A method and device for predicting and controlling an integrated energy station

Abstract

The present invention relates to the technical field of integrated energy stations, and discloses a method and device for predicting and controlling an integrated energy station, the method comprising: determining the current power of an energy storage system of an integrated energy station in a first time period; predicting the power consumption of the power load of the integrated energy station in a second time period of peak power consumption, and determining the predicted power consumption of the power load at each time point in the second time period; determining the predicted amount of power consumption required by the power load in the second time period according to the predicted power consumption of the power load at each time point in the second time period; and charging the energy storage system when the current power consumption does not exceed the predicted amount of power consumption. The present invention can charge the energy storage system in advance, so that in the second time period of peak power consumption, the integrated energy station can supply power to the power load based on the energy storage system, thereby being able to efficiently utilize the resources of the integrated energy station itself, which is beneficial to peak shaving and valley filling of the municipal power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated energy stations, and in particular to a method and device for predicting and controlling an integrated energy station. Background Art

[0002] An integrated energy station (also known as an all-electric energy station) is a distributed power supply energy station that integrates renewable resources such as solar energy and wind energy. It utilizes a variety of different types of power generation methods such as photovoltaic power generation and wind power generation to achieve multi-energy power supply. The coordinated cooperation of multiple energy sources improves the power supply reliability of the integrated energy station. In addition, through the refined management of multiple energy sources, efficient energy utilization can be achieved and low carbon emissions can be achieved.

[0003] In order to reduce the impact on AC mains, during peak periods of AC mains, the integrated energy station can combine renewable resources and the energy stored in the energy storage system to supply power independently. However, during peak periods, if it is not possible to generate electricity based on renewable resources such as solar energy and wind energy, or if the energy storage system is insufficient, it will still be necessary to use the mains, making it difficult to use the integrated energy station efficiently.

[0004] Prior art document 1 (CN118117747A) discloses a regional energy intelligent body economic dispatch optimization system considering carbon emission costs, constructs an operation optimization model of a regional energy intelligent body considering carbon emission costs, realizes the optimal output of the system, and achieves the purpose of optimal economic operation of the regional energy intelligent body.

[0005] Prior art document 2 (CN117634700A) discloses a method and system for optimizing the economic operation of a comprehensive energy system in a university town. By setting a more reasonable objective function and constraints, it can well achieve the optimization of the economic operation of a comprehensive energy system in a university town, so as to guide the actual operation of the comprehensive energy system.

[0006] It is worth noting that based on the technical effects achieved by the existing technical documents 1 and 2, as the proportion of new energy used in smart parks increases, parks that use integrated energy stations will be included in a larger scope for consideration and participate in peak shaving and valley filling, which has broad prospects. How to implement accurate predictive control needs to be urgently addressed. Summary of the invention

[0007] In view of this, the present invention provides a method and device for predicting and controlling an integrated energy station to solve the problem of difficulty in efficiently utilizing the integrated energy station.

[0008] In a first aspect, the present invention provides a method for predicting and controlling an integrated energy station, comprising:

[0009] In a first time period, determining the current power of the energy storage system of the integrated energy station; the first time period is a time period that is not a peak time period;

[0010] Predicting the power consumption of the power load of the integrated energy station in a second time period of peak power consumption, and determining the predicted power consumption of the power load at each time point in the second time period, including: obtaining the power consumption history power of the power load at each time point in the historical time period; correcting the power consumption history power to generate power consumption correction power, including:

[0011] The historical power consumption at the first time point in the historical time period , add Gaussian noise that conforms to the Gaussian distribution , generate the power consumption history at the first time point Corresponding power correction ;

[0012] The power consumption correction at the i-1th time point Based on the historical power consumption at the i-th time point Generate the power consumption history at the i-th time point Corresponding power correction , expressed as the following formula (1):

[0013] (1)

[0014] Where:

[0015] represents the historical power consumption at the i-1th time point,

[0016] k is an adjustment coefficient not less than 0;

[0017] According to the power consumption corrected power of the power load at each time point in the historical time period, the power consumption power of the power load in the second time period is predicted, and the power consumption predicted power of the power load at each time point in the second time period is determined;

[0018] Determining whether the current power consumption exceeds the predicted power consumption;

[0019] When the current power amount does not exceed the predicted power consumption amount, the energy storage system is charged to charge the power of the energy storage system to a level not less than the predicted power consumption amount.

[0020] In some optional implementations, determining the predicted power consumption of the power load at each time point in the second time period further includes:

[0021] Extracting high-frequency characteristic values ​​of the historical power consumption;

[0022] Combining the high frequency characteristic value with the corresponding power consumption correction power into a two-dimensional power characteristic;

[0023] The predicting the power consumption of the power load in the second time period according to the power consumption corrected power of the power load at each time point in the historical time period includes:

[0024] The power consumption of the power load in the second time period is predicted according to the two-dimensional power characteristics of the power load at each time point in the historical time period.

[0025] In some optional implementations, extracting the high-frequency characteristic value of the historical power consumption includes:

[0026] Construct multiple convolution kernels for extracting high-frequency features;

[0027] According to each of the convolution kernels, convolution processing is performed on the historical power sequence to generate a corresponding convolution result sequence; the historical power sequence includes the historical power consumption at each time point in the historical time period;

[0028] Selecting one from the multiple convolution result sequences as a valid convolution result sequence; the larger the value corresponding to the convolution result sequence is, the higher the probability of being selected;

[0029] The convolution result corresponding to each time point in the effective convolution result sequence is used as the high-frequency feature value corresponding to the corresponding time point.

[0030] In some optional embodiments, the convolution kernel includes 2N+1 elements, and the i-th element in the convolution kernel is It is expressed as the following formula (2):

[0031] (2)

[0032] Where:

[0033] is the frequency factor corresponding to the convolution kernel, and different convolution kernels correspond to different frequency factors ;

[0034] is the adjustment factor, and ;

[0035] N is a positive integer, and N is There is a negative correlation between them.

[0036] In some optional implementations, the selecting one from the plurality of convolution result sequences as a valid convolution result sequence includes:

[0037] Respectively determining the extreme value of the convolution result in each of the convolution result sequences or the sum of all the convolution results in the convolution result sequence;

[0038] The convolution result sequence corresponding to the largest extreme value or the largest sum of convolution results is taken as the valid convolution result sequence.

[0039] In some optional embodiments, the method further comprises:

[0040] Predicting the load power of the cooling load and the heating load of the integrated energy station in the second time period respectively, and determining the load prediction power of the cooling load and the heating load at each time point in the second time period;

[0041] According to the load prediction power of the cooling load and the heating load at each time point in the second time period, the power consumption prediction of the electric refrigeration machine of the integrated energy station is determined to be expressed by the following formula (3):

[0042] (3)

[0043] Where:

[0044] represents the predicted power consumption of the electric refrigerator at the i-th time point in the second time period,

[0045] represents the load forecast power (a kind of cooling power) of the cooling load at the i-th time point in the second time period,

[0046] represents the load forecast power (a kind of heating power) of the heat load at the i-th time point in the second time period,

[0047] Indicates the gas power of the integrated energy station,

[0048] Indicates the efficiency of the heat exchanger of the integrated energy station,

[0049] represents the efficiency of the absorption chiller in the integrated energy station,

[0050] represents the efficiency of the electric refrigerator,

[0051] represents a function that seeks a larger value;

[0052] Determining a predicted amount of power consumption required by the electric refrigerator in the second time period according to the predicted power consumption of the electric refrigerator at each time point in the second time period;

[0053] When the current power consumption does not exceed the predicted power consumption, charging the energy storage system includes:

[0054] When the current power amount does not exceed the sum of the predicted power usage amount and the predicted power consumption amount, the energy storage system is charged.

[0055] In a second aspect, the present invention provides a device for predicting and controlling an integrated energy station, comprising:

[0056] The power determination module is used to determine the current power of the energy storage system of the integrated energy station in a first time period; the first time period is a time period that is not a peak power consumption period;

[0057] A prediction module, used to predict the power consumption of the power load of the integrated energy station in a second time period of peak power consumption, and determine the predicted power consumption of the power load at each time point in the second time period; and determine the predicted amount of power consumption required by the power load in the second time period according to the predicted power consumption of the power load at each time point in the second time period;

[0058] A judgment module, used to judge whether the current power consumption exceeds the predicted power consumption;

[0059] The processing module is used to charge the energy storage system when the current power consumption does not exceed the predicted power consumption, so as to charge the power of the energy storage system to be not less than the predicted power consumption.

[0060] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for predictive control of an integrated energy station according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0061] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for predicting and controlling an integrated energy station according to the first aspect or any corresponding embodiment thereof.

[0062] The method for predicting and controlling an integrated energy station provided by the present invention determines the current power of the energy storage system in a first time period when power consumption is not at peak, and can predict in advance the power consumption of the integrated energy station in a second time period when power consumption is at peak thereafter, and further predict the total power consumption of the power load based on the predicted power consumption; when the current power is less than the predicted power consumption, the energy storage system can be charged in advance, so that in the second time period when power consumption is at peak thereafter, the integrated energy station can supply power to the power load based on the energy storage system, thereby making efficient use of the resources of the integrated energy station itself, reducing dependence on the mains, reducing the impact on the mains during the peak period, and facilitating peak shaving and valley filling of the mains power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 is a flow chart of a method for predictive control of an integrated energy station according to an embodiment of the present invention;

[0065] Figure 2 is a structural schematic diagram of a comprehensive energy station according to an embodiment of the present invention;

[0066] Figure 3 is a flow chart of another method for predicting and controlling an integrated energy station according to an embodiment of the present invention;

[0067] Figure 4 is a schematic diagram of historical power consumption according to an embodiment of the present invention;

[0068] Figure 5 is a schematic diagram of power correction according to an embodiment of the present invention;

[0069] Figure 6 is a structural block diagram of a device for predictive control of an integrated energy station according to an embodiment of the present invention;

[0070] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0072] An embodiment of the present invention provides an embodiment of a method for predicting and controlling an integrated energy station. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0073] In embodiment 1 of the present invention, a method for predictive control of an integrated energy station is provided, which can be applied to a controller of the integrated energy station. Figure 1 is a flow chart of a method for predictive control of an integrated energy station according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps.

[0074] Step S101, in a first time period, determining the current power of the energy storage system of the integrated energy station; the first time period is a time period that is not a peak time period for electricity consumption.

[0075] In this embodiment, the time period corresponding to the peak power consumption can be pre-defined according to the power supply situation of the city power. Accordingly, the other time periods except the time period corresponding to the peak power consumption are the non-peak power consumption time periods. For the convenience of description, the non-peak power consumption time period is referred to as the first time period, and the peak power consumption time period is referred to as the second time period.

[0076] In addition, during the first non-peak period, the current power of the energy storage system of the integrated energy station is determined, that is, the current power. For example, the current power of the energy storage system can be calculated based on the current SOC (State Of Charge) of the energy storage system, which is not described in detail here.

[0077] Step S102, predicting the power consumption of the power load of the integrated energy station during the second time period of peak power consumption, and determining the predicted power consumption of the power load at each time point in the second time period.

[0078] In this embodiment, in the first time period when electricity consumption is not at peak, the operating conditions of the integrated energy station in the second time period when electricity consumption is at peak are predicted in advance, so that the power consumption of the power load at each time point in the second time period during the second time period when electricity consumption is at peak can be determined in advance, that is, the predicted power consumption.

[0079] For example, a time period T for predicting power consumption may be preset (for example, T is 10 seconds, 1 minute, 10 minutes, etc.), and the power consumption prediction at the corresponding time point is determined every time period T. For example, if the second time period is 1 hour and the time period T is 1 minute, the power consumption prediction at 60 time points needs to be predicted.

[0080] A prediction model for predicting the power consumption of the power load may be pre-built, and the predicted power consumption of the power load at each time point in the second time period may be predicted based on the prediction model.

[0081] Step S103, determining the predicted amount of electricity consumption required by the electricity load in the second time period according to the predicted power consumption of the electricity load at each time point in the second time period.

[0082] In this embodiment, after determining the predicted power consumption at each time point in the second time period, the total predicted power consumption required by the power load in the second time period can be determined based on the predicted power consumption. The power consumption corresponding to each time point can be calculated, and the power consumption at all time points in the second time period can be summed to determine the total power consumption, that is, the predicted power consumption.

[0083] For example, if the second time period includes n time points, and each time point corresponds to a time period T, that is, the duration of the entire second time period is n×T; for the i-th time point, its power consumption prediction is , then the power consumption corresponding to the i-th time point can be expressed as T× Therefore, in the second time period in the future, the predicted power consumption required by the power load is expressed by the following formula (1):

[0084] (1)

[0085] Where:

[0086] Q is the predicted electricity consumption,

[0087] n is the number of time points in the second time period,

[0088] T is a time period corresponding to each time point,

[0089] Forecast power consumption at the i-th time point, .

[0090] Step S104, determining whether the current power consumption exceeds the predicted power consumption.

[0091] In this embodiment, after determining the predicted amount of electricity required by the power load in the second time period in the future and the current amount of electricity of the energy storage system at the current moment, the two can be compared. If the current amount of electricity exceeds the predicted amount of electricity, it means that in the second time period thereafter, only the energy storage system can be used to supply power to the power load, that is, during the future peak electricity consumption period (i.e., the second time period), the mains electricity can be omitted, thereby reducing the pressure on the mains electricity during the peak electricity consumption period.

[0092] On the contrary, if the current power consumption does not exceed the predicted power consumption, it means that the current power stored in the energy storage system needs to be charged.

[0093] Step S105, when the current power consumption does not exceed the predicted power consumption, the energy storage system is charged to charge the power of the energy storage system to be not less than the predicted power consumption.

[0094] In this embodiment, as described above, if the current power consumption does not exceed the predicted power consumption, in order to enable the power load to be powered based on the energy storage system in the subsequent second time period, the energy storage system needs to be charged and the power of the energy storage system needs to be charged to a level not less than the predicted power consumption.

[0095] For example, if the current power consumption does not exceed the predicted power consumption, the energy storage system can be charged based on the power generation equipment of the integrated energy station. If the power generation of the power generation equipment is insufficient, since this is the first time period of non-peak power consumption, the energy storage system can also be charged based on the city power supply. The power generation equipment can specifically include photovoltaic power generation equipment, wind power generation equipment, etc., which is based on the structure of the integrated energy station.

[0096] Figure 2 A structural diagram of a comprehensive energy station is shown. Figure 2 As shown, the integrated energy station includes one or more power generation equipment and also includes an energy storage system, which can specifically be an energy storage battery; and the integrated energy station can also be connected to the mains, and can provide electrical energy to the electrical load through the mains, power generation equipment or energy storage system, so that the electrical load can work normally; the electrical load can be, for example, lighting, air conditioning, refrigerators and other electrical appliances.

[0097] It can be understood that the method provided in this embodiment can be executed when there is still a certain time left before the second time period to determine whether the current power exceeds the predicted power consumption, so that there is enough time to charge the energy storage system to a power level not less than the predicted power consumption. In addition, if the maximum power of the energy storage system is still less than the predicted power consumption, the process of charging the energy storage system in the above step S105 is only executed until the energy storage system is fully charged, and charging is stopped after the energy storage system is fully charged; in the subsequent second time period, it may still be necessary to rely on the mains to provide a certain amount of power to ensure that the power load can operate stably.

[0098] The method for predicting and controlling an integrated energy station provided in this embodiment determines the current power of the energy storage system in a first time period when power consumption is not at peak, and can predict in advance the power consumption of the integrated energy station in a second time period when power consumption is at peak thereafter, and further predict the total power consumption of the power load based on the predicted power consumption; when the current power is less than the predicted power consumption, the energy storage system can be charged in advance, so that in the second time period when power consumption is at peak thereafter, the integrated energy station can supply power to the power load based on the energy storage system, thereby making efficient use of the resources of the integrated energy station itself, reducing dependence on the mains, and reducing the impact on the mains during peak power consumption, which is beneficial to peak shaving and valley filling of the mains power grid.

[0099] In Embodiment 2 of the present invention, a method for predictive control of an integrated energy station is provided, which can be applied to a controller of an integrated energy station. Figure 3 is a flow chart of a method for predictive control of an integrated energy station according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps.

[0100] Step S301, in a first time period, determining the current power of the energy storage system of the integrated energy station; the first time period is a time period that is not a peak time period for power consumption.

[0101] For details, see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0102] Step S302: predicting the power consumption of the power load of the integrated energy station during the second time period of peak power consumption, and determining the predicted power consumption of the power load at each time point in the second time period.

[0103] Specifically, the above step S302 "predicting the power consumption of the power load of the integrated energy station in the second time period of the peak power consumption, and determining the predicted power consumption of the power load at each time point in the second time period" may include the following steps S3021 to S3023.

[0104] Step S3021, obtaining the historical power consumption of the power load at each time point in the historical time period.

[0105] In this embodiment, in order to predict the power consumption of the power load in the second time period in the future (i.e., the predicted power consumption), the power consumption of the power load of the integrated energy station in the previous historical time period, i.e., the historical power consumption, is obtained, and the future power consumption of the power load is predicted using the historical power consumption as a reference.

[0106] Similar to the second time period mentioned above, the historical time period is also a time period, which includes multiple time points; and, in the historical time period and the second time period, each time point corresponds to the same time period T, that is, in the historical time period, the power consumption (that is, the historical power consumption) is determined once every time period T.

[0107] The historical power consumption is the power consumption actually collected in the previous historical time period, that is, the historical power consumption is an actual value.

[0108] Step S3022: Correct the historical power consumption to generate corrected power consumption.

[0109] There are multiple loads in the integrated energy station. The power load in this embodiment is a general term for all loads in the integrated energy station. As some loads in the integrated energy station start and stop, the overall power consumption of the integrated energy station will be volatile and sudden, that is, the power consumption of the power loads fluctuates, that is, the historical power consumption fluctuates. In order to reduce the impact of fluctuations in the historical power consumption on subsequent predictions, in this embodiment, these historical power consumptions are corrected to weaken the impact of the fluctuations, and the corrected power consumption is called the corrected power consumption.

[0110] In some optional implementations, the above step S3022 "correcting the historical power consumption to generate corrected power consumption" may specifically include steps A1 to A2.

[0111] Step A1: the historical power consumption at the first time point in the historical time period , add Gaussian noise that conforms to the Gaussian distribution , generate the power consumption history at the first time point Corresponding power correction .

[0112] Step A2: Correct the power consumption at the i-1th time point Based on the historical power consumption at the i-th time point Generate the power consumption history at the i-th time point Corresponding power correction .

[0113] In this embodiment, if the historical time period includes m time points, then m power consumption historical power points can be acquired in advance. ,i=1,2,…,m. When making corrections, first determine the power correction power corresponding to the first time point Specifically, Gaussian noise can be generated based on Gaussian distribution , is the historical power consumption at the first time point Add this Gaussian noise , thus obtaining the power correction power corresponding to the first time point ,Right now Among them, the Gaussian noise It can be 0, that is, the power consumption history at the first time point is directly converted to As the corresponding power correction power In other words, the power consumption history at the first point in time can be ignored. Make corrections.

[0114] The historical power consumption at the time point after correction (i=2,3,…,m), the power will be corrected based on the power consumption at the previous time point Implement correction to determine the power correction power at the i-th time point .

[0115] Specifically, the power correction power at the i-th time point is It is expressed as the following formula (2):

[0116] (2)

[0117] Where:

[0118] represents the historical power consumption at the i-1th time point,

[0119] k is an adjustment coefficient not less than 0, for example, k=1 or 2.

[0120] In this embodiment, Indicates the corrected power consumption determined at the i-1th time point Compared with the actual power consumption history The deviation between them; at the i-th time point, even if the two power consumption history and The difference between them is large, based on the weight at this time , can reduce the power consumption caused by changes in historical power consumption to a certain extent , thereby weakening the impact of power fluctuations.

[0121] In addition, the power consumption of the power load of the integrated energy station is generally periodic. For example, the changes in power consumption every day are relatively similar. Based on the above formula, the power correction power corresponding to each time point is determined. , does not affect the periodicity of the power load, and the corrected power It is easier to reflect the periodic changes of the power load, which is conducive to more accurate prediction of the power consumption of the power load in the future.

[0122] Figure 4 It shows a schematic diagram of the change of historical power consumption in a certain historical period; Figure 4 As shown, the horizontal axis is the time axis, corresponding to each time point in the historical time period, and the vertical axis is the historical power consumption. In this embodiment, taking k=3 as an example, after correcting each historical power consumption in the historical time period based on the above formula, the correction result is as follows: Figure 5 As shown, Figure 5 Indicates the corrected power consumption at each time point. Figure 4 and Figure 5 It can be seen that correcting the historical power consumption based on the correction method provided in this embodiment can reduce the fluctuations in the original historical power consumption and make it easier to characterize the periodic changes in the power consumption, thereby facilitating subsequent prediction of the power consumption based on the corrected power consumption.

[0123] Step S3023, predicting the power consumption of the power load in the second time period according to the power consumption corrected power of the power load at each time point in the historical time period, and determining the power consumption predicted power of the power load at each time point in the second time period.

[0124] In this embodiment, the power consumption correction power at each time point in the historical time period is determined. Then, the power can be corrected based on these power consumption The power consumption is predicted to be able to predict the power consumption of the power load in the second time period, that is, the predicted power consumption.

[0125] Among them, the power correction can be based on the time series method. Analyze to determine its changing rules and basic characteristics, so as to predict the future power consumption. Alternatively, a prediction model that can realize power prediction can be established, and the future power consumption prediction can be determined based on the prediction model; for example, the prediction model can be built based on deep learning models such as LSTM, and the specific model can be determined based on actual conditions.

[0126] In some optional embodiments, the above-mentioned step S302 "predicting the power consumption of the power load of the integrated energy station in the second time period of the peak power consumption, and determining the predicted power consumption of the power load at each time point in the second time period" may also include the following steps B1 to B2 in addition to steps S3021 to S3023.

[0127] Step B1, extracting high-frequency characteristic values ​​of historical power consumption.

[0128] Step B2, combining the high-frequency characteristic value and the corresponding power correction power into a two-dimensional power characteristic.

[0129] Furthermore, the above-mentioned step S3023 "predicting the power consumption of the power load in the second time period based on the power consumption corrected power of the power load at each time point in the historical time period" may specifically include: predicting the power consumption of the power load in the second time period based on the two-dimensional power characteristics of the power load at each time point in the historical time period.

[0130] In this embodiment, the power change of the power load also has a certain frequency characteristic. In order to be able to use this frequency characteristic to perform power prediction, so that the predicted power of the second time period can also have a similar frequency characteristic, and to ensure the accuracy of the prediction result, the high-frequency characteristic value of the historical power of power consumption is also extracted, and combined with the corresponding power correction power, it can be combined into a two-dimensional power feature, that is, the two-dimensional power feature includes the power correction power and the high-frequency characteristic value. When performing power prediction, power prediction is achieved based on the two-dimensional power characteristics at each time point.

[0131] For example, for the i-th time point in the historical time period, based on the historical power consumption In addition to calculating the power correction In addition, you can also view the power consumption history Extract the corresponding high-frequency eigenvalues , and then the two-dimensional power characteristics of the i-th time point can be generated .

[0132] Optionally, high-frequency characteristic values ​​are extracted by convolution processing, and the above step B1 "extracting high-frequency characteristic values ​​of historical power consumption" specifically includes the following steps B11 to B14.

[0133] Step B11, construct multiple convolution kernels for extracting high-frequency features.

[0134] In this embodiment, for the historical power consumption at multiple time points in the historical time period, a corresponding sequence can be formed, that is, a historical power sequence. It can be understood that the historical power sequence includes multiple historical power consumptions arranged in chronological order; for example, the historical power sequence can be expressed as The historical power sequence has certain frequency characteristics, but since it is not possible to directly determine which frequency characteristics have the greatest impact on the historical power sequence, in this embodiment, multiple convolution kernels for extracting high-frequency features are pre-set, and different convolution kernels are used to extract high-frequency features corresponding to different frequencies.

[0135] Among them, since the historical power sequence is a one-dimensional sequence, each convolution kernel is also a one-dimensional convolution kernel.

[0136] Optionally, for any convolution kernel, the convolution kernel includes 2N+1 elements, N is a positive integer, that is, the convolution kernel includes an odd number of elements; and, for different convolution kernels, the number of elements 2N+1 is also different, that is, N is different, which will be explained later.

[0137] And, the i-th element in the convolution kernel It is expressed as the following formula (3):

[0138] (3)

[0139] Where:

[0140] is the frequency factor corresponding to the convolution kernel, and different convolution kernels correspond to different frequency factors ;

[0141] is the adjustment factor, and ,For example, or 2 etc.;

[0142] N is a positive integer, and N is There is a negative correlation between them.

[0143] In this embodiment, a corresponding frequency factor is set for each convolution kernel. , different frequency factors Corresponding to different frequencies, and the frequency factor The larger it is, the higher the frequency of features that can be extracted.

[0144] Specifically, as mentioned above, the i-th element in the convolution kernel Among them is a periodic function, the frequency factor can represent the period of the periodic function, and, is an exponential decay function, and reaches its maximum value when i=N+1 (at this time, is 1), so when i=N+1, the elements in the convolution kernel Maximum, as i increases or decreases, the elements in the convolution kernel The overall trend is gradually decreasing periodically.

[0145] In addition, the frequency factor The bigger it is, the The greater the frequency of change, the faster it will drop to a smaller value when looking from i=N+1 to both sides; to ensure that the convolution results of different convolution kernels for the same historical power sequence are comparable, the elements in the convolution kernel are Also increase the amplitude ,Right now , so that the elements in the convolution kernel with larger frequency Setting a larger amplitude can ensure the consistency of different convolution kernels.

[0146] In addition, to ensure that all elements in different convolution kernels For the same number of cycles, set N to There is a negative correlation between them, that is, the frequency factor The larger the value, the smaller N. Preferably, but not limited to, the value of N is obtained by the following formula (4):

[0147] (4)

[0148] Where:

[0149] is a rounding function, such as but not limited to a floor function, ;

[0150] An integer representing a setting.

[0151] Step B12, performing convolution processing on the historical power sequence according to each convolution kernel to generate a corresponding convolution result sequence; the historical power sequence includes the historical power consumption at each time point in the historical time period.

[0152] Step B13, selecting one from multiple convolution result sequences as a valid convolution result sequence; the larger the numerical value corresponding to the convolution result sequence, the higher the probability of being selected.

[0153] Step B14, taking the convolution result corresponding to each time point in the effective convolution result sequence as the high-frequency feature value corresponding to the corresponding time point.

[0154] For each convolution kernel, the historical power sequence can be convolved to generate a corresponding sequence, i.e., a convolution result sequence. Each element in the convolution result sequence corresponds to a convolution result. Moreover, the larger the value of the convolution result, the more relevant the corresponding historical power consumption is to the frequency corresponding to the convolution kernel, i.e., the more high-frequency characteristics the historical power sequence has related to the frequency, the greater its impact on the power consumption. Therefore, based on the values ​​in the convolution result sequence, a suitable convolution result sequence can be selected as a valid convolution result sequence, and the convolution result corresponding to each time point in the valid convolution result sequence is the high-frequency characteristic value corresponding to the corresponding time point.

[0155] Optionally, the above step B13 “selecting one from multiple convolution result sequences as a valid convolution result sequence” includes:

[0156] Step B131, respectively determining the extreme value of the convolution result in each convolution result sequence or the sum of all the convolution results in the convolution result sequence.

[0157] Step B132, taking the convolution result sequence corresponding to the largest extreme value or the largest sum of convolution results as the valid convolution result sequence.

[0158] In this embodiment, for the convolution result sequences determined by different convolution kernels, the larger the convolution result, the more obvious the corresponding high-frequency features. Therefore, the extreme value of the convolution result in each convolution result sequence (i.e., the maximum value in each convolution result sequence) can be determined, and the convolution result sequence corresponding to the largest extreme value can be used as the effective convolution result sequence finally selected. Alternatively, for each convolution result sequence, the sum of all the convolution results can be determined; if the sum of the convolution results of a convolution result sequence is the largest, the convolution result sequence can be used as the effective convolution result sequence.

[0159] Step S303: determining the predicted amount of electricity consumption required by the electricity load in the second time period according to the predicted power consumption of the electricity load at each time point in the second time period.

[0160] For details, see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0161] Step S304, determining whether the current power consumption exceeds the predicted power consumption.

[0162] For details, see Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0163] Step S305, when the current power consumption does not exceed the predicted power consumption, the energy storage system is charged to charge the power of the energy storage system to be not less than the predicted power consumption.

[0164] For details, see Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0165] In addition, optionally, since the integrated energy station is a system that integrates multiple energy devices and optimizes and dispatches them, in addition to wind power and photovoltaic power generation equipment, it can also drive gas turbines, gas internal combustion engines, gas boilers, etc. through natural gas to meet the needs of cold and hot loads. Among them, the integrated energy station is generally equipped with a waste heat recovery system and an electric refrigerator. The waste heat recovery system gives priority to supplying the heat load, and when there is a surplus, the absorption refrigerator is used to supply the cold load. The electric refrigerator can supplement the cold load energy supply when the waste heat recovery system cannot meet the cold load. The electric refrigerator is also a power-consuming device and also requires electricity. This embodiment also includes a process for predicting the power of the electric refrigerator, which specifically includes the following steps C1 to C3.

[0166] Step C1, predicting the load powers of the cooling load and the heating load of the integrated energy station in the second time period respectively, and determining the load prediction powers of the cooling load and the heating load at each time point in the second time period.

[0167] Step C2, determining the predicted power consumption of the electric refrigeration machine of the integrated energy station according to the predicted power of the cooling load and the heating load at each time point in the second time period.

[0168] In addition, the predicted power consumption of the electric refrigerator is expressed by the following formula (5):

[0169] (5)

[0170] Where:

[0171] represents the predicted power consumption of the electric refrigerator at the i-th time point in the second time period,

[0172] represents the load forecast power (a kind of cooling power) of the cooling load at the i-th time point in the second time period,

[0173] represents the load forecast power (a kind of heating power) of the heat load at the i-th time point in the second time period,

[0174] Indicates the gas power of the integrated energy station,

[0175] Indicates the efficiency of the heat exchanger of the integrated energy station,

[0176] represents the efficiency of the absorption chiller in the integrated energy station,

[0177] represents the efficiency of the electric refrigerator,

[0178] Represents a function that seeks a larger value.

[0179] Step C3, determining the predicted amount of power consumption required by the electric refrigerator in the second time period according to the predicted power consumption of the electric refrigerator at each time point in the second time period.

[0180] In addition, the above step S305 "charging the energy storage system when the current power does not exceed the predicted power consumption" specifically includes: charging the energy storage system when the current power does not exceed the sum of the predicted power consumption and the predicted power consumption.

[0181] In this embodiment, the power prediction of the electric refrigerator is realized by predicting the power of the cooling load and the heating load. Specifically, the load power of the two can be predicted based on the historical information of the cooling load and the heating load of the integrated energy station, so that the cooling power of the cooling load at the i-th time point in the second time period in the future, that is, the load prediction power of the cooling load can be predicted. , and the heating power of the heat load, that is, the load prediction power of the heat load .

[0182] Among them, the heat load is supplied by the heat exchanger of the integrated energy station, and the heat exchanger has a certain efficiency. , so the actual power required for the heat load is . Gas power of integrated energy station , is the total power provided by the gas turbine, gas internal combustion engine and gas boiler of the integrated energy station, which is mainly for heat load supply. Therefore, the power that can be provided to the absorption chiller in the gas power is ; And, to avoid the load forecast power of thermal load caused by forecast deviation Larger, making the power is less than 0, so the larger value between it and 0 is taken as the power provided to the absorption refrigeration machine, that is, , Represents a function that seeks a larger value.

[0183] In addition, since the absorption chiller also has a certain efficiency , so the load prediction power of the cooling load The power that the absorption chiller can provide is , the remaining power is the power required to be provided by the electric refrigerator. If the efficiency of the electric refrigerator is , the predicted power consumption is , then at the i-th time point, the power that the electric refrigerator can provide for the cooling load is , which is .

[0184] Based on this, the predicted power consumption of the electric refrigerator at the i-th time point can be determined: Specifically, it is expressed as the above formula (5).

[0185] Determine the predicted power consumption at each time point in the second time period After that, the total power required by the electric refrigerator in the second time period can be predicted and calculated, that is, the predicted power consumption.

[0186] Correspondingly, in the second time period in the future, the energy storage system can supply power to the electric refrigerator, that is, provide the predicted amount of electricity consumption. Therefore, in step S304, it is specifically determined whether the current power exceeds the sum of the predicted amount of electricity consumption and the predicted amount of electricity consumption. If the current power does not exceed the sum of the predicted amount of electricity consumption and the predicted amount of electricity consumption, it means that the energy storage is insufficient and the energy storage system needs to be charged.

[0187] The method for predicting and controlling the integrated energy station provided in this embodiment calculates the current power of the energy storage system in the first time period when power consumption is not at peak, and predicts the power consumption in the second time period when power consumption is at peak. Based on the relationship between the two, it is possible to determine whether the power of the energy storage system is sufficient, and provide a basis for subsequent charging decisions, so as to efficiently utilize the resources of the integrated energy station itself, reduce dependence on the mains, and reduce the impact on the mains during peak power consumption periods, which is beneficial to the peak shaving and valley filling of the mains power grid. By correcting the predicted power consumption, the impact of fluctuations therein on subsequent predictions can be reduced, and the accuracy of subsequent prediction results can be guaranteed; the high-frequency features of the historical power sequence are extracted using the convolution kernel, which not only enables the prediction process to refer to the high-frequency features of the sequence, but also facilitates calculations, and can use GPUs and other devices to implement parallel processing, which can improve calculation efficiency.

[0188] In Example 3 of the present invention, a device for predicting and controlling an integrated energy station is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0189] This embodiment provides a device for predicting and controlling an integrated energy station, such as Figure 6 As shown, including:

[0190] The power determination module 601 is used to determine the current power of the energy storage system of the integrated energy station in a first time period; the first time period is a time period that is not a peak power consumption period;

[0191] The prediction module 602 is used to predict the power consumption of the power load of the integrated energy station in the second time period of peak power consumption, and determine the predicted power consumption of the power load at each time point in the second time period; according to the predicted power consumption of the power load at each time point in the second time period, determine the predicted amount of power consumption required by the power load in the second time period;

[0192] A judgment module 603 is used to judge whether the current power consumption exceeds the predicted power consumption;

[0193] The processing module 604 is used to charge the energy storage system when the current power consumption does not exceed the predicted power consumption, so as to charge the power of the energy storage system to be not less than the predicted power consumption.

[0194] In some optional implementations, the prediction module 602 predicts the power consumption of the power load of the integrated energy station in a second time period of peak power consumption, and determines the predicted power consumption of the power load at each time point in the second time period, including:

[0195] Obtaining the historical power consumption of the power load at each time point in the historical time period;

[0196] Correcting the historical power consumption to generate corrected power consumption;

[0197] The power consumption of the power load in the second time period is predicted based on the power consumption corrected power of the power load at each time point in the historical time period, and the power consumption predicted power of the power load at each time point in the second time period is determined.

[0198] In some optional implementations, the prediction module 602 corrects the historical power consumption to generate corrected power consumption, including:

[0199] The historical power consumption at the first time point in the historical time period , add Gaussian noise that conforms to the Gaussian distribution , generate the power consumption history at the first time point Corresponding power correction ;

[0200] The power consumption correction at the i-1th time point Based on the historical power consumption at the i-th time point Generate the power consumption history at the i-th time point Corresponding power correction ;

[0201] And, the power correction power at the i-th time point is It is expressed as the following formula (6):

[0202] (6)

[0203] Where:

[0204] represents the historical power consumption at the i-1th time point,

[0205] k is an adjustment coefficient not less than 0, for example, k=1 or 2.

[0206] In some optional implementations, the prediction module 602 predicts the power consumption of the power load of the integrated energy station in the second time period of peak power consumption, and determines the predicted power consumption of the power load at each time point in the second time period, and further includes:

[0207] Extracting high-frequency characteristic values ​​of the historical power consumption;

[0208] Combining the high frequency characteristic value with the corresponding power consumption correction power into a two-dimensional power characteristic;

[0209] The prediction module 602 predicts the power consumption of the power load in the second time period according to the power consumption corrected power of the power load at each time point in the historical time period, including:

[0210] The power consumption of the power load in the second time period is predicted according to the two-dimensional power characteristics of the power load at each time point in the historical time period.

[0211] In some optional implementations, the prediction module 602 extracts the high-frequency characteristic value of the historical power consumption, including:

[0212] Construct multiple convolution kernels for extracting high-frequency features;

[0213] According to each of the convolution kernels, convolution processing is performed on the historical power sequence to generate a corresponding convolution result sequence; the historical power sequence includes the historical power consumption at each time point in the historical time period;

[0214] Selecting one from the multiple convolution result sequences as a valid convolution result sequence; the larger the value corresponding to the convolution result sequence is, the higher the probability of being selected;

[0215] The convolution result corresponding to each time point in the effective convolution result sequence is used as the high-frequency feature value corresponding to the corresponding time point.

[0216] In some optional embodiments, the convolution kernel includes 2N+1 elements, and the i-th element in the convolution kernel is It is expressed as the following formula (7):

[0217] (7)

[0218] Where:

[0219] is the frequency factor corresponding to the convolution kernel, and different convolution kernels correspond to different frequency factors ;

[0220] is the adjustment factor, and ,For example, or 2 etc.;

[0221] N is a positive integer, and there is a negative correlation between N and a.

[0222] In some optional implementations, the prediction module 602 selects one from the multiple convolution result sequences as a valid convolution result sequence, including:

[0223] Respectively determining the extreme value of the convolution result in each of the convolution result sequences or the sum of all the convolution results in the convolution result sequence;

[0224] The convolution result sequence corresponding to the largest extreme value or the largest sum of convolution results is taken as the valid convolution result sequence.

[0225] In some optional implementations, the prediction module 602 is further used to: respectively predict the load power of the cooling load and the heating load of the integrated energy station in the second time period, and determine the load prediction power of the cooling load and the heating load at each time point in the second time period;

[0226] According to the load prediction power of the cooling load and the heating load at each time point in the second time period, the power consumption prediction of the electric refrigeration machine of the integrated energy station is determined, which is expressed by the following formula (8):

[0227] (8)

[0228] Where:

[0229] represents the predicted power consumption of the electric refrigerator at the i-th time point in the second time period,

[0230] represents the load forecast power of the cooling load at the i-th time point in the second time period,

[0231] represents the load forecast power of the heat load at the i-th time point in the second time period,

[0232] represents the gas power of the integrated energy station,

[0233] represents the electric-to-heat conversion efficiency of the heat exchanger of the integrated energy station,

[0234] represents the electric-to-cooling conversion efficiency of the absorption chiller of the integrated energy station,

[0235] represents the electric-to-cooling conversion efficiency of the electric refrigerator,

[0236] Represents a function that seeks a larger value.

[0237] Determining a predicted amount of power consumption required by the electric refrigerator in the second time period according to the predicted power consumption of the electric refrigerator at each time point in the second time period;

[0238] When the current power consumption does not exceed the predicted power consumption, the processing module 604 charges the energy storage system, including:

[0239] When the current power amount does not exceed the sum of the predicted power usage amount and the predicted power consumption amount, the energy storage system is charged.

[0240] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0241] The device of the predictive control integrated energy station in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, including a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0242] The embodiment of the present invention also provides a computer device, see Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0243] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0244] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0245] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0246] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0247] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0248] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device may be a touch screen.

[0249] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0250] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined in this application.

Claims

1. A method for predicting and controlling an integrated energy station, characterized in that: The method comprises the following steps: In a first time period, determining the current power of the energy storage system of the integrated energy station; the first time period is a time period that is not a peak time period; Predicting the power consumption of the power load of the integrated energy station in a second time period of peak power consumption, and determining the predicted power consumption of the power load at each time point in the second time period, including: obtaining the power consumption history power of the power load at each time point in the historical time period; correcting the power consumption history power to generate power consumption correction power, including: The historical power consumption at the first time point in the historical time period , add Gaussian noise that conforms to the Gaussian distribution , generate the power consumption history at the first time point Corresponding power correction ; The power consumption correction at the i-1th time point Based on the historical power consumption at the i-th time point Generate the power consumption history at the i-th time point Corresponding power correction , expressed as the following formula (1): (1) Where: represents the historical power consumption at the i-1th time point, k is an adjustment coefficient not less than 0; According to the power consumption corrected power of the power load at each time point in the historical time period, the power consumption power of the power load in the second time period is predicted, and the power consumption predicted power of the power load at each time point in the second time period is determined; Determining whether the current power consumption exceeds the predicted power consumption; When the current power amount does not exceed the predicted power consumption amount, the energy storage system is charged to charge the power of the energy storage system to a level not less than the predicted power consumption amount.

2. A method for predicting and controlling an integrated energy station according to claim 1, characterized in that: Determining the predicted power consumption of the power load at each time point in the second time period also includes: Extracting high-frequency characteristic values ​​of the historical power consumption; Combining the high frequency characteristic value with the corresponding power consumption correction power into a two-dimensional power characteristic; The predicting of the power consumption of the power load in the second time period according to the power consumption corrected power of the power load at each time point in the historical time period includes: The power consumption of the power load in the second time period is predicted according to the two-dimensional power characteristics of the power load at each time point in the historical time period.

3. A method for predicting and controlling an integrated energy station according to claim 2, characterized in that: The step of extracting the high-frequency characteristic value of the historical power consumption includes: Construct multiple convolution kernels for extracting high-frequency features; According to each of the convolution kernels, convolution processing is performed on the historical power sequence to generate a corresponding convolution result sequence; the historical power sequence includes the historical power consumption at each time point in the historical time period; Selecting one from the plurality of convolution result sequences as a valid convolution result sequence includes: determining the extreme value of the convolution result in each of the convolution result sequences or the sum of all the convolution results in the convolution result sequence; and taking the convolution result sequence corresponding to the maximum extreme value or the maximum sum of the convolution results as a valid convolution result sequence; The larger the value corresponding to the convolution result sequence is, the higher the probability of being selected is; The convolution result corresponding to each time point in the effective convolution result sequence is used as the high-frequency feature value corresponding to the corresponding time point.

4. A method for predicting and controlling an integrated energy station according to claim 3, characterized in that: The convolution kernel includes 2N+1 elements, and the i-th element in the convolution kernel is It is expressed as the following formula (2): (2) Where: is the frequency factor corresponding to the convolution kernel, and different convolution kernels correspond to different frequency factors ; is the adjustment factor, and ; N is a positive integer, and N is There is a negative correlation between them.

5. The method for predicting and controlling an integrated energy station according to claim 3, characterized in that: The method further comprises: Predicting the load power of the cooling load and the heating load of the integrated energy station in the second time period respectively, and determining the load prediction power of the cooling load and the heating load at each time point in the second time period; According to the load prediction power of the cooling load and the heating load at each time point in the second time period, the power consumption prediction of the electric refrigeration machine of the integrated energy station is determined to be expressed by the following formula (3): (3) Where: represents the predicted power consumption of the electric refrigerator at the i-th time point in the second time period, represents the load forecast power of the cooling load at the i-th time point in the second time period, represents the load forecast power of the heat load at the i-th time point in the second time period, Indicates the gas power of the integrated energy station, Indicates the efficiency of the heat exchanger of the integrated energy station, represents the efficiency of the absorption chiller in the integrated energy station, represents the efficiency of the electric refrigerator, represents a function that seeks a larger value; Determining a predicted amount of power consumption required by the electric refrigerator in the second time period according to the predicted power consumption of the electric refrigerator at each time point in the second time period; When the current power consumption does not exceed the predicted power consumption, charging the energy storage system includes: When the current power amount does not exceed the sum of the predicted power usage amount and the predicted power consumption amount, the energy storage system is charged.

6. A device for predicting and controlling an integrated energy station, which runs the method for predicting and controlling an integrated energy station according to any one of claims 1 to 5, characterized in that: The device comprises: The power determination module is used to determine the current power of the energy storage system of the integrated energy station in a first time period; the first time period is a time period that is not a peak power consumption period; A prediction module, used to predict the power consumption of the power load of the integrated energy station in a second time period of peak power consumption, and determine the predicted power consumption of the power load at each time point in the second time period; and determine the predicted amount of power consumption required by the power load in the second time period according to the predicted power consumption of the power load at each time point in the second time period; A judgment module, used to judge whether the current power consumption exceeds the predicted power consumption; The processing module is used to charge the energy storage system when the current power consumption does not exceed the predicted power consumption, so as to charge the power of the energy storage system to be not less than the predicted power consumption.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for predictive control of an integrated energy station according to any one of claims 1 to 5 by executing the computer instructions.

Images