An intelligent energy management system and method based on multi-dimensional data analysis

Abstract

This invention discloses an intelligent energy management system and method based on multi-dimensional data analysis, belonging to the field of energy management technology. The method includes: collecting equipment energy data, external data, and behavioral data; performing real-time preprocessing of the data through a distributed computing architecture of edge nodes; capturing long-term dependencies in time-series data to predict future energy demand; introducing a multi-objective optimization algorithm to balance the relationship between energy consumption and customer experience, constructing a strategy library, and automatically generating preliminary strategies; triggering a dynamic strategy adjustment mechanism when actual energy consumption deviates from the predicted value by more than a deviation threshold, environmental comfort indicators exceed the comfort threshold range, or specific user behavior patterns are identified; and achieving real-time distribution and execution of strategies through a distributed collaborative algorithm among edge nodes. This invention effectively reduces energy consumption while meeting customer needs for environmental comfort.

Description

Technical Field

[0001] This invention relates to the field of energy management technology, specifically an intelligent energy management system and method based on multi-dimensional data analysis. Background Technology

[0002] With the continuous growth of global energy demand and the increasing tension in energy supply, energy management has become a focus of attention across various industries. Traditional energy management methods mainly rely on human experience and simple rules for energy regulation, lacking accurate forecasting of energy consumption and comprehensive consideration of multiple factors, making it difficult to find the optimal balance between energy consumption and customer experience.

[0003] Traditional methods often fail to accurately capture the dynamic changes and long-term trends in energy consumption, leading to a mismatch between energy supply and actual demand, resulting in energy waste or insufficient supply. For example, in some commercial establishments, the inability to adjust the operating parameters of energy equipment based on factors such as real-time customer traffic and weather changes causes unnecessary increases in energy consumption.

[0004] Traditional energy management often prioritizes customer experience, and in the pursuit of energy conservation, it may reduce environmental comfort, impacting customer satisfaction and loyalty. For example, excessively lowering air conditioning temperatures or lighting brightness to save energy can make customers feel uncomfortable.

[0005] Traditional energy management systems are slow in data processing and decision-making, making it difficult to respond promptly to sudden changes and anomalies in energy consumption. Furthermore, the lack of effective coordination mechanisms between various energy devices hinders overall optimized operation. Summary of the Invention

[0006] The purpose of this invention is to provide an intelligent energy management system and method based on multi-dimensional data analysis to solve the problems raised in the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an intelligent energy management method based on multi-dimensional data analysis, the method comprising:

[0008] Collect equipment energy data, external data, and behavioral data;

[0009] Data is preprocessed in real time through a distributed computing architecture at edge nodes;

[0010] Capture long-term dependencies in time-series data to predict future energy demand;

[0011] A multi-objective optimization algorithm is introduced to balance the relationship between energy consumption and customer experience, a strategy library is built, and preliminary strategies are automatically generated;

[0012] When the actual energy consumption deviates from the predicted value by more than the deviation threshold, the environmental comfort index exceeds the comfort threshold range, or a specific user behavior pattern is identified, the dynamic adjustment mechanism of the strategy is triggered.

[0013] The strategy is distributed and executed in real time through a distributed collaborative algorithm among edge nodes.

[0014] According to the above scheme, the equipment energy data includes the equipment's power, operating status, health status, operating time, and energy consumption; the external data includes weather data, holiday information, special times, and real-time passenger flow data; and the behavioral data includes dwelling area, dwelling time, and environmental interaction data.

[0015] According to the above scheme, the real-time preprocessing includes:

[0016] After receiving the collected data, each edge node performs data validity verification, removes outliers and missing data, and establishes cross-device data time sequence association using a unified timestamp alignment mechanism.

[0017] According to the above scheme, the step of capturing long-term dependencies in time-series data to predict future energy demand includes:

[0018] The device's energy data, external data, and behavioral data are integrated, and a unified data format and scope are established to construct a multi-dimensional dataset.

[0019] An energy forecasting model is constructed by inputting a multi-dimensional dataset, capturing long-term dependencies in time-series data, extracting key features, and outputting future energy demand forecasts; the future energy demand forecasts include short-term and long-term forecasts.

[0020] The parameters of the energy prediction model are optimized using the backpropagation algorithm and gradient descent method based on the multi-dimensional dataset.

[0021] According to the above scheme, the preliminary strategy includes:

[0022] A multi-objective optimization model is constructed, and an optimization objective function is defined. The optimization objective function includes minimizing energy consumption and maximizing customer experience. Constraints are set, including equipment operation constraints, environmental comfort constraints, and total energy constraints. The equipment operation constraints include a maximum power limit and a minimum start-stop interval. The environmental comfort constraints include comfort range thresholds for temperature, humidity, and illuminance.

[0023] Several sets of equipment operating parameter combinations are randomly generated to construct an initial population; the equipment operating parameter combinations include adjustable variables.

[0024] The system uses energy demand forecasts, equipment operating status, environmental parameters, and behavioral data as inputs for iterative processing. Each iteration includes a complete optimization loop, which involves calculating the objective function value for each individual in the current population, performing non-dominated sorting to stratify the solution set, maintaining the diversity distribution of solutions through crowding calculation, and generating a new generation of population through selection, crossover, and mutation operations. The calculation terminates when the Pareto front improvement rate is below a set threshold for three consecutive generations or when the maximum number of iterations is reached, and outputs the Pareto optimal solution set containing non-dominated solutions.

[0025] The non-dominated solutions in the Pareto optimal solution set are analyzed, and the corresponding combinations of equipment operating parameters are extracted. A solution set mapping table is established, which associates each non-dominated solution with a set of executable equipment control instructions to form a strategy library.

[0026] The strategy library includes device control parameters, execution conditions, and expected results.

[0027] According to the above scheme, the automatic generation of the preliminary strategy includes:

[0028] A decision-making model is constructed, and the decision factors of the decision-making model include current time period characteristics, real-time energy volatility, real-time energy equipment health status, passenger flow density change rate, and user behavior patterns.

[0029] The decision model is used to evaluate the overall fitness of each non-dominated solution in the strategy library, select the non-dominated solution with the highest overall fitness, and obtain the set of associated executable device control instructions through the solution set mapping table to generate a preliminary strategy.

[0030] The initial strategy generates a hierarchical control instruction sequence containing immediate execution instructions, delayed execution instructions, and conditional triggering instructions;

[0031] During the implementation of the strategy, the energy data, external data and behavioral data of the equipment are monitored in real time, and a dynamic adjustment trigger mechanism is set. The trigger mechanism includes threshold-based parameter deviation trigger, immediate trigger in response to sudden events and periodic timed trigger.

[0032] A multi-level fault tolerance mechanism is constructed, which includes primary fault tolerance, intermediate fault tolerance, and advanced fault tolerance; the primary fault tolerance includes automatic retry of failure instructions, the intermediate fault tolerance includes switching to a backup strategy, and the advanced fault tolerance includes enabling a safe mode and issuing an alarm.

[0033] According to the above scheme, the dynamic adjustment mechanism of the strategy includes:

[0034] Based on the execution effect of the current policy, when it is detected that the actual energy consumption deviates from the predicted value by more than the deviation threshold, the environmental comfort index exceeds the comfort threshold range, or a specific user behavior pattern is identified, a policy dynamic adjustment mechanism is triggered; the policy dynamic adjustment mechanism includes locking the target device control parameters that generate deviations in the current policy and retaining the device control parameters of unaffected devices; based on the policy library, extracting associated non-dominated solutions and performing local re-optimization; combining the current time period characteristics, real-time energy volatility, real-time energy device health status, passenger flow density change rate, and user behavior pattern, and screening out the backup policy with the highest comprehensive fitness from the Pareto optimal solution set through a decision model, and converting the backup policy into a hierarchical control instruction sequence;

[0035] Coordinate the control instructions of each region through the distributed cooperation mechanism of the edge node. When multiple policies act on the same device simultaneously, fuse the instructions according to the preset priority.

[0036] According to the above solution, the real-time distribution and execution of the policy are achieved through the distributed cooperation algorithm between edge nodes, including:

[0037] After each edge node receives the hierarchical control instruction sequence, based on the device energy data and the external data, perform instruction adaptability verification to determine the priority and weight distribution of instruction execution; establish a message bus based on the publish-subscribe mode, exchange device status and instruction execution feedback through a lightweight communication protocol, and complete the status synchronization between nodes;

[0038] When detecting multi-node instruction conflicts, adopt the eventual consistency algorithm based on timestamps to coordinate the execution order; the timestamp of instruction I1 is T1, and the timestamp of instruction I2 is T2. If T1 < T2, then execute I1 first; where I represents the index of the instruction number and T represents the timestamp;

[0039] For composite instructions involving multi-region linkage, the two-phase commit protocol is initiated by the leading node to ensure atomic execution. The leading node sends a prepare instruction to all participating nodes, and each node checks its own status and returns a ready or failed message. If all nodes are ready, the leading node sends a commit instruction, and each node executes the instruction; if a node fails, the leading node sends a rollback instruction; at the same time, monitor the execution status of each node through the heartbeat mechanism; the real-time data updates generated during the execution are fed back to the central processing unit through the backpropagation mechanism to form a closed-loop control flow.

[0040] An intelligent energy management system based on multi-dimensional data analysis, the system includes: a data collection and processing module, an intelligent analysis module, a dynamic execution module, a distributed cooperation module, and an interactive interface module;

[0041] The data acquisition and processing module includes a multi-source data acquisition module and an edge preprocessing module; the multi-source data acquisition module is used to acquire equipment energy data, external data, and behavioral data in real time; the edge preprocessing module is used to perform data cleaning and time-series alignment at edge nodes, and to complete data standardization.

[0042] The intelligent analysis module includes an energy forecasting module, a strategy generation module, a strategy decision-making module, and a strategy library module. The energy forecasting module constructs an energy forecasting model to predict future energy demand, including short-term and long-term forecasts. The strategy generation module constructs a multi-objective optimization model to generate a Pareto optimal solution set that balances energy consumption and customer experience. The strategy decision-making module selects the optimal control strategy based on the data collected by the data acquisition and processing module. The strategy library module is used to store and manage strategies.

[0043] The dynamic execution module includes an instruction distribution module, a conflict coordination module, and a fault tolerance control module; the instruction distribution module is used to distribute hierarchical instructions to edge nodes; the conflict coordination module is used to resolve instruction conflicts between multiple nodes to ensure execution consistency; the fault tolerance control module has a real-time three-level fault tolerance mechanism.

[0044] The distributed collaboration module includes an edge collaboration module and a resource scheduling module; the edge collaboration module achieves state synchronization between nodes through a publish-subscribe mechanism; the resource scheduling module dynamically allocates edge computing resources.

[0045] The interactive interface module includes a visualization module and a strategy configuration module; the visualization module displays real-time energy consumption heat maps and passenger flow distribution data for devices in each area; the strategy configuration module predicts energy saving rates and changes in comfort based on keywords selected by the user.

[0046] According to the above scheme, when abnormal data is detected, a graded alarm mechanism is triggered; the alarm levels include emergency, warning, and alert; the emergency is a red signal, the warning is a yellow signal, and the alert is a blue signal; the maintenance record is automatically associated with the equipment, the health status is updated, and an alarm report is generated; the alarm report includes the alarm level, alarm time, alarm area or equipment, alarm maintenance record, and equipment health status.

[0047] Compared with the prior art, the beneficial effects of the present invention are:

[0048] 1. This invention utilizes multi-dimensional data to plan energy supply and improve energy utilization efficiency;

[0049] 2. This invention effectively reduces energy consumption while meeting customers' needs for environmental comfort;

[0050] 3. This invention sets up a dynamic strategy adjustment mechanism to ensure that the energy management strategy always adapts to changes in actual conditions, thereby improving the flexibility and adaptability of energy management;

[0051] 4. This invention achieves real-time distribution and execution of strategies through a distributed collaborative algorithm between edge nodes, ensuring that energy devices can work together and improving the overall operating efficiency of the energy management system. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating the steps of an intelligent energy management method based on multi-dimensional data analysis according to the present invention.

[0053] Figure 2 This is a schematic diagram of the structure of an intelligent energy management system based on multi-dimensional data analysis according to the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Example: Figures 1-2 As shown, the present invention provides a technical solution, an intelligent energy management method based on multi-dimensional data analysis, the method comprising:

[0056] S1. Collect equipment energy data, external data, and behavioral data;

[0057] Specifically, for example, implementing smart energy management in coffee shops involves collecting equipment energy data, external data, and behavioral data. For instance, equipment energy data includes: coffee machine: current power 1.8kW (maximum 2.2kW), total usage time today 4.2 hours; air conditioner: set temperature 24℃, actual temperature 25.5℃, filter remaining lifespan 83%. External data includes: weather: outdoor temperature 30℃, humidity 70%; time period: Saturday morning 10:30 (peak holiday hours). Behavioral data includes: customer distribution: window seats occupancy 90%, 5 standing customers at the bar; special behavior: customer at table number 3 stayed for 45 minutes.

[0058] S2. Data is preprocessed in real time through a distributed computing architecture at edge nodes;

[0059] Specifically, after receiving the collected data, each edge node performs data validity verification, removes outliers and missing data, and establishes cross-device data time sequence association using a unified timestamp alignment mechanism.

[0060] S3. Capture long-term dependencies in time series data to predict future energy demand;

[0061] Specifically, the device energy data, external data, and behavioral data are integrated, and a unified data format and scope are established to construct a multi-dimensional dataset. An energy prediction model is then built, inputting the multi-dimensional dataset to capture long-term dependencies in the time-series data, extracting key features, and outputting future energy demand prediction results. The future energy demand prediction includes both short-term and long-term forecasts. Using the multi-dimensional dataset, the backpropagation algorithm and gradient descent method are used to optimize the parameters of the energy prediction model. For example, input historical energy consumption: average energy consumption for the same period over the past 7 days is 8.2 kWh; environmental parameters: indoor-outdoor temperature difference 6.5℃, solar radiation intensity 850 W / m². 2 Passenger flow pattern: Peak passenger flow characteristics on weekend mornings (40% higher than weekdays); Equipment status: Two coffee machines are online simultaneously, and the freezer defrosting cycle has started; Output forecast results: Short-term forecast (next hour): Total energy consumption demand: 9.5±0.8kWh; Due to peak passenger flow and outdoor temperature, air conditioning load will increase by 25%; Long-term forecast (today): A second peak in passenger flow will occur between 3-4 pm.

[0062] S4. Introduce a multi-objective optimization algorithm to balance the relationship between energy consumption and customer experience, build a strategy library, and automatically generate preliminary strategies;

[0063] Specifically, a multi-objective optimization model is constructed, defining the optimization objective function. The objective function includes minimizing energy consumption and maximizing customer experience. For example, energy consumption is controlled within 90% of the budget (<8.5 kWh / h), and the customer area comfort score is maintained at ≥4.2 points (out of 5). Constraints are set, including equipment operation constraints, environmental comfort constraints, and total energy constraints. Equipment operation constraints include maximum power limits and minimum start-stop intervals. Environmental comfort constraints include comfort range thresholds for temperature, humidity, and illuminance. Several sets of equipment operation parameter combinations are randomly generated to construct an initial population. These combinations include adjustable variables. Energy demand forecasts, equipment operating status, environmental parameters, and behavioral data are used as inputs for iteration. Each iteration includes a complete optimization loop, which includes calculating the objective function value for each individual in the current population, performing non-dominated sorting to stratify the solution set, maintaining the diversity distribution of solutions through crowding calculation, and using selection, crossover, and mutation. The operation generates a new generation of population; when the Pareto front improvement rate is lower than a set threshold for three consecutive generations or the maximum number of iterations is reached, the calculation terminates and outputs a Pareto optimal solution set containing non-dominated solutions; the non-dominated solutions in the Pareto optimal solution set are analyzed, and the corresponding combinations of device operating parameters are extracted; a solution set mapping table is established, which associates each non-dominated solution with a set of executable device control instructions to form a strategy library; the strategy library includes device control parameters, execution conditions, and expected effects; for example: Strategy 1: Coffee machine mode: Coffee machine A is on, coffee machine B is on; air conditioning setting: 26℃; lighting adjustment: area A increases brightness by 20%; estimated energy consumption 7.8kWh; customer area comfort score: 4.3; Strategy 2: Coffee machine mode: Coffee machine A is on, coffee machine B is off; air conditioning setting: 25℃; lighting adjustment: area B increases brightness by 20%; estimated energy consumption 7.2kWh; customer area comfort score: 4.0; This is only an example and is not a limitation;

[0064] Furthermore, the decision factors of the decision model include current time period characteristics, real-time energy volatility, real-time energy equipment health status, passenger flow density change rate, and user behavior patterns. Through the decision model, the comprehensive fitness of each non-dominated solution in the strategy library is evaluated, the non-dominated solution with the highest comprehensive fitness is selected, and a set of associated executable equipment control instructions is obtained through a solution set mapping table to generate a preliminary strategy. The preliminary strategy generates a hierarchical control instruction sequence containing immediate execution instructions, delayed execution instructions, and conditional triggering instructions. For example, strategy 1 is selected because passenger flow is high on weekend mornings, requiring a fast coffee production speed; increasing the brightness of area A can increase customer dwell time.

[0065] Furthermore, during strategy implementation, the device's energy data, external data, and behavioral data are monitored in real time, and a dynamic adjustment trigger mechanism is set up. This trigger mechanism includes threshold-based parameter deviation triggering, immediate triggering in response to sudden events, and periodic timed triggering. A multi-level fault tolerance mechanism is constructed, including primary fault tolerance, intermediate fault tolerance, and advanced fault tolerance. Primary fault tolerance includes automatic retry of failure instructions; intermediate fault tolerance includes switching to a backup strategy; and advanced fault tolerance includes enabling a safe mode and triggering an alarm. For example, in a coffee machine overheating alarm: Primary fault tolerance: automatic retry of startup (2 times with a 5-minute interval); Intermediate fault tolerance: switching to a backup machine and notifying maintenance; Advanced fault tolerance: shutting down the faulty device and triggering electrical detection.

[0066] S5. When the actual energy consumption deviates from the predicted value by more than the deviation threshold, the environmental comfort index exceeds the comfort threshold range, or a specific user behavior pattern is identified, the dynamic adjustment mechanism of the strategy is triggered.

[0067] Specifically, based on the current strategy execution effect, when the actual energy consumption deviates from the predicted value by more than the deviation threshold, the environmental comfort index exceeds the comfort threshold range, or a specific user behavior pattern is identified, a dynamic strategy adjustment mechanism is triggered. This dynamic adjustment mechanism includes: locking the control parameters of the target equipment that caused the deviation in the current strategy, and retaining the control parameters of unaffected equipment; extracting related non-dominated solutions from the strategy library and performing local re-optimization; combining current time period characteristics, real-time energy volatility, real-time energy equipment health status, passenger flow density change rate, and user behavior patterns, using a decision model to select the backup strategy with the highest overall fitness from the Pareto optimal solution set, and converting the backup strategy into a hierarchical control command sequence; for example: identifying a specific user behavior pattern: when a customer sits down in area A, increase the brightness of area A by 20%; when a seat in area B is found to be vacant for more than 5 minutes, turn off the spotlights at the corresponding seat in area B; this is only an example and not a limitation.

[0068] Furthermore, the distributed collaboration mechanism of edge nodes coordinates control commands in various regions. When multiple policies are applied to the same device at the same time, the commands are merged according to the preset priority.

[0069] S6. Real-time distribution and execution of strategies are achieved through a distributed collaborative algorithm among edge nodes;

[0070] Specifically, after receiving the hierarchical control command sequence, each edge node performs command adaptability verification based on the device energy data and the external data to determine the priority and weight allocation of command execution; establishes a message bus based on the publish-subscribe model, and exchanges device status and command execution feedback through a lightweight communication protocol to complete the state synchronization between nodes;

[0071] Furthermore, when multi-node instruction conflicts are detected, a timestamp-based eventual consistency algorithm is used to coordinate the execution order; for composite instructions involving multi-region linkage, the leading node initiates a two-phase commit protocol to ensure atomic execution, while a heartbeat mechanism monitors the execution status of each node; real-time data updates generated during execution are fed back to the central processing unit through a backpropagation mechanism to form a closed-loop control flow.

[0072] This invention provides another technical solution: an intelligent energy management method based on multi-dimensional data analysis, and multi-command conflict coordination;

[0073] For example: Area A and Area B of the coffee shop share the same central air conditioning unit;

[0074] Based on the current data, two strategies are triggered simultaneously: Strategy X: The temperature in area A needs to be lowered to 24℃ (due to the large customer flow, the temperature in area A of the coffee shop is high); Strategy Y: The temperature in area B needs to be raised to 27℃ (due to the reduced customer flow and the equipment overheating alarm).

[0075] After receiving the hierarchical control command sequence, each edge node performs command adaptability verification based on the device energy data and the external data to determine the priority and weight allocation of command execution. According to the edge node verification, strategy X has a priority of 3 and strategy Y has a priority of 2. Among them, strategy X is a comfort strategy with a weight coefficient of 0.6 and strategy Y is an energy efficiency strategy with a weight coefficient of 0.3.

[0076] An eventual consistency algorithm based on timestamps is used to coordinate the execution order;

[0077] The final implementation strategy is to adopt a weighted average of 25.5℃, with additional compensation measures: increase directional air supply in zone A and turn on local recirculation fans in zone B.

[0078] The present invention provides another technical solution, an intelligent energy management system based on multi-dimensional data analysis, the system comprising: a data acquisition and processing module, an intelligent analysis module, a dynamic execution module, a distributed collaboration module, and an interactive interface module;

[0079] The data acquisition and processing module includes a multi-source data acquisition module and an edge preprocessing module; the multi-source data acquisition module is used to acquire equipment energy data, external data, and behavioral data in real time; the edge preprocessing module is used to perform data cleaning and time-series alignment at edge nodes, and to complete data standardization.

[0080] The intelligent analysis module includes an energy forecasting module, a strategy generation module, a strategy decision-making module, and a strategy library module. The energy forecasting module constructs an energy forecasting model to predict future energy demand, including short-term and long-term forecasts. The strategy generation module constructs a multi-objective optimization model to generate a Pareto optimal solution set that balances energy consumption and customer experience. The strategy decision-making module selects the optimal control strategy based on the data collected by the data acquisition and processing module. The strategy library module is used to store and manage strategies.

[0081] The dynamic execution module includes an instruction distribution module, a conflict coordination module, and a fault tolerance control module; the instruction distribution module is used to distribute hierarchical instructions to edge nodes; the conflict coordination module is used to resolve instruction conflicts between multiple nodes to ensure execution consistency; the fault tolerance control module has a real-time three-level fault tolerance mechanism.

[0082] The distributed collaboration module includes an edge collaboration module and a resource scheduling module; the edge collaboration module achieves state synchronization between nodes through a publish-subscribe mechanism; the resource scheduling module dynamically allocates edge computing resources.

[0083] The interactive interface module includes a visualization module and a strategy configuration module; the visualization module displays real-time energy consumption heat maps and passenger flow distribution data for devices in each area; the strategy configuration module predicts energy saving rates and changes in comfort based on keywords selected by the user.

[0084] Specifically, when abnormal data is detected, a tiered alarm mechanism is triggered; the alarm levels include emergency, warning, and alert; the emergency is a red signal, the warning is a yellow signal, and the alert is a blue signal; maintenance records are automatically associated with the equipment, the health status is updated, and an alarm report is generated; the alarm report includes the alarm level, alarm time, alarm area or equipment, alarm maintenance record, and equipment health status.

[0085] This invention provides another technical solution: an intelligent energy management system based on multi-dimensional data analysis, including an interactive interface module;

[0086] Users can configure basic strategies through this module. For example, the system offers several preset modes: In peak business hours mode, the air conditioning will automatically be set to a constant 24°C, and the lighting system will maintain full brightness to prioritize customer comfort; the energy-saving maintenance mode is suitable for off-peak hours, adjusting the air conditioning temperature to 28°C and automatically turning off all display case lighting and display equipment power; the special event mode can extend the operating time of specific equipment to meet special event needs. These are just examples and are not intended to be restrictive. Users can adjust automatic strategies in real time through the interface, such as temporarily turning off the background music system or adjusting the lighting brightness in specific areas. Furthermore, the interface provides a visualization function for strategy execution effects, visually displaying the energy consumption distribution and execution effects of each area in the form of a heat map, helping users quickly understand the strategy implementation status.

[0087] When equipment malfunctions, the interactive interface pushes alarm information in real time, including equipment location, malfunction type, and handling suggestions. Users can directly confirm the handling solution on the interface or manually adjust relevant equipment parameters. All strategy adjustment records and execution effect data are automatically saved, forming a complete operation log and energy efficiency report, which can be queried and analyzed by date, region, or equipment type. Based on historical operation data and user habits, the system intelligently recommends optimization strategies, for example, prompting "Current passenger flow is low, it is recommended to switch to energy-saving mode, which is expected to save 15% of energy consumption." For critical operations, the system sets up a dual verification mechanism to ensure the security of strategy changes. The interactive interface is deeply integrated with other modules of the system, and any adjustment will be synchronized to the edge node for execution in real time, while the execution results are fed back to the system, forming a complete control closed loop.

[0088] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A smart energy management method based on multi-dimensional data analysis, characterized in that: The method includes: Collect equipment energy data, external data, and behavioral data; Data is preprocessed in real time through a distributed computing architecture at edge nodes; Capture long-term dependencies in time-series data to predict future energy demand; A multi-objective optimization algorithm is introduced to balance the relationship between energy consumption and customer experience, a strategy library is built, and preliminary strategies are automatically generated; When the actual energy consumption deviates from the predicted value by more than the deviation threshold, the environmental comfort index exceeds the comfort threshold range, or a specific user behavior pattern is identified, the dynamic adjustment mechanism of the strategy is triggered. The dynamic adjustment mechanism includes: based on the current strategy execution effect, when the actual energy consumption deviates from the predicted value by more than the deviation threshold, the environmental comfort index exceeds the comfort threshold range, or a specific user behavior pattern is identified, the dynamic adjustment mechanism is triggered; the dynamic adjustment mechanism includes: locking the control parameters of the target equipment that causes the deviation in the current strategy, and retaining the equipment control parameters of the unaffected equipment; extracting the associated non-dominated solutions based on the strategy library and performing local re-optimization; combining the current time period characteristics, real-time energy volatility, real-time energy equipment health status, passenger flow density change rate, and user behavior patterns, selecting the backup strategy with the highest comprehensive fitness from the Pareto optimal solution set through a decision model, and converting the backup strategy into a hierarchical control command sequence; coordinating the control commands of each area through the distributed collaboration mechanism of edge nodes, and when multiple strategies act on the same equipment at the same time, the commands are fused according to a preset priority; The strategy is distributed and executed in real time through a distributed collaborative algorithm among edge nodes.

2. The intelligent energy management method based on multi-dimensional data analysis according to claim 1, characterized in that: The equipment energy data includes the equipment's power, operating status, health status, operating time, and energy consumption; the external data includes weather data, holiday information, special times, and real-time passenger flow data; the behavioral data includes dwelling area, dwell time, and environmental interaction data.

3. The intelligent energy management method based on multi-dimensional data analysis according to claim 1, characterized in that: The real-time preprocessing includes: After receiving the collected data, each edge node performs data validity verification, removes outliers and missing data, and establishes cross-device data time sequence association using a unified timestamp alignment mechanism.

4. The intelligent energy management method based on multi-dimensional data analysis according to claim 1, characterized in that: The method of capturing long-term dependencies in time-series data to predict future energy demand includes: The device's energy data, external data, and behavioral data are integrated, and a unified data format and scope are established to construct a multi-dimensional dataset. An energy forecasting model is constructed by inputting a multi-dimensional dataset, capturing long-term dependencies in time-series data, extracting key features, and outputting future energy demand forecasts; the future energy demand forecasts include short-term and long-term forecasts. The parameters of the energy prediction model are optimized using the backpropagation algorithm and gradient descent method based on the multi-dimensional dataset.

5. The intelligent energy management method based on multi-dimensional data analysis according to claim 1, characterized in that: The preliminary strategy includes: A multi-objective optimization model is constructed, and an optimization objective function is defined. The optimization objective function includes minimizing energy consumption and maximizing customer experience. Constraints are set, including equipment operation constraints, environmental comfort constraints, and total energy constraints. The equipment operation constraints include a maximum power limit and a minimum start-stop interval. The environmental comfort constraints include comfort range thresholds for temperature, humidity, and illuminance. Several sets of equipment operating parameter combinations are randomly generated to construct an initial population; the equipment operating parameter combinations include adjustable variables. The system uses energy demand forecasts, equipment operating status, environmental parameters, and behavioral data as inputs for iterative processing. Each iteration includes a complete optimization loop, which involves calculating the objective function value for each individual in the current population, performing non-dominated sorting to stratify the solution set, maintaining the diversity distribution of solutions through crowding calculation, and generating a new generation of population through selection, crossover, and mutation operations. The calculation terminates when the Pareto front improvement rate is below a set threshold for three consecutive generations or when the maximum number of iterations is reached, and outputs the Pareto optimal solution set containing non-dominated solutions. The non-dominated solutions in the Pareto optimal solution set are analyzed, and the corresponding combinations of equipment operating parameters are extracted. A solution set mapping table is established, which associates each non-dominated solution with a set of executable equipment control instructions to form a strategy library. The strategy library includes device control parameters, execution conditions, and expected results.

6. The intelligent energy management method based on multi-dimensional data analysis according to claim 4, characterized in that: The automatically generated preliminary strategy includes: A decision-making model is constructed, and the decision factors of the decision-making model include current time period characteristics, real-time energy volatility, real-time energy equipment health status, passenger flow density change rate, and user behavior patterns. The decision model is used to evaluate the overall fitness of each non-dominated solution in the strategy library, select the non-dominated solution with the highest overall fitness, and obtain the set of associated executable device control instructions through the solution set mapping table to generate a preliminary strategy. The initial strategy generates a hierarchical control instruction sequence containing immediate execution instructions, delayed execution instructions, and conditional triggering instructions; During the implementation of the strategy, the energy data, external data and behavioral data of the equipment are monitored in real time, and a dynamic adjustment trigger mechanism is set. The trigger mechanism includes threshold-based parameter deviation trigger, immediate trigger in response to sudden events and periodic timed trigger. A multi-level fault tolerance mechanism is constructed, which includes primary fault tolerance, intermediate fault tolerance, and advanced fault tolerance; the primary fault tolerance includes automatic retry of failure instructions, the intermediate fault tolerance includes switching to a backup strategy, and the advanced fault tolerance includes enabling a safe mode and issuing an alarm.

7. The intelligent energy management method based on multi-dimensional data analysis according to claim 1, characterized in that: The real-time distribution and execution of the strategy through a distributed collaboration algorithm among edge nodes includes: After receiving the hierarchical control command sequence, each edge node performs command adaptability verification based on the device energy data and the external data to determine the priority and weight allocation of command execution; establishes a message bus based on the publish-subscribe model, and exchanges device status and command execution feedback through a lightweight communication protocol to complete the status synchronization between nodes; When a conflict between multiple nodes is detected, an eventual consistency algorithm based on timestamps is used to coordinate the execution order. For complex instructions involving multi-region linkage, the leading node initiates a two-phase commit protocol to ensure atomic execution, while a heartbeat mechanism monitors the execution status of each node. Real-time data updates generated during execution are fed back to the central processing unit through a backpropagation mechanism, forming a closed-loop control flow.

8. An intelligent energy management system based on multi-dimensional data analysis, applied to the intelligent energy management method based on multi-dimensional data analysis as described in any one of claims 1-7, characterized in that: The system includes: a data acquisition and processing module, an intelligent analysis module, a dynamic execution module, a distributed collaboration module, and an interactive interface module; The data acquisition and processing module includes a multi-source data acquisition module and an edge preprocessing module; the multi-source data acquisition module is used to acquire equipment energy data, external data, and behavioral data in real time; the edge preprocessing module is used to perform data cleaning and time-series alignment at edge nodes, and to complete data standardization. The intelligent analysis module includes an energy forecasting module, a strategy generation module, a strategy decision-making module, and a strategy library module. The energy forecasting module constructs an energy forecasting model to predict future energy demand, including short-term and long-term forecasts. The strategy generation module constructs a multi-objective optimization model to generate a Pareto optimal solution set that balances energy consumption and customer experience. The strategy decision-making module selects the optimal control strategy based on the data collected by the data acquisition and processing module. The strategy library module is used to store and manage strategies. The dynamic execution module includes an instruction distribution module, a conflict coordination module, and a fault tolerance control module; the instruction distribution module is used to distribute hierarchical instructions to edge nodes; the conflict coordination module is used to resolve instruction conflicts between multiple nodes to ensure execution consistency; the fault tolerance control module has a real-time three-level fault tolerance mechanism. The distributed collaboration module includes an edge collaboration module and a resource scheduling module; the edge collaboration module achieves state synchronization between nodes through a publish-subscribe mechanism; the resource scheduling module dynamically allocates edge computing resources. The interactive interface module includes a visualization module and a strategy configuration module; the visualization module displays real-time energy consumption heat maps and passenger flow distribution data for devices in each area; the strategy configuration module predicts energy saving rates and changes in comfort based on keywords selected by the user.

9. The intelligent energy management system based on multi-dimensional data analysis according to claim 8, characterized in that: When abnormal data is detected, a tiered alarm mechanism is triggered; the alarm levels include emergency, warning, and alert; the emergency is a red signal, the warning is a yellow signal, and the alert is a blue signal; maintenance records are automatically associated with the equipment, the health status is updated, and an alarm report is generated; the alarm report includes the alarm level, alarm time, alarm area or equipment, alarm maintenance record, and equipment health status.

Images