Intelligent operation management system for geothermal energy and air energy in severe cold region

Abstract

The application discloses a kind of wisdom operation management systems of geothermal energy and air energy in severe cold area, and it is related to operation management technical field.The wisdom operation management system of geothermal energy and air energy in severe cold area, including load prediction module, peak demand identification module, air energy supplement module, dispatching scheme determination module and collaborative operation determination module, realize heat load accurate prediction by multidimensional data, peak demand is intelligently identified and air energy supplement proportion is reasonably determined, to generate low-consumption efficient energy dispatching scheme with geothermal priority principle, dynamically locate deviation source and adjust collaborative operation mode in combination with real-time feedback, finally realize the energy-saving, precision and stabilization of severe cold area heating operation, solve the problem that heat load is difficult to accurately predict in severe cold area heating, and energy scheduling lacks optimization.

Description

Technical Field

[0001] This invention relates to the field of operation management technology, specifically to a smart operation management system for geothermal and air energy in frigid regions. Background Technology

[0002] As a core unit for ensuring the stability and energy efficiency of heating in low-temperature environments, the intelligent operation and management system for geothermal and air energy in frigid regions directly determines user comfort, energy utilization efficiency, and equipment service life. However, existing solutions have the following shortcomings: First, the heat load prediction of existing systems mostly relies on preset physical models or historical data statistics, lacking precise perception and forward-looking correction of dynamic interference factors in frigid regions. This makes it difficult for subsequent energy dispatch instructions to match actual needs due to the lack of accurate data foundation.

[0003] Secondly, there is a strong coupling relationship between heat load demand and equipment operating conditions, while existing systems often regard load prediction and energy dispatch as two relatively independent links, lacking a deep integration of the dynamic relationship between the two.

[0004] Finally, in scheduling strategy optimization, existing methods are mostly single-objective oriented and lack the exploration and coordinated control of multi-variable coupling relationships, which may undermine the long-term stability of the system.

[0005] Therefore, there is an urgent need for an intelligent operation and management system that can accurately sense dynamic disturbances caused by severe cold, deeply integrate load prediction and equipment operating conditions, and achieve multi-objective collaborative optimization, in order to solve the above-mentioned technical bottlenecks and improve the accuracy, stability and comprehensive energy efficiency of geothermal and air energy synergistic heating in severe cold regions. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a smart operation and management system for geothermal and air energy in frigid regions, solving the problems of difficulty in accurately predicting heat load and lack of optimization in energy dispatching during heating in frigid regions.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solution: a smart operation and management system for geothermal energy and air energy in frigid regions, comprising: a load prediction module, used to obtain a sequence of predicted regional heat load values ​​based on outdoor meteorological data, building thermal parameters and user behavior records.

[0008] The peak demand identification module is used to determine the stability of the heat load based on the regional heat load forecast value sequence. If the stability is normal, a peak demand identification list is obtained based on the regional heat load forecast value sequence and the geothermal basic load threshold. If the stability is abnormal, an early warning is issued based on the set rules.

[0009] The air energy supplement module is used for determining an air energy supplement ratio on the basis of the peak demand identification list, combining the geothermal energy available capacity and the air energy efficiency curve.

[0010] The dispatching scheme determination module is used for simulating total energy consumption in a heating scene based on the air energy supplement ratio to obtain an energy dispatching scheme.

[0011] The cooperative operation determination module is used for judging whether there is a deviation after implementing the energy dispatching scheme in combination with real-time heating feedback data, determining a deviation source if there is a deviation, and determining a cooperative operation mode based on the deviation source.

[0012] Compared with the prior art, the present application has the following beneficial effects: the present application realizes accurate heat load prediction through multi-dimensional data, intelligently identifies peak demand and reasonably determines air energy supplement ratio, optimizes generation of a low-consumption and high-efficiency energy dispatching scheme in the principle of geothermal priority, dynamically locates a deviation source in combination with real-time feedback and adjusts a cooperative operation mode, finally realizes energy-saving, accurate and stable operation of heating in severe cold regions, and solves the problems of difficult accurate prediction of heat load and lack of optimization of energy dispatching in heating in severe cold regions. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 It is a module connection schematic diagram of the intelligent operation and management system of geothermal energy and air energy in severe cold regions.

[0014] Figure 2 It is a process flowchart of obtaining a peak demand identification list in the intelligent operation and management system of geothermal energy and air energy in severe cold regions.

[0015] Figure 3 It is a process flowchart of obtaining a non-zero air energy supplement ratio in the intelligent operation and management system of geothermal energy and air energy in severe cold regions. DETAILED DESCRIPTION

[0016] The present application will be described in detail below in combination with the drawings and embodiments. Figure 1 The embodiment of the present application provides a technical scheme: an intelligent operation and management system of geothermal energy and air energy in severe cold regions, comprising a load prediction module, a peak demand identification module, an air energy supplement module, a dispatching scheme determination module and a cooperative operation determination module, wherein the load prediction module is connected with the peak demand identification module, the peak demand identification module is connected with the air energy supplement module, the air energy supplement module is connected with the dispatching scheme determination module, and the dispatching scheme determination module and the cooperative operation determination module are connected.

[0017] The load prediction module is used for obtaining a regional heat load prediction value sequence based on outdoor meteorological data, building thermal parameters and user behavior records.

[0018] It should be noted that the regional heat load usually has time series characteristics, and is strongly affected by the nonlinearity of meteorology and user behavior. In order to accurately and effectively predict, a neural network model based on LSTM is used for prediction in the embodiment, and the specific process is as follows: first, collect outdoor meteorological data, building thermal parameters and user behavior records in the severe cold region, wherein the outdoor meteorological data includes but is not limited to hourly outdoor temperature, wind speed, sunshine duration; the building thermal parameters include but are not limited to building outer wall heat transfer coefficient, roof heat transfer coefficient, thermal inertia index; the user behavior records include but are not limited to daily heating period distribution, heating intensity at different times, heating difference between weekends and weekdays.

[0019] Considering that the heat load in the severe cold region is affected by many factors, but not all factors are the core driving force, if the full amount of data is directly used, not only the calculation complexity of subsequent model training will be increased, but also irrelevant noise data will be introduced to interfere with model learning, therefore, it is necessary to reduce the interference of redundant information on the model, and focus the model on the key indicators that truly affect the heat load.

[0020] The outdoor meteorological data, building thermal parameters and user behavior records are analyzed for correlation with the heat load, and the data with a correlation greater than a set correlation threshold is retained to obtain multi-dimensional correlation data, wherein the correlation analysis uses Pearson correlation coefficient to calculate the correlation of each specific indicator in the outdoor meteorological data, building thermal parameters and user behavior records with the heat load.

[0021] The multi-dimensional correlation data is cleaned and normalized to obtain standardized input data.

[0022] The standardized input data is input into the neural network model based on LSTM to obtain the regional heat load prediction value sequence, specifically: first, a neural network model based on LSTM is constructed, the number of neurons in the input layer is consistent with the number of indicators of the standardized input data; 1-2 layers of hidden layers are set, and the number of neurons in each layer is 64-128; the output layer is provided with 1 neuron, corresponding to the regional heat load prediction value of a single time.

[0023] Then, the model is trained, and the standardized input data and the actual heat load of the severe cold region in the same period in the past 3 years are selected as the training set, the Adam optimizer is used to minimize the mean square error (MSE) loss function, and the model loss value is stabilized at a low level through iterative training, such as MSE less than 5%.

[0024] Finally, the heat load is predicted, the standardized input data of the current period is imported into the trained LSTM model in chronological order, the model will output the regional heat load prediction value at each time, and the prediction values are arranged in chronological order to obtain the regional heat load prediction value sequence.

[0025] The peak demand identification module is configured to determine the stability of the heat load based on the sequence of regional heat load prediction values, and if the stability is normal, to obtain a peak demand identification list based on the sequence of regional heat load prediction values and a geothermal basic load threshold, and if the stability is abnormal, to perform early warning based on a set rule.

[0026] It should be noted that after obtaining the sequence of regional heat load prediction values, it needs to be tested to determine whether it is within the upper limit of the system output, so as to avoid subsequent energy scheduling errors and overloading of the heating system.

[0027] In one embodiment, the process of determining the stability of the heat load based on the sequence of regional heat load prediction values is to take the ratio of the mean value and the standard deviation of the sequence of regional heat load prediction values as the fluctuation coefficient, which provides an objective indicator of load fluctuation dimension for the stability.

[0028] Then, in combination with the hardware limit of the heating system in severe cold regions, the upper limit of the heat load output is preset, the ratio of the number of regional heat load prediction values that meet the condition of prediction value being less than the output upper limit to the total number of prediction values is calculated, which reflects the matching degree of the predicted load and the system hardware capability.

[0029] In one embodiment, the output upper limit is determined by the maximum heat power of the pipeline, the maximum output of the heat source equipment, and the maximum load of the terminal heat dissipation equipment, and the minimum value of the three is taken as the output upper limit, so as to ensure that the carrying capacity of any link of the system is not exceeded.

[0030] Considering that geothermal energy cannot meet the demand, the air energy is highly dependent on air energy to supplement the peak load in severe cold regions. If the air energy response is too slow, the load gap will occur at the peak time, but the air energy will not be supplemented in time, causing the room temperature to drop sharply. Therefore, the deviation rate between the response speed of air energy and the designed response speed can be calculated using the deviation rate calculation formula, and the response reliability of air energy is represented by the deviation rate. The timeliness of energy supplement is included in the stability evaluation to avoid the implicit risk of meeting the load but lagging in energy supplement, so that the stability judgment is more in line with the actual demand of air energy-dependent peak in severe cold regions.

[0031] Considering that the fluctuation coefficient and the deviation rate are negatively correlated with the stability, in order to avoid reverse interference during calculation, the fluctuation coefficient and the deviation rate need to be positively processed, and then the stability is obtained by weighted sum of the positively processed values and the ratio.

[0032] It should be noted that the judgment standard of whether the stability is normal is to determine whether the stability is greater than the set stability threshold. If it is greater, it is normal, otherwise it is abnormal.

[0033] On the premise that the heat load stability is determined to be normal, it is necessary to combine the upper limit of the stable output of the geothermal energy unit in the severe cold region to accurately identify the peak time when the geothermal energy cannot meet the heat load demand through each time, generate a peak demand identification list with clear time orientation, and provide direct positioning basis for energy supplement time to avoid blindly calculating air energy supplement for the whole period or missing the peak time of energy supplement, such as Figure 2 As shown in the figure, the process of obtaining the peak demand identification list based on the sequence of regional heat load prediction values and the geothermal basic load threshold is: comparing the regional heat load prediction values of multiple continuous time points with the preset geothermal basic load threshold at each time point.

[0034] It should be noted that the geothermal basic load threshold needs to be calibrated based on the rated output of the geothermal energy unit in the severe cold region, the minimum efficient output in long-term operation, and the historical same period geothermal load matching rate data, for example, the rated output of a certain regional geothermal energy unit is 800 kW, and 10% safety margin is reserved to ensure stable operation of the unit, and after calibration, it is 720 kW.

[0035] According to the judgment rule of peak demand or not, each time is assigned a binary identification, if the regional heat load prediction value of a time point is greater than the geothermal basic load threshold, the identification corresponding to the time point is assigned as 1, otherwise the identification corresponding to the time point is assigned as 0. The binary identification has clear non-binary identification, which can be quickly identified by the system without additional conversion. Its advantages are simple and intuitive identification rule, unified data format, which can not only efficiently filter out the time of energy supplement for subsequent modules, but also avoid the deviation of scheduling decision caused by ambiguous identification.

[0036] The identification corresponding to all time points is arranged in chronological order to construct and generate a peak demand identification list.

[0037] The air energy supplement module is used to determine the air energy supplement ratio based on the peak demand identification list, combined with the available capacity of geothermal energy and the air energy efficiency curve.

[0038] It should be noted that in order to avoid blind start of air energy when geothermal energy can meet the demand, and to prevent insufficient or excessive air energy supplement when geothermal energy is insufficient, and to adapt to the characteristics of large fluctuation of air energy efficiency in low temperature environment in severe cold region, the process of determining the air energy supplement ratio is as follows: first, the available capacity of geothermal energy is collected through the real-time monitoring system of geothermal energy unit, and the air energy efficiency curve generated by pre-experiment fitting is retrieved.

[0039] It should be noted that the air energy efficiency curve takes environmental temperature as the abscissa and air energy device COP (Coefficient of Performance) as the ordinate. The COP value of air energy device is measured under different low temperature conditions, and linear interpolation or polynomial fitting is used to form a continuous curve. After fitting, the COP corresponding to any temperature can be accurately queried.

[0040] Afterwards, for each time point identified as 1 in the list of peak demand, that is, the time point that has been determined to possibly need energy supplement, the ambient temperature at the time point identified as 1 is determined through the regional meteorological monitoring station or the temperature sensor of the heating system, and the maximum allowable output power of the air energy equipment at the ambient temperature is determined by calling the technical parameter manual of the air energy equipment or reading in real time through the equipment controller. It is ensured that the key parameters are completely aligned with the actual working conditions at the time point identified as 1, which not only provides a basis for subsequent energy supplement necessity judgment, but also avoids the safety risk of equipment over-power operation in advance.

[0041] Subsequently, the regional heat load prediction value at the time point identified as 1 is directly compared with the available capacity of geothermal energy at the time point: if the regional heat load prediction value at the time point identified as 1 does not exceed the available capacity, it is determined that air energy supplement is not needed, and the air energy supplement ratio is set to 0.

[0042] If the regional heat load prediction value at the time point identified as 1 exceeds the available capacity, the curve segment corresponding to the ambient temperature is located in the air energy efficiency curve.

[0043] It should be noted that geothermal energy in severe cold regions belongs to stable and low-consumption basic energy. If geothermal energy can meet the demand but air energy is started, unnecessary electric energy consumption will be increased. When the load exceeds the available capacity of geothermal energy, the corresponding working condition needs to be located through the efficiency curve, because the air energy efficiency at different temperatures in severe cold regions is greatly different. Only by matching the corresponding curve segment can the subsequent supplement ratio calculation meet the requirement of high-efficiency energy supplement, unnecessary energy supplement can be avoided, energy cost is saved, and high-efficiency calculation benchmark is locked for energy supplement scenarios, avoiding blind energy supplement.

[0044] On the basis of having determined that air energy supplement is needed and having locked the air energy efficiency curve segment corresponding to the ambient temperature, in order to further solve the problem of how to accurately match the load gap with air energy supplement power and ensure that air energy always operates in the high-efficiency interval, the air energy supplement ratio other than 0 needs to be obtained based on the curve segment and the maximum allowable output power, as shown in the following formula: Figure 3 The specific process is as follows: the load rate interval with energy efficiency ratio not less than the preset high-efficiency threshold in the curve segment is defined as the optimal load rate interval.

[0045] It should be noted that the load rate is the ratio of the actual output power of air energy to the maximum allowable output power of air energy. By locking the high-efficiency load range through the energy efficiency ratio threshold, it is avoided that air energy operates in the low-efficiency interval, the high-efficiency energy supplement load boundary is delimited from the source, it is ensured that the subsequent supplement power always expands around low energy consumption and high COP, and the air energy operation cost under severe cold conditions is directly reduced.

[0046] After determining the optimal load rate interval, multiplying the load rate by the maximum allowed output power of the air energy can realize the conversion of the optimal load rate interval into the optimal output power interval of the air energy device based on the maximum allowed output power.

[0047] The capacity difference between the regional heat load prediction value and the available capacity is determined.

[0048] The air energy supplement power matching the capacity difference is selected within the optimal output power interval. Specifically, if the capacity difference is less than or equal to the lower limit of the optimal output power interval, the lower limit of the optimal output power interval is selected as the air energy supplement power; if the capacity difference is within the optimal output power interval, the capacity difference is directly selected as the air energy supplement power; if the capacity difference is greater than the upper limit of the optimal output power interval, the upper limit of the optimal output power interval is selected as the air energy supplement power.

[0049] The air energy supplement ratio is calculated by ratio calculation of the air energy supplement power and the capacity difference.

[0050] The energy scheduling scheme determination module is used to simulate the total energy consumption under the heating scenario based on the air energy supplement ratio to obtain an energy scheduling scheme.

[0051] Considering that the energy scheduling scheme needs to quantify geothermal energy, air energy, and pipe heat loss, and ensuring that geothermal energy and air energy operate cooperatively not only meets the heat load demand but also maximizes the whole cycle operation efficiency, the process of obtaining the energy scheduling scheme is as follows: based on the principle of geothermal priority supply, the actual output power of geothermal energy at each time does not exceed the available capacity and is not lower than the minimum operation load threshold, and the geothermal energy consumption at each time is calculated.

[0052] The air energy consumption at each time is calculated based on the air energy supplement ratio.

[0053] The geothermal energy consumption and the air energy consumption are superimposed in combination with the pipe heat loss energy consumption at each time to obtain the total energy consumption.

[0054] It should be noted that the calculation formulae of the geothermal energy consumption , the air energy consumption , and the pipe heat loss energy consumption are as follows: .

[0055] .

[0056] .

[0057] wherein, is the actual output power of the geothermal energy, is the unit energy consumption coefficient of the geothermal energy, is the actual output power of the air energy, Energy consumption coefficient of air energy unit, Running time, Heat transfer coefficient of pipeline, Surface area of pipeline, Hot water temperature in pipeline, Outdoor environment temperature.

[0058] Considering that a single air energy supplement ratio may not be optimal, it is necessary to select the optimal air energy supplement ratio through multi-gradient coverage. The air energy supplement ratio is adjusted in a gradient manner within a set percentage range according to a benchmark adjustment percentage to generate multiple groups of total energy consumption corresponding to different air energy supplement ratios.

[0059] For example, the percentage range is set to ±10%, and the benchmark adjustment percentage is 5%. That is, within 90% to 110% of the air energy supplement ratio, the adjustment is made at an interval of 5%.

[0060] Based on the total energy consumption and the air energy consumption at each time, the air energy consumption and the pipeline heat loss energy consumption, an initial energy scheduling scheme is generated.

[0061] Each initial energy scheduling scheme is evaluated by a multi-objective function to obtain an index score.

[0062] The initial energy scheduling scheme corresponding to the smallest index score is taken as the energy scheduling scheme.

[0063] It should be noted that, in order to ensure that the evaluation of each initial scheduling scheme is objective and fair, and to meet the actual operation requirements in severe cold regions, the process of evaluating each initial energy scheduling scheme by a multi-objective function to obtain an index score is as follows: the period total energy consumption, energy cost and equipment start-stop times corresponding to each initial energy scheduling scheme are standardized to obtain standardized evaluation data.

[0064] The standardized evaluation data are weighted and summed to obtain the index score.

[0065] The cooperative operation determination module is used to determine whether there is a deviation after implementing the energy scheduling scheme in combination with real-time heating feedback data. If there is a deviation, the source of the deviation is determined, and the cooperative operation mode is determined based on the source of the deviation.

[0066] It should be noted that the heating system in the cold region is easy to deviate from the target value due to sudden changes in low temperature environment, equipment working condition drift, and user behavior fluctuation. Real-time feedback data is needed to accurately judge whether the deviation exists, locate the root cause of the deviation, and match the corresponding collaborative operation mode to avoid the problem of continuous expansion of deviation leading to room temperature not meeting the standard, equipment overload, and energy consumption surge. Ensure that the geothermal energy and air energy collaborative heating in the cold region is always in a stable and efficient operation state. The process of determining the collaborative operation mode is as follows: calculate the deviation rate of each parameter in the real-time heating feedback data and the target value.

[0067] It should be noted that the real-time heating feedback data includes but is not limited to water supply temperature, indoor average temperature, geothermal energy actual output, air energy actual output, and pipe heat loss power. For each parameter, calculate the deviation degree according to the formula deviation rate = |real-time value-target value| / target value x 100%.

[0068] If the deviation rate of a parameter exceeds the corresponding deviation judgment reference value for N consecutive periods, it is confirmed that the parameter has a deviation.

[0069] It should be noted that the deviation judgment reference value is set according to the importance difference of the parameters in the cold region. For example, indoor temperature directly affects user comfort, and the reference value is set to 8%; pipe heat loss power is easy to fluctuate at low temperature, and the reference value is set to 15%. The number of periods N is set in combination with the fluctuation characteristics of the parameters in the cold region. For example, indoor temperature fluctuates slowly, N=3; equipment output fluctuates quickly, N=2, to avoid misjudgment of deviation due to instantaneous interference.

[0070] Based on the pre-constructed traceability matrix, the deviation is traced and verified to determine the source of the deviation. Specifically, compare the deviation type in the row dimension of the traceability matrix with the mapping table of the associated parameters, and match the parameters with deviations to the corresponding deviation type.

[0071] It should be noted that the traceability matrix is a two-dimensional structure, the row dimension is the deviation type, such as indoor temperature deviation, geothermal energy output deviation, and pipe heat loss deviation, and the column dimension is the potential source and the corresponding traceability verification element, such as the potential sources of indoor temperature deviation include air energy supplement deficiency, pipe heat loss exceeding the standard, and user heat increase. Each source corresponds to 2-3 verification elements, such as the verification element of air energy supplement deficiency is that the air energy actual output is less than the dispatch value.

[0072] Match the parameters confirmed to have a deviation to the unique deviation type according to the mapping table: for example, if the parameter with deviation is indoor average temperature, it is directly matched to the indoor temperature deviation type; if the parameter with deviation is the temperature difference between pipe inlet and outlet, it is matched to the pipe heat loss deviation type.

[0073] The target row corresponding to the deviation type in the traceability matrix is located, and potential sources and traceability check element information in the target row are retained to form a simplified list, focusing on high-probability potential sources in cold regions, avoiding invalid checks, and further improving traceability efficiency, while ensuring that the simplified sources are all high-risk items in low-temperature environments, without missing any key hidden dangers.

[0074] For each potential source in the simplified list, the preset traceability check index in its cell is called. If the traceability check index meets the corresponding determination rule, the corresponding potential source is marked as a deviation source, otherwise the potential source is excluded.

[0075] It should be noted that the determination rule needs to be combined with the calibration of the equipment characteristics in the cold region to avoid misjudgment and verify whether each check element meets the determination rule, for example, the determination rule for insufficient air energy supplement is that element ① and element ② meet at the same time, i.e., the actual output is not greater than 90% of the scheduling value and the actual COP is not greater than 90% of the design value; the determination rule for pipe freezing is that element ① or element ② meets, i.e., the outer wall temperature is not greater than 0°C or the flow is not greater than 70% of the design value, because pipe freezing in the cold region may first appear a sudden temperature drop or a flow decrease.

[0076] If there are multiple potential sources that meet the corresponding determination rule, the ratio of the number of check indices that meet the determination rule to the total number of check indices of the potential source is taken as the satisfaction degree, and the potential source corresponding to the maximum satisfaction degree is marked as the deviation source.

[0077] The satisfaction degree objectively quantifies the correlation strength of the source through the element compliance rate, and the stronger the correlation, the greater the contribution of the source to the deviation, so the problem can be maximized by prioritizing processing to avoid subjective decision bias in multiple sources, and to ensure that the final source is the factor that has the greatest impact on the deviation.

[0078] Through the pre-constructed structured traceability matrix, combined with the matching of the deviation type, the simplification of the potential source, the verification of the check index, and the quantification of the satisfaction degree, the fuzzy deviation traceability is converted into accurate and verifiable quantitative judgment, avoiding invalid subsequent collaborative operation mode adjustment due to misjudgment of the deviation source.

[0079] According to the preset deviation source coding mapping table and the deviation rate coding mapping table, the deviation source and the deviation rate are coded to obtain the deviation source code and the deviation rate code.

[0080] For example, the deviation source coding mapping table corresponds each deviation source to a unique letter + number code, such as air energy supplement deficiency → A1, pipe freezing → P2, and geothermal energy water temperature drop → G3. The coding rule needs to reflect the source type, such as A = air energy, P = pipe, and G = geothermal energy, to facilitate quick identification.

[0081] The deviation rate coding mapping table is divided into three levels according to the deviation rate, i.e. mild (deviation rate less than or equal to 10%), moderate (10% greater than deviation rate less than or equal to 20%), and severe (deviation rate greater than 20%), corresponding to codes L, M, and H (e.g. deviation rate = 10%→L, deviation rate = 15%→M, and deviation rate = 25%→H), which adapt to the processing priority of different deviation degrees in severe cold regions (severe deviation requires emergency response).

[0082] The final deviation source and the parameter deviation rate are coded: for example, the deviation source is air energy supplement deficiency, and the deviation rate is 12%, then the deviation source coding is A1+M.

[0083] The automation matching coordination mode lays the foundation to avoid the delay and error of manual intervention, and ensures the timeliness of deviation processing in severe cold regions.

[0084] Based on the deviation source coding, the corresponding deviation source partition in the mapping library is located, and the coordination operation mode corresponding to the deviation rate coding is matched from the deviation source partition.

[0085] Considering that the adjustment logic of different types of deviation sources in severe cold regions is completely different, if not partitioned, it may appear that the air energy deviation is processed by the pipeline mode, so the coordination operation mode mapping library is partitioned according to the deviation source type, such as A zone for air energy related sources, P zone for pipeline related sources, and G zone for geothermal energy related sources, and each partition is subdivided into subdirectories according to the deviation rate coding (L / M / H), and each subdirectory corresponds to a unique coordination operation mode.

[0086] The coordination operation mode needs to be designed in combination with the characteristics of severe cold regions, such as the coordination operation mode corresponding to the air energy supplement deficiency of A zone M level deviation is to improve the air energy load rate to the upper limit of the optimal interval and fine-tune the geothermal energy output by 5%; the coordination operation mode corresponding to the pipeline freeze-up of P zone H level deviation is to start the pipeline heating system, temporarily switch to the backup heat source, and reduce the user end water supply temperature to reduce heat loss.

[0087] The specific process is as follows: first, locate the deviation source partition, locate the corresponding partition in the mapping library according to the first letter of the deviation source coding; then match the deviation rate subdirectory: find the subdirectory corresponding to the deviation rate coding in the partition; finally, determine the coordination operation mode, extract the coordination operation mode under the subdirectory as the adjustment scheme for the current deviation.

[0088] The hierarchical matching ensures that the deviation degree and the adjustment effort are adapted, avoiding excessive adjustment or insufficient adjustment, which can achieve precise correspondence, ensure that the adjustment measures effectively solve the deviation, and meet the equipment operation characteristics and heating demand in severe cold regions, and finally pull the system back to a stable running state.

[0089] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product.

[0090] Those skilled in the art can realize that the modules and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0091] In addition, each functional module in each embodiment of the present application can be integrated in one processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0092] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any modification or replacement within the technical scope disclosed by the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0093] Finally, the above is merely preferred embodiments of the present application, and is not intended to limit the present application, and any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A cold region geothermal energy and air energy intelligent operation management system, characterized in that, The method comprises the following steps: a load prediction module for obtaining a regional heat load prediction value sequence based on outdoor meteorological data, building thermal parameters and user behavior records; a peak demand identification module for determining the stability of the heat load based on the regional heat load prediction value sequence, and if the stability is normal, obtaining a peak demand identification list based on the regional heat load prediction value sequence and a geothermal base load threshold, and if the stability is abnormal, giving a warning based on a set rule; an air energy supplement module for determining an air energy supplement ratio based on the peak demand identification list in combination with the available capacity of geothermal energy and an air energy efficiency curve; a dispatching scheme determination module for simulating total energy consumption in a heating scenario based on the air energy supplement ratio to obtain an energy dispatching scheme; a cooperative operation determination module for determining a deviation source if there is a deviation after implementing the energy dispatching scheme in combination with real-time heating feedback data, and determining a cooperative operation mode based on the deviation source; the process of determining a deviation source if there is a deviation after implementing the energy dispatching scheme in combination with real-time heating feedback data is as follows: calculating the deviation rate of each parameter in the real-time heating feedback data from the target value; if the deviation rate of a certain parameter exceeds the corresponding deviation determination reference value for N consecutive periods, it is confirmed that the parameter has a deviation; tracing the source of the deviation based on a pre-constructed traceability matrix and verifying the deviation to determine the deviation source; encoding the deviation source and the deviation rate according to a preset deviation source encoding mapping table and a deviation rate encoding mapping table to obtain a deviation source code and a deviation rate code; locating the corresponding deviation source partition in the mapping library based on the deviation source code, and matching the cooperative operation mode corresponding to the deviation rate code from the deviation source partition; the process of tracing the source of the deviation based on a pre-constructed traceability matrix and verifying the deviation to determine the deviation source is as follows: matching the parameter with a deviation to the corresponding deviation type by comparing the deviation type of the row dimension of the traceability matrix with the mapping table of the associated parameters; locating the target row corresponding to the deviation type in the traceability matrix, and retaining the potential source and traceability check element information in the target row to form a simplified list; for each potential source in the simplified list, retrieve the preset traceability check index in its cell, and if the traceability check index meets the corresponding judgment rule, mark the corresponding potential source as the deviation source, otherwise exclude the potential source; if there are multiple potential sources that meet the corresponding judgment rule, the ratio of the number of actual check indexes that meet the judgment rule to the total number of check indexes of the potential source is taken as the satisfaction degree, and the potential source corresponding to the maximum satisfaction degree is marked as the deviation source.

2. The intelligent operation management system of geothermal energy and air energy in cold region according to claim 1, characterized in that, The process of obtaining a regional heat load prediction value sequence based on outdoor meteorological data, building thermal parameters and user behavior records is as follows: performing correlation degree analysis on the outdoor meteorological data, building thermal parameters and user behavior records and the heat load, and retaining the data with a correlation degree greater than a set correlation threshold to obtain multi-dimensional correlation data; performing cleaning and normalization processing on the multi-dimensional correlation data to obtain standardized input data; The standardized input data is input into the LSTM-based neural network model to obtain a sequence of regional heat load prediction values.

3. The intelligent operation management system for geothermal and air energy in cold regions according to claim 1, characterized in that, The process of determining the stability of the heat load based on the sequence of regional heat load prediction values is as follows: The ratio of the mean value to the standard deviation of the sequence of regional heat load prediction values is taken as the fluctuation coefficient. The ratio of the number of prediction values less than the output upper limit to the total number of prediction values in the sequence of regional heat load prediction values is calculated. The deviation rate between the air energy response speed and the designed response speed is calculated using the deviation rate calculation formula. After the fluctuation coefficient and the deviation rate are normalized, they are weighted and summed with the ratio to obtain the stability.

4. The intelligent operation management system of geothermal energy and air energy in cold regions according to claim 1, characterized in that, The process of obtaining a peak demand identification list based on the sequence of regional heat load prediction values and the geothermal base load threshold is as follows: The regional heat load prediction values at multiple consecutive time points are compared with the preset geothermal base load threshold at each time point. If the regional heat load prediction value at a certain time point is greater than the geothermal base load threshold, the identification corresponding to that time point is assigned a value of 1, otherwise it is assigned a value of 0. The identifications corresponding to all time points are arranged in chronological order to construct a peak demand identification list.

5. The intelligent operation management system of geothermal energy and air energy in cold regions according to claim 4, characterized in that, The process of determining the air energy supplement ratio based on the peak demand identification list, the available capacity of geothermal energy, and the air energy efficiency curve is as follows: The available capacity of geothermal energy and the pre-fitted air energy efficiency curve are collected. The ambient temperature at the time corresponding to identification 1 and the maximum allowed output power of the air energy device are determined. If the regional heat load prediction value at the time corresponding to identification 1 does not exceed the available capacity, it is determined that there is no need for air energy supplement, and the air energy supplement ratio is set to 0. If the regional heat load prediction value at the time corresponding to identification 1 exceeds the available capacity, the curve segment corresponding to the ambient temperature is located in the air energy efficiency curve. Based on the curve segment and the maximum allowed output power, the air energy supplement ratio that is not 0 is obtained.

6. The intelligent operation management system of geothermal energy and air energy in cold regions according to claim 5, characterized in that, The process of obtaining the air energy supplement ratio that is not 0 based on the curve segment and the maximum allowed output power is as follows: The load rate interval in the curve segment with an energy efficiency ratio not less than the preset high-efficiency threshold is defined as the optimal load rate interval. The optimal load rate interval is converted into the optimal output power interval of the air energy device based on the maximum allowed output power. The capacity difference between the regional heat load prediction value and the available capacity is determined. The air energy supplement power that matches the capacity difference is selected within the optimal output power interval. The air energy supplement ratio is calculated by taking the ratio of the air energy supplement power to the capacity difference.

7. The intelligent operation management system of geothermal energy and air energy in cold region according to claim 1, characterized in that, Based on the air energy supplement ratio, the total energy consumption in the heating scenario is simulated to obtain an energy dispatching scheme. Based on the principle of geothermal priority supply, the actual output power of geothermal energy at each time point does not exceed the available capacity and is not less than the minimum operating load threshold, the energy consumption of geothermal energy at each time point is calculated. Based on the air energy supplement ratio, the energy consumption of air energy at each time point is calculated. The geothermal energy consumption and air energy consumption are superimposed by considering the pipeline heat loss energy consumption at each time point to obtain the total energy consumption. Within a certain percentage range, the air energy supplement ratio is adjusted by a gradient according to the reference adjustment percentage to generate multiple groups of total energy consumption corresponding to different air energy supplement ratios. Generate an initial energy scheduling scheme based on total energy consumption and air energy consumption at each time, air energy consumption and pipe heat loss energy consumption; Evaluate each initial energy scheduling scheme through a multi-objective function to obtain an index score; The initial energy scheduling scheme corresponding to the smallest index score is taken as the energy scheduling scheme.

8. The intelligent operation management system of geothermal energy and air energy in cold regions according to claim 7, characterized in that, The process of evaluating each initial energy scheduling scheme through a multi-objective function to obtain an index score is as follows: Standardize the total energy consumption, energy cost and equipment start-stop times corresponding to each initial energy scheduling scheme to obtain standardized evaluation data; Weighted sum the standardized evaluation data to obtain an index score.

Images