Intelligent energy management system for light-storage integrated prefabricated external wall panel

Abstract

The invention discloses an intelligent energy management system of a photovoltaic-energy storage integrated prefabricated external wall panel. Efficient energy management is realized through a three-layer closed-loop architecture. A data acquisition layer acquires photovoltaic power Ppv, a battery SOC and a temperature Tbatt in real time; the central control layer constructs an energy matrix Ematrix based on an edge computing chip, and executes a three-level scheduling algorithm, and photovoltaic power supplies load preferentially, energy storage and charging are performed, and a surplus feed network is formed; and the communication layer interacts with a power grid through the LoRa module. The system integrates fuzzy PID (Proportion Integration Differentiation) control, LSTM (Long Short Term Memory) prediction, multi-mode dynamic switching (self-sufficiency / power grid assistance / peak shaving / emergency standby) and a safety protection mechanism (thermal runaway blocking and battery health management), and dynamic impedance matching and line loss compensation are combined, so that the energy utilization rate is improved, and the accident rate is reduced.

Description

Technical Field

[0001] This invention relates to the field of building photovoltaic (BPV) technology, specifically to a smart energy management method and hardware architecture for a photovoltaic-energy storage system integrated into a prefabricated exterior wall panel. Background Technology

[0002] Existing photovoltaic energy storage systems suffer from problems such as data silos, slow response, and single mode, resulting in low energy utilization and significant safety hazards. This invention addresses these shortcomings through a closed-loop control chain and multi-module collaboration. Summary of the Invention

[0003] In view of the technical defects and drawbacks existing in the prior art, embodiments of the present invention provide an intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage to overcome or at least partially solve the above problems. The specific solution is as follows:

[0004] An intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage includes the following three layers connected in sequence to form a closed-loop control logic:

[0005] Data acquisition layer: Real-time acquisition of photovoltaic power generation Ppv, battery state of charge SOC and battery temperature Tbatt to generate raw dataset;

[0006] Central control layer: Based on the original dataset, the energy matrix Ematrix=[Ppv,SOC,Tbatt] is dynamically constructed through the built-in edge computing chip, and the energy management algorithm is executed to dynamically adjust the power flow and charging / discharging strategy according to the algorithm results;

[0007] Communication layer: The processing data of the central control layer is transmitted to the building IoT platform via the LoRa module, and external power grid commands are received and fed back to the central control layer; wherein, the energy management algorithm implements a three-level scheduling mechanism that prioritizes photovoltaic power supply to indoor loads, followed by energy storage charging, and feeds surplus power into the power grid.

[0008] Furthermore, the edge computing chips in the central control layer collaboratively build a processing chain through the following hardware components:

[0009] ARM Cortex-M7 main control chip: receives raw data from the data acquisition layer and processes the energy matrix Ematrix, executing core decision-making logic;

[0010] FPGA coprocessor: Directly connected to the main control chip, it receives fuzzy PID algorithm tasks distributed by the chip and performs hardware-accelerated calculations;

[0011] FRAM storage unit: bidirectional connection between the main control chip and the FPGA coprocessor, real-time caching of historical energy matrix data, providing data support for the LSTM neural network prediction module;

[0012] The ATECC608A encryption chip is integrated into the communication layer interface and performs digital signature authentication on output scheduling commands. The components form a closed-loop processing chain via a high-speed bus:

[0013] Data input: The main control chip receives the raw data;

[0014] Algorithm acceleration: The main control chip distributes fuzzy calculation tasks to the FPGA coprocessor;

[0015] Data support: FRAM storage units cache intermediate results for use by the prediction module;

[0016] Secure output: The encrypted chip verifies the command and then sends it to the communication layer.

[0017] Furthermore, the energy management algorithm, based on the fuzzy PID charge-discharge control module, implements dynamic regulation in the following logical sequence:

[0018] Real-time acquisition of input variables:

[0019] Real-time acquisition of the deviation between the target value and the actual value of the battery state of charge ΔSOC = target SOC - current SOC, and simultaneous monitoring of the SOC change rate dSOC / dt and the battery temperature Tbatt;

[0020] Fuzzy rule-based decision making:

[0021] Based on a preset rule base, the input variables are mapped to the charging current adjustment coefficient Kadj, specifically including:

[0022] When ΔSOC > 20% and dSOC / dt < 0.1 and Tbatt < 45°C, set Kadj = 1.2;

[0023] When 10% < ΔSOC < 20% and Tbatt > 50°C, set Kadj = 0.7;

[0024] PID parameter self-tuning:

[0025] Based on the dynamic adjustment of the proportional-integral-derivative parameters using Kadj, the output charging current command value is:

[0026] Icharge = I_rated × Kadj;

[0027] Closed-loop control execution: Icharge controls the battery charging and discharging process, so that the actual SOC value dynamically approaches the target value.

[0028] Furthermore, the power flow direction decision-making achieves dynamic scheduling through the following judgment logic:

[0029] Level 1 Decision: When the indoor load demand exceeds 90% of the photovoltaic power generation capacity Ppv, execute the following:

[0030] Photovoltaic power is prioritized for direct supply to indoor loads;

[0031] Power supply gap capacity status assessment: If the battery state of charge (SOC) > 40%, start battery discharge to make up the gap; if the SOC ≤ 40%, switch to grid power to make up the gap.

[0032] Second-level judgment: When the photovoltaic power generation Ppv exceeds 120% of the load demand, execute:

[0033] Perform storage status judgment on surplus power: if SOC < 95%, use the surplus power for battery charging; otherwise, feed the surplus power into the grid.

[0034] Balanced mode: When the ratio of photovoltaic power generation to load demand is between 90% and 120%, the following applies:

[0035] Photovoltaic power is directly supplied to the load, while a battery floating compensation mechanism absorbs ±5% of instantaneous power fluctuations. During positive fluctuations, the battery absorbs excess power; during negative fluctuations, the battery releases compensation power.

[0036] Furthermore, the energy management system supports dynamic switching between multiple operating modes based on real-time status. The definitions and switching logic of each mode are as follows:

[0037] Self-sufficient mode: When the battery state of charge (SOC) > 60% and the photovoltaic power generation P pv When the power exceeds the real-time load power, it will automatically activate and execute the control action of directly supplying photovoltaic power to the load and storing the excess power in the battery module.

[0038] Grid-assisted mode: When SOC < 30% and P pv When the power is less than the real-time load power, it will automatically activate and execute the control action of supplying the load demand by the grid and using photovoltaic power to compensate for the charging of the battery in a trickle manner.

[0039] Peak shaving mode: Automatically activated when the external grid electricity price is at a preset peak period and SOC > 50%, executing control actions of battery module discharge and photovoltaic power generation to reduce the amount of electricity purchased from the grid;

[0040] Emergency standby mode: This mode is forcibly activated when a grid fault signal is detected, and it performs control actions to independently power the battery and disconnect non-critical loads; the switching of each mode follows the priority cascading principle.

[0041] First priority: The emergency standby mode unconditionally overrides other modes;

[0042] Second priority: When the peak shaving mode is activated, the grid assistance and self - sufficiency modes are paused;

[0043] Third priority: The self - sufficiency and grid assistance modes are mutually exclusive and switched, which is dynamically determined by the real - time ratio R = P pv / load power. When R>1, the self - sufficiency mode is activated; when R<1, the grid assistance mode is activated.

[0044] Furthermore, a safety protection mechanism is added to the central control layer, and the safety protection mechanism achieves dynamic coordination through the following progressive modules;

[0045] Thermal runaway protection module, which is used to continuously collect the battery temperature Tbatt through the built - in thermocouple of the battery module; when 55°C < Tbatt ≤ 60°C, the first - level protection of reducing the charging current by 50% is triggered; when Tbatt>60°C, the second - level protection is executed, immediately stopping charging and activating the fire - proof coating expansion mechanism; Battery health management module, which is used to collect the voltage increment ΔV and the corresponding charge increment ΔQ of the battery during the constant - current charging stage, calculate the aging characteristic coefficient k = ΔQ / ΔV, where k represents the change in the internal impedance of the battery. Based on the deviation between the aging characteristic coefficient k and the initial calibration value k0, the capacity attenuation rate η = |k0 - k| / k0×100% is calculated through the attenuation rate mapping function. When η>50%, a battery replacement warning is generated and the system is switched to the safe mode that only maintains basic power supply.

[0046] Furthermore, the LSTM neural network prediction module integrated in the edge computing chip, the LSTM neural network prediction module includes a data input layer, a prediction processing layer, and a pre - scheduling control layer, which is used to achieve energy pre - scheduling according to the following logic chain:

[0047] Data input layer: Based on the locally stored historical weather data set and the building electricity consumption habit model, a joint input feature vector Xinput = [Wweather, Bload] is generated, where Wweather is the locally stored historical weather data set, including irradiance, cloud cover, and temperature time - series data; Bload is the building electricity consumption habit model;

[0048] Bload={Pbase(t)∣t∈[0:00,24:00]};

[0049] ;

[0050] Among them, The moving average value calculated at time t is based on historical load data for N consecutive working days stored in the data acquisition layer. Let N be the load power value at time t on the i-th historical workday, and N be the number of consecutive historical workdays used in the modeling.

[0051] Prediction Processing Layer: The LSTM neural network performs spatiotemporal modeling on Xinput and outputs the predicted value of light intensity Gpred for the next 2 hours; the photovoltaic power generation potential Ppv-pred=ηpv×Apv×Gpred is calculated based on Gpred, where ηpv is the conversion efficiency and Apv is the photovoltaic area.

[0052] Pre-schedule control layer: Dynamically generates energy storage commands and executes mutual exclusion logic: When Gpred < actual power generation threshold, the battery discharges to SOC ≥ 70% to ensure power supply reliability during low-sunlight periods; when P... pv-pred > 1.5×Pbase(t), release energy storage capacity to SOC ≤ 80%, reserve space to receive surplus power.

[0053] Furthermore, the system also includes a dynamic impedance matching unit and a line loss compensation unit to minimize system losses based on the following synergistic mechanism:

[0054] Dynamic impedance matching unit: Real-time monitoring of the battery module's output current I out The switching frequency f of the DC / DC converter is dynamically adjusted according to the current value. sw Including: when I out When ≤20A, set f sw =100kHz to reduce switching losses; when I out When the current is >20A, the f-step increase is performed. sw Up to 500kHz to suppress conduction losses;

[0055] Line loss compensation unit: Obtains the preset value R of the conductor resistance of the precast wall panel. line Calculate the compensation voltage V comp =I out ×R line In the voltage sampling circuit, the compensation voltage V is superimposed in reverse. comp .

[0056] Furthermore, the energy management system also includes a grid coordination module for achieving grid coordination through a virtual power plant interaction mechanism. The grid coordination module includes:

[0057] Command receiving layer: Receives dispatch command sets D from the external power grid in real time via LoRa modules. cmd ={P cmd V cmd DRevent}, where P cmd For power regulation command, V cmd For voltage regulation command; D Revent This is a demand response event identifier;

[0058] Local decision-making level: Real-time available capacity C based on energy storage modules avail With photovoltaic power generation potential P pv-pred The adjustable capability P of the computing system adj =min(α·C avail ,P pv-pred +β·η dis ·SOC), where α is the power conversion coefficient, β is the discharge efficiency compensation factor, and η dis For battery discharge efficiency; when P cmd ≤P adj Dynamically adjust the charge / discharge plan response command in real time; when P cmd >P adj Time-generated power correction application R adj And upload it to the cloud;

[0059] Cloud coordination layer: Receives R data uploaded by the local decision-making layer. adj renegotiate the feasible power value P with the power grid feasible =γ·P adj γ∈[0.8,1] is the negotiation coefficient;

[0060] Update the instruction D cmd-update ={P feasible V cmd D Revent Feedback is then sent to the local decision-making level.

[0061] Furthermore, the data acquisition layer also includes: an indoor and outdoor temperature and humidity sensor for real-time acquisition of indoor temperature T. in Outdoor temperature T out And ambient relative humidity data; a dynamic acquisition trigger module, directly connected to the temperature and humidity sensor, automatically triggers high-speed acquisition mode when any of the following conditions are met:

[0062] Absolute value of indoor and outdoor temperature difference |T in- T out |>2°C;

[0063] Humidity change rate between adjacent sampling periods |ΔH / H prev |×100%>10%, where ΔH is the instantaneous change in relative humidity, H prev The humidity value for the previous period, ΔH = H current- H prev In high-speed acquisition mode:

[0064] The sensor sampling frequency has been increased to three times that of the conventional mode;

[0065] Real-time data is synchronously input into the energy matrix Ematrix of the central control layer for dynamic correction of photovoltaic power prediction and charging / discharging strategies.

[0066] The present invention has the following beneficial effects:

[0067] This invention forms a closed-loop control chain through a data acquisition layer (sensors collect photovoltaic power generation, SOC, and temperature in real time), a central control layer (dynamically constructing an energy matrix and executing a three-level scheduling algorithm), and a communication layer (LoRa transmission to the Internet of Things platform), solving the data silo problem in existing systems and realizing fully automated control from data acquisition to execution feedback. Attached Figure Description

[0068] Figure 1 This is a schematic diagram of the framework of an intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage, provided as an embodiment of the present invention. Detailed Implementation

[0069] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0070] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0071] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0072] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0073] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0074] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0075] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0076] To address at least one of the technical problems existing in the aforementioned related technologies, the present invention provides an intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage. Figure 1 This invention provides a schematic diagram of the structure of an intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage, comprising the following three layers connected in sequence to form a closed-loop control logic:

[0077] Data Acquisition Layer: Through the light intensity sensor, battery voltage / current sensor and battery temperature sensor integrated into the exterior wall panel, the photovoltaic power generation Ppv, battery state of charge SOC and battery temperature Tbatt are collected in real time, the raw dataset is generated and transmitted to the central control layer.

[0078] Central control layer: Based on the original dataset, the energy matrix Ematrix=[Ppv,SOC,Tbatt] is dynamically constructed through the built-in edge computing chip, and the energy management algorithm is executed to dynamically adjust the power flow and charging / discharging strategy according to the algorithm results;

[0079] Communication layer: The central control layer transmits processed data to the building IoT platform via the LoRa module, and receives external power grid commands and feeds them back to the central control layer.

[0080] The energy management algorithm implements a three-level scheduling mechanism that prioritizes photovoltaic power supply to indoor loads, followed by energy storage charging, and feeds surplus power into the power grid, thereby forming a closed-loop control chain of data acquisition, matrix construction, algorithm decision-making, instruction execution, and communication feedback.

[0081] This invention forms a closed-loop control chain through a data acquisition layer (sensors collect photovoltaic power generation, SOC, and temperature in real time), a central control layer (dynamically constructing an energy matrix and executing a three-level scheduling algorithm), and a communication layer (LoRa transmission to the Internet of Things platform), solving the data silo problem in existing systems and realizing fully automated control from data acquisition to execution feedback.

[0082] The three-tiered dispatch mechanism optimizes energy allocation: it prioritizes power supply to indoor loads, followed by energy storage and charging, and feeds surplus energy into the grid, significantly improving energy self-sufficiency and reducing grid dependence.

[0083] In some embodiments, the edge computing chips of the central control layer collaboratively build a processing chain through the following hardware components:

[0084] ARM Cortex-M7 main control chip (480MHz): Receives raw data from the data acquisition layer and processes the energy matrix Ematrix, executing core decision logic;

[0085] FPGA coprocessor: Directly connected to the main control chip, it receives fuzzy PID algorithm tasks distributed by the chip and performs hardware-accelerated calculations;

[0086] 4MB FRAM storage unit: bidirectional connection between the main control chip and the FPGA coprocessor, real-time caching of historical energy matrix data, providing data support for the LSTM neural network prediction module;

[0087] The ATECC608A encryption chip is integrated into the communication layer interface and performs digital signature authentication on output scheduling commands. The components form a closed-loop processing chain via a high-speed bus:

[0088] Data input: The main control chip receives the raw data;

[0089] Algorithm acceleration: The main control chip distributes fuzzy calculation tasks to the FPGA coprocessor;

[0090] Data support: FRAM storage units cache intermediate results for use by the prediction module;

[0091] Secure output: The encrypted chip verifies the command and then sends it to the communication layer.

[0092] In the above embodiments, the ARM Cortex-M7 main control chip (480MHz) processes the core logic to ensure real-time performance; the FPGA hardware accelerates fuzzy PID calculations, improving efficiency by more than 5 times compared to pure software calculations; the FRAM storage unit (4MB) caches historical data to support the LSTM prediction module; and the ATECC608A encryption chip ensures secure instruction transmission. A high-speed bus connects all components, enabling pipelined processing from "data input → algorithm acceleration → data support → secure output," with a system response latency of ≤10ms.

[0093] In some embodiments, the energy management algorithm implements dynamic regulation based on the fuzzy PID charge-discharge control module in the following logical sequence:

[0094] S301, Real-time acquisition of input variables:

[0095] Real-time acquisition of the deviation between the target value and the actual value of the battery state of charge ΔSOC = target SOC - current SOC, and simultaneous monitoring of the SOC change rate dSOC / dt and the battery temperature Tbatt;

[0096] S302, Fuzzy Rule-Based Decision Making:

[0097] Based on a preset rule base, the input variables are mapped to the charging current adjustment coefficient Kadj, specifically including:

[0098] When ΔSOC > 20% and dSOC / dt < 0.1 and Tbatt < 45°C, set Kadj = 1.2;

[0099] When 10% < ΔSOC < 20% and Tbatt > 50°C, set Kadj = 0.7;

[0100] S303, PID parameter self-tuning:

[0101] Based on the dynamic adjustment of the proportional-integral-derivative parameters using Kadj, the output charging current command value is:

[0102] Icharge = I_rated × Kadj;

[0103] S304, Closed-loop control execution:

[0104] By controlling the battery charging and discharging process with Icharge, the actual SOC value can be dynamically brought closer to the target value.

[0105] Steps S301→S302→S303→S304 form a closed-loop logic chain from data acquisition to control execution, and the temperature variable T batt Simultaneously participate in rule-making and efficiency assurance.

[0106] In the above embodiments, multi-variable decision-making based on temperature (Tbatt), SOC deviation (ΔSOC), and SOC change rate (dSOC / dt) is combined to solve the defects of traditional PID parameter fixation; by dynamically adjusting the charging current (Icharge) through Kadj, overcharging / over-discharging is avoided (such as automatic derating charging at high temperatures), extending battery life and increasing charging and discharging efficiency.

[0107] In some embodiments, the power flow direction decision is dynamically scheduled through the following judgment logic, forming a closed-loop control chain:

[0108] Level 1 Decision (Load Demand-Driven Scenario): When the indoor load demand exceeds 90% of the photovoltaic power generation capacity (Ppv), execute:

[0109] Photovoltaic power is prioritized for direct supply to indoor loads;

[0110] Power supply gap capacity status assessment: If the battery state of charge (SOC) > 40%, start battery discharge to make up the gap; if the SOC ≤ 40%, switch to grid power to make up the gap.

[0111] Second-level judgment (PV-dominated scenario): When the PV power generation Ppv exceeds 120% of the load demand, execute:

[0112] Perform storage status judgment on surplus power: if SOC < 95%, use the surplus power for battery charging; otherwise, feed the surplus power into the grid.

[0113] Balanced mode: When the ratio of photovoltaic power generation to load demand is between 90% and 120%, the following applies:

[0114] Photovoltaic power is directly supplied to the load, while a battery floating compensation mechanism absorbs ±5% of instantaneous power fluctuations. During positive fluctuations (supply > demand), the battery absorbs excess energy; during negative fluctuations (demand > supply), the battery releases compensating energy. This judgment logic forms a closed-loop control chain: first-level judgment ensures power supply reliability → second-level judgment optimizes energy storage efficiency → balanced mode maintains system stability.

[0115] In the above embodiments, in scenarios where load demand dominates, photovoltaic power supply is prioritized, with any shortfall supplemented by batteries (SOC>40%) or the grid, ensuring power supply reliability (reducing the risk of power outages by 90%). In scenarios where photovoltaic power generation dominates, surplus energy is intelligently stored (SOC<95%) or fed into the grid to avoid energy waste. The balancing mode controls battery fluctuations to compensate for ±5% power fluctuations, smoothing output volatility and improving system stability. Seamless switching between the three logic levels optimizes energy utilization and reduces the frequency of grid interactions.

[0116] In some embodiments, the energy management system supports dynamic switching between multiple operating modes based on real-time status. The definitions of each mode and the switching logic are as follows:

[0117] Self-sufficient mode: When the battery state of charge (SOC) > 60% and the photovoltaic power generation P pv When the power exceeds the real-time load power, it will automatically activate and execute the control action of directly supplying photovoltaic power to the load and storing the excess power in the battery module.

[0118] Grid-assisted mode: When SOC < 30% and P pv When the power is less than the real-time load power, it will automatically activate and execute the control action of supplying the load demand by the grid and using photovoltaic power to compensate for the charging of the battery in a trickle manner.

[0119] Peak shaving mode: Automatically activated when the external grid electricity price is at a preset peak period and SOC > 50%, executing control actions of battery module discharge and photovoltaic power generation to reduce the amount of electricity purchased from the grid;

[0120] Emergency Backup Mode: This mode is forcibly activated when a power grid fault signal is detected. It executes control actions to independently power the battery and disconnect non-critical loads to ensure the safety of the building's power supply. Switching between modes follows a priority cascading principle.

[0121] First priority: Emergency backup mode unconditionally overrides other modes;

[0122] Second priority: When peak shaving mode is activated, suspend grid auxiliary and self-sufficiency modes;

[0123] Third priority: Self-sufficiency and grid-assisted mode are mutually exclusive and switched by the real-time ratio R=P pv The load power is dynamically determined. When R>1, the self-sufficient mode is activated, and when R<1, the grid-assisted mode is activated.

[0124] In the above embodiments, the self-sufficient / grid-assisted mode is based on the photovoltaic / load power ratio (R=P). pv / P loadAutomatic switching to maximize the use of clean energy; Discharge during peak electricity prices in the peak shaving mode to reduce electricity costs; Seamlessly switch to battery power supply in the emergency backup mode during grid failures to ensure the safety of critical loads. Emergency mode > Peak shaving > Self-sufficiency / Grid assistance to avoid mode conflicts.

[0125] In some embodiments, a safety protection mechanism is added to the central control layer, and the safety protection mechanism realizes dynamic collaboration through the following progressive modules;

[0126] Thermal runaway protection module, used to continuously collect the battery temperature Tbatt through the built-in thermocouple of the battery module; When 55°C < Tbatt ≤ 60°C, trigger the first-level protection of reducing the charging current by 50%; When Tbatt > 60°C, perform the second-level protection, immediately stop charging and activate the fireproof coating expansion mechanism, and isolate oxygen through the characteristic that the volume expansion rate of the coating when heated is ≥ 300%; Battery health management module, used to collect the voltage increment ΔV and the corresponding charge increment ΔQ of the battery during the constant current charging stage, calculate the aging characteristic coefficient k = ΔQ / ΔV, k represents the change in the internal impedance of the battery, based on the deviation between the aging characteristic coefficient k (the detected value in the current cycle) and the initial calibration value k0 (the ΔQ / ΔV reference value (factory calibration) in the initial healthy state of the battery), calculate the capacity attenuation rate η = |k0 - k| / k0 × 100% through the attenuation rate mapping function. The larger the η value, the more serious the capacity attenuation. When η > 50%, generate a battery replacement warning and switch to the safe mode of only maintaining basic power supply;

[0127] Among them, the output of the thermal runaway protection module (such as the charging stop instruction) is used as the input of the battery health management module, and the two form a collaborative protection chain from temperature monitoring to life management through the edge computing chip.

[0128] In the above embodiments, the thermal runaway protection module responds in stages (55°C charging current reduction → 60°C charging stop + fireproof coating expansion), blocking the risk of heat spread; The battery health management module calculates the capacity attenuation rate η = |k0 - k| / k0 × 100% through the aging coefficient k, and early warns of battery failure (η > 50% triggers a replacement warning); Temperature monitoring → Life management closed-loop linkage to improve the system safety level.

[0129] In some embodiments, the LSTM neural network prediction module integrated in the edge computing chip, the LSTM neural network prediction module includes a data input layer, a prediction processing layer and a pre-scheduling control layer, and is used to realize energy pre-scheduling according to the following logic chain:

[0130] Data Input Layer: Based on the locally stored historical weather dataset and the building electricity consumption habit model, a joint input feature vector Xinput=[Wweather,Bload] is generated, where Wweather is the locally stored historical weather dataset, including irradiance, cloud cover and temperature time series data; Bload is the building electricity consumption habit model.

[0131] Bload={Pbase(t)∣t∈[0:00,24:00]};

[0132] ;

[0133] in, The moving average value calculated at time t is based on historical load data for N consecutive working days stored in the data acquisition layer. The load power value at time t on the i-th historical workday (from data stored in the data acquisition layer), and N is the number of consecutive historical workdays taken for modeling, with a value range of 7≤N≤30 (default N=14) to ensure baseline stability and timeliness;

[0134] Prediction Processing Layer: The LSTM neural network performs spatiotemporal modeling on Xinput and outputs the predicted value of light intensity Gpred for the next 2 hours; the photovoltaic power generation potential Ppv-pred=ηpv×Apv×Gpred is calculated based on Gpred, where ηpv is the conversion efficiency and Apv is the photovoltaic area.

[0135] Pre-dispatch control layer: Dynamically generates energy storage commands and executes mutual exclusion logic: When Gpred < actual power generation threshold (1 hour before work), the battery discharges to SOC ≥ 70% to ensure power supply reliability during low-sunlight periods; when P... pv-pred > 1.5×Pbase(t) (midday), release energy storage capacity to SOC ≤ 80%, reserve space to receive surplus power.

[0136] Based on historical data input → LSTM prediction → pre-schedule instructions → energy storage status adjustment → feedback to the central control layer, a closed-loop logic chain is formed.

[0137] In the above embodiments, historical weather data (Wweather) and building electricity consumption habit model (Bload) are input, and the photovoltaic power generation potential (P) for the next 2 hours is output. pv-pred ); dynamically adjust the SOC target according to Gpred (e.g., discharge to SOC≥70% before low light conditions) to optimize the energy storage state in advance and reduce real-time dispatch pressure; P base (t) Based on N-day moving average (7≤N≤30), a balance is struck between forecast stability and real-time performance.

[0138] In some embodiments, the system further includes a dynamic impedance matching unit and a line loss compensation unit to minimize system loss based on the following synergistic mechanism:

[0139] Dynamic impedance matching unit: Real-time monitoring of the battery module's output current I out The switching frequency f of the DC / DC converter is dynamically adjusted according to the current value. sw Including: when I out When ≤20A, set f sw =100kHz to reduce switching losses; when I out When the current is >20A, the f-step increase is performed. sw Up to 500kHz to suppress conduction losses;

[0140] Line loss compensation unit: Obtains the preset value R of the conductor resistance of the precast wall panel. line Calculate the compensation voltage V comp =I out ×R line In the voltage sampling circuit, the compensation voltage V is superimposed in reverse. comp .

[0141] The DC / DC converter and voltage sampling circuit are inherent components of the battery charging and discharging system. The dual-unit collaboration ensures that the overall system loss is ≤ 97% of the theoretical value. comp It can be fed back to the fuzzy PID control module for current regulation I. charge calculate.

[0142] In the above embodiments, based on the output current I out Step-wise adjustment of the DC / DC switching frequency (20A threshold) reduces switching / conduction losses; via V comp =I out ×R line With reverse compensation for voltage sampling error, the overall system loss is ≤97% of the theoretical value, which improves energy efficiency compared to traditional solutions.

[0143] In some embodiments, the energy management system further includes a grid coordination module for achieving grid coordination through a virtual power plant interaction mechanism, the grid coordination module comprising:

[0144] Command receiving layer: Receives dispatch command sets D from the external power grid in real time via LoRa modules. cmd ={P cmd V cmd D Revent}, where P cmd For power regulation command (kW), V cmd Voltage regulation command (V); D Revent This is a demand response event identifier;

[0145] Local decision-making level: Real-time available capacity C based on energy storage modules avail With photovoltaic power generation potential P pv-pred The adjustable capability P of the computing system adj =min(α·C avail ,P pv-pred +β·η dis ·SOC), where α is the power conversion coefficient, β is the discharge efficiency compensation factor, and η dis For battery discharge efficiency; when P cmd ≤P adj Dynamically adjust the charge / discharge plan response command in real time; when P cmd >P adj Time-generated power correction application R adj And upload it to the cloud;

[0146] Cloud coordination layer: Receives R data uploaded by the local decision-making layer. adj renegotiate the feasible power value P with the power grid feasible =γ·P adj γ∈[0.8,1] is the negotiation coefficient;

[0147] Update the instruction D cmd-update ={Pfeasible,Vcmd,DRevent} is fed back to the local decision-making level.

[0148] In the above embodiments, the local decision-making layer is based on P adj =min(α·C avail ,P pv-pred +β·η dis • SOC) computational adjustability enables precise response to grid commands; when P cmd >P adj Time to generate amendment request R adj After cloud-based negotiation, the feasibility value P was returned. feasible =γ·P adj γ∈[0.8,1], avoid overload risk, support grid demand response, and improve the flexibility of buildings as virtual power plant nodes.

[0149] In some embodiments, the data acquisition layer further includes: an indoor and outdoor temperature and humidity sensor for real-time acquisition of indoor temperature T. in Outdoor temperature T out And ambient relative humidity data; a dynamic acquisition trigger module, directly connected to the temperature and humidity sensor, automatically triggers high-speed acquisition mode when any of the following conditions are met:

[0150] Absolute value of indoor and outdoor temperature difference |T in- T out |>2°C;

[0151] Humidity change rate between adjacent sampling periods |ΔH / H prev |×100%>10%, where ΔH is the instantaneous change in relative humidity, H prev The humidity value for the previous period, ΔH = H current- H prev In high-speed acquisition mode:

[0152] The sensor sampling frequency has been increased to three times that of the conventional mode;

[0153] Real-time data is synchronously input into the energy matrix Ematrix of the central control layer for dynamic correction of photovoltaic power prediction and charging / discharging strategies.

[0154] In the above embodiments, a four-order logic chain of "environmental perception - dynamic triggering - data fusion - strategy correction" solves two major pain points in existing technologies: delayed response to environmental changes and isolated data-driven decision-making. This achieves: preventative control to reduce failure rates; environmental compensation strategies to reduce ineffective losses; and expanded input dimensions of the LSTM model to improve medium- and long-term scheduling accuracy. This enables the photovoltaic-energy storage system to adapt to complex building environments.

[0155] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0156] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0157] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0158] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0159] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0160] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0161] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0162] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0163] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0164] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

[0165] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage, characterized in that, The following three layers, connected in sequence, form a closed-loop control logic: Data acquisition layer: Real-time acquisition of photovoltaic power generation Ppv, battery state of charge SOC and battery temperature Tbatt to generate raw dataset; Central control layer: Based on the original dataset, the energy matrix Ematrix=[Ppv,SOC,Tbatt] is dynamically constructed through the built-in edge computing chip, and the energy management algorithm is executed to dynamically adjust the power flow and charging / discharging strategy according to the algorithm results; Communication layer: The processing data of the central control layer is transmitted to the building IoT platform via the LoRa module, and external power grid commands are received and fed back to the central control layer; wherein, the energy management algorithm implements a three-level scheduling mechanism that prioritizes photovoltaic power supply to indoor loads, followed by energy storage charging, and feeds surplus power into the power grid.

2. The intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage according to claim 1, characterized in that, The edge computing chips in the central control layer collaboratively build a processing chain through the following hardware components: ARM Cortex-M7 main control chip: receives raw data from the data acquisition layer and processes the energy matrix Ematrix, executing core decision-making logic; FPGA coprocessor: Directly connected to the main control chip, it receives fuzzy PID algorithm tasks distributed by the chip and performs hardware-accelerated calculations; FRAM storage unit: bidirectional connection between the main control chip and the FPGA coprocessor, real-time caching of historical energy matrix data, providing data support for the LSTM neural network prediction module; The ATECC608A encryption chip is integrated into the communication layer interface and performs digital signature authentication on output scheduling commands. The components form a closed-loop processing chain via a high-speed bus: Data input: The main control chip receives the raw data; Algorithm acceleration: The main control chip distributes fuzzy calculation tasks to the FPGA coprocessor; Data support: FRAM storage units cache intermediate results for use by the prediction module; Secure output: The encrypted chip verifies the command and then sends it to the communication layer.

3. The intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage according to claim 1, characterized in that, The energy management algorithm, based on the fuzzy PID charge-discharge control module, implements dynamic regulation in the following logical sequence: Real-time acquisition of input variables: Real-time acquisition of the deviation between the target value and the actual value of the battery state of charge ΔSOC = target SOC - current SOC, and simultaneous monitoring of the SOC change rate dSOC / dt and the battery temperature Tbatt; Fuzzy rule-based decision making: Based on a preset rule base, the input variables are mapped to the charging current adjustment coefficient Kadj, specifically including: When ΔSOC > 20% and dSOC / dt < 0.1 and Tbatt < 45°C, set Kadj = 1.2; When 10% < ΔSOC < 20% and Tbatt > 50°C, set Kadj = 0.7; PID parameter self-tuning: Based on the dynamic adjustment of the proportional-integral-derivative parameters using Kadj, the output charging current command value is: Icharge = I_rated × Kadj; Closed-loop control execution: Icharge controls the battery charging and discharging process, so that the actual SOC value dynamically approaches the target value.

4. The intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage according to claim 1, characterized in that, The power flow direction decision is implemented through the following judgment logic to achieve dynamic scheduling: Level 1 Decision: When the indoor load demand exceeds 90% of the photovoltaic power generation capacity Ppv, execute the following: Photovoltaic power is preferentially directly supplied to indoor loads; Judgment on the power supply gap capacity status: If the state of charge (SOC) of the battery > 40%, start the battery discharge to supplement the gap; if SOC ≤ 40%, switch to grid power to supplement the gap; Second-level judgment: When the photovoltaic power generation power Ppv exceeds 120% of the load demand power, execute: Judgment on the storage status of surplus power: If SOC < 95%, use the surplus power for battery charging, otherwise feed the surplus power into the grid; Balanced mode: When the ratio of photovoltaic power generation power to load demand power is between 90% and 120%, execute: Photovoltaic power is directly supplied to the load, and at the same time, the instantaneous power fluctuation of ±5% is absorbed through the battery floating compensation mechanism. Among them, the battery absorbs the excess power during the positive fluctuation; the battery releases the compensated power during the negative fluctuation.

5. The intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage according to claim 1, characterized in that, The energy management system supports dynamic switching of multiple working modes based on real-time status. The definitions and switching logics of each mode are as follows: Self-sufficient mode: When the battery state of charge (SOC) > 60% and the photovoltaic power generation P pv When the power exceeds the real-time load power, it will automatically activate and execute the control action of directly supplying photovoltaic power to the load and storing the excess power in the battery module. Grid-assisted mode: When SOC < 30% and P pv When the power is less than the real-time load power, it will automatically activate and execute the control action of supplying the load demand by the grid and using photovoltaic power to compensate for the charging of the battery in a trickle manner. Peak shaving and valley filling mode: Automatically activated when the external grid electricity price is in the preset peak period and SOC > 50%, execute the control action of combined power supply by battery module discharge and photovoltaic power generation, and reduce the grid power purchase; Emergency standby mode: Forcibly activated when the grid fault signal is detected, execute the control action of independent power supply by the battery and cut off the non-critical loads; The switching of each mode follows the priority cascade principle; First priority: The emergency standby mode unconditionally overrides other modes; Second priority: When the peak shaving and valley filling mode is activated, suspend the grid assistance and self-sufficient modes; Third priority: Self-sufficiency and grid-assisted mode are mutually exclusive and switched by the real-time ratio R=P pv The load power is dynamically determined. When R>1, the self-sufficient mode is activated, and when R<1, the grid-assisted mode is activated.

6. The intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage according to claim 1, characterized in that, The central control layer is additionally provided with a safety protection mechanism, and the safety protection mechanism realizes dynamic coordination through the following progressive modules; Thermal runaway protection module, used to continuously collect the battery temperature Tbatt through the built-in thermocouple of the battery module; when 55°C < Tbatt ≤ 60°C, trigger the first-level protection of reducing the charging current by 50%; when Tbatt > 60°C, execute the second-level protection, immediately stop charging and activate the fireproof coating expansion mechanism; Battery health management module, used to collect the voltage increment ΔV and the corresponding charge increment ΔQ of the battery during the constant current charging stage, calculate the aging characteristic coefficient k = ΔQ / ΔV, k characterizes the change of the internal impedance of the battery, and based on the deviation between the aging characteristic coefficient k and the initial calibration value k0, calculate the capacity attenuation rate η = |k0 - k| / k0 × 100% through the attenuation rate mapping function. When η > 50%, generate a battery replacement warning and switch to the safe mode of only maintaining basic power supply.

7. The intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage according to claim 1, characterized in that, The LSTM neural network prediction module integrated in the edge computing chip, the LSTM neural network prediction module includes a data input layer, a prediction processing layer and a pre-scheduling control layer, and is used to realize energy pre-scheduling according to the following logic chain: Data Input Layer: Based on the locally stored historical weather dataset and the building electricity consumption habit model, a joint input feature vector Xinput=[Wweather,Bload] is generated, where Wweather is the locally stored historical weather dataset, including irradiance, cloud cover and temperature time series data; Bload is the building electricity consumption habit model. Bload={Pbase(t)∣t∈[0:00,24:00]}; ； in, The moving average value is calculated at time t based on historical load data for N consecutive working days stored in the data acquisition layer. Let N be the load power value at time t on the i-th historical workday, and N be the number of consecutive historical workdays used in the modeling. Prediction Processing Layer: The LSTM neural network performs spatiotemporal modeling on Xinput and outputs the predicted value of light intensity Gpred for the next 2 hours; the photovoltaic power generation potential Ppv-pred=ηpv×Apv×Gpred is calculated based on Gpred, where ηpv is the conversion efficiency and Apv is the photovoltaic area. Pre-schedule control layer: Dynamically generates energy storage commands and executes mutual exclusion logic: When Gpred < actual power generation threshold, the battery discharges to SOC ≥ 70% to ensure power supply reliability during low-sunlight periods; when P... pv-pred > 1.5×Pbase(t), release energy storage capacity to SOC ≤ 80%, reserve space to receive surplus power.

8. The intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage according to claim 1, characterized in that, The system also includes a dynamic impedance matching unit and a line loss compensation unit, which are used to minimize system loss based on the following synergistic mechanism: Dynamic impedance matching unit: Real-time monitoring of the battery module's output current I out The switching frequency f of the DC / DC converter is dynamically adjusted according to the current value. sw Including: when I out When ≤20A, set f sw =100kHz to reduce switching losses; when I out When >20A, the f is increased in a stepwise manner. sw Up to 500kHz to suppress conduction losses; Line loss compensation unit: Obtains the preset value R of the conductor resistance of the precast wall panel. line Calculate the compensation voltage V comp =I out ×R line In the voltage sampling circuit, the compensation voltage V is superimposed in reverse. comp .

9. The intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage according to claim 1, characterized in that, The energy management system also includes a grid coordination module for achieving grid coordination through a virtual power plant interaction mechanism. The grid coordination module includes: Command receiving layer: Receives dispatch command sets D from the external power grid in real time via LoRa modules. cmd ={P cmd V cmd D Revent }, where P cmd For power regulation command, V cmd For voltage regulation command; D Revent This is a demand response event identifier; Local decision-making level: Real-time available capacity C based on energy storage modules avail With photovoltaic power generation potential P pv-pred The adjustable capability P of the computing system adj =min(α·C avail ,P pv-pred +β·η dis ·SOC), where α is the power conversion coefficient, β is the discharge efficiency compensation factor, and η dis For battery discharge efficiency; when P cmd ≤P adj Dynamically adjust the charge / discharge plan response command in real time; when P cmd >P adj Time-generated power correction application R adj And upload it to the cloud; Cloud coordination layer: Receives R data uploaded by the local decision-making layer. adj renegotiate the feasible power value P with the power grid feasible =γ·P adj γ∈[0.8,1] is the negotiation coefficient; Update the instruction D cmd-update ={P feasible V cmd D Revent Feedback is then sent to the local decision-making level.

10. The intelligent energy management system for prefabricated exterior wall panels integrating photovoltaic and energy storage according to claim 1, characterized in that, The data acquisition layer also includes: an indoor and outdoor temperature and humidity sensor for real-time acquisition of indoor temperature T. in Outdoor temperature T out And ambient relative humidity data; a dynamic acquisition trigger module, directly connected to the temperature and humidity sensor, automatically triggers high-speed acquisition mode when any of the following conditions are met: Absolute value of indoor and outdoor temperature difference |T in- T out |>2°C; Humidity change rate between adjacent sampling periods |ΔH / H prev |×100%>10%, where ΔH is the instantaneous change in relative humidity, H prev The humidity value for the previous period, ΔH = H current- H prev In high-speed acquisition mode: The sensor sampling frequency has been increased to three times that of the conventional mode; Real-time data is synchronously input into the energy matrix Ematrix of the central control layer for dynamic correction of photovoltaic power prediction and charging / discharging strategies.

Images