Method and system for optimizing power infrastructure based on low-altitude economic power consumption

Abstract

The invention provides a method and a system for optimizing electric power infrastructure based on low-altitude economic electricity consumption, which are characterized in that multi-source electricity consumption data (low-altitude manufacturing industry electricity consumption, low-altitude flight electricity consumption and low-altitude guarantee electricity consumption) are fused, so that scientific parameter support is provided for planning and operation of the electric power infrastructure; and meanwhile, by virtue of the specific time sequence dependence of the long-short-term memory network, the forward movement of the predicted weight in the time dimension is realized, so that the weight prediction accuracy is improved. Besides, the low-altitude economic electricity consumption is combined with the power grid safe and stable operation constraint condition of the to-be-measured area, so that the cooperative management of the low-altitude economy and the power grid output quality of the power foundation arrangement in the to-be-measured area is realized, and the optimization accuracy of the power infrastructure in the next time period can be further improved. Therefore, the planning and operation cost of the power infrastructure can be accurately adjusted and optimized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of low-altitude economy, and particularly relates to a method and system for optimizing power infrastructure based on low-altitude economy electricity consumption. BACKGROUND

[0002] With the rapid development of low-altitude economy, it has gradually empowered many fields such as military, commercial, public service, etc., involving low-altitude transportation, monitoring, emergency, etc. The electricity demand of low-altitude manufacturing, low-altitude aircraft operation and related support services associated with low-altitude economy has increased dramatically, thereby posing new challenges to the planning and operation of power infrastructure in the relevant area. However, in the prior art, the load forecasting method of power infrastructure is mainly for fixed load scenarios such as industrial, commercial and residential electricity, which cannot accurately reflect the dynamic demand of multiple electricity consumers in low-altitude economy, and thus cannot accurately predict the configuration and operation of power infrastructure under low-altitude economy. SUMMARY

[0003] In order to solve the problems of the prior art, the present application provides a method and system for optimizing power infrastructure based on low-altitude economy electricity consumption, aiming to accurately adjust and optimize the planning and operation cost of power infrastructure.

[0004] The object of the present application is achieved by using the following technical solutions:

[0005] In one aspect, the present application provides a method for optimizing power infrastructure based on low-altitude economy electricity consumption, the method comprising:

[0006] obtaining low-altitude manufacturing electricity consumption and low-altitude support electricity consumption of a to-be-tested area in a current time period;

[0007] using a flight electricity consumption calculation formula to calculate the number of various low-altitude aircraft and flight parameters of the to-be-tested area in the current time period, to obtain low-altitude flight electricity consumption;

[0008] using a dynamic weight prediction model constructed by a long short-term memory network to predict the weights of the low-altitude manufacturing electricity consumption, the low-altitude flight electricity consumption and the low-altitude support electricity consumption, to obtain dynamic weight values;

[0009] based on the dynamic weight values, performing weighted fusion on the low-altitude manufacturing electricity consumption, the low-altitude flight electricity consumption and the low-altitude support electricity consumption, to obtain low-altitude economy electricity consumption of the to-be-tested area in a next time period; wherein the next time period is a time period adjacent to the current time period;

[0010] According to the low-altitude economy electricity consumption and the power grid safety and stability operation constraint condition of the to-be-measured region, the planning and operation of the power infrastructure of the to-be-measured region in the next time period are optimized.

[0011] Optionally, the flight parameter includes: flight electricity conversion efficiency, flight average power, and flight time in the current time period; and the flight electricity calculation formula satisfies the following formula:

[0012]

[0013] Wherein, D is the low-altitude flight electricity consumption; N i is the number of the to-be-measured region in the current time period; P i is the flight average power of the i-th low-altitude aircraft; S i is the flight time of the i-th low-altitude aircraft in the current time period; M i is the battery electricity conversion efficiency of the i-th low-altitude aircraft; Q i is the total electricity consumption of the i-th low-altitude aircraft in the current time period; T1, T2, T3, T4, T5, T6, and T7 are respectively the take-off time, the climbing time, the level flight time, the hovering time, the circling time, the descending time, and the landing time of the i-th low-altitude aircraft in the current time period.

[0014] Optionally, the construction process of the dynamic weight prediction model includes:

[0015] The historical electricity consumption sequence set of the to-be-measured region is obtained; wherein, the historical electricity consumption sequence set includes: historical electricity consumption sequences corresponding to a plurality of historical time periods, the historical electricity consumption sequence includes: historical electricity consumption items labeled with real weights determined based on actual proportions and external environment characteristics, the historical electricity consumption items include: historical low-altitude manufacturing industry electricity consumption, historical low-altitude guarantee electricity consumption, and historical low-altitude flight electricity consumption; and the plurality of historical time periods are a plurality of time periods before the current time period.

[0016] The neural network model constructed by the long short-term memory network is iteratively trained by using the historical electricity consumption sequence set, to obtain the dynamic weight prediction model.

[0017] Wherein, the number of input channels of the neural network model is the same as the number of the historical electricity consumption items.

[0018] Optionally, the iteratively training the neural network model constructed by the long short-term memory network by using the historical electricity consumption sequence set, to obtain the dynamic weight prediction model, includes:

[0019] input the historical power consumption sequence set into the neural network model to perform weight prediction, to obtain a predicted weight value of each historical power consumption sub-item in each historical power consumption sequence in the historical power consumption sequence set;

[0020] Based on each historical power consumption sequence, a mean square error loss function is used to determine the loss between the predicted weight value of each historical power consumption sub-item in the historical power consumption sequence and the true weight.

[0021] Based on the loss, the network parameters of the neural network model are adjusted until the dynamic weight prediction model output satisfies the preset condition.

[0022] Optionally, the low-altitude manufacturing power consumption and the low-altitude guarantee power consumption of the to-be-tested region in the current time period are obtained, including:

[0023] The total output scale value of low-altitude equipment corresponding to low-altitude equipment manufacturing of the to-be-tested region in the current time period is obtained.

[0024] The low-altitude manufacturing power consumption is obtained according to the product of a specific low-altitude manufacturing industry proportion coefficient and the total output scale value of low-altitude equipment.

[0025] The low-altitude communication power consumption and the low-altitude computing power consumption of the to-be-tested region in the current time period are obtained.

[0026] The low-altitude communication power consumption and the low-altitude computing power consumption are fused to obtain the low-altitude guarantee power consumption.

[0027] Optionally, the low-altitude communication power consumption and the low-altitude computing power consumption of the to-be-tested region in the current time period are obtained, including:

[0028] The deployment amount of low-altitude communication base stations and the deployment amount of standard computing power racks of the to-be-tested region in the current time period are obtained.

[0029] The low-altitude communication power consumption is obtained according to the product of the deployment amount of low-altitude communication base stations, the power loss of a single low-altitude communication base station, and the running time length of the single low-altitude communication base station in the current time period.

[0030] The low-altitude computing power consumption is obtained according to the product of the deployment amount of standard computing power racks, the power reference coefficient of a single rack, the load utilization rate of the single rack, and the running time length of the single rack in the current time period.

[0031] Optionally, the power grid safety and stability operation constraint condition of the to-be-tested region comprises: a substation capacity upper limit constraint condition, a substation power supply radius constraint condition and a line thermal stability constraint condition; the optimization of the planning and operation of the power infrastructure of the to-be-tested region in the next time period according to the low-altitude economic power consumption and the power grid safety and stability operation constraint condition of the to-be-tested region comprises:

[0032] According to the low-altitude economic power consumption, the substation capacity upper limit constraint condition, the substation power supply radius constraint condition and the line thermal stability constraint condition, the investment cost and load balancing degree of the power infrastructure of the to-be-tested region are analyzed to obtain the operation planning parameter of the power infrastructure in the next time period;

[0033] The power infrastructure is optimized by using the operation planning parameter.

[0034] In another aspect, the embodiment of the present application also provides a system for optimizing power infrastructure based on low-altitude economic power consumption, which comprises:

[0035] An acquisition module is configured to acquire low-altitude manufacturing power consumption and low-altitude guarantee power consumption of a to-be-tested region in a current time period;

[0036] A calculation module is configured to calculate the quantity and flight parameters of a plurality of low-altitude aircraft in the to-be-tested region in the current time period by using a flight power consumption calculation formula to obtain low-altitude flight power consumption;

[0037] A weight prediction module is configured to use a dynamic weight prediction model constructed by a long short-term memory network to predict the weights of the low-altitude manufacturing power consumption, the low-altitude flight power consumption and the low-altitude guarantee power consumption to obtain dynamic weight values;

[0038] A fusion module is configured to perform weighted fusion on the low-altitude manufacturing power consumption, the low-altitude flight power consumption and the low-altitude guarantee power consumption based on the dynamic weight values to obtain low-altitude economic power consumption of the to-be-tested region in a next time period; wherein the next time period is a time period adjacent to the current time period;

[0039] An optimization module is configured to optimize the planning and operation of the power infrastructure of the to-be-tested region in the next time period according to the low-altitude economic power consumption and the power grid safety and stability operation constraint condition of the to-be-tested region.

[0040] Optionally, the flight parameters comprise: flight power consumption conversion efficiency, flight average power and flight time in the current time period; and the flight power consumption calculation formula satisfies the following formula:

[0041]

[0042] wherein, D is the electricity consumption of the low-altitude flight; N i is the number of the low-altitude aircraft of the i-th kind in the current time period; n is the number of kinds of the low-altitude aircraft in the current time period; P i is the average flight power of the i-th kind of low-altitude aircraft; S i is the flight time of the i-th kind of low-altitude aircraft in the current time period; M i is the battery power conversion efficiency of the i-th kind of low-altitude aircraft; Q i is the total electricity consumption of the i-th kind of low-altitude aircraft in the current time period; T1, T2, T3, T4, T5, T6, and T7 are the take-off time, the climbing time, the level flight time, the hovering time, the circling time, the descending time, and the landing time of the i-th kind of low-altitude aircraft in the current time period, respectively.

[0043] Optionally, the system further comprises:

[0044] The construction module is configured to obtain a historical electricity consumption sequence set of the to-be-tested region; wherein, the historical electricity consumption sequence set comprises historical electricity consumption sequences corresponding to a plurality of historical time periods, the historical electricity consumption sequences comprise historical low-altitude manufacturing electricity consumption, historical low-altitude guarantee electricity consumption, and historical low-altitude flight electricity consumption, which are annotated with real weights determined based on actual proportions and external environmental characteristics; the plurality of historical time periods are a plurality of time periods before the current time period; the neural network model constructed by a long short-term memory network is iteratively trained by using the historical electricity consumption sequence set, to obtain the dynamic weight prediction model; wherein, the number of input channels of the neural network model is the same as the number of the historical electricity consumption items.

[0045] Optionally, the construction module is specifically configured to input the historical electricity consumption sequence set into the neural network model for weight prediction, to obtain predicted weight values of each historical electricity consumption item in each historical electricity consumption sequence in the historical electricity consumption sequence set; based on each historical electricity consumption sequence, a mean square error loss function is used to determine a loss between the predicted weight values and the real weights of each historical electricity consumption item in the historical electricity consumption sequence; based on the loss, the network parameters of the neural network model are adjusted until the dynamic weight prediction model that meets the preset condition is obtained.

[0046] Optionally, the obtaining module comprises:

[0047] The obtaining unit is configured to obtain a total low-altitude equipment output scale value corresponding to low-altitude equipment manufacturing of the to-be-tested region in the current time period.

[0048] a calculation unit configured to obtain the low-altitude manufacturing industry electricity consumption according to a product of a specific low-altitude manufacturing industry proportion coefficient and the total output scale value of the low-altitude equipment;

[0049] The acquisition unit is further configured to acquire low-altitude communication electricity consumption and low-altitude computing power electricity consumption of the to-be-tested region in the current time period.

[0050] The calculation unit is further configured to fuse the low-altitude communication electricity consumption and the low-altitude computing power electricity consumption to obtain the low-altitude guarantee electricity consumption.

[0051] Optionally, the acquisition unit is specifically configured to acquire a deployment amount of low-altitude communication base stations and a deployment amount of standard computing power racks of the to-be-tested region in the current time period; obtain the low-altitude communication electricity consumption according to a product of the deployment amount of the low-altitude communication base stations, power consumption of a single low-altitude communication base station and a running time length of the single low-altitude communication base station in the current time period; and obtain the low-altitude computing power electricity consumption according to a product of the deployment amount of the standard computing power racks, a power reference coefficient of a single rack, a load utilization rate of the single rack and a running time length of the single rack in the current time period.

[0052] Optionally, the power grid safety and stability operation constraint condition of the to-be-tested region comprises a substation capacity upper limit constraint condition, a substation power supply radius constraint condition and a line thermal stability constraint condition; and the optimization module comprises:

[0053] an analysis unit configured to analyze an investment cost and a load balancing degree of the power infrastructure of the to-be-tested region according to the low-altitude economy electricity consumption, the substation capacity upper limit constraint condition, the substation power supply radius constraint condition and the line thermal stability constraint condition, to obtain a running planning parameter of the power infrastructure in the next time period.

[0054] an optimization unit configured to optimize the power infrastructure by using the running planning parameter.

[0055] In still another aspect, an electronic device is also provided, comprising at least one processor and a memory; the memory and the processor are connected through a bus;

[0056] The memory is configured to store one or more programs.

[0057] When the one or more programs are executed by the at least one processor, the method for optimizing a power infrastructure based on low-altitude economy electricity consumption is implemented.

[0058] Correspondingly, the embodiment of the present application also provides a readable storage medium, which has an execution program stored thereon, and the execution program, when executed, implements the method for optimizing power infrastructure based on low-altitude economic power consumption according to any one of the above.

[0059] Compared with the prior art, the present application has the following advantages:

[0060] The present application provides a method and system for optimizing power infrastructure based on low-altitude economic power consumption, which utilizes a dynamic weight prediction model constructed by a long short-term memory network to dynamically predict the obtained multi-source power consumption data (low-altitude manufacturing industry power consumption, low-altitude flight power consumption, and low-altitude support power consumption) of the current time period, and utilizes the obtained dynamic weight value to weight and fuse the multi-source power consumption data of the current time period, to obtain the low-altitude economic power consumption of the next time period. In this way, by fusing the multi-source power consumption data (low-altitude manufacturing industry power consumption, low-altitude flight power consumption, and low-altitude support power consumption), scientific parameter support is provided for the planning and operation of power infrastructure, and by virtue of the time sequence dependency of the long short-term memory network, the weight of the prediction is moved forward in the time dimension, to improve the accuracy of weight prediction. In addition, the low-altitude economic power consumption is combined with the power grid safety and stability operation constraint condition of the to-be-tested region, to realize the collaborative management of the low-altitude economy and power grid output quality of the power infrastructure in the to-be-tested region, so as to further improve the optimization accuracy of the power infrastructure in the next time period, that is, to accurately adjust and optimize the planning and operation cost of the power infrastructure.

[0061] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, but not limiting the technical solutions provided by the embodiments of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0063] Figure 1 A flowchart of a method for optimizing power infrastructure based on low-altitude economic power consumption provided by the embodiment of the present application;

[0064] Figure 2 A composition diagram of low-altitude economic power consumption provided by the embodiment of the present application;

[0065] Figure 3 A structure diagram of a system for optimizing power infrastructure based on low-altitude economic power consumption provided by the embodiment of the present application;

[0066] Figure 4 A schematic diagram of an electronic device according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0067] Other advantages and effects of the present application can be easily understood by those skilled in the art from the description of the present application. The present application can also be implemented or applied by other different specific embodiments, and the details in the description can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, but not for limiting the protection scope of the present application.

[0068] In the following description, "some embodiments" are referred to, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subset of all possible embodiments, and can be combined with each other without conflict.

[0069] In the following description, the terms "first\second\third" are only to distinguish similar objects, and do not represent a specific order of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence as allowed, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0070] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which embodiments of the present application belong. The terms used herein are only for the purpose of describing embodiments of the present application, and are not intended to limit embodiments of the present application.

[0071] Embodiment 1:

[0072] Referring to Figure 1 As shown in the figure, a flowchart of a method for optimizing power infrastructure based on low-altitude economic power consumption according to an embodiment of the present application is provided, and the method comprises the following steps:

[0073] In step 101, the low-altitude manufacturing power consumption and the low-altitude security power consumption of the to-be-tested region in the current time period are obtained.

[0074] In some embodiments of the present application, the to-be-tested region can refer to a certain area, specifically, it can refer to a certain country; the current time period can refer to the current month, the current week or the current quarter; correspondingly, the low-altitude manufacturing power consumption and the low-altitude security power consumption of the to-be-tested region in the current time period can be the low-altitude manufacturing power consumption and the low-altitude security power consumption of region A in the current quarter.

[0075] It should be noted that the "low altitude" involved in the low-altitude manufacturing electricity consumption and the low-altitude guarantee electricity consumption refers to the corresponding low-altitude economy (Low-altitude Economy) industry which takes low-altitude flight activities as the core and is composed of manned or unmanned flight, low-altitude intelligent networking and other technologies.

[0076] In some embodiments of the present application, the low-altitude manufacturing electricity consumption of the to-be-measured region in the current time period is the electricity consumption of the low-altitude equipment manufacturing of the to-be-measured region in the current time period; and the low-altitude guarantee electricity consumption of the to-be-measured region in the current time period is the electricity consumption of the infrastructure for serving the low-altitude economy in the to-be-measured region in the current time period.

[0077] It should be noted that the low-altitude equipment manufacturing can refer to the low-altitude aircraft manufacturing of the to-be-measured region. In other words, the low-altitude equipment can take the low-altitude aircraft as an example. Here, the low-altitude aircraft includes but is not limited to: logistics unmanned aerial vehicle, inspection unmanned aerial vehicle, agricultural plant protection unmanned aerial vehicle, navigation manned electric vertical take-off and landing aircraft (electric Vertical Take-off and Landing, eVTOL), navigation electric aircraft, navigation electric helicopter, etc.

[0078] In some embodiments of the present application, the above step 101 can be realized by the following steps 1011 to 1014 (not shown in the figure): Figure 1

[0079] Step 1011, acquiring a low-altitude equipment total output scale value corresponding to low-altitude equipment manufacturing of the to-be-measured region in the current time period.

[0080] Here, continuing the description above, the low-altitude equipment manufacturing can take the low-altitude aircraft as an example.

[0081] In some embodiments of the present application, the low-altitude equipment total output scale value of the to-be-measured region in the current time period can be acquired based on existing data sources. At the same time, the low-altitude equipment total output scale value can be the total output scale value of the low-altitude economy of the to-be-measured region in the current time period, which can be represented by T here.

[0082] Step 1012, obtaining the low-altitude manufacturing electricity consumption according to the product of a specific low-altitude manufacturing industry proportion coefficient and the low-altitude equipment total output scale value.

[0083] In some embodiments of the present application, the specific low-altitude manufacturing industry proportion coefficient in the to-be-measured region can be determined according to the actual generated data in the to-be-measured region. Obviously, the specific low-altitude manufacturing industry proportion coefficients of different to-be-measured regions can be the same or different. ​

[0084] In some embodiments of the present invention, a specific low-altitude manufacturing proportion coefficient may include multiple parameters, thereby obtaining the electricity consumption of the low-altitude manufacturing industry in the area to be tested by multiplying the multiple parameters by the total output scale of low-altitude equipment.

[0085] In some embodiments of the present invention, the specific low-altitude manufacturing proportion coefficient includes: a system-preset proportion coefficient, a low-altitude manufacturing segment proportion coefficient, a preset value-added rate, and a low-altitude manufacturing unit value-added electricity consumption coefficient; correspondingly, the above step 1012 can be implemented by the following steps A1 to A4:

[0086] Step A1: Obtain the scale value of low-altitude aircraft manufacturing and operation services by multiplying the preset proportion coefficient of the system with the total output scale value of the low-altitude equipment.

[0087] Step A2: Obtain the industrial scale value of low-altitude aircraft manufacturing by multiplying the proportion coefficient of the low-altitude manufacturing sector by the scale value of the low-altitude aircraft manufacturing and operation services.

[0088] Step A3: Obtain the added value of the low-altitude aircraft manufacturing industry by multiplying the preset added value rate by the scale value of the low-altitude aircraft manufacturing industry.

[0089] Step A4: Obtain the electricity consumption of the low-altitude manufacturing industry by multiplying the electricity consumption coefficient per unit added value of the low-altitude aircraft manufacturing industry by the added value of the low-altitude manufacturing industry.

[0090] In some embodiments of the present invention, the total output scale value T of low-altitude equipment and the system preset proportion coefficient α can be substituted into the following formula (1) for calculation to obtain the low-altitude aircraft manufacturing and operation service scale value S1, and S1 can also represent the low-altitude equipment (low-altitude aircraft) manufacturing and operation service scale value in the area to be tested; wherein, formula (1) can be expressed as:

[0091] S1=α·T formula (1);

[0092] Where α∈[0.5, 0.6].

[0093] Correspondingly, the scale value S1 of low-altitude aircraft manufacturing and operation services and the proportion coefficient β of low-altitude manufacturing can be substituted into the following formula (2) for calculation, thereby obtaining the scale value S of the low-altitude aircraft manufacturing industry. _m That is, the S _m Let be the industrial scale value of low-altitude aircraft (spacecraft) manufacturing in the area to be measured; where, formula (2) can be expressed as:

[0094] S _m =β·S1 Formula (2);

[0095] wherein β ∈ [0.4, 0.9].

[0096] and the low-altitude aircraft manufacturing industry scale value S _m and the preset value-added rate γ into the following formula (3) for calculation, so as to obtain the low-altitude aircraft (aircraft) manufacturing industry value-added V; wherein formula (3) can be expressed as:

[0097] V = γ · S _m formula (3);

[0098] wherein γ ∈ [0.30, 0.45].

[0099] Further, the low-altitude aircraft (aircraft) manufacturing industry value-added V and the low-altitude manufacturing industry unit value-added power consumption coefficient δ are substituted into the following formula (4) for calculation, so as to obtain the low-altitude manufacturing industry power consumption E in the to-be-measured region; wherein formula (4) can be expressed as:

[0100] E = δ · V formula (4);

[0101] wherein δ ∈ [800, 900] kWh / ten thousand yuan. Here, δ can also be expressed as the low-altitude economic manufacturing industry unit value-added power consumption coefficient in the to-be-measured region. Here, δ can be calculated according to the economic and power data of 133 industries in past years, and the unit value-added power consumption of "railway / ship / air and space transportation equipment manufacturing industry" in 133 industries is determined.

[0102] Step 1013, obtaining the low-altitude communication power consumption and low-altitude computing power consumption of the to-be-measured region in the current time period.

[0103] In some embodiments of the present application, the low-altitude communication power consumption of the to-be-measured region in the current time period can refer to the power consumption of the low-altitude communication base station in the to-be-measured region in the current time period; correspondingly, the low-altitude computing power consumption of the to-be-measured region in the current time period can refer to the power consumption of the computing power rack for serving low-altitude economy in the to-be-measured region in the current time period.

[0104] In some embodiments of the present application, the above step 1013 can be realized by the following steps B1 to step B3 (not shown in the figure): Figure 1

[0105] Step B1, obtaining the deployment amount of low-altitude communication base stations and the deployment amount of standard computing power racks in the to-be-measured region in the current time period.

[0106] ​Step B2, obtaining the low-altitude communication electricity consumption of the to-be-tested region in the current time period according to the product of the deployment quantity of the low-altitude communication base station, the power loss of a single low-altitude communication base station, and the running time length of the single low-altitude communication base station in the current time period.

[0107] Step B3, obtaining the low-altitude computing power electricity consumption of the to-be-tested region in the current time period according to the product of the deployment quantity of the standard computing power rack, the power reference coefficient of a single rack, the load utilization rate of the single rack, and the running time length of the single rack in the current time period.

[0108] In some embodiments of the present application, the deployment quantity NBS of the low-altitude communication base station of the to-be-tested region in the current time period, the power loss PBS of a single low-altitude communication base station, and the running time length T 1annual of the single low-altitude communication base station in the current time period can be obtained. communication :

[0109] E communication = NBS*PBS*T 1annual

[0110] , wherein the unit of NBS is piece; the unit of PBS is kW / base station; T 1annual takes 8760 hours / year as an example.

[0111] Correspondingly, the deployment quantity Nrack of the standard computing power rack of the to-be-tested region in the current time period, the power reference coefficient p of a single rack, the load utilization rate η of the single rack, and the running time length T 2annual of the single rack in the current time period can be obtained. computing :

[0112] E computing = Nrack*p*T 2annual *η

[0113] , wherein the unit of Nrack is rack; the value of p can be 2.5 kW / rack; η ∈ [0.3, 0.9]; T 2annual takes 8760 hours / year as an example.

[0114] Based on the above description, the low-altitude communication electricity consumption E communication of the to-be-tested region in the current time period and the low-altitude computing power electricity consumption E computing of the to-be-tested region in the current time period can be calculated according to the following formula (7) to obtain the low-altitude guarantee electricity consumption E total of the to-be-tested region in the current time period:

[0115] E​​total = E communication + E computing Equation (7).

[0116] It should be noted that, due to the low-altitude economic take-off field and other infrastructure and the low proportion of electricity consumption of ground service industry, the network guarantee (communication network + sensing network + navigation network / computing power network) occupies a large proportion of electricity consumption, so the low-altitude service and guarantee electricity consumption in the to-be-tested area can be represented by the low-altitude guarantee electricity consumption, that is, the low-altitude guarantee electricity consumption of the to-be-tested area in the current time period is mainly calculated by the electricity consumption of the infrastructure such as base station and special computing power facility.

[0117] Step 1014, fusing the low-altitude communication electricity consumption and the low-altitude computing power electricity consumption to obtain the low-altitude guarantee electricity consumption.

[0118] In some embodiments of the present application, the low-altitude communication electricity consumption and the low-altitude computing power electricity consumption of the to-be-tested area in the current time period can be directly combined (added) to obtain the low-altitude guarantee electricity consumption of the to-be-tested area in the current time period.

[0119] Step 102, calculating the low-altitude flight electricity consumption by using a flight electricity calculation formula on the quantity and flight parameters of the low-altitude aircraft in the to-be-tested area in the current time period.

[0120] In some embodiments of the present application, the low-altitude aircraft in the to-be-tested area includes but is not limited to: logistics unmanned aerial vehicle, inspection unmanned aerial vehicle, agricultural plant protection unmanned aerial vehicle, navigation manned eVTOL, navigation electric aircraft, navigation electric helicopter, etc.

[0121] In some embodiments of the present application, the quantity of the low-altitude aircraft in the to-be-tested area in the current time period refers to the number of the low-altitude aircraft registered in the to-be-tested area in the current time period. Meanwhile, the quantities of different types of low-altitude aircraft in the to-be-tested area in the current time period can be the same or different.

[0122] In some embodiments of the present application, the flight parameters of the low-altitude aircraft in the to-be-tested area (i.e. the flight parameters involved in each type of low-altitude aircraft) include but are not limited to: flight electricity conversion efficiency, flight average power, and annual flight time, etc.

[0123] In some embodiments of the present application, when the flight parameters include flight electricity conversion efficiency, flight average power, and flight time in the current time period, the flight electricity calculation formula can be represented by the following formula (8):

[0124]

[0125] Wherein, D is the low-altitude flight electricity consumption; Ni is the number of the i-th low-altitude aircraft; n is the number of types of low-altitude aircraft in the region to be measured at the current time period; P i is the flight average power of the i-th low-altitude aircraft; S i is the flight time of the i-th low-altitude aircraft in the current time period; M i is the battery power conversion efficiency of the i-th low-altitude aircraft; Q i is the total power consumption of the i-th low-altitude aircraft in the current time period; T1, T2, T3, T4, T5, T6, and T7 are the take-off time, the climbing time, the flat flying time, the hovering time, the circling time, the descending time, and the landing time of the i-th low-altitude aircraft in the current time period, respectively.

[0126] It should be noted that, considering the certain loss between charging and actual power consumption of the low-altitude aircraft, the flight power conversion efficiency M i of the i-th low-altitude aircraft mainly reflects this part of loss. The current value is 1.1, and the values in previous years are 1.08 and 1.05, etc.

[0127] At the same time, since the power consumption of the low-altitude aircraft is different in different stages of flight such as take-off, hovering, and flat flying, the power consumption is the largest in the take-off stage and the smallest in the flat flying stage, but the flat flying time is relatively long, therefore, after comprehensive consideration, the flight average power P i of the i-th low-altitude aircraft in the current time period is determined. i Here, for the change of P i in the future, on the one hand, the increase of load and the increase of sensing accuracy and other factors will increase P i , on the other hand, the improvement of battery energy density (5%-10% per year) will reduce the influence of flight energy consumption.

[0128] In addition, the flight time S i of the i-th low-altitude aircraft in the current time period will increase in the future with the increase of application scenarios and flight frequency.

[0129] Step 103, using a dynamic weight prediction model constructed by a long short-term memory network, the low-altitude manufacturing electricity consumption, the low-altitude flight electricity consumption, and the low-altitude guarantee electricity consumption are predicted to obtain a dynamic weight value.

[0130] In some embodiments of the present application, a dynamic weight prediction model constructed by a long short-term memory network (LSTM) is adopted to predict the weights of low-altitude manufacturing electricity consumption, low-altitude flight electricity consumption and low-altitude support electricity consumption, and obtain dynamic weight values. Here, the dynamic weight values can include: weight value 1 of low-altitude manufacturing electricity consumption, weight value 2 of low-altitude flight electricity consumption and weight value 3 of low-altitude support electricity consumption.

[0131] In some embodiments of the present application, the construction process of the dynamic weight prediction model constructed by the long short-term memory network, i.e. the training process, can be realized by the following steps C1 and C2:

[0132] Step C1, obtaining a historical electricity consumption sequence set of the to-be-tested region.

[0133] The historical electricity consumption sequence set includes: historical electricity consumption sequences corresponding to a plurality of historical time periods, the historical electricity consumption sequences include: historical electricity consumption items labeled with real weights determined based on actual proportions and external environmental characteristics, the historical electricity consumption items include: historical low-altitude manufacturing electricity consumption, historical low-altitude support electricity consumption and historical low-altitude flight electricity consumption; and the plurality of historical time periods are a plurality of time periods before the current time period.

[0134] Step C2, using the historical electricity consumption sequence set to iteratively train a neural network model constructed by a long short-term memory network, and obtain the dynamic weight prediction model.

[0135] The input channel number of the neural network model is the same as the number of the historical electricity consumption items.

[0136] In some embodiments of the present application, the historical electricity consumption sequence set of the to-be-tested region can include historical electricity consumption sequences corresponding to a plurality of time periods before the current time period of the to-be-tested region. Here, the plurality of historical time periods can be a plurality of time periods in time sequence, or a plurality of time periods not in time sequence, and the present application does not make any limitation thereon.

[0137] Exemplarily, taking a current time period as a current quarter as an example, a corresponding historical power consumption sequence set of the to-be-tested region includes a historical power consumption sequence 1 of a historical quarter 1, a historical power consumption sequence 2 of a historical quarter 2, and a historical power consumption sequence 3 of a historical quarter 3. The historical power consumption sequence 1 includes historical low-altitude manufacturing power consumption of the to-be-tested region in the historical quarter 1, historical low-altitude guarantee power consumption in the historical quarter 1, and historical low-altitude flight power consumption in the historical quarter 1, which are marked with real weights 1, 2, and 3 respectively. Here, specific examples of the historical power consumption sequence 2 of the historical quarter 2 and the historical power consumption sequence 3 of the historical quarter 3 can refer to the historical power consumption sequence 1 of the historical quarter 1, and details are not described herein again.

[0138] It should be noted that the real weight 1 + the real weight 2 + the real weight 3 = 1. The value of the real weight is determined by a normalization algorithm based on the real proportion of each historical power consumption subitem and the environmental feature corresponding to the environment in which the historical power consumption subitem is located.

[0139] In some embodiments of the present application, the external environmental feature can include an environmental feature of a physical environment (such as weather, geographical location, etc.) and an environmental feature of a humanistic environment (such as a holiday, a power consumption deployment policy, etc.).

[0140] In some embodiments of the present application, the historical power consumption sequence set can be used as a training sample to iteratively train a neural network model constructed by a long short-term memory network to obtain a dynamic weight prediction model. Further, the historical power consumption sequence set can be first preprocessed, including but not limited to data cleaning (using linear interpolation or adjacent time period mean for missing value supplement, anomaly value filtering, etc.), time sequence alignment, etc. Then, the historical power consumption sequence set after data preprocessing is randomly sampled to obtain a training set and a test set. Finally, the training set and the test set are used to perform multiple rounds of iterative training and performance evaluation on the neural network model until a dynamic weight prediction model with a performance evaluation index meeting a preset condition is obtained.

[0141] In some embodiments of the present application, the number of input channels of the neural network model is the same as the number of historical power consumption subitems. Here, the historical power consumption subitems include historical low-altitude manufacturing power consumption, historical low-altitude guarantee power consumption, and historical low-altitude flight power consumption, and correspondingly, the number of input channels of the neural network is 3.

[0142] In some embodiments of the present application, the above step C2 can be realized by the following process:

[0143] First, the historical power consumption sequence set is input into the neural network model for weight prediction to obtain a predicted weight value of each historical power consumption subitem in each historical power consumption sequence in the historical power consumption sequence set.

[0144] Secondly, based on each historical electricity consumption sequence, a mean square error loss function is adopted to determine the loss between the predicted weight value and the true weight of each historical electricity consumption sub-item in the historical electricity consumption sequence.

[0145] Then, based on the loss, the network parameters of the neural network model are adjusted until the output of the dynamic weight prediction model meets the preset condition.

[0146] In some embodiments of the present application, by means of the dynamic weight prediction model constructed by the long short-term memory network, the weight prediction of multi-source data in the time dimension can be realized on the basis of considering the external environmental characteristics and true proportion of multi-source electricity consumption data (low-altitude manufacturing industry electricity consumption, low-altitude flight electricity consumption and low-altitude support electricity consumption), that is, the forward movement in the time dimension is realized, so that the prediction accuracy of the obtained dynamic weight value can be improved.

[0147] Step 104, based on the dynamic weight value, the low-altitude manufacturing industry electricity consumption, the low-altitude flight electricity consumption and the low-altitude support electricity consumption are weighted and fused to obtain the low-altitude economic electricity consumption of the to-be-measured region in the next time period.

[0148] Wherein, the next time period is a time period adjacent to the current time period.

[0149] In some embodiments of the present application, taking the current time period as the first quarter of xx year as an example, the next time period is the second quarter of xx year.

[0150] As described above, the weight value 1 of the low-altitude manufacturing industry electricity consumption and the product 1 of the low-altitude manufacturing industry electricity consumption, the weight value 2 of the low-altitude flight electricity consumption and the product 2 of the low-altitude flight electricity consumption, and the weight value 3 of the low-altitude support electricity consumption and the product 3 of the low-altitude support electricity consumption can be determined first; then the product 1, the product 2 and the product 3 are fused to obtain the low-altitude economic electricity consumption of the to-be-measured region in the next time period.

[0151] In some embodiments of the present application, the low-altitude manufacturing industry electricity consumption, the low-altitude flight electricity consumption and the low-altitude support electricity consumption of the to-be-measured region in the current time period are added according to the predicted dynamic weight value to obtain the low-altitude economic electricity consumption of the to-be-measured region in the next time period. In other words, the low-altitude economic electricity consumption of the to-be-measured region in the next time period mainly includes three parts, that is, electricity consumption, which can be seen from Figure 2 As shown, it mainly includes: low-altitude flight electricity consumption, low-altitude economic manufacturing industry electricity (i.e. the low-altitude manufacturing industry electricity consumption involved above) and other electricity consumption (i.e. the low-altitude support electricity consumption involved above) of infrastructure; wherein, the key influencing factors of low-altitude flight electricity consumption include:

[0152] 1. Aircraft categories, including but not limited to: logistics drones, manned eVTOLs, navigation charging, inspection drones, navigation electric flight, flying cars, agricultural plant protection drones, and navigation electric helicopters.

[0153] 2. The number of aircraft in the area to be measured, which is the number of aircraft registered in the area to be measured.

[0154] 3. Average power, which is closely related to the load + weight of the aircraft and the battery density.

[0155] 4. Annual flight time, which involves time parameters including but not limited to: take-off and landing time, level flight time, climb time, and flight frequency.

[0156] 5. Conversion efficiency, i.e. the conversion efficiency of electric power.

[0157] Correspondingly, the key influencing factors of low-altitude economic manufacturing industry electricity consumption include: manufacturing industry proportion and unit output value electricity consumption; the key influencing factors of other electricity consumption of infrastructure include: communication perception, computing power electricity consumption, airport and ground service, etc.

[0158] Step 105, according to the low-altitude economic electricity consumption of the area to be measured and the safe and stable operation constraint condition of the power grid of the area to be measured, optimizing the planning and operation of the power infrastructure of the area to be measured in the next time period.

[0159] In some embodiments of the present application, after obtaining the low-altitude economic electricity consumption of the area to be measured in the next time period, the planning and operation of the power infrastructure in the area to be measured in the next time period can be optimized according to the low-altitude economic electricity consumption, and the optimization content includes but is not limited to:

[0160] 1. Power resource allocation: according to the low-altitude economic electricity consumption of the area to be measured, reasonably allocate the power resources of the area to be measured, and ensure the stability of the power supply of the area to be measured.

[0161] 2. Energy management strategy: develop energy-saving measures to optimize the energy supply of the area to be measured and reduce operating costs.

[0162] 3. Risk early warning mechanism: establish a risk early warning mechanism to warn of possible power supply shortages or surpluses in the area to be measured, and take measures in advance.

[0163] In some embodiments of the present application, the safe and stable operation constraint condition of the power grid of the area to be measured can include: the upper limit constraint condition of the transformer capacity in the area to be measured, the transformer power supply radius constraint condition, and the line thermal stability constraint condition. Correspondingly, the above step 105 can be realized by the following step 1051 and step 1052 (not shown in the present application): Figure 1 ​

[0164] Step 1051, according to the low-altitude economic electricity consumption, the transformer substation capacity upper limit constraint condition, the transformer substation power supply radius constraint condition and the line thermal stability constraint condition, the investment cost and load balancing degree of the power infrastructure of the to-be-tested region are analyzed to obtain the operation planning parameter of the power infrastructure in the next time period.

[0165] In some embodiments of the present application, according to the low-altitude economic electricity consumption, the transformer substation capacity upper limit constraint condition, the transformer substation power supply radius constraint condition and the line thermal stability constraint condition, the investment cost and load balancing degree of the power infrastructure of the to-be-tested region are analyzed, that is, the minimum value of the investment cost is solved on the basis of the moderate configuration of the load balancing degree, thereby obtaining the operation planning parameter of the power infrastructure in the next time period; wherein the operation planning parameter includes but is not limited to: power grid physical parameters, power quality parameters, etc.

[0166] Step 1052, using the operation planning parameter, the power infrastructure is optimized.

[0167] In some embodiments of the present application, the current operation parameter of the power infrastructure can be optimized or adjusted by using the operation planning parameter.

[0168] As a person skilled in the art should know, accurate measurement or evaluation of low-altitude economic electricity consumption is of great significance to the planning of power infrastructure, optimization of operation cost and energy management. However, there are few related literatures on the measurement method of low-altitude economic electricity consumption in the prior art, such as: lacking of accurate data collection system for low-altitude economic manufacturing and low-altitude economic service guarantee electricity, lacking of stable acquisition channel for key parameters such as rated power and flight time of aircraft, so as to accurately reflect the actual electricity consumption of low-altitude economy.

[0169] In other words, since low-altitude economy is a new industry, there is currently no related measurement research on low-altitude economic electricity consumption. Some power supply companies only identify the user as a low-altitude economic user when the user is installed (such as using a tagging form to make a note or preliminarily identifying its keywords), and roughly identify the meter of the user as low-altitude economic electricity. In addition, only new users can be tagged, and whether they are real low-altitude economic users cannot be identified. In this way, there will be an inaccurate identification problem, that is, it is difficult to accurately identify which electricity consumption of the meter statistics is really used for low-altitude economy, and the flight electricity of various aircrafts is scattered and difficult to statistically analyze, so it is difficult to estimate the electricity consumption of the low-altitude economic industry chain.

[0170] Based on this, the embodiment of the present application not only provides a method for calculating low-altitude economic power consumption, but also further optimizes the planning and operation of power infrastructure by using the calculated low-altitude economic power consumption, that is, provides scientific support for the planning and operation of power infrastructure. First, by using existing data that can be obtained, such as existing economic data sources, the operation parameters and application situations of low-altitude aircraft are comprehensively considered, and the low-altitude economic overall power consumption is calculated from the perspectives of low-altitude manufacturing industry power consumption, low-altitude flight power consumption, and low-altitude service and support power consumption, that is, a power consumption calculation method including the main industries covered by low-altitude economy is provided. Second, the low-altitude economic power consumption calculated accurately optimizes the planning and operation of power infrastructure.

[0171] In other words, the method for optimizing power infrastructure based on low-altitude economic power consumption provided by the embodiment of the present application first acquires low-altitude manufacturing industry power consumption and low-altitude support power consumption of a to-be-measured region in a current time period; calculates the number of low-altitude aircraft and flight parameters of the to-be-measured region in the current time period by using a flight power calculation formula to obtain low-altitude flight power consumption; then, a dynamic weight prediction model constructed by a long short-term memory network is used to predict the weights of low-altitude manufacturing industry power consumption, low-altitude flight power consumption, and low-altitude support power consumption to obtain dynamic weight values; based on the dynamic weight values, the low-altitude manufacturing industry power consumption, the low-altitude flight power consumption, and the low-altitude support power consumption are weighted and fused to obtain low-altitude economic power consumption of the to-be-measured region in a next time period; wherein the next time period is a time period adjacent to the current time period; finally, according to the low-altitude economic power consumption and the power grid safety and stability operation constraint condition of the to-be-measured region, the planning and operation of the power infrastructure of the to-be-measured region in the next time period are optimized. In this way, the dynamic weight prediction model constructed by the long short-term memory network is used to dynamically predict the weights of the obtained multi-source power consumption data (low-altitude manufacturing industry power consumption, low-altitude flight power consumption, and low-altitude support power consumption) in the current time period, and the dynamic weight values obtained are used to weightedly fuse the multi-source power consumption data in the current time period to obtain the low-altitude economic power consumption in the next time period; in this way, by fusing the multi-source power consumption data (low-altitude manufacturing industry power consumption, low-altitude flight power consumption, and low-altitude support power consumption), scientific parameter support for the planning and operation of power infrastructure is realized, and by virtue of the time sequence dependency of the long short-term memory network, the weights of the prediction are moved forward in the time dimension, so as to improve the accuracy of the weight prediction. In addition, the low-altitude economic power consumption is combined with the power grid safety and stability operation constraint condition of the to-be-measured region to realize the collaborative management of the power infrastructure in the to-be-measured region in the low-altitude economy and the power grid output quality, so as to further improve the optimization accuracy of the power infrastructure in the next time period, that is, to accurately adjust and optimize the planning and operation cost of the power infrastructure.

[0172] Embodiment 2

[0173] Based on the same inventive concept, the application also provides a system for optimizing power infrastructure based on low-altitude economic power consumption, which is shown in Figure 3 The system 300 comprises:

[0174] An acquisition module 301 is configured to acquire low-altitude manufacturing power consumption and low-altitude guarantee power consumption of a to-be-tested region in a current time period.

[0175] A calculation module 302 is configured to calculate the number of low-altitude aircraft and flight parameters of the to-be-tested region in the current time period by using a flight power consumption calculation formula, to obtain low-altitude flight power consumption.

[0176] A weight prediction module 303 is configured to predict the weights of the low-altitude manufacturing power consumption, the low-altitude flight power consumption, and the low-altitude guarantee power consumption by using a dynamic weight prediction model constructed by a long short-term memory network, to obtain dynamic weight values.

[0177] A fusion module 304 is configured to perform weighted fusion on the low-altitude manufacturing power consumption, the low-altitude flight power consumption, and the low-altitude guarantee power consumption based on the dynamic weight values, to obtain low-altitude economic power consumption of the to-be-tested region in a next time period; the next time period is a time period adjacent to the current time period.

[0178] An optimization module 305 is configured to optimize planning and operation of power infrastructure of the to-be-tested region in the next time period according to the low-altitude economic power consumption and a power grid safety and stability operation constraint condition of the to-be-tested region.

[0179] Optionally, the flight parameters comprise flight power consumption conversion efficiency, flight average power, and flight time in the current time period; and the flight power consumption calculation formula satisfies the following formula:

[0180]

[0181] wherein D represents the low-altitude flight power consumption; N i represents the number of the i-th low-altitude aircraft; n represents the number of types of low-altitude aircraft in the to-be-tested region in the current time period; P i represents the flight average power of the i-th low-altitude aircraft; S i represents the flight time of the i-th low-altitude aircraft in the current time period; M i represents the battery power consumption conversion efficiency of the i-th low-altitude aircraft; and Q iis the total power consumption of the ith low-altitude flying vehicle in the current time period; T1, T2, T3, T4, T5, T6, and T7 are respectively the take-off time length, the climbing time length, the cruising time length, the hovering time length, the circling time length, the descending time length, and the landing time length of the ith low-altitude flying vehicle in the current time period.

[0182] Optionally, the system 300 further includes:

[0183] The construction module 306 is configured to acquire a historical power consumption sequence set of the to-be-tested region; the historical power consumption sequence set includes historical power consumption sequences corresponding to a plurality of historical time periods; the historical power consumption sequence includes historical low-altitude manufacturing power consumption, historical low-altitude guarantee power consumption, and historical low-altitude flight power consumption, which are historical power consumption items labeled with real weights determined based on actual proportions and external environment characteristics; the plurality of historical time periods are a plurality of time periods before the current time period; the historical power consumption sequence set is used to iteratively train a neural network model constructed by a long short-term memory network to obtain the dynamic weight prediction model; the input channel number of the neural network model is the same as the number of the historical power consumption items.

[0184] Optionally, the construction module 306 is specifically configured to input the historical power consumption sequence set into the neural network model to perform weight prediction and obtain predicted weight values of each historical power consumption item in each historical power consumption sequence in the historical power consumption sequence set; based on each historical power consumption sequence, a mean square error loss function is used to determine a loss between the predicted weight values and real weights of each historical power consumption item in the historical power consumption sequence; based on the loss, network parameters of the neural network model are adjusted until the dynamic weight prediction model that meets a preset condition is obtained.

[0185] Optionally, the acquisition module 301 includes:

[0186] The acquisition unit is configured to acquire a total low-altitude equipment output scale value corresponding to low-altitude equipment manufacturing of the to-be-tested region in the current time period;

[0187] The calculation unit is configured to obtain the low-altitude manufacturing power consumption according to a product of a specific low-altitude manufacturing proportion coefficient and the total low-altitude equipment output scale value.

[0188] The acquisition unit is further configured to acquire low-altitude communication power consumption and low-altitude computing power consumption of the to-be-tested region in the current time period.

[0189] The calculation unit is further configured to fuse the low-altitude communication power consumption and the low-altitude computing power consumption to obtain the low-altitude guarantee power consumption.

[0190] Optionally, the acquisition unit is specifically configured to acquire a deployment amount of low-altitude communication base stations and a deployment amount of standard computing power racks in the to-be-tested region in the current time period; obtain the low-altitude communication power consumption according to a product of the deployment amount of the low-altitude communication base stations, power consumption of a single low-altitude communication base station, and a running time length of the single low-altitude communication base station in the current time period; and obtain the low-altitude computing power consumption according to a product of the deployment amount of the standard computing power racks, a power reference coefficient of a single rack, a load utilization rate of the single rack, and a running time length of the single rack in the current time period.

[0191] Optionally, the power grid safe and stable operation constraint condition of the to-be-tested region comprises a substation capacity upper limit constraint condition, a substation power supply radius constraint condition, and a line thermal stability constraint condition; and the optimization module 305 comprises:

[0192] The analysis unit is configured to analyze an investment cost and a load balancing degree of the power infrastructure of the to-be-tested region according to the low-altitude economic power consumption, the substation capacity upper limit constraint condition, the substation power supply radius constraint condition, and the line thermal stability constraint condition, and obtain a running planning parameter of the power infrastructure in the next time period.

[0193] The optimization unit is configured to optimize the power infrastructure by using the running planning parameter.

[0194] It should be noted that the description of the system for optimizing the power infrastructure based on the low-altitude economic power consumption is similar to the description of the method for optimizing the power infrastructure based on the low-altitude economic power consumption, and has similar beneficial effects to the method for optimizing the power infrastructure based on the low-altitude economic power consumption. For technical details not disclosed in the system for optimizing the power infrastructure based on the low-altitude economic power consumption, please refer to the description of the method for optimizing the power infrastructure based on the low-altitude economic power consumption provided in the embodiments of the present application.

[0195] Embodiment 3:

[0196] Based on the same inventive concept, as shown in Figure 4 The electronic device in the embodiment can comprise a processor 410, a memory 420, a transceiver component 430, and the like. The processor 410, the memory 420, and the transceiver component 430 are connected through a bus 440; the memory 420 can be used to store an execution program, and the exemplary execution program can comprise instructions; the processor 410 is configured to execute the instructions stored in the memory. The memory 420 can also be used to store data, which can be called and / or modified when the instructions are executed.

[0197] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, and are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in the storage medium to implement a corresponding method flow or a corresponding function, so as to implement the method for optimizing power infrastructure based on low-altitude economic power consumption in the above embodiment.

[0198] Embodiment 4:

[0199] Based on the same inventive concept, the application further provides a readable storage medium, specifically an electronic device readable storage medium (Memory). The electronic device readable storage medium is a memory device in the electronic device, and is used for storing programs and data. It can be understood that the storage medium herein can include a built-in storage medium in the electronic device, and of course can also include an expansion storage medium supported by the electronic device. The storage medium provides a storage space, and the storage space stores an operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and the instructions can be one or more execution programs (including program codes). It should be noted that the storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory. The processor loads and executes one or more instructions stored in the storage medium to implement the method for optimizing power infrastructure based on low-altitude economic power consumption in the above embodiment.

[0200] Those skilled in the art should understand that the embodiments of the application can be provided as a method, a system, or a computer program product. Therefore, the application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0201] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0202] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0203] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 one or more flow or blocks

[0204] Finally, it should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, rather than limit the technical solutions of the present application. Although the present application is described in detail with reference to the above embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced, and any modification or replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A method for optimizing power infrastructure based on low altitude economic electricity consumption, characterized by, The method comprises: obtaining low-altitude manufacturing electricity consumption and low-altitude guarantee electricity consumption of a to-be-tested region in a current time period; calculating the number and flight parameters of various low-altitude aircraft in the to-be-tested region in the current time period by using a flight electricity consumption calculation formula to obtain low-altitude flight electricity consumption; using a dynamic weight prediction model constructed by a long short-term memory network to predict the weights of the low-altitude manufacturing electricity consumption, the low-altitude flight electricity consumption, and the low-altitude guarantee electricity consumption to obtain dynamic weight values; based on the dynamic weight values, performing weighted fusion on the low-altitude manufacturing electricity consumption, the low-altitude flight electricity consumption, and the low-altitude guarantee electricity consumption to obtain low-altitude economic electricity consumption of the to-be-tested region in a next time period; wherein the next time period is a time period adjacent to the current time period; optimizing planning and operation of power infrastructure of the to-be-tested region in the next time period according to the low-altitude economic electricity consumption and a power grid safety and stability operation constraint condition of the to-be-tested region.

2. The method of claim 1, wherein, The flight parameters include flight electricity conversion efficiency, flight average power, and flight time in the current time period; and the flight electricity consumption calculation formula satisfies the following formula: Wherein, D is the electricity consumption of the low-altitude flight; N i is the number of the i-th low-altitude aircraft; n is the number of categories of low-altitude aircraft in the to-be-detected area in the current time period; P i is the average flight power of the i-th low-altitude aircraft; S i is the flight time of the i-th low-altitude aircraft in the current time period; M i is the battery electricity conversion efficiency of the i-th low-altitude aircraft; Q i is the total electricity consumption of the i-th low-altitude aircraft in the current time period; T1, T2, T3, T4, T5, T6, and T7 are respectively the take-off time, the climbing time, the level flight time, the hovering time, the circling time, the descending time, and the landing time of the i-th low-altitude aircraft in the current time period.

3. The method of claim 1, wherein, The construction process of the dynamic weight prediction model comprises: obtaining a historical electricity consumption sequence set of the to-be-tested region; wherein the historical electricity consumption sequence set comprises historical electricity consumption sequences corresponding to a plurality of historical time periods, the historical electricity consumption sequences comprise historical electricity consumption items labeled with real weights determined based on actual proportions and external environment characteristics, the historical electricity consumption items comprise historical low-altitude manufacturing electricity consumption, historical low-altitude guarantee electricity consumption, and historical low-altitude flight electricity consumption, and the plurality of historical time periods are a plurality of time periods before the current time period; using the historical electricity consumption sequence set to iteratively train a neural network model constructed by a long short-term memory network to obtain the dynamic weight prediction model; wherein the number of input channels of the neural network model is the same as the number of the historical electricity consumption items.

4. The method of claim 3, wherein, The using the historical electricity consumption sequence set to iteratively train a neural network model constructed by a long short-term memory network to obtain the dynamic weight prediction model comprises: inputting the historical electricity consumption sequence set into the neural network model to predict weights to obtain predicted weight values of each historical electricity consumption item in each historical electricity consumption sequence in the historical electricity consumption sequence set; based on each historical electricity consumption sequence, using a mean square error loss function to determine a loss between the predicted weight values and real weights of each historical electricity consumption item in the historical electricity consumption sequence; based on the loss, adjusting network parameters of the neural network model until the dynamic weight prediction model satisfying a preset condition is obtained.

5. The method of claim 1, wherein, The obtaining low-altitude manufacturing electricity consumption and low-altitude guarantee electricity consumption of a to-be-tested region in a current time period comprises: obtaining a total low-altitude equipment output scale value of the to-be-tested region corresponding to low-altitude equipment manufacturing in the current time period; obtaining the low-altitude manufacturing electricity consumption according to a product of a specific low-altitude manufacturing proportion coefficient and the total low-altitude equipment output scale value. obtain low-altitude communication power consumption and low-altitude computing power consumption of the to-be-tested region in the current time period; fuse the low-altitude communication power consumption and the low-altitude computing power consumption to obtain the low-altitude support power consumption.

6. The method of claim 5, wherein, The obtaining of the low-altitude communication power consumption and the low-altitude computing power consumption of the to-be-tested region in the current time period comprises: obtaining the deployment amount of low-altitude communication base stations and the deployment amount of standard computing power racks of the to-be-tested region in the current time period; obtaining the low-altitude communication power consumption according to the product of the deployment amount of the low-altitude communication base stations, the power consumption of a single low-altitude communication base station, and the running time length of the single low-altitude communication base station in the current time period; obtaining the low-altitude computing power consumption according to the product of the deployment amount of the standard computing power racks, the power reference coefficient of a single rack, the load utilization rate of the single rack, and the running time length of the single rack in the current time period.

7. The method of claim 1, wherein, The power grid safety and stability operation constraint condition of the to-be-tested region comprises: a substation capacity upper limit constraint condition, a substation power supply radius constraint condition, and a line thermal stability constraint condition; and the optimization of the planning and operation of the power infrastructure of the to-be-tested region in the next time period according to the low-altitude economic power consumption and the power grid safety and stability operation constraint condition of the to-be-tested region comprises: analyzing the investment cost and load balancing degree of the power infrastructure of the to-be-tested region according to the low-altitude economic power consumption, the substation capacity upper limit constraint condition, the substation power supply radius constraint condition, and the line thermal stability constraint condition to obtain the operation planning parameter of the power infrastructure in the next time period; optimizing the power infrastructure by using the operation planning parameter.

8. A system for optimizing power infrastructure based on low altitude economic electricity consumption, characterized by, The system comprises: an obtaining module configured to obtain low-altitude manufacturing industry power consumption and low-altitude support power consumption of a to-be-tested region in a current time period; a calculating module configured to calculate the quantity and flight parameters of a plurality of low-altitude aircraft of the to-be-tested region in the current time period by using a flight power calculation formula to obtain low-altitude flight power consumption; a weight prediction module configured to predict the weights of the low-altitude manufacturing industry power consumption, the low-altitude flight power consumption, and the low-altitude support power consumption by using a dynamic weight prediction model constructed by a long short-term memory network to obtain dynamic weight values; a fusion module configured to perform weighted fusion on the low-altitude manufacturing industry power consumption, the low-altitude flight power consumption, and the low-altitude support power consumption based on the dynamic weight values to obtain low-altitude economic power consumption of the to-be-tested region in a next time period; wherein the next time period is a time period adjacent to the current time period; an optimization module configured to optimize the planning and operation of the power infrastructure of the to-be-tested region in the next time period according to the low-altitude economic power consumption and the power grid safety and stability operation constraint condition of the to-be-tested region.

9. An electronic device, comprising: comprise: at least one processor and a memory; the memory and the processor are connected through a bus; the memory is configured to store one or more programs; When the one or more programs are executed by the at least one processor, the method for optimizing power infrastructure based on low altitude economic electricity consumption according to any one of claims 1 to 7 is implemented.

10. A readable storage medium, characterized by, A storage medium having stored thereon an execution program, which when executed, implements the method for optimizing power infrastructure based on low altitude economic electricity consumption according to any one of claims 1 to 7.

Images