatically adjust or turn off non-essential equipment, such as some lighting and air conditioning systems. At the same time, the basic environmental conditions of key areas are maintained to ensure the basic operation requirements of the venue. The automatic equipment control strategy can use the following formula to adjust the equipment operation parameters:

[0167] Parameter new =Parameter old ×(1 - AdjustmentFactor)

[0168] where Parameter new is the adjusted equipment parameter, Parameter old is the original parameter, and AdjustmentFactor is the adjustment factor.

[0169] The system designs a multi-level energy saving strategy. According to the energy consumption prediction and actual demand, the strictness of the energy saving measures is gradually increased. The multi-level energy saving strategy can be defined as different levels, and each level has different energy saving measures: EnergySavingLevel = 1, 2,..., N where N is the total number of energy saving levels, and each level corresponds to a different set of energy saving measures.

[0170] Users can customize the parameter settings in the energy saving mode through the user interface, such as temperature set points, lighting intensity, etc., to meet specific energy saving requirements. Users can customize the parameters in the energy saving mode, such as:

[0171] Custom Temperature = Base Temperature + ΔT

[0172] where CustomTemperature is the user-defined temperature set point, BaseTemperature is the base temperature, and ΔT is the temperature change adjusted by the user.

[0173] The system provides an energy-saving effect evaluation function. By comparing the energy consumption data before and after the energy-saving mode, the energy-saving effect is quantified. The energy-saving effect can be quantified by the following formula:

[0174]

[0175] Where SavingsEffectiveness is the energy-saving effect, Energy before is the energy consumption before the energy-saving mode, and Energy after is the energy consumption after the energy-saving mode.

[0176] While implementing energy-saving measures, the system takes into account the impact of environmental comfort to ensure that the energy-saving measures do not significantly reduce the experience of the audience and athletes. While saving energy, the system optimizes comfort, which can be achieved by the following formula:

[0177] ComfortScore = w 1 ·Temperature + w 2 ·Humidity + w 3 ·Lighting

[0178] Where ComfortScore is the comfort score, w 1 , W 2 , W 3 are the weights corresponding to the environmental parameters, and Temperature, Humidity, and Lighting are the normalized values of temperature, humidity, and lighting respectively.

[0179] VII. Automatic adjustment of environmental comfort

[0180] The system automatically adjusts the air-conditioning system according to the data collected by the temperature and humidity sensors to maintain a suitable temperature range. Advanced control algorithms, such as fuzzy control, are used to achieve smoother temperature changes. The temperature adjustment can use the PID control algorithm, such as:

[0181]

[0182] Where u(t) is the control output, K p , K i and K d are the proportional, integral, and derivative control parameters respectively, and e(t) is the deviation between the current temperature and the set temperature e set .

[0183] The fuzzy control algorithm is used to handle the uncertainties in temperature control, and fuzzy rules are used, such as:

[0184] IF the temperature IS too low THEN increase heating

[0185] Humidity control is crucial for maintaining human comfort. The system monitors the humidity level and automatically adjusts the humidifier or dehumidifier to maintain the optimal relative humidity. The regulation of relative humidity can adopt a method similar to PID control:

[0186]

[0187] where u h is the control signal for the humidifier or dehumidifier, rh(t) is the current relative humidity, and rh set is the set relative humidity.

[0188] Illuminance not only affects visual comfort but also affects mood and biological clocks. The system intelligently adjusts artificial lighting according to natural light and indoor activities to provide a uniform and comfortable lighting environment. The regulation of illuminance can be based on the external environmental brightness and indoor needs:

[0189] new =I old +ΔI×scale(ambient_light_level)

[0190] where I new is the new illuminance, I old is the old illuminance, ΔI is the adjustment amplitude, and scale is a function that adjusts the ratio according to the environmental brightness.

[0191] The system monitors the noise level in the venue and automatically adjusts the volume and sound quality of the audio system to ensure clarity and comfort. At the same time, echo and noise are controlled through sound-absorbing materials and sound insulation measures. The optimization of the sound environment can use a feedback control system:

[0192] V new =V target +k v ×(V target -V current )

[0193] where V new is the adjusted volume level, V target is the target volume level, V current is the current volume level, and k v is the volume adjustment coefficient.

[0194] Air quality directly affects people's health and comfort. The system monitors the pollutants and carbon dioxide levels in the air and automatically adjusts the fresh air system and air purification equipment to keep the indoor air fresh. The control of carbon dioxide concentration can adopt a simple feedback control:

[0195]

[0196] Among them, is the control signal of the fresh air system, is the set fresh air volume, C set is the set carbon dioxide concentration, C current is the current carbon dioxide concentration.

[0197] The system defines a series of environmental comfort indicators, such as temperature, humidity, illuminance, sound intensity, and air quality, and monitors and adjusts these indicators in real time to meet the requirements of human comfort. A comprehensive score can be defined to quantify comfort:

[0198] ComfortScore = w 1 ·T + w 2 ·RH + w 3 ·L + w 4 ·V + w 5 ·A

[0199] Among them, T, RH, L, V, and A represent temperature, relative humidity, illuminance, volume level, and air quality respectively, and w 1 to w 5 are the corresponding weight coefficients.

[0200] Users can set their comfort preferences through the user interface, and the system will automatically adjust the environmental parameters according to the user's preferences. The user's comfort preferences can be represented by the following model:

[0201] UserPreference = {T set , RH set , L set , T set , A set}

[0202] Among them, T set , RH set , L set , V set and A set are the temperature, relative humidity, illuminance, volume, and air quality set by the user.

[0203] VIII. Green Energy Utilization

[0204] The system designs an integration scheme to combine renewable energy such as solar energy and wind energy with the main energy supply system of the venue. Through photovoltaic panels and wind turbines, the system can capture and convert natural energy for the venue to use. The electrical output of the photovoltaic panels can be calculated by the following formula:

[0205] P PV = A PV × η PV × I

[0206] Among them, P PV is the power generated by the photovoltaic panel, A PV is the area of the photovoltaic panel, η PV is the energy conversion efficiency of the photovoltaic panel, and I is the sunlight intensity.

[0207] The energy output of the wind turbine can be calculated by the following formula:

[0208]

[0209] Among them, P Wind is the power generated by the wind turbine, ρ is the air density, A rotor is the rotor swept area, v is the wind speed, C p is the power coefficient.

[0210] Using an advanced energy management system, the venue energy efficiency management system can intelligently switch between green energy and traditional energy, give priority to using green energy, and reduce the carbon footprint. The switching logic of the intelligent energy management system can be expressed as:

[0211]

[0212] Among them, E select is the selected energy type, E renewable is the current output of renewable energy, E demand is the energy demand of the venue.

[0213] The system is equipped with energy storage devices, such as a battery energy storage system, which can store energy when the green energy production is excessive and release energy during peak demand or energy shortage. The charge and discharge control of the energy storage system can be managed by the following formula:

[0214]

[0215] Among them, E storage (t) is the energy level of the energy storage system at time t, η charge and η discharge are the charging and discharging efficiencies respectively, P charge and P discharge are the charging and discharging powers respectively.

[0216] By real-time monitoring and analyzing the generation and consumption patterns of green energy, the system optimizes the energy use efficiency and reduces energy waste. The energy use efficiency can be calculated by the following formula:

[0217]

[0218] Among them, η energy is the energy use efficiency, E usefulis the useful energy output, E input is the total input energy.

[0219] The utilization of green energy significantly reduces the venue's dependence on fossil fuels, reduces greenhouse gas emissions, and contributes to achieving the venue's environmental sustainability goals. The carbon footprint of the venue can be estimated using the following formula:

[0220] CarbonFootprint = ∑[E source × EF source

[0221] where E source is the energy consumption from different energy sources, and EF source is the carbon emission factor of the corresponding energy source.

[0222] Although the green energy system may require an initial investment, in the long run, it can reduce energy costs and provide economic benefits.

[0223] The user interface provides real-time data and statistical information on green energy generation, enabling users to clearly understand the venue's green energy usage.​

Claims

1. An energy efficiency management system for sports venues, characterized in that: include: -Real-time activity monitoring module, using macro- and micro-layer sensor networks deployed in different areas of the venue to achieve comprehensive coverage; -Environmental adaptive adjustment module, which automatically adjusts the operating parameters of air conditioners and lighting equipment through PID control algorithm according to real-time monitoring data and preset thresholds; -Energy consumption prediction and intelligent scheduling module, which uses time series analysis and machine learning models to predict energy consumption trends and optimize energy usage strategies.

2. The energy efficiency management system according to claim 1, wherein the real-time activity monitoring module further comprises: - The infrared imaging monitoring units are deployed in the auditorium, the competition venue and the rest area; -The video analysis processing unit adopts a crowd counting algorithm based on deep learning.

3. The energy efficiency management system according to claim 1, wherein the environment adaptive adjustment module further comprises: -The temperature and humidity sensing units are deployed in key areas; -The light intensity sensing unit uses the lux unit to automatically adjust the brightness according to a preset light intensity threshold.

4. The energy efficiency management system according to claim 1, wherein the energy consumption prediction and intelligent scheduling module further comprises: -The energy consumption prediction algorithm processing unit realizes energy consumption prediction based on ARIMA model; -The deep learning energy consumption analysis unit analyzes time series data based on the LSTM model.

5. The energy efficiency management system according to claim 1, further comprising: -The data collection frequency dynamic adjustment unit automatically adjusts the data collection frequency according to the activity type and the number of spectators; -The energy consumption monitoring and recording unit records the total energy consumption and sub-item energy consumption of the venue in real time, such as lighting, air conditioning and equipment operation.

6. A method for implementing the energy efficiency management system according to any one of claims 1 to 5, characterized in that: The following steps are involved: -Use the data acquisition and processing unit to remove noise from sensor data and improve data quality by using Kalman filtering and fuzzy logic algorithms; -Using the data processing and analysis unit, a distributed database system is adopted to store and retrieve data, and the data storage uses a consistent hashing algorithm.

7. A sports stadium, characterized in that: The energy efficiency management system according to any one of claims 1 to 6, further comprising: -The user interface control unit provides language options and supports different environmental control parameter settings; -The intelligent energy-saving control unit is automatically activated according to real-time data and prediction results.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, the program being designed to perform the following operations: - Implement the real-time monitoring and data analysis display unit to display different energy consumption indicators; -Implement the environmental adaptive adjustment and energy consumption prediction unit, and provide different prediction models and scheduling strategies.

9. A computer device, characterized in that: It includes a processor and a memory, wherein a computer program is stored in the memory, and the program is designed to implement the functions of the energy efficiency management system described in any one of claims 1 to 8, and the processor and the memory further optimize the real-time performance and data processing capability of the system.

10. The energy efficiency management system or method according to any one of claims 1 to 9, characterized in that: The system or method further comprises: -The green energy utilization control unit integrates solar photovoltaic panels and wind turbines; - The energy storage device management unit uses a battery energy storage system, and the stored energy is not less than the total energy consumption of the venue in one day; - The carbon footprint estimation unit calculates the venue’s carbon emissions and supports carbon emission reduction strategies.

Images