Building renewable energy regulation method integrating energy storage and electricity consumption prediction

Abstract

This invention relates to the field of building energy management and energy storage regulation technology, specifically to a building renewable energy regulation method that integrates energy storage and electricity consumption forecasting. By fusing power generation forecast data, electricity consumption forecast data, and real-time status data of the energy storage system, a net load power forecast curve for a future preset period is constructed. Combined with state of charge, health status, and temperature, the expected operating condition range of the energy storage system is dynamically determined. Furthermore, based on the core regulation objectives of the operating condition range, the expected charging and discharging behavior is simulated and derived, and compared with the safe charging and discharging boundaries to generate regulation conflict prediction results. On this basis, before the generation of energy storage charging and discharging commands, the charging and discharging power limits, the state of charge working window, and the cycle depth reference value are proactively adjusted. This allows for the active avoidance of potential operational conflicts while meeting current regulation objectives, thereby improving the stability, safety, and economy of system operation.

Description

Technical Field

[0001] This invention relates to the field of building energy management and energy storage regulation technology, and in particular to a building renewable energy regulation method that integrates energy storage and electricity consumption forecasting. Background Technology

[0002] With the widespread application of distributed renewable energy in the building sector, clean energy sources such as photovoltaic power generation are gradually becoming deeply integrated with building energy systems. The building energy structure is shifting from a single external energy supply to a collaborative operation mode of "renewable energy-energy storage-load". To alleviate the contradiction between the fluctuation of renewable energy output and building electricity demand, energy storage systems are widely deployed for peak shaving, valley filling, smoothing power fluctuations, and improving energy utilization efficiency. At the same time, building energy management systems are continuously introducing functions such as power generation forecasting, load forecasting, and condition monitoring, providing a data foundation for building-side energy regulation.

[0003] However, existing building energy storage control methods mostly focus on real-time power allocation based on the current state or simple predictions. They typically address temperature, state of charge, and power constraints by setting fixed thresholds or triggering limiting and protection mechanisms during operation, lacking a systematic analysis of future operational challenges. These methods struggle to identify potential conflicts between expected charging and discharging behavior and constraints such as health status and temperature before control commands are generated, easily leading to frequent protection triggers, passive power reduction, or accelerated health degradation during operation. Furthermore, existing technologies lack a unified coordination mechanism between economical control and power assurance, often making it difficult to dynamically adjust control parameters according to different operating scenarios, hindering the achievement of multi-objective, forward-looking, and comprehensive optimized control of energy storage systems. Summary of the Invention

[0004] This invention provides a building renewable energy regulation method that integrates energy storage and electricity consumption forecasting, which solves the problem in the prior art that it is difficult to comprehensively consider load forecasting, operating conditions and energy storage health constraints before the generation of energy storage charging and discharging commands, so as to achieve multi-objective coordinated regulation.

[0005] A building renewable energy regulation method integrating energy storage and electricity consumption forecasting includes the following steps: S1: Real-time acquisition of power generation forecast data of distributed renewable energy sources within the building, power consumption forecast data of the building as a whole and its individual loads, and real-time status data of the energy storage system, the real-time status data including state of charge, health status and temperature; fusion processing of the power generation forecast data and the power consumption forecast data to generate a net load power forecast curve for a future preset period. S2: Based on the net load power prediction curve and the real-time status data of the energy storage system, dynamically determine the expected operating range of the energy storage system within a future preset period. S3: For the aforementioned operating range, analyze the potential contradictions between the expected charging and discharging behavior of the energy storage system and the constraints implicit in its real-time status data when achieving the core control target of the range, and generate control contradiction prediction results; the constraints include safe charging and discharging boundaries based on health status and temperature. S4: Based on the predicted results of the regulation contradiction, before generating the energy storage charging and discharging command at the current moment, the control parameter set of the energy storage system is proactively adjusted; the control parameter set includes charging and discharging power limits, state of charge working window, and cycle depth reference value; the adjusted control parameter set will be used to generate the final energy storage charging and discharging command, so that the command meets the current regulation target while actively avoiding contradictions with the energy storage system's own state and long-term operation requirements.

[0006] Optionally, the operating range includes a high-efficiency lifespan priority range, an economy priority range, and a power guarantee priority range.

[0007] Optionally, S1 includes: S11: Through the data interface of the building energy management system, synchronously and in real time acquire power generation prediction data from the photovoltaic power generation prediction module, power consumption prediction data from the building load prediction module, and real-time status data of the energy storage system from the battery management system, wherein the real-time status data of the energy storage system includes at least the state of charge, health status, and temperature. S12: Perform time series alignment and data cleaning on the power generation prediction data and the power consumption prediction data, and unify the power generation prediction data and the power consumption prediction data into a future preset periodic sequence with the same time granularity and time label to form time-aligned power generation prediction data and time-aligned power consumption prediction data. S13: Perform time-by-time power value fusion calculation on the time-aligned power generation prediction data and the time-aligned power consumption prediction data, that is, subtract the power generation prediction data of the corresponding time tag from the power consumption prediction data of each time tag to generate the net load power prediction curve for the future preset period.

[0008] Optionally, the time series alignment and data cleaning process in S12 specifically includes: detecting missing or outlier values ​​in the power generation prediction data and the power consumption prediction data, filling in the missing values ​​using linear interpolation or forward filling, and smoothing outlier values ​​using sliding window filtering to ensure data continuity.

[0009] Optionally, S2 includes: S21: Based on the net load power prediction curve, extract the power fluctuation characteristics within the future preset period. The power fluctuation characteristics include at least the maximum power difference, the duration of exceeding the rated power of the energy storage system, and the rate of change of the net load curve. S22: The power fluctuation characteristic quantity is comprehensively evaluated with the real-time status data of the energy storage system, wherein the real-time status data includes at least the state of charge, health status and temperature. Logical operations are performed according to a preset multi-level judgment rule set to generate a preliminary judgment operating condition range. The preliminary judgment operating condition range is one of the following: high efficiency life priority range, economic priority range or power guarantee priority range. S23: Cross-validate the initially determined operating condition range with the historical operating condition range records of the same period and the current external electricity price signal. If the initially determined operating condition range deviates significantly from the historical records or is seriously inconsistent with the economic potential indicated by the external electricity price signal, then correct the initially determined operating condition range according to the verification rules, and finally determine the operating condition range in which the energy storage system is expected to operate in the future preset period.

[0010] Optionally, the preset multi-level judgment rule set in S22 is as follows: when the health status in the real-time status data is lower than a preset health threshold, or the temperature is higher than a preset temperature threshold, the initially determined operating condition interval is forcibly set as a high-efficiency lifespan priority interval; when both the health status and temperature are within the normal range and the maximum power difference in the power fluctuation characteristic quantity is lower than the energy storage system's regulation capacity, combined with the time-of-use electricity price data within a future preset period, if there is an electricity price difference higher than a preset threshold, the initially determined operating condition interval is determined as an economic priority interval; when the power fluctuation characteristic quantity indicates a power demand exceeding the rated power or duration of the energy storage system, the initially determined operating condition interval is determined as a power guarantee priority interval.

[0011] Optionally, S3 includes: S31: Based on the operating condition range, analyze and determine the core control target quantitative parameters corresponding to the operating condition range. If the operating condition range is a high-efficiency lifespan priority range, then its core control target quantitative parameters are temperature control target and health state decay rate limit target. If the operating condition range is an economic priority range, then its core control target quantitative parameters are electricity price arbitrage profit maximization target. If the operating condition range is a power guarantee priority range, then its core control target quantitative parameters are power gap filling success rate target and voltage support reliability target. S32: Based on the core control target quantification parameters and the real-time status data of the energy storage system, simulate and derive the expected charging and discharging behavior of the energy storage system to achieve the core control target quantification parameters. The expected charging and discharging behavior includes the planned charging and discharging power curve, the planned state of charge change trajectory, and the expected cycle depth. S33: Compare and analyze the expected charging and discharging behavior with the safe charging and discharging boundary dynamically calculated based on the health status and temperature in the real-time status data, identify the parts of the expected charging and discharging behavior that violate or approach the safe charging and discharging boundary, and summarize all the identified conflict points to generate the regulation contradiction prediction result.

[0012] Optionally, the step of parsing and determining the core control target quantification parameters corresponding to the operating condition interval specifically includes: when the operating condition interval is a high-efficiency lifespan priority interval, the temperature control target is set to limit the maximum operating temperature of the energy storage system to below the safety threshold calculated based on the current temperature and historical temperature rise rate in the real-time status data; the health status decay rate limit target is set to ensure that the single-cycle health status loss value calculated based on the current health status and expected cycle depth does not exceed the preset maximum allowable loss value; when the operating condition interval is an economic priority interval, the electricity price arbitrage profit maximization target is calculated through an optimization model, which uses the time-of-use electricity price prediction data within the future preset period and the planned charge and discharge power curve as input; when the operating condition interval is a power guarantee priority interval, the power gap filling success rate target is calculated based on the peak amplitude and duration of the peak exceeding the rated power of the energy storage in the net load power prediction curve.

[0013] Optionally, S4 includes: S41: Analyze the predicted results of the regulation contradictions, identify the specific contradiction types and quantify the degree of conflict contained therein, the specific contradiction types include at least temperature over-limit contradictions, health state loss acceleration contradictions, or power support power insufficient contradictions, and output the predicted results of the regulation contradictions after analysis, which include the contradiction types and degree of conflict. S42: Based on the predicted result of the control contradiction after analysis, map and select the corresponding targeted adjustment strategy in the preset parameter adjustment strategy library. The targeted adjustment strategy clearly specifies the modification operation of the control parameter set required to resolve the specific contradiction type. The control parameter set includes the charging and discharging power limit, the state of charge working window, and the cycle depth reference value. S43: Execute the targeted adjustment strategy to numerically adjust the charging and discharging power limits, state of charge working window and cycle depth reference value in the control parameter set, generate the adjusted control parameter set, and output the adjusted control parameter set to the energy storage charging and discharging command generation module for generating the final energy storage charging and discharging command.

[0014] Optionally, in S41, identifying specific contradiction types and quantifying the degree of conflict specifically involves: if the prediction result of the regulation contradiction indicates that the planned charge and discharge power curve will cause the energy storage system temperature to exceed the upper temperature limit in the safe charge and discharge boundary, then it is identified as a temperature over-limit contradiction, and its degree of conflict is the estimated over-temperature amplitude and duration; if it indicates that the expected cycle depth will accelerate the health state decay and exceed the health state decay rate limit target, then it is identified as a health state loss acceleration contradiction, and its degree of conflict is the estimated additional health state loss value; if it indicates that the planned state of charge change trajectory planned to meet the current core regulation target quantification parameters will result in insufficient state of charge available for power support in subsequent periods, then it is identified as a power support power shortage contradiction, and its degree of conflict is the product of the estimated power shortage and the power deficit.

[0015] The beneficial effects of this invention are: 1. This invention integrates power generation and consumption forecast data to construct a net load power forecast curve for a predetermined future period. By combining this with real-time status data such as the energy storage system's state of charge, health status, and temperature, it dynamically determines the future operating condition range. This allows the energy storage system's regulation to be based not only on the current state but also on a holistic understanding of future load changes and operational demands. Furthermore, by simulating and deriving expected charging and discharging behaviors and identifying potential conflicts with safe charging and discharging boundaries, it achieves early risk exposure and quantitative analysis. This enables proactive adjustment of the control parameter set before command generation, avoiding frequent triggering of protection mechanisms or passive limiting during operation, and improving the overall operational stability and continuity of building renewable energy systems under complex load conditions.

[0016] 2. This invention incorporates health status and temperature as core constraints into the regulation decision-making process. By limiting the rate of health status decay, establishing safe charge / discharge boundaries, and defining cycle depth constraints, it comprehensively assesses the expected charge / discharge behavior of the energy storage system. Furthermore, based on the predicted regulation contradictions, it makes targeted adjustments to the charge / discharge power limits, state-of-charge working window, and cycle depth reference value to address contradictions related to temperature exceeding limits, accelerated health status degradation, and insufficient power support. This ensures that the energy storage system operates within a parameter range more conducive to maintaining its lifespan while performing regulation tasks. This forward-looking parameter tuning mechanism, with health status as the core constraint, effectively reduces the cumulative damage to the battery caused by overcharging, over-discharging, and high-rate operation, delays health status decay, and improves the overall reliability of the energy storage system throughout its lifecycle.

[0017] 3. This invention, by introducing time-of-use electricity price signals and historical operating condition interval records, cross-validates and corrects the operating condition intervals. In the economic priority interval, it fully explores the electricity price arbitrage potential of the energy storage system; simultaneously, in the power guarantee priority interval, it ensures the energy storage system has the necessary power support capability by addressing the power gap in the net load power prediction curve. The adjustment of the control parameter set is not driven by a single objective, but rather by differentiated adjustments based on the specific type and degree of conflict, enabling the energy storage system to achieve a dynamic balance between economic benefits, power guarantee, and lifespan safety. Therefore, this invention can achieve synergistic optimization of economy, reliability, and safety in complex and ever-changing building energy consumption scenarios, significantly enhancing the comprehensive application value of building renewable energy control systems. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the method flow according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the S2 process in an embodiment of the present invention. Detailed Implementation

[0020] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should also be noted that, to make the embodiments more comprehensive, the following embodiments are the best and preferred embodiments, and those skilled in the art can use other alternative methods to implement some well-known technologies; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0021] It should be noted that the use of terms such as "an embodiment," "an embodiment," "an exemplary embodiment," and "some embodiments" in the specification indicates that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, when a specific feature, structure, or characteristic is described in connection with an embodiment, implementing such a feature, structure, or characteristic in conjunction with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the art.

[0022] Generally, terms can be understood at least partly from their use in context. For example, depending at least partly on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in a singular sense, or a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood not necessarily to convey an exclusive set of factors, but rather, alternatively, depending at least partly on the context, to allow for the presence of other factors that are not necessarily explicitly described.

[0023] like Figures 1-2 As shown, a building renewable energy regulation method integrating energy storage and electricity consumption forecasting includes the following steps: S1: Real-time acquisition of power generation forecast data from distributed renewable energy sources within the building, power consumption forecast data for the building as a whole and its individual loads, and real-time status data of the energy storage system. Real-time status data includes state of charge, health status, and temperature. The power generation forecast data and power consumption forecast data are then fused to generate a net load power forecast curve for a future preset period. The specific steps are as follows: S11: Through the data interface of the building energy management system, synchronously and in real-time acquire power generation prediction data from the photovoltaic power generation prediction module, power consumption prediction data from the building load prediction module, and real-time status data of the energy storage system from the battery management system. The real-time status data of the energy storage system includes at least the state of charge, health status, and temperature, specifically: 1. During the system startup phase, the building energy management system performs fixed configuration on the data interface. The configuration includes: the start time, end time, time granularity, time tag generation rules, and data acquisition trigger cycle for the future preset period. The building energy management system generates a data acquisition trigger signal based on the data acquisition trigger cycle. At the time each data acquisition trigger signal arrives, it sends a request message containing the time tag sequence of the current future preset period to the photovoltaic power generation prediction module, the building load prediction module, and the battery management system, respectively, so that the three types of data are acquired synchronously around the same future preset period.

[0024] 2. Upon receiving a request message, the photovoltaic power generation prediction module reads the future preset period time tag sequence carried in the request message. The photovoltaic power generation prediction module generates the power generation prediction value corresponding to each time tag in the order of the future preset period time tag sequence, forming a power generation prediction data sequence that corresponds one-to-one with the time tag sequence. The power generation prediction data sequence is encapsulated into a set of "time tag-power generation prediction value" data pairs using a unified structure, and the future preset period identifier and time granularity identifier of this request are written into the encapsulation. The photovoltaic power generation prediction module returns the encapsulated power generation prediction data through the data interface of the building energy management system, and the returned data covers all time tags of the future preset period.

[0025] 3. Upon receiving the request message, the building load forecasting module reads the future preset period time tag sequence carried in the request message. The module generates the power consumption forecast value for each corresponding time tag according to the order of the future preset period time tag sequence, and simultaneously generates the power consumption forecast value for the overall building load and the power consumption forecast value for each sub-load under each time tag. The module encapsulates the above power consumption forecast values ​​according to the structure of "time tag - overall building load power consumption forecast value - sub-load power consumption forecast value set", and writes the future preset period identifier and time granularity identifier of this request into the encapsulation. The module returns the encapsulated power consumption forecast data through the data interface of the building energy management system, and the returned data covers all time tags of the future preset period.

[0026] 4. The battery management system performs a real-time status data refresh calculation every time a data acquisition trigger signal arrives. The output of the refresh calculation is the state of charge, health status, and temperature, and these three are bound to the same data acquisition time stamp to form a real-time status data packet.

[0027] The process of obtaining the state of charge is as follows: the battery management system performs real-time state sampling of the energy storage system, calculates the current state of charge based on the sampling results according to the preset state of charge calculation process, and writes the state of charge into the real-time state data packet.

[0028] The process of obtaining the health status is as follows: the battery management system maintains a set of health status assessment parameters, updates the set of health status assessment parameters at the refresh calculation time to obtain the current health status, and writes the health status into the real-time status data packet.

[0029] The temperature acquisition process is as follows: the battery management system reads the temperature sampling value of the energy storage system and writes the temperature sampling value as the temperature into the real-time status data packet.

[0030] The battery management system transmits real-time status data packets back through the data interface of the building energy management system. After receiving the data packets, the building energy management system binds them with the power generation prediction data and power consumption prediction data into a data set for the same data acquisition transaction, thereby completing synchronous real-time acquisition.

[0031] S12: Perform time series alignment and data cleaning on the power generation forecast data and power consumption forecast data, unifying the power generation forecast data and power consumption forecast data into a future preset periodic series with the same time granularity and time label, forming time-aligned power generation forecast data and time-aligned power consumption forecast data, specifically: 1. The building energy management system reads the time granularity identifier and time tag sequence carried in the power generation forecast data and the power consumption forecast data. When the time granularity identifiers of the two are consistent, the building energy management system compares the time tag sequences of the two with the future preset period time tag sequence in the request message one by one to generate an alignment index table. The alignment index table records the location of each time tag in the two types of forecast data.

[0032] 2. The building energy management system traverses each time tag of the future preset period based on the alignment index table, and checks whether the power generation prediction value and power consumption prediction value under the time tag are missing. For missing values ​​in the middle of the sequence, linear interpolation is used to fill them in, and for missing values ​​in the continuous missing segment at the beginning of the sequence, forward filling is used to fill them in, so that the power generation prediction data and power consumption prediction data form a continuous sequence in the future preset period.

[0033] 3. The building energy management system performs outlier detection on the power generation forecast data and power consumption forecast data after missing value filling. The outlier detection calculates the local fluctuation amplitude within the window point by point using a sliding window traversal method, and marks the points that exceed the preset fluctuation limit as outliers. The points marked as outliers are smoothed and corrected using a sliding window filtering method, and the corrected values ​​are written back to the corresponding time tag position.

[0034] 4. The building energy management system compares the time-aligned power generation forecast data and time-aligned power consumption forecast data after the cleaning process with the historical statistical data at the corresponding time point to determine their reasonableness range. When the forecast value under any time tag exceeds the preset reasonable range threshold, the building energy management system first calls the forecast data output by the correction model to generate a replacement value and performs the replacement. When the forecast data output by the correction model is unavailable at that time tag, the building energy management system calls the historical data from the same period to generate a replacement value and performs the replacement. After the replacement is completed, the building energy management system outputs the final time-aligned power generation forecast data and time-aligned power consumption forecast data. The two types of data are completely consistent in terms of time tag, time granularity, and future preset period range.

[0035] S13: The time-aligned power generation forecast data and time-aligned power consumption forecast data are fused and calculated hourly. Specifically, the power generation forecast data for the corresponding time tag is subtracted from the power consumption forecast data for each time tag to generate the net load power forecast curve for the future preset period. 1. The building energy management system reads the time stamp sequence for future preset periods and processes them sequentially according to the time stamp sequence; at each time stamp... The time tag is then read from the time-aligned power consumption prediction data. The corresponding power consumption forecast value is obtained by reading the time tag from the time-aligned power generation forecast data. The corresponding predicted power generation value.

[0036] 2. The building energy management system, according to the time tag sequence of the future preset period, records each time tag... Perform a time-by-time power value fusion calculation sequentially; at each time tag The system then reads the corresponding time-aligned power consumption prediction data. Time-aligned power generation forecast data The calculation is performed according to the preset fusion calculation relationship to obtain the predicted net load power value under this time tag. The fusion calculation relationship satisfies: ; Building energy management system completes a single time tag After the calculation of the load factor, the net load power prediction value is obtained. Write the net load power prediction curve sequence and associate the net load power prediction value with the corresponding time tag. Establish the corresponding storage relationship; By repeating the above point-by-point calculation and writing process for all time tags within the future preset period, a complete net load power prediction curve is formed.

[0037] 3. Once all time tags within the future preset period have been calculated, the building energy management system will output the set of net load power prediction curves (t) arranged in the order of time tags as the net load power prediction curve. The net load power prediction curve maintains the same time granularity and time tag as the time tag sequence of the future preset period, and is used in subsequent steps to determine the expected operating range of the energy storage system within the future preset period.

[0038] S2: Based on the net load power prediction curve and the real-time status data of the energy storage system, dynamically determine the expected operating range of the energy storage system within a preset period in the future. The specific steps are as follows: S21: Based on the net load power prediction curve, extract its power fluctuation characteristics within a future preset period. These characteristics include at least the maximum power difference, the duration exceeding the rated power of the energy storage system, and the rate of change of the net load curve. Specifically: The building energy management system first reads the complete time series of the net load power prediction curve within a future preset period, and then iterates through and calculates the net load power prediction values ​​at each time point according to the time tag order. During the traversal, the system calculates the maximum and minimum power prediction values ​​of the net load power prediction curve by comparing the net load power prediction values ​​corresponding to all time tags within the future preset period, and uses the difference between the two as the maximum power difference. At the same time, the building energy management system compares the net load power prediction curve with the rated power parameters of the energy storage system on a time-by-time basis, identifies the time-stamped segments in which the net load power prediction value exceeds the rated power of the energy storage system, and accumulates the duration of continuous segments to obtain the duration of exceeding the rated power of the energy storage system. In addition, the building energy management system calculates the rate of change of the net load curve based on the difference and time interval between the predicted net load power values ​​under adjacent time tags, and forms a rate of change sequence within a preset future period; After completing the above calculations, the building energy management system further counts the number of times the net load power prediction curve crosses the zero power point in the future preset period, and calculates the power standard deviation based on the net load power prediction values ​​under all time tags. This forms a set of power fluctuation characteristics, including the maximum power difference, the duration of exceeding the rated power of the energy storage system, the rate of change of the net load curve, the number of times it crosses the zero power point, and the power standard deviation, which serve as inputs for subsequent comprehensive evaluation.

[0039] S22: A comprehensive evaluation is performed on the power fluctuation characteristics and the real-time status data of the energy storage system. The real-time status data includes at least the state of charge, health status, and temperature. Logical operations are performed based on a preset multi-level judgment rule set to generate a preliminary operating condition range. This preliminary operating condition range is one of three: a high-efficiency lifespan priority range, an economic priority range, or a power guarantee priority range. Specifically: After obtaining the set of power fluctuation characteristics, the building energy management system synchronously reads the real-time status data of the energy storage system corresponding to the current judgment time, and uses the state of charge, health status and temperature in the real-time status data as state constraint inputs. The system first performs a safety-priority judgment on health status and temperature. When the health status is lower than the preset health threshold or the temperature is higher than the preset temperature threshold, the building energy management system directly sets the initially determined operating condition range as the high-efficiency life priority range and ends the subsequent judgment process. Under the premise that the health status and temperature are within the normal range, the building energy management system compares the maximum power difference in the power fluctuation characteristic with the regulation capacity parameter of the energy storage system. When the maximum power difference is lower than the regulation capacity of the energy storage system, the system further introduces time-of-use electricity price data within the future preset period, analyzes the electricity price level of each time period, and calculates the electricity price difference within the future preset period. When the electricity price difference is higher than the preset threshold, the building energy management system determines the initially determined operating condition range as the economic priority range. When the power fluctuation characteristic indicates that there is a power demand exceeding the rated power of the energy storage system or the duration of exceeding the rated power of the energy storage system reaches the preset limit, the building energy management system will initially determine the operating condition range as the power guarantee priority range. Through the multi-level judgment rule set executed in priority order, the building energy management system outputs a uniquely determined preliminary judgment of the operating condition range.

[0040] S23: Cross-validate the initially determined operating condition range with historical records of operating condition ranges from the same period and the current external electricity price signal. If the initially determined operating condition range deviates significantly from historical records or is seriously inconsistent with the economic potential indicated by the external electricity price signal, then the initially determined operating condition range is corrected according to the verification rules. Finally, the expected operating condition range for the energy storage system in the future preset period is determined, specifically as follows: The building energy management system queries the historical database for operating condition interval records that match the above conditions based on the current seasonal information, date type information, and weather conditions, and counts the frequency of occurrence of various operating condition intervals in the corresponding time period in the historical records. The system performs a consistency analysis between the initially determined operating condition interval and the operating condition interval with the highest frequency in the historical operating condition interval records for the same period, and calculates the consistency probability between the initially determined operating condition interval and the historical high-frequency operating condition interval. At the same time, the building energy management system obtains time-of-use electricity price forecast data for the future preset period, and analyzes the potential benefits corresponding to the energy storage system entering the economic priority zone based on the time-of-use electricity price forecast data; When the consistency probability is lower than the preset probability threshold and the potential benefit is higher than the preset benefit threshold, the building energy management system will revise the initially determined operating condition range to the economic priority range. When the above conditions are not met simultaneously, the building energy management system maintains the initially determined operating range unchanged. After completing the consistency verification and economic verification, the building energy management system outputs the final determined operating condition range of the energy storage system within the future preset period, and uses it as the basis for determining the generation of the energy storage charging and discharging control parameter set in subsequent steps.

[0041] S3: For the operating range, analyze the potential contradictions between the expected charging and discharging behavior of the energy storage system and the constraints implicit in its real-time state data when achieving the core control target of the range, and generate control contradiction prediction results; the constraints include safe charging and discharging boundaries based on health status and temperature. The specific steps are as follows: S31: Based on the operating condition range, analyze and determine the core control target quantification parameters corresponding to that operating condition range. If the operating condition range is a high-efficiency lifespan priority range, then its core control target quantification parameters are temperature control target and health state decay rate limitation target. If the operating condition range is an economic priority range, then its core control target quantification parameters are electricity price arbitrage profit maximization target. If the operating condition range is a power guarantee priority range, then its core control target quantification parameters are power gap filling success rate target and voltage support reliability target. Specifically: After receiving the operating condition range, the building energy management system first calls the corresponding core control target quantification parameter parsing logic according to the type of operating condition range. When the operating range is the high-efficiency lifespan priority range, the system calculates the safety threshold corresponding to the temperature control target based on the current temperature and historical temperature rise rate in the real-time status data of the energy storage system. The safety threshold is determined by the following formula for calculating the safety threshold of the temperature control target: ; in, This indicates the maximum permissible safe operating temperature threshold corresponding to the temperature control target. This indicates the current temperature in the real-time status data. This represents the historical temperature rise rate calculated from historical temperature time series. This represents the time span from the current moment to the highest risk moment within a preset future period; At the same time, the building energy management system calculates the single-cycle health status loss value based on the current health status and the expected cycle depth, and compares the loss value with the preset maximum allowable loss value to determine the health status decay rate limit target. When the operating period is the economic priority period, the building energy management system constructs an electricity price arbitrage profit calculation model with the time-of-use electricity price forecast data and the planned charging and discharging power curve in the future preset period as input, and determines the profit maximization condition corresponding to the optimal result obtained by the model under the system constraint conditions as the electricity price arbitrage profit maximization target. When the operating range is a power guarantee priority range, the building energy management system calculates the power compensation demand that the energy storage system needs to bear based on the peak amplitude and duration of the peak exceeding the rated power of the energy storage system in the net load power prediction curve, and determines the power gap filling success rate target accordingly; at the same time, the system determines the voltage support reliability target based on the evaluation results of the support effect of power compensation behavior on voltage stability. Through the above analysis process, the building energy management system determines a set of quantifiable and calculable core control target parameters for the current operating condition range.

[0042] S32: Based on the core control target quantification parameters and the real-time status data of the energy storage system, the expected charging and discharging behavior of the energy storage system planned to achieve the core control target quantification parameters is simulated and derived. The expected charging and discharging behavior includes the planned charging and discharging power curve, the planned state of charge change trajectory, and the expected cycle depth, specifically: The building energy management system uses the core control target quantification parameters as the optimization target input, the real-time status data of the energy storage system as the initial state input, and the net load power prediction curve and the time-of-use electricity price prediction data within the future preset period as external inputs. It uses model predictive control algorithms to perform rolling optimization calculations on the operation of the energy storage system within the future preset period. The model predictive control algorithm solves for the optimal control sequence that satisfies the quantification parameters of the core regulation target in each rolling cycle, and obtains the planned charging and discharging power curve within the corresponding time range; After obtaining the planned charge and discharge power curves, the building energy management system derives the planned state of charge (SOC) change trajectory based on the energy balance relationship of the energy storage system. The derivation is achieved through the energy balance formula for the planned SOC change trajectory: ; in, Indicates time label The planned trajectory of the change in state of charge is as follows. This represents the initial value of the state of charge in the real-time state data. This indicates the available energy capacity of the energy storage system. This indicates the planned charge / discharge power curve over time. The value below, This indicates the start time label for a future preset period.

[0043] After obtaining the planned state of charge change trajectory, the building energy management system calculates the number of cycles and single discharge depth that the energy storage system will experience in the future preset period based on the planned charge and discharge power curve and the planned state of charge change trajectory, thereby determining the expected cycle depth. Thus, the building energy management system completes the simulation derivation of the expected charging and discharging behavior.

[0044] S33: Compare and analyze the expected charge / discharge behavior with the safe charge / discharge boundary dynamically calculated based on the health status and temperature in real-time state data, identify the parts of the expected charge / discharge behavior that violate or approach the safe charge / discharge boundary, and summarize all identified conflict points to generate a regulation conflict prediction result, specifically: The building energy management system dynamically calculates the corresponding safe charge and discharge boundary based on the health status and temperature in the real-time status data of the energy storage system, and represents the safe charge and discharge boundary as a three-dimensional boundary surface of power-temperature-health status. The system maps the planned charge / discharge power curve of the expected charge / discharge behavior to a three-dimensional boundary surface time by time, and judges each time tag by the following safe charge / discharge boundary crossing judgment formula: ; in, Indicates time label The amount exceeding the limit, This indicates the planned charge / discharge power curve at time stamps. The value below, This indicates the upper limit of the allowable power range given by the safe charge and discharge boundaries. This indicates the temperature under the corresponding time label. This indicates the health status under the corresponding time tag; when When the value is greater than zero, the building energy management system will mark the corresponding time tag as a power over-limit conflict point.

[0045] Meanwhile, the system compares the planned state of charge change trajectory with the optimal state of charge maintenance interval determined by the health state on a time-by-time basis to identify state of charge boundary conflict points, and compares the expected cycle depth with the maximum allowable cycle depth calculated based on the health state to identify cycle depth conflict points. The building energy management system will summarize the above-mentioned power outage conflict points, state of charge outage conflict points, and cycle depth conflict points to form a prediction result of regulation contradictions, and output the result to subsequent steps for proactive adjustment of the control parameter set of the energy storage system.

[0046] S4: Based on the predicted results of regulatory conflicts, before generating the energy storage charging and discharging command for the current moment, the control parameter set of the energy storage system is proactively adjusted. The control parameter set includes charging and discharging power limits, state of charge working window, and cycle depth reference value. The adjusted control parameter set will be used to generate the final energy storage charging and discharging command, so that the command meets the current regulatory objectives while actively avoiding conflicts with the energy storage system's own state and long-term operational needs. The specific steps are as follows: S41: Analyze the prediction results of the control contradictions, identify the specific contradiction types and quantify the degree of conflict. The specific contradiction types include at least temperature exceedance contradictions, accelerated health state loss contradictions, or insufficient power support capacity contradictions. Output the post-analysis prediction results of the control contradictions, including the contradiction type and degree of conflict, specifically: After receiving the prediction results of the control conflict, the building energy management system analyzes the conflict points one by one, and performs the conflict type identification and conflict degree quantification process based on the expected charging and discharging behavior and the triggered constraints corresponding to the conflict points. When the prediction results of the regulation conflict indicate that the planned charge and discharge power curve will cause the energy storage system temperature to exceed the upper limit of the safe charge and discharge boundary within a preset period in the future, the building energy management system identifies this type of conflict as a temperature overrun conflict. Based on the overheating amplitude and duration, the temperature overrun conflict is quantified, and its degree of conflict is calculated using the following formula: ; in, This indicates the degree of conflict corresponding to the temperature exceeding the limit. This indicates the maximum temperature exceedance within the safe charge / discharge boundary during the preset future charging / discharge cycle. This indicates the cumulative duration during which the temperature exceeds the upper temperature limit.

[0047] When the prediction results of the regulation conflict indicate that the expected cycle depth will cause the rate of health status decline to exceed the health status decline rate limit target, the building energy management system identifies this type of conflict as a health status loss acceleration conflict, and quantifies its conflict degree based on the difference between the expected health status loss value and the maximum allowable loss value. When the prediction results of the regulation conflict indicate that the planned state of charge change trajectory formed to achieve the quantitative parameters of the current core regulation target will lead to insufficient state of charge available for power support in the subsequent period, the building energy management system will identify this type of conflict as a power support power shortage conflict, and quantify its degree of conflict by calculating the product of the power shortage and the power deficit. After completing the above identification and quantification, the building energy management system generates a post-analysis control conflict prediction result containing specific conflict type identifiers and corresponding conflict degree values, and outputs it to subsequent steps.

[0048] S42: Based on the predicted results of the control contradictions after analysis, map and select the corresponding targeted adjustment strategy from the preset parameter adjustment strategy library. The targeted adjustment strategy clearly specifies the modification operations required to resolve the specific contradiction type of the control parameter set. The control parameter set includes the charging and discharging power limit, the state of charge working window, and the cycle depth reference value, specifically: The building energy management system pre-builds a parameter adjustment strategy library and establishes a strategy mapping table in the strategy library. The strategy mapping table uses the specific contradiction type and conflict degree as a joint input index and uniquely corresponds to a targeted adjustment strategy for each index. To generate the joint index, the building energy management system encodes the specific conflict types in the parsed control conflict prediction results and categorizes the conflict severity. The index is calculated using the following strategy mapping table index coding formula: ; in, This represents the input index of the policy mapping table. Type codes representing specific contradiction types, such as temperature out-of-bounds contradictions. The contradiction of accelerated deterioration of health status The contradiction between power support and insufficient power supply , This indicates the degree of conflict corresponding to a specific type of contradiction. The step size indicating the degree of conflict; Building Energy Management System Based on Input Index Locate and output the unique corresponding targeted adjustment strategy in the strategy mapping table; When the targeted adjustment strategy encounters a temperature-related conflict, the strategy explicitly stipulates that the charging and discharging power limits be lowered and the state-of-charge working window be expanded. When the targeted adjustment strategy addresses the contradiction of accelerated health state loss, the strategy explicitly stipulates that the cycle depth reference value should be increased and the overall state of charge working window should be shifted upward. When the targeted adjustment strategy encounters a contradiction between insufficient power support and the target power, the strategy explicitly stipulates that the lower limit of the state-of-charge working window be tightened and the current charging and discharging power limit be dynamically lowered.

[0049] S43: Execute a targeted adjustment strategy to numerically adjust the charging and discharging power limits, state-of-charge working window, and cycle depth reference value in the control parameter set, generate an adjusted control parameter set, and output the adjusted control parameter set to the energy storage charging and discharging command generation module for generating the final energy storage charging and discharging command to be executed. Specifically: After obtaining a targeted adjustment strategy, the building energy management system performs numerical adjustment operations on the control parameter set according to the predefined parameter modification rules in the strategy. When a targeted adjustment strategy requires a reduction in the charging and discharging power limits, the building energy management system calculates the adjusted charging and discharging power limits using the following formula for attenuation adjustment: ; in, This indicates the adjusted charge and discharge power limits. This indicates the originally set charging and discharging power limits. This represents the attenuation coefficient between zero and one. The specific value of the attenuation coefficient is determined by the degree of conflict through a predetermined functional relationship. When a targeted adjustment strategy requires adjustment of the state of charge working window, the building energy management system applies a numerical offset calculated based on the degree of conflict to the original upper and lower limit thresholds, thereby forming a new range of the state of charge working window. When a targeted adjustment strategy requires an adjustment to the cycle depth reference value, the building energy management system adds a numerical increment calculated based on the degree of conflict to the original set value, thereby forming the adjusted cycle depth reference value. After completing the above numerical adjustments, the building energy management system integrates the adjusted charging and discharging power limits, state of charge working window, and cycle depth reference value to form an adjusted control parameter set, and outputs the adjusted control parameter set to the energy storage charging and discharging command generation module to generate the final energy storage charging and discharging command to be executed.

[0050] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0051] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A building renewable energy regulation method integrating energy storage and electricity consumption forecasting, characterized in that, Includes the following steps: S1: Real-time acquisition of power generation forecast data of distributed renewable energy sources within the building, power consumption forecast data of the building as a whole and its individual loads, and real-time status data of the energy storage system, the real-time status data including state of charge, health status and temperature; fusion processing of the power generation forecast data and the power consumption forecast data to generate a net load power forecast curve for a future preset period. S2: Based on the net load power prediction curve and the real-time status data of the energy storage system, dynamically determine the expected operating range of the energy storage system within a future preset period. S3: For the aforementioned operating range, analyze the potential contradictions between the expected charging and discharging behavior of the energy storage system and the constraints implicit in its real-time status data when achieving the core control target of the range, and generate control contradiction prediction results; the constraints include safe charging and discharging boundaries based on health status and temperature. S4: Based on the predicted results of the regulation contradiction, before generating the energy storage charging and discharging command at the current moment, the control parameter set of the energy storage system is proactively adjusted; the control parameter set includes charging and discharging power limits, state of charge working window, and cycle depth reference value; the adjusted control parameter set will be used to generate the final energy storage charging and discharging command, so that the command meets the current regulation target while actively avoiding contradictions with the energy storage system's own state and long-term operation requirements.

2. The building renewable energy regulation method integrating energy storage and electricity consumption forecasting according to claim 1, characterized in that, The operating range includes a high-efficiency lifespan priority range, an economy priority range, and a power guarantee priority range.

3. The building renewable energy regulation method integrating energy storage and electricity consumption forecasting according to claim 1, characterized in that, S1 includes: S11: Through the data interface of the building energy management system, synchronously and in real time acquire power generation prediction data from the photovoltaic power generation prediction module, power consumption prediction data from the building load prediction module, and real-time status data of the energy storage system from the battery management system, wherein the real-time status data of the energy storage system includes at least the state of charge, health status, and temperature. S12: Perform time series alignment and data cleaning on the power generation prediction data and the power consumption prediction data, and unify the power generation prediction data and the power consumption prediction data into a future preset periodic sequence with the same time granularity and time label to form time-aligned power generation prediction data and time-aligned power consumption prediction data. S13: Perform time-by-time power value fusion calculation on the time-aligned power generation prediction data and the time-aligned power consumption prediction data, that is, subtract the power generation prediction data of the corresponding time tag from the power consumption prediction data of each time tag to generate the net load power prediction curve for the future preset period.

4. The building renewable energy regulation method integrating energy storage and electricity consumption forecasting according to claim 3, characterized in that, The time series alignment and data cleaning process in S12 specifically includes: detecting missing or outlier values ​​in the power generation prediction data and the power consumption prediction data, filling in the missing values ​​using linear interpolation or forward filling, and smoothing outlier values ​​using sliding window filtering to ensure data continuity.

5. A building renewable energy regulation method integrating energy storage and electricity consumption forecasting according to claim 3, characterized in that, S2 includes: S21: Based on the net load power prediction curve, extract the power fluctuation characteristics within the future preset period. The power fluctuation characteristics include at least the maximum power difference, the duration of exceeding the rated power of the energy storage system, and the rate of change of the net load curve. S22: The power fluctuation characteristic quantity is comprehensively evaluated with the real-time status data of the energy storage system, wherein the real-time status data includes at least the state of charge, health status and temperature. Logical operations are performed according to a preset multi-level judgment rule set to generate a preliminary judgment operating condition range. The preliminary judgment operating condition range is one of the following: high efficiency life priority range, economic priority range or power guarantee priority range. S23: Cross-validate the initially determined operating condition range with the historical operating condition range records of the same period and the current external electricity price signal. If the initially determined operating condition range deviates significantly from the historical records or is seriously inconsistent with the economic potential indicated by the external electricity price signal, then correct the initially determined operating condition range according to the verification rules, and finally determine the operating condition range in which the energy storage system is expected to operate in the future preset period.

6. A building renewable energy regulation method integrating energy storage and electricity consumption forecasting according to claim 5, characterized in that, The preset multi-level judgment rule set in S22 is as follows: when the health status in the real-time status data is lower than a preset health threshold, or the temperature is higher than a preset temperature threshold, the initially determined operating condition interval is forcibly set as a high-efficiency lifespan priority interval; when both the health status and temperature are within the normal range and the maximum power difference in the power fluctuation characteristic quantity is lower than the energy storage system's regulation capacity, combined with the time-of-use electricity price data within a future preset period, if there is an electricity price difference higher than a preset threshold, the initially determined operating condition interval is determined as an economic priority interval; when the power fluctuation characteristic quantity indicates a power demand exceeding the rated power or duration of the energy storage system, the initially determined operating condition interval is determined as a power guarantee priority interval.

7. A building renewable energy regulation method integrating energy storage and electricity consumption forecasting according to claim 5, characterized in that, S3 includes: S31: Based on the operating condition range, analyze and determine the core control target quantitative parameters corresponding to the operating condition range. If the operating condition range is a high-efficiency lifespan priority range, then its core control target quantitative parameters are temperature control target and health state decay rate limit target. If the operating condition range is an economic priority range, then its core control target quantitative parameters are electricity price arbitrage profit maximization target. If the operating condition range is a power guarantee priority range, then its core control target quantitative parameters are power gap filling success rate target and voltage support reliability target. S32: Based on the core control target quantification parameters and the real-time status data of the energy storage system, simulate and derive the expected charging and discharging behavior of the energy storage system to achieve the core control target quantification parameters. The expected charging and discharging behavior includes the planned charging and discharging power curve, the planned state of charge change trajectory, and the expected cycle depth. S33: Compare and analyze the expected charging and discharging behavior with the safe charging and discharging boundary dynamically calculated based on the health status and temperature in the real-time status data, identify the parts of the expected charging and discharging behavior that violate or approach the safe charging and discharging boundary, and summarize all the identified conflict points to generate the regulation contradiction prediction result.

8. A building renewable energy regulation method integrating energy storage and electricity consumption forecasting according to claim 7, characterized in that, The process of analyzing and determining the core control target quantification parameters corresponding to the operating condition interval is as follows: When the operating condition interval is a high-efficiency lifespan priority interval, the temperature control target is set to limit the maximum operating temperature of the energy storage system to below the safety threshold calculated based on the current temperature and historical temperature rise rate in the real-time status data; the health status decay rate limit target is set to ensure that the single-cycle health status loss value calculated based on the current health status and expected cycle depth does not exceed the preset maximum allowable loss value; when the operating condition interval is an economic priority interval, the electricity price arbitrage profit maximization target is calculated through an optimization model, which uses the time-of-use electricity price prediction data within the future preset period and the planned charge and discharge power curve as input; when the operating condition interval is a power guarantee priority interval, the power gap filling success rate target is calculated based on the peak amplitude and duration of the peak exceeding the rated power of the energy storage in the net load power prediction curve.

9. A building renewable energy regulation method integrating energy storage and electricity consumption forecasting according to claim 7, characterized in that, S4 includes: S41: Analyze the predicted results of the regulation contradictions, identify the specific contradiction types and quantify the degree of conflict contained therein, the specific contradiction types include at least temperature over-limit contradictions, health state loss acceleration contradictions, or power support power insufficient contradictions, and output the predicted results of the regulation contradictions after analysis, which include the contradiction types and degree of conflict. S42: Based on the predicted result of the control contradiction after analysis, map and select the corresponding targeted adjustment strategy in the preset parameter adjustment strategy library. The targeted adjustment strategy clearly specifies the modification operation of the control parameter set required to resolve the specific contradiction type. The control parameter set includes the charging and discharging power limit, the state of charge working window, and the cycle depth reference value. S43: Execute the targeted adjustment strategy to numerically adjust the charging and discharging power limits, state of charge working window and cycle depth reference value in the control parameter set, generate the adjusted control parameter set, and output the adjusted control parameter set to the energy storage charging and discharging command generation module for generating the final energy storage charging and discharging command.

10. A building renewable energy regulation method integrating energy storage and electricity consumption forecasting according to claim 9, characterized in that, In S41, identifying specific contradiction types and quantifying the degree of conflict specifically means: if the prediction result of the regulation contradiction indicates that the planned charge and discharge power curve will cause the temperature of the energy storage system to exceed the upper temperature limit in the safe charge and discharge boundary, then it is identified as a temperature over-limit contradiction, and its degree of conflict is the estimated over-temperature amplitude and duration. If it is indicated that the predicted cycle depth will accelerate the decline of health status and exceed the target limit of the decline rate of health status, it is identified as a contradiction in the acceleration of health status loss, and the degree of the contradiction is the estimated additional health status loss value. If the planned state of charge change trajectory, designed to meet the current core control target quantification parameters, will result in insufficient state of charge available for power support in subsequent periods, it is identified as a power support power shortage contradiction, the degree of which is the product of the estimated power shortage and the power deficit.

Images