Building energy consumption optimization method and device, storage medium and computer device

Abstract

The building energy consumption optimization method and device, the storage medium and the computer device provided by the application obtain short-time and next-day load curves through short-term and medium-term load prediction, and based on the linkage regulation and control of the short-term load curve, environmental parameters and equipment energy efficiency, the regulation and control lag caused by rough prediction granularity is avoided, thereby improving the timeliness and accuracy of energy consumption response. At the same time, according to the next-day load curve, a peak-valley electricity price optimization strategy is generated, which can make the electricity consumption of each region more in line with the actual demand and electricity price fluctuation, fully utilize the peak-valley electricity price, and reduce the electricity cost. When the personalized electricity consumption scheme is executed, personnel distribution data is introduced for adjustment to ensure that the electricity consumption scheme is highly matched with personnel activities, unnecessary energy consumption waste is avoided, and then fine energy consumption management of each region in the building is realized, energy saving potential is fully tapped, and energy consumption optimization effect is improved.

Description

Technical Field

[0001] This application relates to the field of energy monitoring technology, and in particular to a method, apparatus, storage medium and computer equipment for optimizing building energy consumption. Background Technology

[0002] In the field of smart buildings, existing energy management methods mainly rely on real-time monitoring and feedback control based on preset rules, such as starting and stopping air conditioning based on the current temperature or adjusting lighting based on light intensity. These solutions are essentially passive responses, lacking the ability to predict future energy demand, resulting in delayed adjustments, poor user experience, and a tendency to cause energy consumption peaks.

[0003] Therefore, existing technologies can guide energy management based on simple electricity load forecasting. However, these methods are essentially macro-level forecasts for the entire building and are difficult to adapt to the individual needs of different areas within the building. This limits the full realization of the overall energy-saving potential, making it difficult to achieve the expected energy optimization results. Summary of the Invention

[0004] The purpose of this application is to address at least one of the aforementioned technical shortcomings, particularly the difficulty of adapting existing energy management technologies to the individualized needs of different areas within a building. This limits the full realization of overall energy-saving potential, making it difficult to achieve the expected energy optimization results.

[0005] In a first aspect, this application provides a building energy consumption optimization method, the method comprising: Obtain load forecast data, and perform short-term and medium-term load forecasts based on the load forecast data to obtain short-term load curves and next-day load curves; The energy efficiency model and environmental parameters of the equipment are obtained, and the power of each electrical device in the building is regulated by combining the short-term load curve, the environmental parameters and the energy efficiency model of the equipment. Based on the load curve of the next day, a peak-valley electricity price optimization strategy for the next day is generated, and personalized electricity consumption plans for each area inside the building are obtained. When implementing each personalized electricity plan, personnel distribution data is obtained, and each personalized electricity plan is adjusted based on the personnel distribution data.

[0006] In one embodiment, the step of acquiring load forecast data and performing short-term and medium-term load forecasts based on the load forecast data to obtain short-term load curves and next-day load curves includes: Acquire historical energy consumption data, weather forecast data, employee scheduling data, and event booking data to generate load forecast data; The load forecast data is input into the pre-trained short-term forecast model and medium-term forecast model respectively to obtain the short-term load curve output by the short-term forecast model and the next-day load curve output by the medium-term forecast model.

[0007] In one embodiment, the step of combining the short-term load curve, the environmental parameters, and the equipment energy efficiency model to regulate the power consumption of various electrical devices in the building includes: Based on the equipment energy efficiency model, determine the energy efficiency curves and optimal operating parameter ranges for each electrical device; Based on the short-term load curve, the electricity demand for each time period is determined, and combined with the environmental parameters, the energy efficiency curves of each electrical device and the optimal operating parameter range, the target operating power of each electrical device is calculated. Based on the target operating power of each electrical device, power control commands are issued to each electrical device.

[0008] In one embodiment, generating the next-day peak-valley electricity price optimization strategy based on the next-day load curve includes: Obtain the local power grid's time period divisions and corresponding electricity price standards to divide the off-peak electricity price period and peak electricity price period within the time period of the load curve of the next day; Based on the load curve of the next day, the distribution of flexible load and energy storage load in each time period is determined; For the off-peak electricity price period, the flexible load and the energy storage load are controlled to operate at full load during the period to generate a load filling scheme; For the peak electricity price period, the peak electricity load is reduced by fine-tuning the air conditioning temperature, reducing the brightness of unnecessary lighting, and delaying non-emergency electricity use tasks, so as to generate a load shaving scheme. The load filling scheme and the load peak shaving scheme are combined to obtain the next day's peak-valley electricity price optimization strategy.

[0009] In one embodiment, adjusting each personalized electricity plan based on the personnel distribution data includes: Based on the personnel distribution data, determine the current personnel usage in each area of ​​the building; Based on the current usage of personnel in each area, the personalized electricity plans for that area will be dynamically adjusted.

[0010] In one embodiment, when regulating the power of various electrical devices in a building, the method further includes: When any electrical device is turned off, personnel distribution data is obtained, and a multi-level power outage strategy is adopted based on the personnel distribution data.

[0011] In one embodiment, the method further includes: When a temporary fluctuation in electricity price is detected, the next day's peak-valley electricity price optimization strategy is adjusted to maximize the utilization of low-priced electricity.

[0012] Secondly, this application provides a building energy consumption optimization device, the device comprising: The load forecasting module is used to acquire load forecasting data and perform short-term and medium-term load forecasting based on the load forecasting data to obtain short-term load curves and next-day load curves. The power regulation module is used to acquire equipment energy efficiency models and environmental parameters, and combine the short-time load curve, the environmental parameters and the equipment energy efficiency model to regulate the power of various electrical devices in the building; The electricity price optimization module is used to generate a peak-valley electricity price optimization strategy for the next day based on the next day's load curve, and to obtain personalized electricity consumption plans for each area inside the building. The scheme adjustment module is used to obtain personnel distribution data when executing each personalized electricity consumption scheme, and adjust each personalized electricity consumption scheme based on the personnel distribution data.

[0013] Thirdly, this application provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the building energy consumption optimization method as described in any of the above embodiments.

[0014] Fourthly, this application provides a computer device, including: one or more processors, and a memory; The memory stores computer-readable instructions, and when the one or more processors execute the computer-readable instructions, they perform the steps of the building energy consumption optimization method as described in any of the above embodiments.

[0015] As can be seen from the above technical solutions, the embodiments of this application have the following advantages: The building energy consumption optimization method, device, storage medium, and computer equipment provided in this application obtain short-term and next-day load curves through short-term and medium-term load forecasting. Based on the coordinated control of short-term load curves, environmental parameters, and equipment energy efficiency, it avoids control lag caused by coarse forecast granularity, thereby improving the timeliness and accuracy of energy consumption response. Simultaneously, it generates peak-valley electricity price optimization strategies based on the next-day load curve, enabling electricity consumption in each area to better match actual demand and electricity price fluctuations, fully utilizing peak-valley pricing to reduce electricity costs. When implementing personalized electricity consumption plans, personnel distribution data is incorporated for adjustment, ensuring a high degree of matching between electricity consumption plans and personnel activities, avoiding unnecessary energy waste, and thus achieving refined energy consumption management in each area of ​​the building, fully tapping energy-saving potential, and improving energy consumption optimization effects. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating a building energy consumption optimization method provided in an embodiment of this application; Figure 2 A schematic diagram of a building energy consumption optimization device provided in an embodiment of this application; Figure 3 This is an internal structural diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] In one embodiment, this application provides a building energy consumption optimization method, which is illustrated in the following embodiments using a server as an example. It is understood that the building energy consumption optimization method can be executed by a single server or a server cluster consisting of multiple servers; this application does not impose any specific limitations on this. Furthermore, with the authorization of customers within the building, load forecast data, equipment energy efficiency models, environmental parameters, and other data used to implement the building energy consumption optimization method provided in this application can be obtained.

[0020] like Figure 1 As shown, this application provides a building energy consumption optimization method, the method comprising: S101: Obtain load forecast data, and perform short-term and medium-term load forecasts based on the load forecast data to obtain short-term load curves and next-day load curves.

[0021] Load forecasting data refers to the set of input data used to predict the future electricity demand of a building, including but not limited to historical energy consumption data, weather forecast data, and employee scheduling data. The short-time load curve reflects the building's electricity demand forecast at a high time resolution over the next few minutes to hours, representing the recent dynamic load trend. The next-day load curve reflects the building's electricity demand forecast for various time periods on the following day.

[0022] In this step, a scheduled task can be set up to periodically issue energy consumption optimization commands. When the server receives the command, it can extract information related to electricity load from multiple data sources (such as smart meters, sensors, historical databases, etc.) to form load forecast data. This data may include historical electricity consumption records, real-time weather data, user behavior patterns, etc. Next, algorithms or models such as time series analysis can be used to perform short- and medium-term load forecasting on the load forecast data to determine the electricity load situation in different future time periods.

[0023] For example, in the daily energy consumption optimization of an office building, the server can automatically collect data such as historical electricity consumption, time period information, future weather forecasts, employee work schedules, and meeting room reservations through devices or systems such as smart meters, sensors, attendance systems, and meeting room reservation platforms to form load forecast data. Then, by analyzing the correlation patterns of various data in the load forecast data, the power consumption for each 15 minutes in the next hour is calculated, and a short-term load curve is plotted. At the same time, the power load situation for each time period from morning to evening of the next day is calculated, generating the load curve for the next day.

[0024] S102: Obtain equipment energy efficiency models and environmental parameters, and combine short-time load curves, environmental parameters, and equipment energy efficiency models to regulate the power of various electrical devices in the building.

[0025] Among them, the equipment energy efficiency model refers to a mathematical model or data mapping relationship used to describe the quantitative relationship between the energy input and effective output of various electrical equipment in a building under different operating conditions. Environmental parameters refer to indoor and outdoor environmental physical quantities that affect the building's energy demand and equipment operating efficiency, including but not limited to temperature, humidity, light intensity, and carbon dioxide concentration.

[0026] In this step, the established equipment energy efficiency model is first obtained, which describes the efficiency characteristics of various electrical devices in the building at different output levels. Simultaneously, environmental data such as temperature, humidity, illuminance, and CO2 concentration are collected in real time by sensors deployed in various areas of the building. Combined with short-term load curves, environmental parameters, and the equipment energy efficiency model, a comprehensive analysis and calculation are performed to determine how to most effectively allocate and adjust the operating power of each electrical device while meeting predicted load demands and comfort constraints.

[0027] Specifically, the system retrieves short-term load curves to clarify current and future short-term electricity load demands, simultaneously acquires real-time environmental parameters for each area of ​​the building and determines whether they are within a comfortable range, then calls a preset equipment energy efficiency model to determine the optimal operating power of various equipment under corresponding load and environmental conditions; subsequently, it integrates the data from these three sources for calculation and analysis, generates personalized power control commands for different electrical equipment such as air conditioners and lighting, and finally sends the commands to the control modules of each device to adjust the power of each electrical device.

[0028] Furthermore, during the comprehensive analysis of the three sets of data, a pre-trained power control model can be used to analyze the data and output the target operating power of each electrical device. This power control model can be trained using past data from the above three types as training data, and the target operating power of the corresponding electrical devices as training labels. The pre-trained model is iteratively trained until the training conditions are met, at which point the pre-trained model is determined as the power control model. These training conditions can be set to reach a preset number of iterations or to achieve a preset convergence accuracy. This application does not impose specific limitations on this.

[0029] S103: Generate the next day's peak-valley electricity price optimization strategy based on the next day's load curve, and obtain personalized electricity consumption plans for each area inside the building.

[0030] The next-day peak-valley electricity pricing optimization strategy refers to an electricity control scheme that maximizes the use of low-priced electricity and reduces peak-hour electricity costs by adjusting electricity consumption periods and optimizing load distribution. This includes specific measures such as off-peak energy storage, peak-hour shaving, and demand control. Personalized electricity consumption plans refer to electricity control schemes developed based on the functional attributes, usage patterns, and energy consumption differences of different areas within a building. These plans encompass equipment start-up and shutdown times, operating parameters, and other related aspects.

[0031] In this step, the load curve for the following day is analyzed to clarify the distribution of electricity load at different times of the day. Combined with the peak-valley and off-peak periods and electricity price data released by the local power grid, overlapping periods of peak load and peak electricity price, as well as off-peak load and off-peak electricity price, are identified, allowing for the development of targeted control strategies. Simultaneously, personalized electricity usage plans for each area within the building are obtained. Based on the functional positioning, historical usage data, staff scheduling plans, and special needs (such as meeting room reservations, 24-hour operation of the computer room, etc.) of each area, the electricity usage patterns and preferences of each area are analyzed to form a customized electricity control plan for each area—a personalized electricity usage plan.

[0032] For example, suppose that in the management of office buildings in a smart park, the backend server can predict the peak electricity consumption period of a certain office building from 10:00 to 15:00 the next day, which coincides with the peak electricity price, and the low electricity consumption period from 6:00 to 7:00, which coincides with the low electricity price. Based on this, the peak-valley electricity price optimization strategy can be generated as follows: during the low-valley period, start the air conditioner to pre-cool / pre-heat and the water heater to heat and store energy at full load. During the peak period, fine-tune the air conditioner temperature and reduce the power of unnecessary lighting to reduce the load.

[0033] S104: When implementing each personalized electricity plan, obtain personnel distribution data and adjust each personalized electricity plan based on the personnel distribution data.

[0034] Among them, personnel distribution data refers to comprehensive data reflecting the real-time number, density, length of stay, and activity status of personnel in various areas within the building.

[0035] In this step, during the implementation of the personalized power consumption plan, pre-set sensing devices continuously collect information on the distribution of people in various areas of the building. Then, the personalized power consumption plan for the corresponding areas is adjusted based on the personnel distribution data. Specifically, the collected personnel distribution data can be analyzed to determine whether the activity patterns of people in each area match the pre-set scenario. If they do not match, the personalized power consumption plan is adjusted according to the actual personnel activity. This ensures that the power consumption plan aligns with actual usage needs, avoiding energy waste or poor user experience caused by a disconnect between the pre-set plan and personnel status. For example, in a certain personalized power consumption plan, lighting equipment typically turns on automatically half an hour before the start of work. However, if employees are detected arriving in the office area half an hour before the start of work, the personalized power consumption plan will be adjusted to turn on the lighting equipment earlier.

[0036] In the above embodiments, short-term and next-day load curves are obtained through short-term and medium-term load forecasting. Based on the coordinated control of short-term load curves, environmental parameters, and equipment energy efficiency, control lag caused by coarse forecast granularity is avoided, thereby improving the timeliness and accuracy of energy consumption response. Simultaneously, peak-valley electricity pricing optimization strategies are generated based on the next-day load curves, allowing electricity consumption in each area to better align with actual demand and price fluctuations, fully utilizing peak-valley pricing to reduce electricity costs. When implementing personalized electricity consumption plans, personnel distribution data is incorporated for adjustment, ensuring a high degree of matching between the electricity consumption plan and personnel activities, avoiding unnecessary energy waste, and thus achieving refined energy consumption management in each area of ​​the building, fully tapping energy-saving potential, and improving energy consumption optimization effects.

[0037] In one embodiment, load forecasting data is acquired, and short-term and medium-term load forecasts are performed based on the load forecasting data to obtain short-term load curves and next-day load curves, including: S1: Acquire historical energy consumption data, weather forecast data, employee scheduling data, and event booking data to generate load forecast data.

[0038] S2: Input the load forecast data into the pre-trained short-term forecast model and medium-term forecast model respectively to obtain the short-term load curve output by the short-term forecast model and the next-day load curve output by the medium-term forecast model.

[0039] Historical energy consumption data refers to the electricity consumption records of various areas and equipment categories within a building over a past period. Weather forecast data refers to meteorological parameter forecasts for a future period provided by meteorological services, such as temperature, humidity, and sunlight. Employee scheduling data includes the planned arrival and departure times and attendance status of employees in each area. Event booking data refers to information on planned future space usage events obtained from meeting systems, public space booking platforms, etc., such as meeting room bookings, reception activities, and training arrangements.

[0040] In this embodiment, past energy consumption records are first collected using smart meters, sensors, and other devices within the building. Then, future weather forecasts are retrieved from a meteorological service platform, employee work schedules are exported from an attendance system, and event booking details are extracted from a meeting booking platform and an OA system. This multi-source data is then cleaned, integrated, and its features are extracted to form standardized load forecast data. This load forecast data is then input into pre-trained short-term and medium-term forecast models. The models analyze data correlation patterns using built-in algorithms, outputting the corresponding electricity load forecast results for each time period and plotting them as curves: the short-term load curve and the next day's load curve.

[0041] In one example, the short-term forecasting model can be trained using an LSTM (Long Short-Term Memory) model, while the medium-term forecasting model can be trained using an XGBoost (eXtreme Gradient Boosting) model. Specifically, for the short-term forecasting model, past load forecast data samples can be used as training data, and the short-term load curves corresponding to the training data period can be used as sample labels to iteratively train a pre-defined first model until the corresponding iteration conditions are met. This first model is then identified as the short-term forecasting model, and it is a pre-trained LSTM model. For the medium-term forecasting model, past load forecast data samples can be used as training data, and the next-day load curves corresponding to the training data period can be used as sample labels to iteratively train a pre-defined second model until the corresponding iteration conditions are met. This second model is then identified as the medium-term forecasting model, and it is a pre-trained XGBoost model.

[0042] It is understandable that, due to the differences in the influencing factors and changing patterns of electricity load at different times, load forecast data is input into pre-trained short-term and medium-term forecasting models. These specialized models improve forecast accuracy, resulting in short-term and next-day load curves. This process fully integrates multi-dimensional influencing factors and, with the help of specialized models, enables accurate prediction of electricity load at different time dimensions, providing reliable data support for subsequent strategies such as equipment power regulation and peak-valley electricity pricing optimization.

[0043] In one embodiment, power regulation is performed on various electrical devices in a building by combining short-term load curves, environmental parameters, and equipment energy efficiency models, including: S1: Based on the equipment energy efficiency model, determine the energy efficiency curves and optimal operating parameter ranges for each electrical device.

[0044] S2: Determine the electricity demand for each time period based on the short-term load curve, and calculate the target operating power of each electrical device by combining environmental parameters, the energy efficiency curves of each electrical device and the optimal operating parameter range.

[0045] S3: Issue power control commands to each electrical device based on its target operating power.

[0046] The energy efficiency curve refers to the performance efficiency variation diagram of a specific electrical device under different load rates or operating conditions. The optimal operating parameter range refers to a set of operating parameter values ​​determined based on the device's energy efficiency curve, device characteristics, and constraints. Within this range, the device can meet output requirements with high overall energy efficiency.

[0047] In this embodiment, a pre-built equipment energy efficiency model is retrieved, and energy efficiency variation curves of various electrical devices (such as air conditioners, lighting, elevators, etc.) are extracted. Based on the peak range of the curves and energy loss thresholds, the optimal operating parameter range for each type of equipment is defined. Then, based on short-term load curves, the electricity demand for each time period is determined, clarifying the overall building and regional electricity load demand for each time period in the future short term. The target operating power is calculated by combining environmental parameters, the energy efficiency curves of each electrical device, and the optimal operating parameter range. That is, by integrating the variation patterns of environmental parameters and equipment energy efficiency curves, the corresponding time period's electricity demand is matched within the optimal operating parameter range, and the specific operating power of each device is calculated using an algorithm. Finally, power control commands are issued to each electrical device according to the target operating power. This ensures that each electrical device operates in an efficient and suitable state, avoiding energy waste and lifespan loss caused by overload or inefficient operation, and accurately matching the electricity demand and environmental conditions for each time period, thereby achieving refined optimization of building energy consumption.

[0048] Specifically, environmental parameters such as temperature, humidity, illuminance, and CO2 concentration in various areas are collected in real time by sensors deployed within the building to determine the difference between the current environment and the preset comfort standard. Then, the energy efficiency curves of each electrical device are retrieved to clarify the energy efficiency performance of the equipment at different power levels, while simultaneously locking in the optimal operating parameter range as the calculation boundary. Subsequently, combined with the electricity demand for each time period decomposed from the short-term load curve, with the goals of "meeting demand, adapting to the environment, and minimizing energy consumption," an algorithm is used to convert environmental deviations and electricity demand into equipment operating power requirements. Within the optimal operating parameter range, referring to the peak efficiency segment of the energy efficiency curve, a specific power value that can both compensate for environmental deviations, match the electricity load, and enable the equipment to operate in a highly efficient and low-consumption state is calculated—that is, the target operating power. The algorithm can employ some multi-objective optimization algorithms, and this application does not impose specific restrictions on this.

[0049] For example, suppose that in the energy management system of a smart office building, the energy efficiency curve of a certain brand of air conditioner can be retrieved from the equipment energy efficiency model to determine that its energy efficiency is highest when the operating power is 2000W-3000W, and the corresponding temperature setting is 24-26℃ as the optimal parameter range; then, through the short-time load curve, it is found that the power demand of the office area at 10 am is at a moderate level, and at the same time, the environmental sensor shows that the current temperature is 28℃ and the light is sufficient. At this time, by combining this information, the target operating power of the air conditioner in this area is calculated to be 2500W, and the target operating power of the lighting equipment is adjusted to 50% of the rated power because of the sufficient natural light.

[0050] In one embodiment, a peak-valley electricity price optimization strategy for the next day is generated based on the next day's load curve, including: S1: Obtain the local power grid's time period divisions and corresponding electricity price standards to divide the off-peak electricity price period and peak electricity price period within the time period of the load curve for the next day.

[0051] S2: Based on the load curve of the next day, determine the distribution of flexible load and energy storage load in each time period.

[0052] S3: For off-peak electricity pricing periods, control flexible loads and energy storage loads to operate at full capacity during these periods to generate load filling schemes.

[0053] S4: For peak electricity pricing periods, reduce peak electricity load by fine-tuning air conditioning temperature, reducing unnecessary lighting brightness, and delaying non-emergency electricity tasks to generate a load shaving scheme.

[0054] S5: Summarize the load filling scheme and the load peak shaving scheme to obtain the peak-valley electricity price optimization strategy for the next day.

[0055] Off-peak electricity pricing periods refer to specific time periods stipulated by the local power grid where electricity demand is low and electricity prices are at their lowest. Peak electricity pricing periods refer to specific time periods stipulated by the local power grid where electricity demand is high and electricity prices are at their highest.

[0056] In this embodiment, the specific division of local peak, flat, and valley periods (such as start and end times) and corresponding electricity prices are obtained through official power grid channels or real-time electricity price APIs. Combined with the 24-hour time range covered by the next day's load curve, the valley and peak electricity price periods are marked. The load composition of each period in the next day's load curve is analyzed to distinguish between flexible loads and energy storage loads, determining the scale and operational potential of these two types of adjustable loads within different electricity price periods. For valley electricity price periods, flexible loads and energy storage loads are controlled to operate at full capacity to generate a load shaving scheme. For example, during valley periods, a plan can be formulated to allow loads such as air conditioning pre-cooling, water heater heating, and energy storage device charging to operate at full capacity, making full use of low-priced electricity. For peak electricity price periods, peak loads are reduced by fine-tuning air conditioning temperatures, lowering unnecessary lighting brightness, and delaying non-emergency electricity tasks to generate a load shaving scheme. Finally, the two schemes are summarized to obtain the next day's peak-valley electricity price optimization strategy.

[0057] Furthermore, when formulating the next day's peak-valley electricity pricing optimization strategy, the optimization of demand charges can also be taken into account to avoid sudden increases in demand charges.

[0058] Specifically, by developing load shaving and peak-shaving schemes, it is possible to rationally allocate electricity load during different electricity price periods. This not only fully utilizes the low-priced electricity during off-peak hours to reduce overall electricity costs, but also avoids energy waste and high-cost electricity consumption through peak-shaving. This, in turn, improves the effectiveness of energy consumption optimization.

[0059] In one embodiment, adjustments are made to each personalized electricity plan based on personnel distribution data, including: S1: Determine the current occupancy status of each area of ​​the building based on the personnel distribution data.

[0060] S2: Dynamically adjust the personalized electricity usage plan for each area based on the current usage of personnel in each area.

[0061] In this embodiment, the current occupancy status of each area of ​​the building is determined based on personnel distribution data. This involves integrating and analyzing personnel distribution data collected from multiple sources, including access control systems, WiFi probes, workstation sensors, and camera AI analysis, to determine whether each area is occupied, temporarily unoccupied, or unmanned. Simultaneously, the personnel density and dwell time in occupied areas are determined. Personalized power consumption plans for each area are dynamically adjusted based on occupancy status. Specifically, based on occupancy status, the original personalized power consumption plans are modified in real time to adjust equipment start-up and shutdown, operating parameters, etc., to adapt the plans to actual usage needs. This effectively reduces energy waste caused by personnel movement while ensuring that the power demand of occupied areas is fully met, thereby improving the flexibility and accuracy of energy consumption optimization.

[0062] In one embodiment, the building energy consumption optimization method further includes the following when regulating the power of various electrical devices in a building: When any electrical device is turned off, personnel distribution data is obtained, and a multi-level power outage strategy is adopted based on the personnel distribution data.

[0063] In this embodiment, if power regulation of various electrical devices in a building involves shutting down a particular device, the personnel distribution data is used to obtain information about the people around the device to execute a multi-level power-off strategy. For example, a power-off reminder can be issued one minute after an employee leaves, the device can be put into standby mode after two to five minutes, and the device can be put into deep energy-saving mode after six minutes.

[0064] In addition, when someone is detected entering the area of ​​the electrical equipment, a rapid recovery mechanism is immediately activated to start the electrical equipment.

[0065] For example, a tiered power outage strategy can be represented as: Warning prompt (1 minute): Light flashes once, voice prompt: "Long period of inactivity detected. Energy saving mode will be entered in 1 minute."

[0066] Standby mode (minutes 2-5): Lighting: Reduce brightness to 30% (guide light), Air conditioning: Increase / decrease by 2°C (reduce load), Sockets: Keep power supplied (avoid computer power outage).

[0067] Deep Energy Saving Mode (6th minute): Lighting: Off (emergency lighting on), Air Conditioning: Fresh air off, only recirculation on (or completely off), Outlets: Disconnect non-essential circuits (servers, etc. on).

[0068] In one embodiment, the building energy consumption optimization method further includes: When a temporary fluctuation in electricity price is detected, the peak-valley electricity price optimization strategy for the next day is adjusted to maximize the use of low-priced electricity.

[0069] In this embodiment, electricity price fluctuations can be detected by accessing the real-time electricity price API of the power grid. For example, when a temporary price reduction is detected, energy storage devices such as high-power equipment, water heaters, and charging piles can be activated in advance to adjust the peak-valley electricity price optimization strategy for the next day, thereby maximizing the utilization of low-priced electricity.

[0070] In one embodiment, the building energy consumption optimization method further includes: acquiring multi-dimensional energy consumption data and generating visual reports from each dimension. The multiple dimensions include department, floor, time period, and equipment dimensions. In addition, a departmental energy consumption ranking list can be generated for display.

[0071] In one embodiment, a special scenario handling strategy can also be formulated. When the current scenario matches the scenario specified in the strategy, the priority of the strategy can be adjusted to the highest priority. The following are some common special scenarios and their corresponding strategies: Scene 1: Conference Room 1. 15 minutes before the meeting starts: automatically turn on the air conditioning (pre-cool / pre-heat to a comfortable temperature), turn on the lighting, and preheat the projector.

[0072] 2. After the meeting: Power off 5 minutes later (personnel may be delayed in leaving), and power off after confirming that no one is left.

[0073] Scenario 2: Tea room / Restroom (High-frequency, short-time use area)

[0074] 1. Lighting: Turn on when someone enters and turn off 30 seconds after they leave.

[0075] 2. Exhaust fan: Delay turning it off for 3 minutes (to eliminate odors).

[0076] 3. Water dispenser: Keeps water warm 24 hours a day (uninterrupted power supply).

[0077] Scenario 3: Server room (critical equipment area)

[0078] 1. Air conditioning: Runs 24 hours a day and is not affected by unattended operation.

[0079] 2. Lighting: Can be turned off automatically.

[0080] 3. An alarm will sound if the temperature is abnormal; power off is prohibited.

[0081] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0082] The building energy consumption optimization device provided in the embodiments of this application is described below. The building energy consumption optimization device described below and the building energy consumption optimization method described above can be referred to in correspondence.

[0083] like Figure 2 As shown, this application provides a building energy consumption optimization device 200, the device comprising: The load forecasting module 201 is used to acquire load forecasting data and perform short-term and medium-term load forecasting based on the load forecasting data to obtain short-term load curves and next-day load curves. The power regulation module 202 is used to acquire equipment energy efficiency models and environmental parameters, and combine short-time load curves, environmental parameters and equipment energy efficiency models to regulate the power of various electrical devices in the building; The electricity price optimization module 203 is used to generate the next day's peak-valley electricity price optimization strategy based on the next day's load curve, and to obtain personalized electricity consumption plans for each area inside the building. The scheme adjustment module 204 is used to obtain personnel distribution data when executing each personalized electricity consumption scheme, and adjust each personalized electricity consumption scheme based on the personnel distribution data.

[0084] In the above embodiments, short-term and next-day load curves are obtained through short-term and medium-term load forecasting. Based on the coordinated control of short-term load curves, environmental parameters, and equipment energy efficiency, control lag caused by coarse forecast granularity is avoided, thereby improving the timeliness and accuracy of energy consumption response. Simultaneously, peak-valley electricity pricing optimization strategies are generated based on the next-day load curves, allowing electricity consumption in each area to better align with actual demand and price fluctuations, fully utilizing peak-valley pricing to reduce electricity costs. When implementing personalized electricity consumption plans, personnel distribution data is incorporated for adjustment, ensuring a high degree of matching between the electricity consumption plan and personnel activities, avoiding unnecessary energy waste, and thus achieving refined energy consumption management in each area of ​​the building, fully tapping energy-saving potential, and improving energy consumption optimization effects.

[0085] In one embodiment, the load forecasting module includes: The data acquisition submodule is used to acquire historical energy consumption data, weather forecast data, employee shift data, and event booking data to generate load forecast data. The load forecasting submodule is used to input load forecasting data into the pre-trained short-term forecasting model and medium-term forecasting model, respectively, to obtain the short-term load curve output by the short-term forecasting model and the next-day load curve output by the medium-term forecasting model.

[0086] In one embodiment, the power regulation module includes: The energy efficiency determination submodule is used to determine the energy efficiency curve and optimal operating parameter range of each electrical device based on the equipment energy efficiency model. The power calculation submodule is used to determine the electricity demand for each time period based on the short-term load curve, and to calculate the target operating power of each electrical device by combining environmental parameters, the energy efficiency curves of each electrical device and the optimal operating parameter range. The instruction issuing submodule is used to issue power control instructions to each electrical device according to the target operating power of each device.

[0087] In one embodiment, the electricity price optimization module includes: The time period segmentation submodule is used to obtain the time period segmentation and corresponding electricity price standards of the local power grid, so as to divide the off-peak electricity price period and peak electricity price period within the time period of the load curve of the next day; The distribution determination submodule is used to determine the distribution of flexible load and energy storage load for each time period based on the next day's load curve; The first generation submodule is used to control the flexible load and energy storage load to operate at full load during off-peak electricity price periods in order to generate a load filling scheme. The second generation submodule is used to reduce peak electricity load during peak electricity price periods by fine-tuning air conditioning temperature, reducing unnecessary lighting brightness, and delaying non-emergency electricity tasks, so as to generate a load shaving scheme. The strategy generation submodule is used to summarize the load valley filling scheme and the load peak shaving scheme to obtain the peak valley electricity price optimization strategy for the next day.

[0088] In one embodiment, the scheme adjustment module includes: The situation determination submodule is used to determine the current occupancy status of each area of ​​the building based on personnel distribution data; The scheme adjustment submodule is used to dynamically adjust the personalized electricity scheme for each area based on the current usage of personnel in each area.

[0089] In one embodiment, the building energy consumption optimization device further includes: The multi-level power-off module is used to acquire personnel distribution data when any electrical equipment is turned off, and to adopt a multi-level power-off strategy based on the personnel distribution data.

[0090] In one embodiment, the building energy consumption optimization device further includes: The strategy adjustment module is used to adjust the peak-valley electricity price optimization strategy for the next day when a temporary fluctuation in electricity price is detected, in order to maximize the use of low-priced electricity.

[0091] The division of modules in the above-described building energy consumption optimization device is merely illustrative. In other embodiments, the building energy consumption optimization device can be divided into different modules as needed to complete all or part of its functions. Each module in the above-described building energy consumption optimization device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0092] In one embodiment, this application also provides a storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the building energy consumption optimization method as described in any of the above embodiments.

[0093] In one embodiment, this application also provides a computer device storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the building energy consumption optimization method as described in any of the above embodiments.

[0094] Indicatively, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the internal structure of a computer device 300 provided in an embodiment of this application. The computer device 300 can be provided as a server. (Refer to...) Figure 3 The computer device 300 includes a processing component 302, which further includes one or more processors, and memory resources represented by memory 301 for storing instructions, such as application programs, that can be executed by the processing component 302. The application programs stored in memory 301 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 302 is configured to execute instructions to perform the building energy optimization method of any of the above embodiments.

[0095] The computer device 300 may also include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate on an operating system stored in memory 301, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or similar.

[0096] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0097] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a…" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. In this document, the singular forms "a," "an," and "the" may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising / including” or “having” specify the presence of the stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0098] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0099] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing building energy consumption, characterized in that, The method includes: Obtain load forecast data, and perform short-term and medium-term load forecasts based on the load forecast data to obtain short-term load curves and next-day load curves; The energy efficiency model and environmental parameters of the equipment are obtained, and the power of each electrical device in the building is regulated by combining the short-term load curve, the environmental parameters and the energy efficiency model of the equipment. Based on the load curve of the next day, a peak-valley electricity price optimization strategy for the next day is generated, and personalized electricity consumption plans for each area inside the building are obtained. When implementing each personalized electricity plan, personnel distribution data is obtained, and each personalized electricity plan is adjusted based on the personnel distribution data.

2. The building energy consumption optimization method according to claim 1, characterized in that, The process of acquiring load forecast data and performing short-term and medium-term load forecasts based on the load forecast data to obtain short-term load curves and next-day load curves includes: Acquire historical energy consumption data, weather forecast data, employee scheduling data, and event booking data to generate load forecast data; The load forecast data is input into the pre-trained short-term forecast model and medium-term forecast model respectively to obtain the short-term load curve output by the short-term forecast model and the next-day load curve output by the medium-term forecast model.

3. The building energy consumption optimization method according to claim 1, characterized in that, The method of combining the short-term load curve, the environmental parameters, and the equipment energy efficiency model to regulate the power of various electrical devices in the building includes: Based on the equipment energy efficiency model, determine the energy efficiency curves and optimal operating parameter ranges for each electrical device; Based on the short-term load curve, the electricity demand for each time period is determined, and combined with the environmental parameters, the energy efficiency curves of each electrical device and the optimal operating parameter range, the target operating power of each electrical device is calculated. Based on the target operating power of each electrical device, power control commands are issued to each electrical device.

4. The building energy consumption optimization method according to claim 1, characterized in that, The strategy for generating the next day's peak-valley electricity price optimization based on the next day's load curve includes: Obtain the local power grid's time period divisions and corresponding electricity price standards to divide the off-peak electricity price period and peak electricity price period within the time period of the load curve of the next day; Based on the load curve of the next day, the distribution of flexible load and energy storage load in each time period is determined; For the off-peak electricity price period, the flexible load and the energy storage load are controlled to operate at full load during the period to generate a load filling scheme; For the peak electricity price period, the peak electricity load is reduced by fine-tuning the air conditioning temperature, reducing the brightness of unnecessary lighting, and delaying non-emergency electricity use tasks, so as to generate a load shaving scheme. The load filling scheme and the load peak shaving scheme are combined to obtain the next day's peak-valley electricity price optimization strategy.

5. The building energy consumption optimization method according to claim 1, characterized in that, The adjustment of each personalized electricity consumption plan based on the personnel distribution data includes: Based on the personnel distribution data, determine the current personnel usage in each area of ​​the building; Based on the current usage of personnel in each area, the personalized electricity plans for that area will be dynamically adjusted.

6. The building energy consumption optimization method according to any one of claims 1 to 5, characterized in that, When regulating the power of various electrical devices in a building, the method further includes: When any electrical device is turned off, personnel distribution data is obtained, and a multi-level power outage strategy is adopted based on the personnel distribution data.

7. The building energy consumption optimization method according to any one of claims 1 to 5, characterized in that, The method further includes: When a temporary fluctuation in electricity price is detected, the next day's peak-valley electricity price optimization strategy is adjusted to maximize the utilization of low-priced electricity.

8. A building energy consumption optimization device, characterized in that, The device includes: The load forecasting module is used to acquire load forecasting data and perform short-term and medium-term load forecasting based on the load forecasting data to obtain short-term load curves and next-day load curves. The power regulation module is used to acquire equipment energy efficiency models and environmental parameters, and combine the short-time load curve, the environmental parameters and the equipment energy efficiency model to regulate the power of various electrical devices in the building; The electricity price optimization module is used to generate a peak-valley electricity price optimization strategy for the next day based on the next day's load curve, and to obtain personalized electricity consumption plans for each area inside the building. The scheme adjustment module is used to obtain personnel distribution data when executing each personalized electricity consumption scheme, and adjust each personalized electricity consumption scheme based on the personnel distribution data.

9. A storage medium, characterized in that: The storage medium stores computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the building energy consumption optimization method as described in any one of claims 1 to 7.

10. A computer device, characterized in that, include: One or more processors, and memory; The memory stores computer-readable instructions, which, when executed by the one or more processors, perform the steps of the building energy consumption optimization method as described in any one of claims 1 to 7.

Images