Power equipment load scheduling method and system based on big data analysis

Abstract

The invention relates to the technical field of power load scheduling, and discloses a power equipment load scheduling method and system based on big data analysis. The method comprises the following steps: predicting a power load at a future moment in a selected dispatching area through a multi-feature time sequence machine learning model, judging whether a power load insufficient supply prompt is generated or not, and judging whether an available standby power supply exists or not by combining power supply parameters of the standby power supply according to the power load insufficient supply condition; performing power load scheduling on the electric quantity in the standby power supply according to the scheduling duration; compared with the prior art, the potential safety hazard of power load insufficiency possibly occurring in the selected dispatching area in the future can be found in time in advance, and power load dispatching remedial measures are taken for the power load insufficiency, so that the situation that the power load in the selected dispatching area increases instantly at a certain moment is avoided. Therefore, the negative influence caused by the lagging of the power load dispatching is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of power load dispatching, and more specifically, to a method and system for power equipment load dispatching based on big data analysis. Background Art

[0002] Power load dispatch refers to the reasonable arrangement of power production and consumption according to the power demand and supply situation in the power consumption area, so as to ensure the stable operation of the power system in the power consumption area and meet the power demand of different regions. In the power load dispatch of the power consumption area, it is necessary to flexibly adjust the supply and demand relationship between the power station and the power consumption area, and carry out corresponding dispatch and management of the power load according to different regions, so as to improve the utilization efficiency of power resources and realize the efficient dispatch of power load in the power consumption area.

[0003] A Chinese patent with publication number CN116544934A discloses a power dispatching method and system based on power load forecasting. It optimizes the power supply plan based on multiple fitness constructed, obtains the recommended power supply plan for power dispatching, and realizes that through power load forecasting, the peak and valley values ​​of power demand can be better predicted, thereby improving the refinement of power supply dispatching control.

[0004] The prior art has the following deficiencies:

[0005] Since the power loads in different areas of the power consumption area are set according to pre-statistical data, real-time monitoring of power load operation data provides data support for subsequent power load scheduling. When a short-term power consumption peak occurs in a certain area of ​​the power consumption area, causing the power load in the area to increase instantly, the power dispatching center cannot accurately predict the power load data in the area in advance, resulting in a lag in power load dispatching management operations, and it is impossible to implement the power supply dispatching plan in advance, which can easily lead to irreversible economic and property losses.

[0006] In view of this, the present invention proposes a power equipment load scheduling method and system based on big data analysis to solve the above problems. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a power equipment load scheduling method based on big data analysis, applied to a power monitoring server, the method comprising:

[0008] S1: pre-collect historical power load data of the selected dispatching area, where the historical power load data includes comprehensive power consumption data and power load corresponding to the comprehensive power consumption data;

[0009] S2: Based on historical power load data, a machine learning model is trained to predict the power load at future times, and the power load at future times is predicted based on the trained machine learning model;

[0010] S3: Compare and analyze the predicted future power load with the preset selected dispatching area load threshold to generate a power load gap value, and determine whether to generate a power load supply shortage prompt based on the power load gap value. If generated, execute S4; if not, repeat S3;

[0011] S4: Collect the power supply parameters of b backup power sources corresponding to the selected dispatching area, generate b dispatchable power supplies based on the power supply parameters, compare and analyze the b dispatchable power supplies with the power load gap value one by one, and determine whether there is an available backup power source. If so, execute S5; if not, execute S6;

[0012] S5: Collect the first power supply preparation time of t available backup power sources, t∈b, compare and analyze the t first power supply preparation time with the preset preparation time threshold, generate m first scheduling time, m∈t, and select the available backup power source corresponding to the first scheduling time ranked first after descending order for power load scheduling;

[0013] S6: Collect the second power supply preparation time and power supply distance of b backup power sources, calculate and generate b second scheduling time periods one by one, and accumulate the dispatchable power supply of the backup power sources corresponding to c second scheduling time periods one by one in ascending order, c∈b, until the sum of the c dispatchable power supply is greater than or equal to the power load gap value, stop accumulating, and perform power load scheduling on the backup power sources corresponding to the c second scheduling time periods.

[0014] Furthermore, the comprehensive electricity consumption data includes production electricity consumption data, public electricity consumption data and temperature control electricity consumption data;

[0015] The training method of the machine learning model for predicting power load at future moments includes:

[0016] Arrange the comprehensive electricity consumption data according to the collection time, and preset the prediction time step K, sliding step P and sliding window length N; convert the comprehensive electricity consumption data into multiple training samples using the sliding window method, and convert the power load into labels corresponding to the comprehensive electricity consumption data according to the sliding step P. One training sample corresponds to one label and constitutes a group of training data, and multiple groups of training data constitute a training set;

[0017] The training samples are used as the input of the multi-feature time series prediction machine learning model, and the power load at future moments is used as the output of the multi-feature time series prediction machine learning model. The power load at future moments is taken as the prediction target, and minimizing the sum of prediction accuracies of all training data is taken as the training target. The multi-feature time series prediction machine learning model is trained until the sum of prediction accuracies converges and the training is stopped.

[0018] Furthermore, the generation method of the power load gap value includes:

[0019] Preset the selected dispatch area load threshold, denoted as FH yz ;

[0020] The predicted future power load FH wl Compare the difference with the preset load threshold of the selected dispatching area to obtain the power load gap value;

[0021] The expression of power load gap value is: FH qk =FH wl -FH yz ;

[0022] Where FH qk is the power load gap value.

[0023] Further, the method for determining whether to generate a prompt of insufficient power load supply includes:

[0024] When FH qk When >0, an insufficient power load supply prompt is generated;

[0025] When FH qk When ≤0, no power load supply shortage prompt is generated.

[0026] Furthermore, the power supply parameters include power supply margin and power supply loss;

[0027] Methods for obtaining power loss include:

[0028] Divide the cable between the backup power source and the power line of the selected dispatching area into W sub-loss areas of equal length, and mark Q sub-loss areas consecutively and number them, where Q is an integer multiple of 2;

[0029] The instantaneous currents of all the sub-loss areas with odd numbers are obtained in sequence through the current sensor, and the cable resistances of all the sub-loss areas with even numbers are obtained in sequence through the resistance measuring instrument. The instantaneous currents and the cable resistances are respectively accumulated and averaged to obtain the loss current and loss resistance.

[0030] Obtain the power supply distance from b backup power sources to the selected dispatching area through the power dispatching center:

[0031] The expression of loss current is:

[0032] In the formula, I shb is the loss current of the bth backup power supply, X bi is the instantaneous current of the ith sub-loss area of ​​the bth backup power supply;

[0033] The expression for loss resistance is:

[0034] In the formula, R shb is the loss current of the bth backup power supply, T bi is the cable resistance of the ith sub-loss zone of the bth backup power source;

[0035] The expression of power loss is:

[0036] Where P shb is the power loss of the bth backup power supply, L shb is the power supply distance of the bth backup power supply;

[0037] Methods for obtaining dispatchable power supply include:

[0038] The expression of dispatchable power supply is: P ddb =P ylb -P shb ;

[0039] Where P ddb is the dispatchable power supply of the bth backup power source, P ylb is the power margin of the bth backup power supply.

[0040] Furthermore, the method for determining whether there is an available backup power supply includes:

[0041] When P ddb ≥FH qk When a backup power supply is available;

[0042] When P ddb <FH qk When no backup power is available.

[0043] Furthermore, the method for generating the first scheduling duration includes:

[0044] Obtain the first power supply preparation time SJ through the power dispatch center zbt1 , the first power supply preparation time and the preset preparation time threshold SJ yz Perform difference comparison;

[0045] When SJ yz ≥SJ zbt1 When , the first scheduling duration is generated;

[0046] The expression of the first scheduling duration is: SJ ddm1 =SJ yz -SJ zbt1 ;

[0047] In the formula, SJ ddm1 is the first dispatch duration of the mth available backup power source, SJ zbt1 The first power supply preparation time for the tth available backup power source;

[0048] When SJ yz <SJ zbt1 The first scheduling duration is not generated.

[0049] Furthermore, the method for generating the second scheduling duration includes:

[0050] Obtain the second power supply preparation time and power supply distance of b backup power sources through the power dispatching center, and calculate the second dispatching time according to the formula based on the second power supply preparation time and power supply distance;

[0051] The expression of the second scheduling duration is:

[0052]

[0053] In the formula, SJ ddb2 is the second dispatching duration of the bth backup power source, SJ zbb2 The second power supply preparation time for the bth backup power source, is the weight factor.

[0054] Furthermore, the method for performing power load scheduling using the backup power sources corresponding to the c second scheduling durations includes:

[0055] When the c second scheduling durations are all inconsistent, the backup power sources corresponding to the c second scheduling durations are sequentially scheduled for power load in ascending order;

[0056] When there are x second scheduling durations of the same size, x∈c, the power load of the backup power supplies corresponding to the c second scheduling durations are scheduled in ascending order, and when the power load is scheduled to the backup power supplies corresponding to the x second scheduling durations of the same size, the x backup power supplies are scheduled at the same time.

[0057] The power equipment load dispatching system based on big data analysis is applied to the power dispatching center to implement the above-mentioned power equipment load dispatching method based on big data analysis, including a first data acquisition module, a second data acquisition module, a model training module, a load analysis module, a first load dispatching module and a second load dispatching module, wherein each module is connected through a wired and / or wireless network;

[0058] A first data collection module collects historical power load data of a selected dispatching area in advance, wherein the historical power load data includes comprehensive power consumption data and power load corresponding to the comprehensive power consumption data;

[0059] The second data collection module collects the power supply parameters of the b backup power sources corresponding to the selected scheduling area, and generates b dispatchable power supply amounts based on the power supply parameters;

[0060] The model training module trains a machine learning model for predicting future power loads based on historical power load data, and predicts future power loads based on the trained machine learning model;

[0061] The load analysis module compares and analyzes the predicted future power load with the preset selected dispatching area load threshold, generates a power load gap value, and determines whether to generate a power load supply shortage prompt based on the power load gap value, and compares and analyzes the b dispatchable power supplies with the power load gap value one by one to determine whether there is an available backup power supply;

[0062] The first load scheduling module collects the first power supply preparation time of t available backup power sources, compares and analyzes the t first power supply preparation time with a preset preparation time threshold, generates m first scheduling time, and selects the available backup power source corresponding to the first scheduling time ranked first after being sorted in descending order for power load scheduling;

[0063] The second load scheduling module collects the second power supply preparation time and power supply distance of b backup power supplies, calculates and generates b second scheduling time periods one by one, and accumulates the dispatchable power supply of the backup power supplies corresponding to c second scheduling time periods one by one in ascending order until the sum of the c dispatchable power supplies is greater than or equal to the power load gap value, and stops accumulating, and performs power load scheduling on the backup power supplies corresponding to the c second scheduling time periods.

[0064] Technical effects and advantages of the power equipment load dispatching method and system based on big data analysis of the present invention:

[0065] The present invention predicts the future power load in the selected scheduling area through a multi-feature time series machine learning model, and analyzes and obtains the power load gap value based on the predicted future power load, determines whether to generate a prompt of insufficient power load supply, and at the same time, for the insufficient power load supply, determines whether there is an available backup power supply in combination with the power supply parameters of the backup power supply, and performs power load dispatching on the power in the backup power supply according to the dispatching duration to meet the power load required by the selected scheduling area. Compared with the prior art, the present invention can timely and in advance discover the potential safety hazards of insufficient power load in the selected scheduling area in the future, and perform power load dispatching remedial measures for insufficient power load, thereby avoiding irreparable economic and property losses in the selected scheduling area after the power load in the selected scheduling area increases instantly at a certain moment, and avoiding the negative impact caused by the lag of power load dispatching. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a schematic diagram of a method for load dispatching of electric power equipment based on big data analysis of the present invention;

[0067] Figure 2 It is a schematic diagram of a power equipment load dispatching system based on big data analysis of the present invention;

[0068] Figure 3 A schematic diagram of a structural diagram of an electronic device provided in Embodiment 3 of the present invention;

[0069] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0070] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] Example 1

[0072] See also Figure 1 As shown, the power equipment load scheduling method based on big data analysis described in this embodiment is applied to a power monitoring server, and the method includes:

[0073] S1: In the experimental environment, the historical power load data of the selected dispatching area is collected in advance. The historical power load data includes comprehensive power consumption data and power load. The comprehensive power consumption data includes production power consumption data, public power consumption data and temperature control power consumption data;

[0074] Production power consumption data refers to the power consumption data generated by factories, enterprises and other manufacturing industries in the selected dispatching area when they are engaged in production and processing. When the number of manufacturing industries that start production and manufacturing in the selected dispatching area in the same time period is more, the production power consumption data is larger, and the power load of the selected dispatching area is also larger; the production power consumption data is obtained by accumulating the power consumption data of all manufacturing industries in the selected dispatching area by retrieving them at the power dispatching center;

[0075] Public power consumption data refers to the power consumption data generated by public places such as roads and hospitals in the selected dispatching area when engaged in production and processing. The more people and equipment are in the public places in the selected dispatching area during the same time period, the larger the public power consumption data is, and the greater the power load in the selected dispatching area is; public power consumption data is obtained by accumulating the power consumption data of all public places in the selected dispatching area by retrieving them at the power dispatching center;

[0076] The temperature control power consumption data refers to the power consumption data of the equipment used to reduce or increase the indoor and outdoor temperatures in the selected dispatching area. When the number of equipment that reduces or increases the indoor and outdoor temperatures in the selected dispatching area is more, the temperature control power consumption data is larger, and the power load of the selected dispatching area is also larger; the temperature control power consumption data is obtained by accumulating the power consumption data of all public places in the selected dispatching area by calling the power dispatching center;

[0077] The power load is used to indicate the electricity consumption of the selected dispatching area within a certain period of time, including the accumulated production power consumption data, public power consumption data and temperature control power consumption data; the power load is retrieved from the power dispatching center.

[0078] S2: Based on historical power load data, a machine learning model is trained to predict the power load at future times, and the power load at future times is predicted based on the trained machine learning model;

[0079] The training method of the machine learning model for predicting power load at future moments includes:

[0080] The comprehensive electricity consumption data is used as the input of the multi-feature time series prediction machine learning model, and the power load at the future moment is used as the output of the multi-feature time series prediction machine learning model. The power load at the future moment is used as the prediction target, and the sum of the prediction accuracies of all training data is minimized as the training target. The multi-feature time series prediction machine learning model is trained until the sum of the prediction accuracies reaches convergence and the training is stopped;

[0081] The loss function value of the machine learning model is the mean square error;

[0082] Mean square error is one of the commonly used loss functions. By transforming the loss function formula Minimization is used as the goal to train the model so that the machine learning model better fits the data, thereby improving the performance and accuracy of the model;

[0083] In the loss function, MSE is the loss function value of the machine learning model, x is the feature vector group number; m is the number of feature vector groups; y is the number of feature vector groups; x is the future power load corresponding to the xth group of eigenvectors, is the future power load actually corresponding to the xth group of eigenvectors;

[0084] Other model parameters of the machine learning model, such as target loss value, optimization algorithm, ratio of training set, test set, validation set, and optimization of loss function, are obtained through actual engineering implementation and continuous experimental tuning.

[0085] Methods for predicting power load at future times include:

[0086] The comprehensive electricity consumption data is arranged according to the collection time, and the prediction time step K, sliding step P and sliding window length N are preset; the comprehensive electricity consumption data is converted into multiple training samples using the sliding window method, and the power load is converted into a label corresponding to the comprehensive electricity consumption data according to the sliding step P. One training sample corresponds to one label and constitutes a group of training data. Multiple groups of training data constitute a training set. The training samples are used as the input of the machine learning model, and the power load at the future moment after the prediction time step K is used as the output. The subsequent power load of each training set is used as the prediction target. The prediction accuracy is used as the training target to train the machine learning; a machine learning model is generated for predicting the power load at the future moment based on the comprehensive electricity consumption data;

[0087] Specifically, a simple example of the sliding window method is as follows: Assume that you want to use the comprehensive electricity consumption data (1, 2, 3, 4, 5, 6, 7) to train a time prediction model to predict the value of one time step in the future. You can use a sliding window of length 4 and a sliding step of length 1 to generate a predicted future training set and a prediction target. For example, the training set is (1, 2, 3, 4), (2, 3, 4, 5) and (3, 4, 5, 6), and the prediction targets are (5), (6) and (7);

[0088] The sliding window method can accurately and in advance predict the future power load based on the existing historical power data in the selected dispatching area, so as to obtain the power load change data in advance before the power load in the selected dispatching area increases instantly, which serves as the basis for the power dispatching center to dispatch the power load, thereby avoiding huge losses of economic property.

[0089] S3: Compare and analyze the predicted future power load with the preset selected dispatching area load threshold to generate a power load gap value, and determine whether to generate a power load supply shortage prompt based on the power load gap value. If a power load supply shortage prompt is generated, execute S4; if no power load supply shortage prompt is generated, repeat S3;

[0090] The generation methods of power load gap value include:

[0091] The preset load threshold of the selected dispatching area is denoted as FH yz , F.H. yz It is obtained after collecting multiple groups of historical power load data of the selected dispatching area, analyzing and judging, and can distinguish between insufficient and sufficient power load supply in the selected dispatching area. Therefore, the setting of the load threshold of the selected dispatching area is based on the analysis of the historical power load of the selected dispatching area. Its specific value is obtained by analyzing and calculating the historical power load data of the selected dispatching area, and needs to meet the power load demand of the selected dispatching area under normal circumstances.

[0092] The predicted future power load FH wl Compare the difference with the preset load threshold of the selected dispatching area to obtain the power load gap value;

[0093] The expression of power load gap value is: FH qk =FH wl -FH yz ;

[0094] Where FH qk is the power load gap value;

[0095] Methods for determining whether to generate a warning of insufficient power load supply include:

[0096] When FH qk >0, it means that the power load at the future moment is greater than the preset load threshold of the selected dispatching area. At this time, the power load in the selected dispatching area will be undersupplied, and a prompt of insufficient power load supply will be generated;

[0097] When FH qk When ≤0, it means that the power load at the future moment is less than or equal to the preset load threshold of the selected dispatching area. At this time, the power load in the selected dispatching area will not be undersupplied, and no power load undersupplied prompt will be generated;

[0098] S4: Collect the power supply parameters of b backup power sources corresponding to the selected dispatching area, generate b dispatchable power supplies based on the power supply parameters, compare and analyze the b dispatchable power supplies with the power load gap value one by one, and determine whether there is an available backup power source. If there is an available backup power source, execute S5; if not, execute S6;

[0099] The backup power source in the selected dispatching area refers to an energy reserve station that is deployed within the power load dispatching range of the selected dispatching area and stores backup power. At the same time, when the power load supply in the selected dispatching area is insufficient, a dispatching instruction can be issued to the energy reserve station through the power dispatching center to dispatch the backup power of the energy reserve station to the selected dispatching area to meet the power load demand;

[0100] Power supply parameters include power supply margin and power supply loss;

[0101] The power supply margin refers to the power margin of the backup power supply at the current moment. In order to prevent the power in the backup power supply from being fully dispatched to the selected dispatching area, it is necessary to set a safe dispatching threshold for the power of the backup power supply, so that the safe dispatching threshold is less than the rated power of the backup power supply, to ensure that the backup power supply can still have enough power to maintain the standby state after dispatching. The more the power supply margin, the more power can be dispatched; the power supply margin is obtained by the power dispatching center by using the electric energy meter on the backup power supply;

[0102] Power supply loss refers to the loss caused by the transmission of available power on the power line when the backup power source dispatches the available power to the power line in the selected dispatching area. The greater the power supply loss, the less available power will be dispatched to the power line in the selected dispatching area.

[0103] Methods for obtaining power loss include:

[0104] Divide the cable between the backup power source and the power line of the selected dispatching area into W sub-loss areas of equal length, and mark and number Q sub-loss areas continuously (Q is an integer multiple of 2);

[0105] The instantaneous current of all the sub-loss zones with odd numbers is obtained in sequence through the current sensor, and the cable resistance of all the sub-loss zones with even numbers is obtained in sequence through the resistance measuring instrument. The instantaneous current and the cable resistance are respectively accumulated and averaged to obtain the loss current and the loss resistance. By collecting the instantaneous current of the odd-numbered sub-loss zones and the cable resistance of the even-numbered sub-loss zones, on the one hand, the amount of collected data can be reduced and the data processing time can be reduced. On the other hand, it can also avoid the phenomenon that the cable resistance in the same sub-monitoring zone changes too much due to the increase of the instantaneous current in the sub-monitoring zone, thereby ensuring the stability of the cable resistance and improving the calculation accuracy of the power supply loss.

[0106] The expression of loss current is:

[0107] In the formula, I shb is the loss current of the bth backup power supply, X bi is the instantaneous current of the ith sub-loss area of ​​the bth backup power supply;

[0108] The expression for loss resistance is:

[0109] In the formula, R shb is the loss current of the bth backup power supply, T bi is the cable resistance of the ith sub-loss zone of the bth backup power source;

[0110] Obtain the power supply distance from b backup power sources to the selected dispatching area through the power dispatching center, and calculate the power supply loss according to the formula;

[0111] The expression of power loss is:

[0112] Where P shb is the power loss of the bth backup power supply, L shb is the power supply distance of the bth backup power supply;

[0113] Methods for obtaining dispatchable power supply include:

[0114] The expression of dispatchable power supply is: P ddb =P ylb -P shb ;

[0115] Where P ddb is the dispatchable power supply of the bth backup power source, P ylb is the power margin of the bth backup power supply;

[0116] Methods for determining whether backup power is available include:

[0117] When P ddb ≥FH qk When , it means that the dispatchable power supply of the bth backup power source is greater than or equal to the power load gap value, and there is an available backup power source;

[0118] When P ddb <FH qk When , it means that the dispatchable power supply of the bth backup power source is less than the power load gap value, and there is no available backup power source;

[0119] It should be noted that the existence of available backup power sources means that the backup power sources in the selected scheduling area can be directly used to schedule power loads to the selected scheduling area, while the absence of available backup power sources means that the b backup power sources in the selected scheduling area cannot be directly used to schedule power loads to the selected scheduling area, but the dispatchable power supply of the b backup power sources needs to be subsequently processed before power loads can be scheduled to the selected scheduling area.

[0120] S5: Collect the first power supply preparation time of t available backup power sources, t∈b, compare and analyze the t first power supply preparation time with the preset preparation time threshold, generate m first scheduling time, m∈t, arrange the m first scheduling time in descending order, and select the available backup power source corresponding to the first-ranked first scheduling time for power load scheduling;

[0121] The first power supply preparation time refers to the time required for the remaining power of the backup power supply to start and connect to the power line of the selected dispatching area. The longer the time required for starting and connecting the backup power supply, the longer the first power supply preparation time. The first power supply preparation time is obtained by the power dispatching center of the backup power supply.

[0122] The preset preparation time threshold is denoted as SJ yz , S.J. yz The setting of SJ is based on the length of time that the selected dispatching area needs to dispatch the power load. When the selected dispatching area needs to dispatch the power load in a short time, SJ yz The smaller the value of , the opposite is true;

[0123] The method for obtaining the first scheduling duration includes:

[0124] When SJ yz ≥SJ zbt1 , indicating that the preset preparation time threshold is greater than or equal to the first power supply preparation time, then the first scheduling time is generated;

[0125] The expression of the first scheduling duration is: SJ ddm1 =SJ yz -SJ zbt1 ;

[0126] In the formula, SJ ddm1 is the first dispatch duration of the mth available backup power source, SJ zbt1 The first power supply preparation time for the tth available backup power source;

[0127] When SJ yz <SJ zbt1 , it indicates that the preset preparation time threshold is less than the first power supply preparation time, and the first scheduling time is not generated;

[0128] Arrange the generated m first scheduling durations in descending order, mark the first-ranked first scheduling duration, and select the available backup power source corresponding to the first-ranked first scheduling duration for power load scheduling.

[0129] S6: Collect the second power supply preparation time of b backup power sources, combine the power supply distance and the second power supply preparation time, generate b second scheduling time, arrange the b second scheduling time in ascending order, and accumulate the dispatchable power supply of the backup power sources corresponding to c second scheduling time in ascending order, c∈b, until the sum of the c dispatchable power supply is greater than or equal to the power load gap value, stop accumulating, and perform power load scheduling on the backup power sources corresponding to the c second scheduling time;

[0130] The method for generating the second scheduling duration includes:

[0131] Obtain the second power supply preparation time and power supply distance of b backup power sources through the power dispatching center, and calculate the second dispatching time according to the formula based on the second power supply preparation time and power supply distance;

[0132] The expression of the second scheduling duration is:

[0133]

[0134] In the formula, SJ ddb2 is the second dispatching duration of the bth backup power source, SJ zbb2 The second power supply preparation time for the bth backup power source, is the weight factor. Substitute the set weight factor and the collected request feature data into the formula. Any two formulas form a binary linear equation system. The calculated weight factors are screened and averaged to obtain The mean of

[0135] In addition, it should be noted that the size of the weight factor is a specific value obtained by quantifying each data, which is convenient for subsequent comparison. The size of the weight factor depends on the amount of requested feature data and the corresponding weight factor initially set by those skilled in the art for each set of requested feature data;

[0136] Exemplarily, Table 1 is a table of the dispatchable power supply of the backup power supply corresponding to the second scheduling duration, as follows:

[0137] Table 1 Dispatchable power supply of backup power source corresponding to the second dispatch duration

[0138]

[0139]

[0140] The specific values ​​in the table are all virtual values. The actual second scheduling duration and dispatchable power supply are obtained according to the actual situation.

[0141] The method for performing power load dispatching with a backup power source corresponding to c second dispatching durations includes:

[0142] When the c second scheduling durations are all inconsistent, the backup power sources corresponding to the c second scheduling durations are sequentially scheduled for power load in ascending order;

[0143] When there are x second scheduling durations of the same size, x∈c, the power load of the backup power sources corresponding to the c second scheduling durations are scheduled in ascending order, and when the power load is scheduled to the backup power sources corresponding to the x second scheduling durations of the same size, the x backup power sources are scheduled at the same time.

[0144] This embodiment predicts the future power load in the selected scheduling area through a multi-feature time series machine learning model, and analyzes the power load gap value based on the predicted future power load to determine whether to generate a prompt of insufficient power load supply. At the same time, in response to the insufficient power load supply, it is determined whether there is an available backup power supply in combination with the power supply parameters of the backup power supply, and the power load is dispatched according to the dispatching duration to meet the power load required by the selected scheduling area. Compared with the existing technology, it can timely and in advance discover the safety hazards of insufficient power load in the selected scheduling area that may occur in the future, and take remedial measures for power load dispatching for insufficient power load, thereby avoiding irreparable economic and property losses in the selected scheduling area after the power load in the selected scheduling area increases instantly at a certain moment, and avoiding the negative impact caused by the lag of power load dispatching.

[0145] Example 2

[0146] See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, and a power equipment load dispatching system based on big data analysis is provided, which is applied to a power dispatching center and is used to implement the above-mentioned power equipment load dispatching method based on big data analysis, including a first data acquisition module, a second data acquisition module, a model training module, a load analysis module, a first load dispatching module and a second load dispatching module, wherein each module is connected via a wired and / or wireless network;

[0147] A first data collection module collects historical power load data of a selected dispatching area in advance under an experimental environment, wherein the historical power load data includes comprehensive power consumption data and power load corresponding to the comprehensive power consumption data;

[0148] The second data collection module collects the power supply parameters of the b backup power sources corresponding to the selected scheduling area, and generates b dispatchable power supply amounts based on the power supply parameters;

[0149] The model training module trains a machine learning model for predicting future power loads based on historical power load data, and predicts future power loads based on the trained machine learning model;

[0150] The load analysis module compares and analyzes the predicted future power load with the preset selected dispatching area load threshold, generates a power load gap value, and determines whether to generate a power load supply shortage prompt based on the power load gap value, and compares and analyzes the b dispatchable power supplies with the power load gap value one by one to determine whether there is an available backup power supply;

[0151] The first load scheduling module collects the first power supply preparation time of t available backup power sources, compares and analyzes the t first power supply preparation time with a preset preparation time threshold, generates m first scheduling time, and selects the available backup power source corresponding to the first scheduling time ranked first after being sorted in descending order for power load scheduling;

[0152] The second load scheduling module collects the second power supply preparation time and power supply distance of b backup power supplies, calculates and generates b second scheduling time periods one by one, and accumulates the dispatchable power supply of the backup power supplies corresponding to c second scheduling time periods one by one in ascending order until the sum of the c dispatchable power supplies is greater than or equal to the power load gap value, and stops accumulating, and performs power load scheduling on the backup power supplies corresponding to the c second scheduling time periods.

[0153] Example 3

[0154] See also Figure 3 As shown, this embodiment discloses an electronic device, including: a processor and a memory;

[0155] Wherein, the memory stores a computer program that can be called by the processor;

[0156] The processor executes the power equipment load scheduling method based on big data analysis by calling the computer program stored in the memory.

[0157] Since the electronic device introduced in this embodiment is an electronic device used to implement the power equipment load dispatching method based on big data analysis in Example 1 of this application, based on the power equipment load dispatching method based on big data analysis introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the power equipment load dispatching method based on big data analysis in the embodiment of this application, it belongs to the scope of protection of this application.

[0158] Example 4

[0159] See also Figure 4 As shown, this embodiment discloses a computer-readable storage medium on which a rewritable computer program is stored;

[0160] When the computer program is run, the power equipment load scheduling method based on big data analysis is implemented.

[0161] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A power equipment load dispatching method based on big data analysis, applied to a power monitoring server, characterized in that: The method comprises: S1: pre-collect historical power load data of the selected dispatching area, where the historical power load data includes comprehensive power consumption data and power load corresponding to the comprehensive power consumption data; S2: Based on historical power load data, a machine learning model is trained to predict the power load at future times, and the power load at future times is predicted based on the trained machine learning model; S3: Compare and analyze the predicted future power load with the preset selected dispatching area load threshold to generate a power load gap value, and determine whether to generate a power load supply shortage prompt based on the power load gap value. If generated, execute S4; if not, repeat S3; S4: Collect the power supply parameters of b backup power sources corresponding to the selected dispatching area, generate b dispatchable power supplies based on the power supply parameters, compare and analyze the b dispatchable power supplies with the power load gap value one by one, and determine whether there is an available backup power source. If so, execute S5; if not, execute S6; S5: Collect the first power supply preparation time of t available backup power sources, t∈b, compare and analyze the t first power supply preparation time with the preset preparation time threshold, generate m first scheduling time, m∈t, and select the available backup power source corresponding to the first scheduling time ranked first after descending order for power load scheduling; S6: Collect the second power supply preparation time and power supply distance of b backup power sources, calculate and generate b second scheduling time periods one by one, and accumulate the dispatchable power supply of the backup power sources corresponding to c second scheduling time periods one by one in ascending order, c∈b, until the sum of the c dispatchable power supply is greater than or equal to the power load gap value, stop accumulating, and perform power load scheduling on the backup power sources corresponding to the c second scheduling time periods.

2. The method for power equipment load dispatching based on big data analysis according to claim 1 is characterized in that: Comprehensive electricity consumption data includes production electricity consumption data, public electricity consumption data and temperature control electricity consumption data; The training method of the machine learning model for predicting power load at future moments includes: Arrange the comprehensive electricity consumption data according to the collection time, and preset the prediction time step K, sliding step P and sliding window length N; The comprehensive electricity consumption data is converted into multiple training samples using a sliding window method, and the power load is converted into a label corresponding to the comprehensive electricity consumption data according to the sliding step size P. One training sample corresponds to one label and constitutes a group of training data, and multiple groups of training data constitute a training set; The training samples are used as the input of the multi-feature time series prediction machine learning model, and the power load at future moments is used as the output of the multi-feature time series prediction machine learning model. The power load at future moments is taken as the prediction target, and minimizing the sum of prediction accuracies of all training data is taken as the training target. The multi-feature time series prediction machine learning model is trained until the sum of prediction accuracies converges and the training is stopped.

3. The method for power equipment load dispatching based on big data analysis according to claim 2 is characterized in that: The generation methods of power load gap value include: Preset the selected dispatch area load threshold, denoted as FH yz ; The predicted future power load FH wl Compare the difference with the preset load threshold of the selected dispatching area to obtain the power load gap value; The expression of power load gap value is: FH qk =FH wl -FH yz ; Where FH qk is the power load gap value.

4. The method for power equipment load dispatching based on big data analysis according to claim 3 is characterized in that: Methods for determining whether to generate a warning of insufficient power load supply include: When FH qk When >0, an insufficient power load supply prompt is generated; When FH qk When ≤0, no power load supply shortage prompt is generated.

5. The method for power equipment load dispatching based on big data analysis according to claim 4 is characterized in that: Power supply parameters include power supply margin and power supply loss; Methods for obtaining power loss include: Divide the cable between the backup power source and the power line of the selected dispatching area into W sub-loss areas of equal length, and mark Q sub-loss areas consecutively and number them, where Q is an integer multiple of 2; The instantaneous currents of all the sub-loss areas with odd numbers are obtained in sequence through the current sensor, and the cable resistances of all the sub-loss areas with even numbers are obtained in sequence through the resistance measuring instrument. The instantaneous currents and the cable resistances are respectively accumulated and averaged to obtain the loss current and loss resistance. Obtain the power supply distance from b backup power sources to the selected dispatching area through the power dispatching center; The expression of loss current is: In the formula, I shb is the loss current of the bth backup power supply, X bi is the instantaneous current of the ith sub-loss area of ​​the bth backup power supply; The expression for loss resistance is: In the formula, R shb is the loss current of the bth backup power supply, T bi is the cable resistance of the ith sub-loss zone of the bth backup power source; The expression of power loss is: Where P shb is the power loss of the bth backup power supply, L shb is the power supply distance of the bth backup power supply; Methods for obtaining dispatchable power supply include: The expression of dispatchable power supply is: P ddb =P ylb -P shb ; Where P ddb is the dispatchable power supply of the bth backup power source, P ylb is the power margin of the bth backup power supply.

6. The method for power equipment load dispatching based on big data analysis according to claim 5 is characterized in that: Methods for determining whether backup power is available include: When P ddb ≥FH qk When a backup power supply is available; When P ddb <FH qk When no backup power is available.

7. The method for power equipment load dispatching based on big data analysis according to claim 6 is characterized in that: The method for generating the first scheduling duration includes: Obtain the first power supply preparation time SJ through the power dispatch center zbt1 , the first power supply preparation time and the preset preparation time threshold SJ yz Perform difference comparison; When SJ yz ≥SJ zbt1 When , the first scheduling duration is generated; The expression of the first scheduling duration is: SJ ddm1 =SJ yz -SJ zbt1 ; In the formula, SJ ddm1 is the first dispatch duration of the mth available backup power source, SJ zbt1 The first power supply preparation time for the tth available backup power source; When SJ yz <SJ zbt1 The first scheduling duration is not generated.

8. The method for power equipment load dispatching based on big data analysis according to claim 7 is characterized in that: The method for generating the second scheduling duration includes: Obtain the second power supply preparation time and power supply distance of b backup power sources through the power dispatching center, and calculate the second dispatching time according to the formula based on the second power supply preparation time and power supply distance; The expression of the second scheduling duration is: In the formula, SJ ddb2 is the second dispatching duration of the bth backup power source, SJ zbb2 The second power supply preparation time for the bth backup power source, is the weight factor.

9. The method for power equipment load dispatching based on big data analysis according to claim 8, characterized in that: The method for performing power load dispatching with a backup power source corresponding to c second dispatching durations includes: When the c second scheduling durations are all inconsistent, the backup power sources corresponding to the c second scheduling durations are sequentially scheduled for power load in ascending order; When there are x second scheduling durations of the same size, x∈c, the power load of the backup power supplies corresponding to the c second scheduling durations are scheduled in ascending order, and when the power load is scheduled to the backup power supplies corresponding to the x second scheduling durations of the same size, the x backup power supplies are scheduled at the same time.

10. A power equipment load dispatching system based on big data analysis, applied to a power dispatching center, for implementing the power equipment load dispatching method based on big data analysis as described in any one of claims 1 to 9, characterized in that: It includes a first data acquisition module, a second data acquisition module, a model training module, a load analysis module, a first load scheduling module and a second load scheduling module, wherein each module is connected via a wired and / or wireless network; A first data collection module collects historical power load data of a selected dispatching area in advance, wherein the historical power load data includes comprehensive power consumption data and power load corresponding to the comprehensive power consumption data; The second data collection module collects the power supply parameters of the b backup power sources corresponding to the selected dispatching area, and generates b dispatchable power supply amounts based on the power supply parameters; The model training module trains a machine learning model for predicting future power loads based on historical power load data, and predicts future power loads based on the trained machine learning model; The load analysis module compares and analyzes the predicted future power load with the preset selected dispatching area load threshold, generates a power load gap value, and determines whether to generate a power load supply shortage prompt based on the power load gap value, and compares and analyzes the b dispatchable power supplies with the power load gap value one by one to determine whether there is an available backup power supply; The first load scheduling module collects the first power supply preparation time of t available backup power sources, compares and analyzes the t first power supply preparation time with a preset preparation time threshold, generates m first scheduling time, and selects the available backup power source corresponding to the first scheduling time ranked first after being sorted in descending order for power load scheduling; The second load scheduling module collects the second power supply preparation time and power supply distance of b backup power supplies, calculates and generates b second scheduling time periods one by one, and accumulates the dispatchable power supply of the backup power supplies corresponding to c second scheduling time periods one by one in ascending order until the sum of the c dispatchable power supplies is greater than or equal to the power load gap value, and stops accumulating, and performs power load scheduling on the backup power supplies corresponding to the c second scheduling time periods.

Images