Constructional engineering energy consumption regulation and control system and method based on Internet of Things

Abstract

The invention discloses a building engineering energy consumption regulation and control system and method based on the Internet of Things, and relates to the technical field of power monitoring and energy efficiency management. Comprising a sensing module for determining equipment operation parameters, environment parameters and energy storage data through a sensor and an OPC-UA protocol; the decision module is used for acquiring a COP value according to the equipment operation parameters, the environment parameters and the energy storage data, and acquiring a regulation and control instruction according to the COP value; and the execution module is used for carrying out self-adaptive control on an air conditioner and a water pump according to the regulation and control instruction and carrying out collaborative management on energy storage equipment and a battery. According to the method, the power supply proportion of the power grid and the energy storage system is dynamically distributed through integer linear programming, and is combined with the real-time electricity price, so that the cost optimization is realized, and meanwhile, the maximum discharge current is limited and the health degree of the battery is protected through an exponential decay algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring and energy efficiency management, and in particular to a construction engineering energy consumption control system and method based on the Internet of Things. Background Art

[0002] In recent years, with the development of Internet of Things (IoT) technology, it has become possible to use IoT technology to effectively manage and control building energy consumption. IoT technology achieves seamless connection between the physical world and the digital world through sensor networks, wireless communications, etc., so that various devices in the building can communicate with each other and upload the collected data to the cloud for processing and analysis.

[0003] The Chinese invention patent with publication number CN117200176A discloses a demand-side control method and system based on collaborative control of new energy multiple loads; including step 1, counting the number of all smart loads in the target area; step 2, counting the adjustable capacity of different types of smart loads in the target area respectively; step 3, counting the gap power Z between the grid-side supply and the load-side demand in the target area; step 4, reducing the gap power Z through scheduling means; the invention fully considers the double-sided fluctuation characteristics of renewable energy power stations and smart loads, optimizes the load characteristics of power grids at all levels in different time periods, further explores flexible demand-side response resources to increase the scheduling capacity of the power system, and fully considers the grid scheduling cost during grid scheduling. While improving the grid scheduling and transaction efficiency, it also improves the economy of grid scheduling, improves the grid operation efficiency and is conducive to alleviating the imbalance caused by grid fluctuations.

[0004] Most of the existing and similar traditional static control strategies rely on manually preset fixed schedules or simple thresholds (such as starting the air conditioner when the temperature is >26℃) for setting. They are not combined with the equipment operation efficiency curve (such as the compressor load rate-energy efficiency ratio relationship), environmental dynamic parameters (such as personnel density, indoor and outdoor temperature difference) and user behavior preferences (such as conference room reservation data) collected in real time by the IoT terminal, nor are they integrated with the energy storage system charging and discharging status and grid electricity price signals, resulting in a disconnect between the equipment control strategy and the dynamic supply and demand of energy. In addition, the air conditioning unit has been running in the low-efficiency range for a long time (energy efficiency drops by 30%~50% at partial load) and the water pump has not been dynamically adjusted according to the pressure fluctuation of the pipeline network, which will reduce the power utilization rate by 15%~25%. At the same time, due to the extensive charging and discharging strategy of the energy storage battery failing to match the real-time power demand of the equipment (such as overcharging during low-price periods and forced discharge at peak loads), the cycle life of the energy storage battery is reduced by 20%~30%, which ultimately leads to multiple contradictions of energy efficiency waste, equipment loss and rising operation and maintenance costs. Summary of the invention

[0005] The purpose of the present invention is to provide a construction engineering energy consumption control system and method based on the Internet of Things to solve the problems raised in the above background technology.

[0006] To achieve the above purpose, the present invention provides the following technical solution: a building engineering energy consumption control system based on the Internet of Things, comprising: The perception module determines the equipment operating parameters, environmental parameters and energy storage data through sensors and OPC-UA protocol; The decision module obtains the COP value according to the equipment operation parameters, environmental parameters and energy storage data, and obtains the control instruction according to the COP value, including: SB1: Obtain COP value: Take the load rate, temperature difference and occupant density as the input of the constructed energy efficiency prediction model, and output the energy efficiency ratio prediction value, specifically: , in: is the mean square error, is the number of data points, is the actual energy efficiency ratio of the i-th sample, is the predicted energy efficiency ratio of the i-th sample, is the index variable of the sample; SB2: Determine the control instruction: establish the objective function through the real-time electricity price and the predicted value of the predicted energy efficiency ratio, obtain the minimum electricity fee, the predicted energy efficiency ratio and the discharge depth, and compare the predicted energy efficiency ratio with the upper limit and lower limit of the preset predicted energy efficiency ratio. When the predicted energy efficiency ratio is not less than the upper limit of the preset predicted energy efficiency ratio, the running equipment runs at full power. When the predicted energy efficiency ratio is less than the lower limit of the preset predicted energy efficiency ratio, the running equipment stops running. Otherwise, the running equipment maintains the current power operation. The execution module performs adaptive control on the air conditioner and the water pump and coordinates the management of the energy storage device and the battery according to the control instructions.

[0007] Furthermore, equipment operating parameters, environmental parameters and energy storage data are determined, including: SA1: Operation parameter collection: Through sensors, the operation parameters of the compressor and the operation parameters at the inlet and outlet flanges of the water pump are obtained, and the energy efficiency ratio of the compressor and the nonlinear equation of the water pump are obtained, specifically: , in: is the energy efficiency ratio of the refrigeration equipment, is the amount of heat removed from the room by the cooling equipment per unit time. It is the actual power consumed by the refrigeration equipment during operation. is the input power of the pump, is the linear coefficient related to the mechanical efficiency of the pump, is the head of the pump, is the flow rate of the pump, is a nonlinear system related to hydraulic loss; SA2: Environmental parameter perception: Through millimeter wave radar, infrared imager and temperature and humidity gradient sensor, the movement direction of human body, thermal radiation distribution and indoor and outdoor temperature are obtained, and the density of people in the area is obtained. Specifically: , in: is the number of people per unit area, is the number of people detected, is the plane area of ​​the monitored area; SA3: Synchronization of power grid and energy storage data: Obtain real-time electricity prices through the OPC-UA protocol, and determine the electricity cost of energy-consuming equipment and the energy consumption cost of the battery based on the real-time electricity price.

[0008] Furthermore, the electricity cost of energy-consuming equipment and the energy consumption cost of batteries are determined, including: SA3.1: Obtain real-time electricity prices: Connect to the power grid dispatching system through the OPC-UA protocol to obtain real-time electricity price data and build a time period-electricity price mapping table; SA3.2: Energy storage status monitoring: Obtain the SOC and SOH values ​​of the battery through the Coulomb integration method and internal resistance measurement method, specifically: , in: is the battery charging status, is the remaining battery power, is the rated capacity of the battery, The health status of the battery. is the initial internal resistance of a new battery, is the actual internal resistance of the battery after aging; SA3.3: Obtain the minimum total electricity cost: According to the time period-electricity price mapping table, obtain the electricity price of each time period and the power purchased by the power grid, build an integer linear programming model, and determine the minimum total electricity cost.

[0009] Furthermore, the minimum total electricity cost is determined, including: SA3.3.1: Set constraints: According to the SOC value and SOH value of the battery and the charge and discharge power of the energy storage system, set constraints, specifically: , in: is the total power consumed by the building in time t, is the power obtained from the grid during time t, is the charging and discharging power of the energy storage system within time t, is the battery charge state at time t+1, is the time interval, is the rated capacity of the energy storage system, is the minimum state of charge of the battery, is the maximum state of charge of the battery, is the maximum charging and discharging power of the energy storage system, is the charging and discharging state of the energy storage system within time t; SA3.3.2: Construct an integer linear programming model: Based on the constraints, construct an integer linear programming model to determine the electricity cost, specifically: , in: For the minimum electricity bill, is the power obtained from the grid during time t, is the electricity price at time t, For the time period.

[0010] Furthermore, an objective function is established by using the real-time electricity price and the predicted energy efficiency ratio predicted value, specifically: , in: is the weight coefficient of electricity cost, is the weight coefficient for energy efficiency optimization, is the battery life weight coefficient, For the minimum electricity bill, To predict the energy efficiency ratio, is the discharge depth; At the same time, the objective function is combined with the constraint condition to obtain the minimum electricity fee, predicted energy efficiency ratio and discharge depth. The constraint formula of the constraint condition is specifically: ,

[0011] in: To predict the energy efficiency ratio, is the battery charging status, is the charging and discharging power of the energy storage system within time t, is the maximum charge and discharge current.

[0012] Furthermore, the weight coefficient determination process includes: SB2.1: Setting the action space: Each weight coefficient is increased or decreased by a preset step size to set the action space, specifically: , in: is the weight coefficient of electricity cost, is the weight coefficient for energy efficiency optimization, is the battery life weight coefficient, is the action space; SB2.2: Perform reward calculation: Obtain reward results based on the action space, specifically: , in: For reward results, For the minimum electricity bill, To predict the energy efficiency ratio, is the discharge depth, is the weight coefficient of electricity cost, is the weight coefficient for energy efficiency optimization, is the battery life weight coefficient; SB2.3: Set state coding: Normalize the real-time electricity price, predicted energy efficiency ratio and SOC value to form a state vector, specifically: , in: is the state vector, For real-time electricity prices, To predict the energy efficiency ratio, is the battery charge status; SB2.4: Update the Q table. According to the action space, reward result and state encoding, construct and update the Q table to obtain the maximum Q value. The weight coefficient corresponding to the maximum Q value is the final weight coefficient. The update formula of the Q table is specifically: , in: For the state vector Take action The Q value, is the state vector, is the action space, is the discount factor, is the learning rate, For reward results, For the state vector Take action The Q value, is the next state vector, The next action space.

[0013] Furthermore, the air conditioner and water pump are adaptively controlled, including: SC1.1: Compressor control: According to the indoor and outdoor temperature difference and the density of people, the compressor frequency is obtained and adjusted, specifically: , in: is the adjusted compressor frequency, is the compressor frequency before adjustment, , , are the parameters of the PID controller, is the integral of the error accumulated over time, is the rate of change of error over time, is the difference between the temperature and the actual temperature; SC1.2: Water pump speed adjustment: According to the speed of the water pump, adjust the real-time operating speed of the water pump.

[0014] Furthermore, the coordinated management of energy storage equipment and batteries includes: SC2.1: Execution of charging and discharging strategy: Determine the charging and discharging status of the energy storage device based on the health status of the energy storage device, specifically: When the SOH value is not less than the upper limit of the preset SOH value, the battery is discharged; when the SOH value is not greater than the lower limit of the preset SOH value, the battery is charged; otherwise, the battery maintains the current state of operation; The discharge current of the battery is specifically: , in: For the The discharge current at the moment, is the maximum discharge current, is the time after discharge starts, is the time constant, is the base of natural logarithms; SC2.2: Multi-energy synergy: The energy storage system is charged according to the real-time power generation of the photovoltaic system and the total power consumed by the equipment. At the same time, the energy storage system is discharged according to the real-time electricity price of the power grid. Specifically: When the real-time power generation of the photovoltaic system is greater than the total power consumed by the equipment, the energy storage system is charged. The charging power of the energy storage system is specifically: , in: is the charging power of the energy storage system, is the maximum discharge current, is the total power consumed by the building in time t, is the real-time power generation of the photovoltaic system, is the rated voltage of the battery pack; When the real-time electricity price is at the peak electricity price, the energy storage system discharges, and the discharge power of the energy storage system is specifically: , in: is the discharge power of the energy storage system, is the power obtained from the grid during time t, is the total power consumed by the building in time t, is the maximum discharge current, is the rated voltage of the battery pack.

[0015] A method for controlling energy consumption of a building project based on the Internet of Things uses the above-mentioned system for controlling energy consumption of a building project based on the Internet of Things.

[0016] Compared with the prior art, the present invention has the following beneficial effects: First, the present invention dynamically allocates the power supply ratio between the power grid and the energy storage system through integer linear programming and combines it with the real-time electricity price, thereby achieving cost optimization. At the same time, the exponential decay algorithm limits the maximum discharge current and protects the health of the battery. Second, the present invention combines the load rate, temperature difference and personnel density through the COP prediction algorithm, so that the air-conditioning operating parameters are dynamically optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the flow chart of the energy consumption control system of the construction project of the present invention; Figure 2 It is a scatter diagram of COP value of the present invention; Figure 3 This is a comparison chart of electricity charges of the present invention; Figure 4 The discharge current curve diagram of the battery of the present invention; Figure 5 This is a comparison diagram of the adjustment of the compressor frequency under PID control of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Traditional static control strategies mostly rely on manually preset fixed schedules or simple thresholds (such as starting the air conditioner when the temperature is >26℃). They are not combined with the equipment operation efficiency curve (such as the compressor load rate-energy efficiency ratio relationship), environmental dynamic parameters (such as personnel density, indoor and outdoor temperature difference) and user behavior preferences (such as conference room reservation data) collected in real time by the IoT terminal, nor are they integrated with the energy storage system charging and discharging status and grid electricity price signals, resulting in a disconnect between the equipment control strategy and the dynamic supply and demand of energy. In addition, the air conditioning unit has been running in the inefficient range for a long time (energy efficiency drops by 30%~50% at partial load) and the water pump has not been dynamically adjusted according to the pressure fluctuation of the pipeline network, which will reduce the power utilization rate by 15%~25%. At the same time, the extensive charging and discharging strategy of the energy storage battery fails to match the real-time power demand of the equipment (such as overcharging during low-price periods and forced discharge at peak loads), resulting in a 20%~30% reduction in the cycle life of the energy storage battery, which ultimately leads to multiple contradictions of energy efficiency waste, equipment loss and rising operation and maintenance costs. The technical solution of the present application obtains the energy efficiency ratio of the air conditioner by acquiring multi-dimensional data, and obtains peak and valley electricity prices in real time, coordinates power supply from the power grid and charging and discharging of the energy storage system to minimize electricity costs. At the same time, it combines the exponential decay current model to protect battery health, and adjusts the compressor frequency in real time through the PID control algorithm to quickly stabilize the indoor temperature within 8-12 seconds.

[0020] Example 1

[0021] refer to Figure 1-Figure 5 This embodiment provides a construction project energy consumption control system based on the Internet of Things, which includes a perception module, a decision module, an execution module and a verification module. The perception module determines the equipment operation parameters, environmental parameters and energy storage data through sensors and OPC-UA protocol. The decision module obtains the COP value according to the equipment operation parameters, environmental parameters and energy storage data, and obtains the control instruction according to the COP value. The execution module adaptively controls the air conditioner and the water pump according to the control instruction, and collaboratively manages the energy storage device and the battery.

[0022] In this embodiment, the perception module obtains the operating parameters of the air-conditioning compressor and the water pump through sensors to obtain their corresponding energy efficiency ratio and nonlinear equation. At the same time, the millimeter wave radar, infrared imager and temperature and humidity gradient sensor are used to obtain the movement direction of the human body, the distribution of thermal radiation and the indoor and outdoor temperatures to determine the density of people in the area. Furthermore, the electricity cost of energy-consuming equipment and the energy consumption cost of the battery are determined through real-time electricity prices. The details are as follows: Step SA1: Operation parameter acquisition. That is, the operation parameters of the central air-conditioning compressor and the operation parameters of the water pump inlet and outlet flanges are obtained through sensors, and the energy efficiency ratio of the corresponding central air-conditioning and the nonlinear equation of the water pump are obtained according to the operation parameters obtained by the sensors, which are specifically: , in: is the energy efficiency ratio of the refrigeration equipment, is the amount of heat removed from the room by the cooling equipment per unit time. It is the actual power consumed by the refrigeration equipment during operation. is the input power of the pump, is the linear coefficient related to the mechanical efficiency of the pump, is the head of the pump, is the flow rate of the pump, is the nonlinear coefficient related to hydraulic loss.

[0023] Furthermore, a high-frequency vibration sensor is installed on the surface of the central air-conditioning compressor shaft to monitor and obtain the vibration spectrum characteristics of the central air-conditioning (such as the main frequency and harmonic amplitude) in real time through the high-frequency vibration sensor, and the corresponding central air-conditioning load rate is calculated through the vibration spectrum characteristics obtained in real time, specifically: , in: is the load rate of the refrigeration equipment, It is the actual power consumed by the refrigeration equipment during operation. is the rated power of the refrigeration equipment.

[0024] It is worth noting that the input current and voltage of the central air-conditioning motor can be obtained through the current transformer. At the same time, the input current and voltage obtained can be combined with the power factor to obtain the actual power consumed by the refrigeration equipment during operation, specifically: , in: It is the actual power consumed by the refrigeration equipment during operation. is the effective value of the voltage of the refrigeration equipment in the AC circuit, is the effective value of the current of the refrigeration equipment in the AC circuit, It is the ratio of the active power to the apparent power of the refrigeration equipment.

[0025] Furthermore, the evaporator and condenser fins of the central air conditioner are scanned by an infrared thermal imager to obtain the cooling capacity of the central air conditioner through the intensity of thermal radiation, specifically: , in: is the amount of heat removed from the room by the cooling equipment per unit time. is the air density, is the specific heat capacity of air, is the inlet and outlet temperature difference of the refrigeration equipment, The air volume of the refrigeration equipment.

[0026] In the specific implementation process, the compressor load rate of the central air conditioner is 60%, the actual power consumption is 50kW, and the heat removed from the room per unit time is 200kW, then the cooling capacity of the central air conditioner is 4.0.

[0027] Furthermore, by installing a differential pressure sensor at the inlet and outlet flanges of the water pump, the pressure difference between the inlet and outlet of the water pump can be obtained, and the pressure difference can be combined with the water flow density and gravity acceleration to obtain the corresponding water pump head, specifically: , in: is the head of the pump, is the pressure difference between the inlet and outlet of the pump, is the water density, is the acceleration due to gravity.

[0028] In the specific implementation process, the pump head is 30m and the flow rate of the pump is 50m 3 / h, and in this embodiment, the linear coefficient related to the mechanical efficiency of the water pump is set to 0.02, and the nonlinear coefficient related to the hydraulic loss is set to 0.0001, then the input power of the water pump is 42.5kW.

[0029] Step SA2: Environmental parameter perception. That is, the movement direction and thermal radiation distribution of the human body are obtained through millimeter wave radar and infrared imager, and the corresponding indoor and outdoor temperature difference is obtained through temperature and humidity gradient sensor.

[0030] Furthermore, the frequency modulated continuous wave emitted by the millimeter wave radar is combined with the Doppler effect to obtain the human body's movement speed and azimuth to generate the corresponding point cloud data. At the same time, the infrared thermal imager is used to capture the human body's thermal radiation distribution and combine it with the generated point cloud data. Specifically, the combined human body thermal radiation distribution and point cloud data are fused through the Kalman filter algorithm to obtain the regional personnel density, which is: , in: is the number of people per unit area, is the number of people detected, is the plane area of ​​the monitored area.

[0031] Furthermore, temperature and humidity gradient sensors are installed at key nodes inside and outside the building (such as exterior walls, corridors, and air-conditioning outlets) to obtain the indoor and outdoor temperatures at the key nodes inside and outside the building and determine the temperature difference at the key nodes.

[0032] In the specific implementation process, the plane area of ​​the monitored area is 30m 2 , the number of people in the area is 15, then the number of people in the unit area is 0.5 people / m 2 At the same time, the indoor temperature is set at 24°C, and the outdoor temperature is measured to be 35°C, so the temperature difference between the two is -11°C.

[0033] Step SA3: Synchronize the grid and energy storage data. That is, access the grid dispatching system through the OPC-UA protocol to obtain the forecast results of the time-of-use electricity price and regional load, and determine the electricity cost and battery loss cost of the energy-consuming equipment based on the time-of-use electricity price and forecast results. The details are as follows: Step SA3.1: Obtain real-time electricity prices. That is, connect to the power grid dispatching system through the OPC-UA protocol to obtain real-time electricity price data, and establish a time period-electricity price mapping table based on the obtained real-time electricity price data and time data.

[0034] Step SA3.2: Energy storage status monitoring. That is, the SOC value of the battery is obtained by using the Coulomb integration method and the current obtained during battery charging and discharging, specifically: , in: is the battery charging status, is the remaining battery power, is the rated capacity of the battery.

[0035] Furthermore, the battery charge and discharge current is measured by a Hall effect current sensor, with a sampling frequency of not less than 10 Hz. At the same time, the remaining battery power is determined based on the acquired charge and discharge current, specifically: , in: is the remaining battery power, is the battery power at the initial moment, is the real-time charge and discharge current, is the initial moment, For the ending moment.

[0036] Specifically, during the process of charging the battery, when the remaining power of the battery is the same as the preset voltage threshold, the remaining power of the battery is kept consistent with the rated capacity of the battery. Furthermore, during the process of discharging the battery, when the remaining power of the battery is the same as the cut-off voltage, the remaining power of the battery is set to 0.

[0037] Furthermore, the SOH value of the battery is obtained by the internal resistance measurement method, specifically: , in: The health status of the battery. is the initial internal resistance of a new battery, is the actual internal resistance of the battery after aging.

[0038] Furthermore, after the battery is at rest, a short-term high current pulse (such as 1C rate) is applied to measure the transient response of the voltage, that is, to obtain the actual internal resistance of the battery after aging, specifically: , in: is the actual internal resistance of the battery after aging, is the change in the applied DC pulse current, is the voltage change of the battery under the DC pulse.

[0039] In the specific implementation process, the applied DC pulse current change is 100A, and the voltage change is 0.5V, so the actual internal resistance of the battery after aging is 0.005Ω. At the same time, the initial internal resistance of the new battery is 0.05Ω, and the battery health state, that is, the SOH value, is 90%.

[0040] It is worth noting that when the SOH value of the battery is greater than 80%, the maximum allowed charge and discharge rate is 1C, and when the SOH value of the battery is less than 70%, the charge and discharge rate does not exceed 0.5C. Otherwise, the charge and discharge rate is set between 0.5C-1C.

[0041] Step SA3.3: Obtain the minimum total electricity cost. That is, according to the time period-electricity price mapping table established in step SA3.3, obtain the electricity price of each time period within 24 hours and the power purchased by the power grid, build an integer linear programming model, and determine the minimum total electricity cost of 24 hours through the constructed integer linear programming model. The details are as follows: Step SA3.3.1: Set constraints. That is, according to the battery SOC value and the charge and discharge power of the energy storage system obtained in step SA3.2, set corresponding constraints, specifically: , in: is the total power consumed by the building in time t, is the power obtained from the grid during time t, is the charging and discharging power of the energy storage system within time t, is the battery charge state at time t+1, is the time interval, is the rated capacity of the energy storage system, is the minimum state of charge of the battery, is the maximum state of charge of the battery, is the maximum charging and discharging power of the energy storage system, is the charging and discharging state of the energy storage system within time t.

[0042] Step SA3.3.2: Construct an integer linear programming model. That is, construct an integer linear programming model based on the time-of-use electricity price, load forecast and SOC value. At the same time, combine the constructed integer linear programming model with the constraints set in step SA3.3.1 to obtain the corresponding electricity cost, which is: , in: For the minimum electricity bill, is the power obtained from the grid during time t, is the electricity price at time t, For the time period.

[0043] In this embodiment, the decision module determines the corresponding COP value according to the load rate, temperature difference and personnel density obtained by the perception module, and obtains the control instructions of each device according to the determined COP value. The details are as follows: Step SB1: Get the COP value. That is, through the constructed energy efficiency prediction model, the load rate, temperature difference and personnel density obtained by the perception module are used as input, and the corresponding energy efficiency ratio prediction value COP is obtained as output. Specifically: , in: is the mean square error, is the number of data points, is the actual energy efficiency ratio of the i-th sample, is the predicted energy efficiency ratio of the i-th sample, is the index variable of the sample.

[0044] During the specific implementation, the load rate was 60%, the temperature difference was -10℃, and the personnel density was 0.5 people / m 2 , the corresponding predicted energy efficiency ratio is 4.2.

[0045] Step SB2: Determine the control command. That is, establish the objective function through the rated capacity, maximum charge and discharge current and initial SOC value, real-time electricity price and predicted energy efficiency ratio of the energy storage system, specifically: , in: is the weight coefficient of electricity cost, is the weight coefficient for energy efficiency optimization, is the battery life weight coefficient, For the minimum electricity bill, To predict the energy efficiency ratio, is the depth of discharge.

[0046] Furthermore, by combining the established objective function with the constraint conditions, the corresponding charge and discharge power, start and stop instructions, and adjustment instructions can be obtained. Specifically, according to the acquired charge and discharge power, the energy storage device is discharged when the electricity price is peak and charged when the electricity price is valley. At the same time, the charge and discharge state of the energy storage device is determined according to the SOC value of the energy storage device.

[0047] Furthermore, the obtained predicted energy efficiency ratio is compared with the upper and lower limits of the preset predicted energy efficiency ratio. When the obtained predicted energy efficiency ratio is not less than the upper limit of the preset predicted energy efficiency ratio, the currently running equipment can be operated at full power. When the obtained predicted energy efficiency ratio is less than the lower limit of the preset predicted energy efficiency ratio, the currently running equipment stops running. Otherwise, the currently running equipment can maintain the current power and continue to run.

[0048] Furthermore, the speed of the water pump is determined according to the target head of the water pump and the speed formula, that is, the adjustment instruction of the water pump is determined according to the speed of the water pump. The speed formula is specifically: , in: is the speed of the water pump, is the characteristic parameter of the water pump, is the target head of the pump.

[0049] In this embodiment, the restriction formula of the restriction condition is specifically: , in: To predict the energy efficiency ratio, is the battery charging status, is the charging and discharging power of the energy storage system within time t, is the maximum charge and discharge current.

[0050] In the specific implementation process, the rated capacity of the energy storage system is 500kWh, the maximum charge and discharge current is 250A, that is, the maximum charge and discharge power is 200kW, and the battery charge state is 60%. Further, the electricity price data is the electricity price-time data table in Table 1, and the load data is the load-energy efficiency ratio-time data table in Table 2, which is as follows: Table 1: Electricity price-time data table Time period Electricity price / yuan / kWh 00:00-06:00 0.3 06:00-18:00 0.5 18:00-24:00 1.2 Table 2: Load-Energy Efficiency Ratio-Time Data Table Time / h Load / kW Predicted Energy Efficiency Ratio 13:00 600 4.5 14:00 620 4.2 Specifically, the control instruction data obtained through the objective function is shown in Table 3 below: Table 3: Control data table Time / h Get power / kW Charging and discharging power / kW Charge and discharge status 13:00 400 200 1 14:00 420 200 1 00:00-06:00 0 -150 0 Specifically, at 13:00 and 14:00, the energy storage system discharges 200kW, and the SOC value of the energy storage system drops from 60% to 20%, and when the SOC value of the energy storage system drops to 20%, the energy storage coefficient prohibits continued discharge and switches to charging or idle. Further, from 00:00 to 06:00, the energy storage system charges -150k, and the SOC value of the energy storage system rises from 20% to 80%. Further, at 13:00, the predicted energy efficiency ratio is 4.5, which is greater than the upper limit of the preset predicted energy efficiency ratio (4.0), that is, the compressor operates normally.

[0051] In this embodiment, the execution module performs adaptive control on the air conditioner and the water pump according to the control instructions obtained by the decision module, and performs collaborative management on the energy storage device and the battery. The details are as follows: Step SC1: Adaptive control. That is, according to the control instructions determined in step SB2, the air conditioner and the water pump are adaptively controlled, as follows: Step SC1.1: compressor control. That is, according to the obtained indoor and outdoor temperature difference and personnel density, the corresponding compressor frequency is obtained, and the compressor frequency is adjusted in real time through the quantum adaptive PID controller. In this embodiment, the compressor frequency acquisition formula is specifically: , in: is the adjusted compressor frequency, is the compressor frequency before adjustment, , , are the parameters of the PID controller, is the integral of the error accumulated over time, is the rate of change of error over time, is the difference between the measured temperature and the actual temperature.

[0052] In the specific implementation process, when the temperature difference is 2℃ and the population density is 0.8 people / m 2 When the air conditioner compressor frequency is adjusted from 50Hz to 55Hz, the temperature difference converges to ±0.5℃ within 5 seconds.

[0053] Step SC1.2: water pump speed adjustment: that is, according to the water pump speed obtained in step SB2, the real-time running speed of the water pump is adjusted so that the pressure fluctuation does not exceed 5%.

[0054] Step SC2: Coordinated management of energy storage. That is, collaborative management of energy storage equipment and batteries is performed based on the health status of the battery, the real-time power generation of the photovoltaic system, and the total power consumed by the equipment. The details are as follows: Step SC2.1: Execution of the charge and discharge strategy. That is, the charge and discharge state of the battery is determined according to the health state of the battery, that is, the size of the SOH value. That is, when the obtained SOH value is not less than the upper limit threshold of the preset SOH value (i.e. 80%), the battery is discharged. When the obtained SOH value is not greater than the lower limit of the preset SOH value, the battery is charged. Otherwise, the battery maintains the current state for operation.

[0055] It is worth noting that during the discharge process of the energy storage device, it can adjust the discharge current in real time according to the corresponding maximum discharge current, specifically: , in: For the The discharge current at the moment, is the maximum discharge current, is the time after discharge starts, is the time constant, is the base of natural logarithms.

[0056] Step SC2.2: Multi-energy synergy. That is, the energy storage system is charged according to the real-time power generation of the photovoltaic system and the total power consumed by the equipment. Specifically, when the real-time power generation of the photovoltaic system is greater than the total power consumed by the equipment, the energy storage system is charged, and the charging power of the energy storage system is specifically: , in: is the charging power of the energy storage system, is the maximum discharge current, is the total power consumed by the building in time t, is the real-time power generation of the photovoltaic system, is the rated voltage of the battery pack.

[0057] During the specific implementation process, when the real-time power generation of the photovoltaic system is 300kW and the total power consumed by the equipment is 200kW, the charging power of the energy storage system is -100kW.

[0058] Furthermore, the energy storage system discharges according to the real-time electricity price of the power grid. That is, when the real-time electricity price is at the peak price, the energy storage system discharges, and the discharge power of the energy storage system is specifically: , in: is the discharge power of the energy storage system, is the power obtained from the grid during time t, is the total power consumed by the building in time t, is the maximum discharge current, is the rated voltage of the battery pack.

[0059] refer to Figure 2 , Figure 2 is the COP value scatter plot, Figure 2 It can be seen that the scatter points of the predicted values ​​and the actual values ​​are densely distributed near the dotted line, that is, the model prediction results are almost consistent with the true values. At the same time, the prediction mean square error (MSE) of the random forest model on the training set is 0.0438, that is, the average deviation between the predicted value and the actual value is only about 0.21, and the error range is significantly smaller than the noise amplitude of the data itself.

[0060] refer to Figure 3 , Figure 3 The electricity fee comparison chart is Figure 3 It can be seen that: without the energy storage system, the building's full-day electricity bill is 1,023.6 yuan. Through the charging and discharging scheduling of the energy storage system, the total electricity bill is reduced to 782.3 yuan, saving 23.6%. At the same time, energy storage is charged during the low electricity price period (such as 0:00-4:00 electricity price ¥0.35 / kWh), and energy storage is used for power supply during peak hours (such as 17:00-18:00, electricity price ¥1.2 / kWh) to reduce the purchase of high-priced electricity. Furthermore, the optimized power grid power consumption (line chart) is significantly lower than the actual load (bar chart) during the peak electricity price period, so the energy storage system discharges during this period to replace the power grid.

[0061] refer to Figure 4 , Figure 4 is the battery discharge current curve, Figure 4 It can be seen that after the discharge current is controlled, the current quickly rises to the safety threshold (about 63.2A, that is, after 1 time constant) in the initial stage, and then slowly approaches the maximum current (100A), avoiding instantaneous large current shock. Furthermore, the discharge current increases smoothly from 0A to about 91.8A within 5 hours, without mutation or step throughout the process.

[0062] refer to Figure 5 , Figure 5 This is the adjustment comparison diagram of PID control compressor frequency. Figure 5 It can be seen that: starting from the initial temperature of 26.0℃, the PID controller lowers the temperature to the set value of 24.0℃ within 8 minutes and remains stable in the subsequent period. At the same time, after the temperature stabilizes, the maximum deviation between the actual temperature and the set temperature is only 0.2℃, which is significantly better than traditional switch control.

[0063] This embodiment also provides a method for controlling energy consumption of a construction project based on the Internet of Things. The method for controlling energy consumption of a construction project uses a system for controlling energy consumption of a construction project based on the Internet of Things described in the above embodiment.

[0064] Example 2

[0065] This embodiment provides an energy consumption control system for construction projects based on the Internet of Things. Its specific implementation method is the same as that of Example 1. The difference lies in that in the process of establishing the objective function, the corresponding weights are obtained. The present invention is illustrated below with reference to the specific implementation method of this embodiment.

[0066] In this embodiment, the weights of each weight in the objective function are specifically set. That is, through the Q-learning reinforcement learning algorithm, the weight coefficient of the electricity cost, the weight coefficient of the energy efficiency optimization, and the weight coefficient of the battery life are optimized to obtain their corresponding sizes, and the specific objective function is obtained according to the optimized sizes. The details are as follows: Step SB2.1: Set the action space. That is, each weight coefficient is increased or decreased by a preset step size (for example, ±0.1), and the corresponding action space is set, specifically: , in: is the weight coefficient of electricity cost, is the weight coefficient for energy efficiency optimization, is the battery life weight coefficient, For the action space.

[0067] Furthermore, the sum of the weight coefficient of electricity cost, the weight coefficient of energy efficiency optimization and the weight coefficient of battery life is 1. That is, after obtaining the magnitudes of two of the weight coefficients, the magnitude of the third weight coefficient can be directly obtained.

[0068] Step SB2.2: Calculate the reward. That is, according to the action space set in step SB2.1, establish the reward calculation formula, specifically: , in: For reward results, For the minimum electricity bill, To predict the energy efficiency ratio, is the discharge depth, is the weight coefficient of electricity cost, is the weight coefficient for energy efficiency optimization, is the battery life weight coefficient.

[0069] Step SB2.3: Set the state code. That is, according to the real-time electricity price, predicted energy efficiency ratio and current SOC value, normalize them and form a state vector, specifically: , in: is the state vector, For real-time electricity prices, To predict the energy efficiency ratio, The battery charging status.

[0070] Step SB2.4: Update the Q table. That is, according to the action space set in step SB2.1, the reward result obtained in step SB2.2, and the state vector formed in step SB2.3, build the Q table, obtain the Q value, and update the Q value. The specific update formula is: , in: For the state vector Take action The Q value, is the state vector, is the action space, is the discount factor, is the learning rate, For reward results, For the state vector Take action The Q value, is the next state vector, The next action space.

[0071] In other words, by obtaining the action space corresponding to the maximum Q value, the size of each optimized weight coefficient can be determined.

[0072] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.

Claims

1. A building engineering energy consumption control system based on the Internet of Things, characterized in that: Included are: The perception module determines the equipment operating parameters, environmental parameters and energy storage data through sensors and OPC-UA protocol; The decision module obtains the COP value according to the equipment operation parameters, environmental parameters and energy storage data, and obtains the control instruction according to the COP value, including: SB1: Obtain COP value: Take the load rate, temperature difference and occupant density as the input of the constructed energy efficiency prediction model, and output the energy efficiency ratio prediction value, specifically: ， in: is the mean square error, is the number of data points, is the actual energy efficiency ratio of the i-th sample, is the predicted energy efficiency ratio of the i-th sample, is the index variable of the sample; SB2: Determine the control instruction: establish the objective function through the real-time electricity price and the predicted value of the predicted energy efficiency ratio, obtain the minimum electricity fee, the predicted energy efficiency ratio and the discharge depth, and compare the predicted energy efficiency ratio with the upper limit and lower limit of the preset predicted energy efficiency ratio. When the predicted energy efficiency ratio is not less than the upper limit of the preset predicted energy efficiency ratio, the running equipment runs at full power. When the predicted energy efficiency ratio is less than the lower limit of the preset predicted energy efficiency ratio, the running equipment stops running. Otherwise, the running equipment maintains the current power operation. The execution module performs adaptive control on the air conditioner and the water pump and coordinates the management of the energy storage device and the battery according to the control instructions.

2. According to the Internet of Things-based building energy consumption control system of claim 1, it is characterized in that: Determine equipment operating parameters, environmental parameters and energy storage data, including: SA1: Operation parameter collection: Through sensors, the operation parameters of the compressor and the operation parameters at the inlet and outlet flanges of the water pump are obtained, and the energy efficiency ratio of the compressor and the nonlinear equation of the water pump are obtained, specifically: ， in: is the energy efficiency ratio of the refrigeration equipment, is the amount of heat removed from the room by the cooling equipment per unit time. It is the actual power consumed by the refrigeration equipment during operation. is the input power of the pump, is the linear coefficient related to the mechanical efficiency of the pump, is the head of the pump, is the flow rate of the pump, is a nonlinear system related to hydraulic loss; SA2: Environmental parameter perception: Through millimeter wave radar, infrared imager and temperature and humidity gradient sensor, the movement direction of human body, thermal radiation distribution and indoor and outdoor temperature are obtained, and the density of people in the area is obtained. Specifically: ， in: is the number of people per unit area, is the number of people detected, is the plane area of ​​the monitored area; SA3: Synchronization of power grid and energy storage data: Obtain real-time electricity prices through the OPC-UA protocol, and determine the electricity cost of energy-consuming equipment and the energy consumption cost of the battery based on the real-time electricity price.

3. The construction engineering energy consumption control system based on the Internet of Things according to claim 2 is characterized in that: Determine the electricity cost of energy-consuming equipment and the energy cost of batteries, including: SA3.1: Obtain real-time electricity prices: Connect to the power grid dispatching system through the OPC-UA protocol to obtain real-time electricity price data and build a time period-electricity price mapping table; SA3.2: Energy storage status monitoring: Obtain the SOC and SOH values ​​of the battery through the Coulomb integration method and internal resistance measurement method, specifically: ， in: is the battery charging status, is the remaining battery power, is the rated capacity of the battery, The health status of the battery. is the initial internal resistance of a new battery, is the actual internal resistance of the battery after aging; SA3.3: Obtain the minimum total electricity cost: According to the time period-electricity price mapping table, obtain the electricity price of each time period and the power purchased by the power grid, build an integer linear programming model, and determine the minimum total electricity cost.

4. The construction engineering energy consumption control system based on the Internet of Things according to claim 3 is characterized in that: Determine the minimum total electricity cost, including: SA3.3.1: Set constraints: According to the SOC value and SOH value of the battery and the charge and discharge power of the energy storage system, set constraints, specifically: ， in: is the total power consumed by the building in time t, is the power obtained from the grid during time t, is the charging and discharging power of the energy storage system within time t, is the battery charge state at time t+1, is the time interval, is the rated capacity of the energy storage system, is the minimum state of charge of the battery, is the maximum state of charge of the battery, is the maximum charging and discharging power of the energy storage system, is the charging and discharging state of the energy storage system within time t; SA3.3.2: Construct an integer linear programming model: Based on the constraints, construct an integer linear programming model to determine the electricity cost, specifically: ， in: For the minimum electricity bill, is the power obtained from the grid during time t, is the electricity price at time t, For the time period.

5. The construction engineering energy consumption control system based on the Internet of Things according to claim 1 is characterized in that: The objective function is established by using the real-time electricity price and the predicted energy efficiency ratio predicted value, which is specifically: ， in: is the weight coefficient of electricity cost, is the weight coefficient for energy efficiency optimization, is the battery life weight coefficient, For the minimum electricity bill, To predict the energy efficiency ratio, is the discharge depth; At the same time, the objective function is combined with the constraint condition to obtain the minimum electricity fee, predicted energy efficiency ratio and discharge depth. The constraint formula of the constraint condition is specifically as follows: ， in: To predict the energy efficiency ratio, is the battery charging status, is the charging and discharging power of the energy storage system within time t, is the maximum charge and discharge current.

6. The construction engineering energy consumption control system based on the Internet of Things according to claim 5 is characterized in that: The process of determining the weight coefficient includes: SB2.1: Setting the action space: Each weight coefficient is increased or decreased by a preset step size to set the action space, specifically: ， in: is the weight coefficient of electricity cost, is the weight coefficient for energy efficiency optimization, is the battery life weight coefficient, is the action space; SB2.2: Perform reward calculation: Obtain reward results based on the action space, specifically: ， in: For reward results, For the minimum electricity bill, To predict the energy efficiency ratio, is the discharge depth, is the weight coefficient of electricity cost, is the weight coefficient for energy efficiency optimization, is the battery life weight coefficient; SB2.3: Set state coding: Normalize the real-time electricity price, predicted energy efficiency ratio and SOC value to form a state vector, specifically: ， in: is the state vector, For real-time electricity prices, To predict the energy efficiency ratio, is the battery charge status; SB2.4: Update the Q table. According to the action space, reward result and state encoding, construct and update the Q table to obtain the maximum Q value. The weight coefficient corresponding to the maximum Q value is the final weight coefficient. The update formula of the Q table is specifically: ， in: For the state vector Take action The Q value, is the state vector, is the action space, is the discount factor, is the learning rate, For reward results, For the state vector Take action The Q value, is the next state vector, The next action space.

7. The construction engineering energy consumption control system based on the Internet of Things according to claim 1 is characterized in that: Adaptive control of air conditioners and water pumps, including: SC1.1: Compressor control: According to the indoor and outdoor temperature difference and the density of people, the compressor frequency is obtained and adjusted, specifically: ， in: is the adjusted compressor frequency, is the compressor frequency before adjustment, , , are the parameters of the PID controller, is the integral of the error accumulated over time, is the rate of change of error over time, is the difference between the temperature and the actual temperature; SC1.2: Water pump speed adjustment: According to the speed of the water pump, adjust the real-time operating speed of the water pump.

8. The construction engineering energy consumption control system based on the Internet of Things according to claim 7 is characterized in that: Coordinated management of energy storage equipment and batteries, including: SC2.1: Execution of charging and discharging strategy: Determine the charging and discharging status of the energy storage device based on the health status of the energy storage device, specifically: When the SOH value is not less than the upper limit of the preset SOH value, the battery is discharged; when the SOH value is not greater than the lower limit of the preset SOH value, the battery is charged; otherwise, the battery maintains the current state of operation; The discharge current of the battery is specifically: ， in: For the The discharge current at the moment, is the maximum discharge current, is the time after discharge starts, is the time constant, is the base of natural logarithms; SC2.2: Multi-energy synergy: The energy storage system is charged according to the real-time power generation of the photovoltaic system and the total power consumed by the equipment. At the same time, the energy storage system is discharged according to the real-time electricity price of the power grid. Specifically: When the real-time power generation of the photovoltaic system is greater than the total power consumed by the equipment, the energy storage system is charged. The charging power of the energy storage system is specifically: ， in: is the charging power of the energy storage system, is the maximum discharge current, is the total power consumed by the building in time t, is the real-time power generation of the photovoltaic system, is the rated voltage of the battery pack; When the real-time electricity price is at the peak electricity price, the energy storage system discharges, and the discharge power of the energy storage system is specifically: ， in: is the discharge power of the energy storage system, is the power obtained from the grid during time t, is the total power consumed by the building in time t, is the maximum discharge current, is the rated voltage of the battery pack.

9. A method for controlling energy consumption of building projects based on the Internet of Things, characterized in that: An energy consumption control system for building projects based on the Internet of Things is used as described in any one of claims 1 to 8.

Images