Mapping electrical connections to pumping units in a wellbore environment

Abstract

A system can be used to control a power load to electrical pumps in a wellbore environment via switchgears by generating mappings between switchgears and electrical pumps. For example, the system can detect power data associated with a set of electrical pumps or a set of switchgears. The system can determine, based on the power data, one or more causal relationships between one or more pairs of individual electrical pumps in the set of electrical pumps and individual switchgears in the set of switchgears. The system can generate, based on the one or more causal relationships, a mapping indicating that a first electrical pump in the set of electrical pumps is electrically coupled to a first switchgear in the set of switchgears. The system can control, based on the mapping, an adjustment to a power load provided to the first electrical pump via the first switchgear.

Description

TECHNICAL FIELD

[0001] The present disclosure relates generally to wellbore operations and, more particularly (although not necessarily exclusively), to mapping electrical connections to pumping units in a wellbore environment.BACKGROUND

[0002] Hydrocarbons, such as oil and gas, can be extracted from subterranean formations that may be located onshore or offshore. Hydrocarbons can be extracted through a wellbore formed in the subterranean formations. Wellbore operations for extracting hydrocarbons can include drilling operations, completion operations, production operations, fracturing operations, etc. Some wellbore operations may involve the use of electrical pumps. For instance, electrical pumps may be used to pump drilling fluid, fracturing fluid, or the like downhole into the wellbore. In some cases, electrical pumps can be powered via couplings to switchgears of a power distribution unit.BRIEF DESCRIPTION OF THE DRAWINGS

[0003] FIG. 1 is a cross-sectional view of a wellbore environment including a pumping system, according to one example of the present disclosure.

[0004] FIG. 2 is a block diagram of a computing system used to map electrical connections to electrical pumps in a wellbore environment, according to one example of the present disclosure.

[0005] FIG. 3 is a block diagram of a pumping system including electrical pumps and switchgears, according to one example of the present disclosure.

[0006] FIG. 4 is a flow chart of a process for mapping electrical connections electrical pumps in a wellbore environment, according to one example of the present disclosure.DETAILED DESCRIPTION

[0007] Certain aspects and examples of the present disclosure relate to mapping electrical connections to pumping units (e.g., electrical pumps) in a wellbore environment. The wellbore environment may include one or more electrical pumps, also referred to as electrical pumping units, that can pump fluid downhole into a wellbore. Each electrical pump can be electrically coupled to a switchgear in a power distribution unit. The power distribution unit can supply power to the electrical pumps via the switchgears. The power distribution unit may have a power limit for total power supplied to various electrical pumps via the switchgears. In many cases, the power distribution unit and / or the electrical pumps may be mobile and frequently reconfigured. For example, one or both of the power distribution unit or the electrical pumps may be mounted on trucks that are frequently moved to different wellsites in the wellbore environment. It may be common to frequently rearrange pairings of electrical pumps and switchgears. In some cases, having operators manually specify which electrical pumps are connected to which switchgears may be error prone. Further, such pairing configurations may be relatively complex, particularly in cases where a power distribution unit has multiple sets of buses, causing further difficulty in manually identifying pairing configurations.

[0008] To enable efficient and automatic power redistribution by the power distribution unit, it may be beneficial to automatically map which electrical pumps are electrically coupled to which switchgears. For example, techniques described herein can involve monitoring power data for the switchgears or the electrical pumps to determine causal relationships therebetween. In a non-limiting example, for a given pair of a particular switchgear and a particular electrical pump, a correlation coefficient (e.g., the causal relationship) can be determined between a power consumption of the particular electrical pump and a power load provided by the particular switchgear. Correlation coefficients may also be determined for other possible pairs of switchgears and electrical pumps. For each electrical pump, the switchgear that has a highest correlation coefficient can be selected as being most likely to be electrically coupled to the electrical pump. In this way, mappings between pairs of electrically coupled electrical pumps and switchgears can be automatically identified without requiring manual input.

[0009] The power distribution unit can then automatically control distribution of power between the various switchgears to supply the different electrical pumps with appropriate power loads without exceeding an overall power limit for the power distribution unit. For example, if one of the switchgears has experienced a failure, the power distribution unit can use the mappings to automatically prevent power distribution to the failed switchgear and to reallocate such power to the other switchgears. Such reallocation can minimize the impact of unexpected power distribution failures. For example, with a subsequent spread rebalance after unexpected failure, a total slurry rate for the electrical pumps in the wellbore environment may remain stable.

[0010] Illustrative examples are given to introduce the reader to the general subject matter discussed herein and are not intended to limit the scope of the disclosed concepts. The following sections describe various additional features and examples with reference to the drawings in which like numerals indicate like elements, and directional descriptions are used to describe the illustrative aspects, but, like the illustrative aspects, should not be used to limit the present disclosure.

[0011] FIG. 1 is a cross-sectional view of a wellbore environment 100 including a wellbore 102 and a pumping system 104 according to one example of the present disclosure. The wellbore 102 can extend through various earth strata. The wellbore 102 includes a substantially vertical section 108 and a substantially horizontal section 110, but other configurations are possible. The substantially vertical section 108 may include a casing string 112 cemented at an upper portion of the substantially vertical section 108. The substantially horizontal section 110 can extend through a hydrocarbon bearing subterranean formation 114. A tubing string 116 can extend from a surface 118 of the wellbore environment 100 into the wellbore 102. The tubing string 116 can provide a conduit for pumping a fracturing fluid into the wellbore 102 from the pumping system 104 to perform hydraulic fracturing operations on the wellbore 102. The wellbore 102 can include a hydraulic fracture 120 (or induced fracture) that can extend from the substantially horizontal section 110. Proppant materials can be entrained in the fracturing fluid at the pumping system 104 and can be deposited in the hydraulic fracture 120 to maintain the hydraulic fracture 120 in an open state.

[0012] The pumping system 104 can include a pumping truck 134 or other pumping device, fracturing fluid storage tanks (not shown), and any other components or systems associated with a hydraulic fracturing or stimulation operation performed by the pumping system 104. A pumping computing device 136 may control operations of the pumping system 104. The pumping computing device 136 can control an injection flow rate of the fracturing fluid that is introduced into the formation 114 during a hydraulic fracturing operation. The pumping computing device 136 may also control power distribution to components of the pumping system 104, such as a power load between switchgears (e.g., of a power distribution unit) and electrical pumps of the pumping truck 134. Components of the pumping system 104 are described in further detail below with reference to FIG. 3.

[0013] The pumping computing device 136 can include a processing device interfaced with other hardware via a bus. A memory, which can include any suitable tangible (and non-transitory) computer-readable medium, such as random-access memory (RAM), ROM, electrically erasable and programmable read-only memory (EEPROM), or the like, can embody program components that configure operation of the pumping computing device 136. In some aspects, the pumping computing device 136 can include input / output interface components (e.g., a display, a keyboard, a touch-sensitive surface, a mouse) and additional storage.

[0014] The pumping computing device 136 can transmit data to and receive data from other computing devices via a communication link 132. The communication link 132 can be wireless and can include wireless interfaces such as IEEE 802.11, Bluetooth, or radio interfaces for accessing cellular telephone networks (e.g., transceiver / antenna for accessing a CDMA, GSM, UMTS, or other mobile communications network). In other aspects, the communication link 132 can be wired and can include interfaces such as Ethernet, USB, IEEE 1394, or a fiber optic interface. While the pumping computing device 136 is depicted as separate from other components of the pumping system 104, the pumping computing device 136 may also be integrated with another component of the pumping system 104. For example, the pumping computing device 136 may form a part of pumping truck 134.

[0015] Although the example depicted in FIG. 1 involves fracturing operations, techniques described herein may be applied in all phases of hydrocarbon production (e.g., well drilling, well completion, recovery, production, etc.).

[0016] FIG. 2 is a block diagram of a computing system 200 used to map electrical connections to electrical pumps in a wellbore environment, according to one example of the present disclosure. The computing system 200 may be or may include, for example, the pumping computing device 136 of FIG. 1. The computing system 200 can include a processing device 202, a bus 204, a communication interface 206, a memory device 208, a user input device 224, a display device 226, and a control module 230. In some examples, some or all of the components shown in FIG. 2 can be integrated into a single structure, such as a single housing. In other examples, some or all of the components shown in FIG. 2 can be distributed (e.g., in separate housings) and in communication with each other.

[0017] The processing device 202 can execute instructions 214 stored in the memory device 208 to perform operations. The processing device 202 can include one processing device or multiple processing devices. Non-limiting examples of the processing device 202 include a Field-Programmable Gate Array (FGPA), an application-specific integrated circuit (ASIC), a microprocessing device, etc.

[0018] The processing device 202 can be communicatively coupled to the memory device 208 via the bus 204. The non-volatile memory device 208 may include any type of memory device that retains stored information when powered off. Non-limiting examples of the memory device 208 include electrically erasable and programmable read-only memory (EEPROM), flash memory, or any other type of non-volatile memory. In some examples, at least some of the memory device 208 can include a non-transitory computer-readable medium from which the processing device 202 can read instructions. A computer-readable medium can include electronic, optical, magnetic, or other storage devices capable of providing the processing device 202 with computer-readable instructions or other program code. Non-limiting examples of a computer-readable medium include (but are not limited to) magnetic disk(s), memory chip(s), read-only memory (ROM), random-access memory (RAM), an ASIC, a configured processing device, optical storage, or any other medium from which a computer processing device can read instructions. The instructions can include device-specific instructions generated by a compiler or an interpreter from code written in any suitable computer-programming language, including, for example, C, C++, C#, etc.

[0019] In some examples, the memory device 208 can include power data 210, for example, power consumption of an electrical pump (e.g., as reported by a variable frequency drive controlling a motor for the electrical pump); electric voltage, current, torque, or rotational speed of the motor (e.g., measured as rotations per minute of the motor shaft), pump rate of the electrical pump, differential pressure between a suction end and a discharge end of the electrical pump, power load provided by a switchgear to the electrical pump, etc. The memory device 208 can include computer program code instructions 214 for control of various aspects of the pumping system 104. For example, the computing system 200 may execute the instructions 214 to generate and store causal relationships 215 between pairs of electrical pumps and switchgears in the pumping system 104. The computing system 200 may also execute the instructions 214 to generate and store mappings 216 of electrical connections between pairs of electrical pumps and switchgears in the pumping system 104.

[0020] In some examples, the computing system 200 can include a communication interface 206. The communication interface 206 can represent one or more components that facilitate a network connection or otherwise facilitate communication between electronic devices. Examples include, but are not limited to, wired interfaces such as Ethernet, USB, IEEE 1394, and / or wireless interfaces such as IEEE 802.11, Bluetooth, near-field communication (NFC) interfaces, RFID interfaces, or radio interfaces for accessing cellular telephone networks (e.g., transceiver / antenna for accessing a CDMA, GSM, UMTS, or other mobile communications network). In some examples, the computing system 200 can include a user input device 224. The user input device 224 can represent one or more components used to input data. Examples of the user input device 224 can include a keyboard, mouse, touchpad, button, or touch-screen display. The display device 226 can represent one or more components used to output data. Examples of the display device 226 can include a liquid-crystal display (LCD), a computer monitor, a touch-screen display, etc. In some examples, the user input device 224 and the display device 226 can be a single device, such as a touch-screen display.

[0021] The control module 230 may implement and automate operations for the pumping system 104 according to some aspects of the present disclosure as described in more detail below.

[0022] FIG. 3 is a block diagram of a pumping system 300 including electrical pumps 302a-i and switchgears 308a-i, according to one example of the present disclosure. The pumping system 300 can be an example of the pumping system 104 of FIG. 1. The pumping system 300 can include power distribution units 304a-b. The power distribution units 304a-b may include buses 306a-c. The switchgears 308a-i may be distributed among the buses 306a-c.

[0023] It can be assumed that the location of a switchgear 308 in a power distribution unit 304 is known a priori (e.g., by the computing system 200 of FIG. 2). For instance, first switchgear 308a, second switchgear 308b, and third switchgear 308c reside in first bus 306a of first power distribution unit 304a; fourth switchgear 308d, fifth switchgear 308e, and sixth switchgear 308f reside in second bus 306b of the first power distribution unit 304a; and seventh switchgear 308g, eighth switchgear 308h, and ninth switchgear 308i reside in third bus 306c of second power distribution unit 304b.

[0024] The power for each electrical pump 302 can come from a single switchgear 308. The pairings between electrical pumps 302a-i and switchgears 308a-i may be unknown (e.g., by the computing system 200). The computing system 200 can determine mappings 216 between pairs of electrical pumps 302a-i and switchgears 308a-i based on power data 210 detected from components of the pumping system 300.

[0025] For example, the computing system 200 can execute the control module 230 to modify a pump rate for at least one of the electrical pumps 302a-i. The change in pump rate can result in a change in power consumption of the electrical pumps 302a-i (e.g., higher pump rates may result in increased power consumption). In some examples, the change in pump rate may be conducted sequentially for different electrical pumps 302a-i. For example, at t=0, first electrical pump 302a can ramp up from 0 barrels per minute (bpm) to a new rate setpoint of 4 bpm; at t=1, second electrical pump 302b can ramp up from 0 bpm to a new rate setpoint of 5 bpm; etc. The new rate setpoints may be the same or different for different electrical pumps 302a-i. In other examples, the change in pump rate for different electrical pumps 302a-i may be performed simultaneously.

[0026] After modifying the pump rates, the computing system 200 can sample power consumption for each electrical pump 302 and / or power load provided by each switchgear 308 for a certain time period (e.g., 10 seconds with a sample time of 1 second). The resulting power data 210 (e.g., power time series data including the power consumption and power load) can be used to determine causal relationships 215 between the electrical pumps 302a-i and switchgears 308a-i.

[0027] In some examples, the causal relationships 215 can be correlation coefficients. For example, the computing system 200 can determine a correlation coefficient, such as a Pearson correlation coefficient, for power usage between electrical pumps 302a-i and switchgears 308a-i. The Pearson correlation coefficient between the first electrical pump 302a and the first switchgear 308a can be:r1⁢1=∑ i=1N⁢(Pp⁢ump,1(i)-Pp⁢ump,1_)⁢(Pswg,1(i)-Pswg,1_)∑ i=1N⁢(Pp⁢ump,1(i)-Pp⁢ump,1_)2∑ i=1N⁢(Pswg,1(i)-Pswg,1_)2(Equation⁢ 1)where Ppump,1(i) is the i-th sample of power consumption used by first electrical pump 302a and Pswg,1(i) is the i-th sample of power load provided by first switchgear 308a. Ppump,1 can be the mean power consumption value of the first electrical pump 302a and Pswg,1 can be the mean power load value of the first switchgear 308a. Correlation coefficients can be determined for each pair of switchgear 308 and electrical pump 302. The switchgear connection for each electrical pump 302 can be determined by selecting the highest correlation coefficient. For example, the switchgear 308 associated with the first electrical pump 302a can be determined by argmax (r1,j), j=1, . . . , M if there are M switchgears 308. The second switchgear 308b can be identified as having the highest correlation coefficient with the first electrical pump 302a, and therefore a first mapping can be determined between first electrical pump 302a and second switchgear 308b.

[0029] Other causal relationships 215 can additionally or alternatively be used to generate the mappings 216. For example, the processing device 202 can use the power data 210 (e.g., of sampled power consumption and sampled power load) to generate a linear regression model of regression slopes between pairs of electrical pumps 302 and switchgears 308. In some examples, the linear regression model may also include a bias term. The regression slope (e.g., of paired power consumption and power load) with a value that is closest to 1 may indicate an electrical coupling between the associated electrical pump 302 and switchgear 308.

[0030] In some examples, additional factors may be considered in determining the first mapping. For example, a switchgear 308 with the highest correlation coefficient or regression slope value that is closest to 1 can be mapped to an electrical pump 302 if the correlation coefficient or regression slope value has an uncertainty value that is less than a predefined threshold. This can improve accuracy in mapping electrically coupled electrical pumps 302 and switchgears 308.

[0031] In some examples, none of the causal relationships 215 determined for a given electrical pump, such as second electrical pump 302b, may have an uncertainty value that is lower than the predefined threshold. This relatively high uncertainty may indicate that the power data 210 for the second electrical pump 302b is not sufficient for accurately identifying the switchgear 308 coupled to the second electrical pump 302b. Thus, the control module 230 can adjust the pump rate of the second electrical pump 302b to modify the power consumption of the second electrical pump 302b. Additional power data 210 can then be sampled after adjusting the pump rate. The additional power data 210 can be used to determine updated causal relationships 215. The updated causal relationship 215 between the second electrical pump 302b and the third switchgear 308c may have an uncertainty value that is lower than the predefined threshold, and the computing system 200 can thus map the second electrical pump 302b to the third switchgear 308c.

[0032] In some examples, rather than modifying pump rates and then sampling the resulting power data 210, the computing system 200 may instead sample power data 210 from typical pumping operations to determine causal relationships 215. If some electrical pumps 302 remain unmapped (e.g., due to insufficient uncertainty values), the computing system 200 may then modify pump rates for the unmapped electrical pumps 302. Pump rates may be modified at the same or different rates for different electrical pumps 302 and at the same or different times. For example, if different electrical pumps 302 have different historical power consumption values, their pump rates may be modified simultaneously (e.g., to have different new rate setpoints).

[0033] The power consumption of the electrical pumps 302a-i can be detected with various techniques. For example, the computing system 200 may detect the actual power consumption by an electrical pump 302 as reported by a variable frequency drive that controls a motor (e.g., on the pumping truck 134 of FIG. 1) for the electrical pump 302. Or, the computing system 200 may determine the power consumption by determining a product of electric voltage and current sampled for the motor of the electrical pump 302. The computing system 200 may also determine the power consumption by determining a product of torque and rotational speed (e.g., rotations per minute) of the motor shaft for the electrical pump 302. The computing system 200 may also determine the power consumption by determining a product of the pump rate (e.g., as set by the control module 230) and a differential pressure detected between a suction end and a discharge end of the electrical pump 302. The computing system 200 may detect the power consumption using one or more of the aforementioned techniques.

[0034] The computing system 200 may also determine the power load for each switchgear 308 based on different sources. For instance, the power load may be determined based on the power distribution allocated by the control module 230. Additionally or alternatively, the power load provided by a particular switchgear 308 can be determined based on a current measurement (e.g., measured by a current transformer coupled to the particular switchgear 308).

[0035] After the mappings 216 are generated and stored (e.g., in the memory device 208 of FIG. 2), the computing system 200 may generate a user interface that depicts the mappings 216 between electrical pumps 302a-i and switchgears 308a-i. The user interface can be output via the display device 226. Additionally or alternatively, the control module 230 can automatically control power distribution to the different electrical pumps 302a-i via the mapped switchgears 308a-i.

[0036] For example, each of the power distribution units 304a-b can have their own total power limit of power that can be distributed via their associated switchgears 308. In addition, each of the buses 306a-c and in some examples, each of the switchgears 308a-i, can have their own power limits. Awareness of the mappings 216 can allow the control module 230 to intelligently distribute power while keeping power to or for various components of the pumping system 300 within associated power limits. For example, when a new (e.g., lower) spread rate setpoint for the first power distribution unit 304a is set, the control module 230 can limit the total pump rate of electrical pumps 302 associated with the first bus 306a and the second bus 306b given the total available power of the first power distribution unit 304a and the second power distribution unit 304b.

[0037] Further, the control module 230 may detect a failed power distribution unit 304, a failed bus 306 within a power distribution unit 304, or a failed switchgear 308. Failure can involve a power failure (e.g., inability to provide power load to an associated electrical pump 302). Because of the stored mappings 216, the control module 230 can automatically shut down electrical pumps 302 associated with the failed power distribution unit 304, failed bus 306, or failed switchgear 308. For example, if the second bus 306b experiences a failure, the control module 230 can automatically shut down the third electrical pump 302c, the fifth electrical pump 302e, and the sixth electrical pump 302f. Additionally, the control module 230 may shift power load previously allocated to the second bus 306b to the first bus 306a, while keeping such reallocated power load within a power limit for the first bus 306a.

[0038] FIG. 4 is a flow chart of a process 400 for mapping electrical connections to electrical pumps in a wellbore environment, according to one example of the present disclosure. In other examples, the process 400 can include more steps, fewer steps, different steps, or a different order of the steps depicted in FIG. 4. The steps of FIG. 4 are described below with reference to components discussed above in FIGS. 1-3.

[0039] At block 402, the process 400 involves detecting, by a processing device 202, power data 210 associated with a set of electrical pumps 302a-i or a set of switchgears 308a-i in a wellbore environment 100. Individual electrical pumps 302 in the set of electrical pumps 302a-i may be electrically coupled to individual switchgears 308 in the set of switchgears 308a-i. In some examples, detecting the power data 210 can involve modifying a pump rate of at least one electrical pump 302 in the set of electrical pumps 302a-i. Modifying the pump rate can modify a power consumption of the first electrical pump 302a. After modifying the pump rate, the processing device 202 can sample power consumption of the first electrical pump 302a and power load provided by the first switchgear 308a. In other examples, the processing device 202 may detect the power data 210 (e.g., sample power consumption and / or power load) without first modifying the pump rate of at least one electrical pump 302. Instead, the processing device 202 may detect power data 210 during typical operations performed by the electrical pumps 302a-i.

[0040] At block 404, the process 400 involves determining, by the processing device 202 and based on the power data 210, one or more causal relationships 215 between one or more pairs of the individual electrical pumps 302 and the individual switchgears 308. In some examples, determining the one or more causal relationships 215 can involve determining a correlation coefficient between the power consumption and power load of pairs of electrical pumps 302 and switchgears 308. An electrical pump 302 that is electrically coupled to a particular switchgear 308 may be likely to have a relatively high correlation coefficient between power load provided by the switchgear 308 and power consumption of the electrical pump 302. In other examples, the processing device 202 can generate a linear regression model based on the power consumption and the power load for pairs of electrical pumps 302 and switchgears 308. Pairs that have regression slopes on the linear regression model that is relatively closer to 1 may be more likely to be electrically coupled.

[0041] At block 406, the process 400 involves generating, by the processing device 202 and based on the one or more causal relationships 215, a mapping 216 indicating that a first electrical pump 302a in the set of electrical pumps 302a-i is electrically coupled to a first switchgear 308a in the set of switchgears 308a-i. For example, the mapping may be generated based on the correlation coefficient or the linear regression model. In some examples, for each electrical pump 302, the mapping can be generated by identifying a switchgear 308 that has a highest associated correlation coefficient. Additionally or alternatively, the mapping can be generated by determining that an uncertainty value for a causal relationship between the first electrical pump and the first switchgear is lower than a predefined threshold.

[0042] In some examples, none of the coefficient correlations for a given electrical pump 302 may have uncertainty values that are lower than the predefined threshold. Thus, it may be beneficial to detect additional power data 210 to determine more accurate causal relationships. To detect additional power data 210, the processing device 202 may adjust a pump rate for the given electrical pump 302. The adjusted pump rate can cause a change to the power consumption of the given electrical pump 302. The change in power consumption can be sampled and used to re-determine causal relationships 215 between power loads provided by the unpaired switchgears 308. At least one of the causal relationships 215 may have an uncertainty value below the predefined threshold, and may therefore be identified as having a mapping 216 to the given electrical pump 302.

[0043] At block 408, the process 400 involves controlling, by the processing device 202 and based on the mapping 216, an adjustment to a power load to the first electrical pump 302a via the first switchgear 308a. In some examples, controlling the adjustment to the power load can involve the processing device 202 determining a power limit for a power distribution unit that includes the set of switchgears 308a-i. The processing device 202 can use the mappings 216 and the power limit to determine a power distribution to the individual electrical pumps 302 via the individual switchgears 308 (e.g., without exceeding the power limit). The processing device 202 can then automatically execute the power distribution to the individual electrical pumps 302 (e.g., by supplying power to the individual switchgears 308 according to the power distribution).

[0044] In some examples, the adjustment to the power load can involve the processing device 202 identifying a power failure of one of the switchgears. Since the mappings 216 between the electrical pumps 302 and switchgears 308 is known, the processing device 202 can automatically reallocate the power load from the failed switchgear to other switchgears 308 (e.g., in a power distribution unit).

[0045] In some aspects, systems, methods, and computer-readable media for mapping electrical connections for electrical pumps in a wellbore environment are provided according to one or more of the following examples:

[0046] Example 1 is a system comprising: a set of electrical pumps in a wellbore environment; a set of switchgears, wherein individual electrical pumps in the set of electrical pumps are electrically coupled to individual switchgears in the set of switchgears; a processing device communicatively coupled to the set of switchgears and the set of electrical pumps; and a memory device that includes instructions executable by the processing device for causing the processing device to: detect power data associated with the set of electrical pumps or the set of switchgears; determine, based on the power data, one or more causal relationships between one or more pairs of the individual electrical pumps and the individual switchgears; generate, based on the one or more causal relationships, a mapping indicating that a first electrical pump in the set of electrical pumps is electrically coupled to a first switchgear in the set of switchgears; and control, based on the mapping, an adjustment to a power load provided to the first electrical pump via the first switchgear.

[0047] Example 2 is the system of example 1, wherein the memory device further includes instructions executable by the processing device for causing the processing device to detect the power data associated with the set of electrical pumps or the set of switchgears by: modifying a pump rate of the first electrical pump in the set of electrical pumps; and subsequent to modifying the pump rate, sampling a first power consumption of the first electrical pump and a first power load provided by the first switchgear.

[0048] Example 3 is the system of example 2, wherein the memory device further includes instructions that are executable by the processing device for causing the processing device to determine the one or more causal relationships by: determining a correlation coefficient between the first power consumption and the first power load, wherein the mapping is generated based on the correlation coefficient.

[0049] Example 4 is the system of examples 2-3, wherein the memory device further includes instructions that are executable by the processing device for causing the processing device to determine the one or more causal relationships by: generating, based on the first power consumption and the first power load, a linear regression model, wherein the mapping is generated based on the linear regression model.

[0050] Example 5 is the system of examples 1-4, wherein the memory device further includes instructions executable by the processing device for causing the processing device to control the adjustment to the power load by: identifying, based on the mapping, a power failure of the first switchgear; and automatically reallocating, based on the power failure, the power load from the first switchgear to a second switchgear in the set of switchgears.

[0051] Example 6 is the system of examples 1-5, wherein the memory device further includes instructions executable by the processing device for causing the processing device to control the adjustment to the power load by: determining a power limit for a power distribution unit that comprises the set of switchgears; determining, based on the mapping and the power limit, a power distribution to the individual electrical pumps via the individual switchgears; and automatically executing the power distribution to the individual electrical pumps.

[0052] Example 7 is the system of examples 1-6, wherein the memory device further includes instructions executable by the processing device for causing the processing device to generate the mapping by: determining that an uncertainty value for a first causal relationship between the first electrical pump and the first switchgear is lower than a predefined threshold.

[0053] Example 8 is a method comprising: detecting, by a processing device, power data associated with a set of electrical pumps or a set of switchgears in a wellbore environment, wherein individual electrical pumps in the set of electrical pumps are electrically coupled to individual switchgears in the set of switchgears; determining, by the processing device and based on the power data, one or more causal relationships between one or more pairs of the individual electrical pumps and the individual switchgears; generating, by the processing device and based on the one or more causal relationships, a mapping indicating that a first electrical pump in the set of electrical pumps is electrically coupled to a first switchgear in the set of switchgears; and controlling, by the processing device and based on the mapping, an adjustment to a power load provided to the first electrical pump via the first switchgear.

[0054] Example 9 is the method of example 8, wherein detecting the power data associated with the set of electrical pumps or the set of switchgears further comprises: modifying a pump rate of the first electrical pump in the set of electrical pumps; and subsequent to modifying the pump rate, sampling a first power consumption of the first electrical pump and a first power load provided by the first switchgear.

[0055] Example 10 is the method of example 9, wherein determining the one or more causal relationships further comprises: determining a correlation coefficient between the first power consumption and the first power load, wherein the mapping is generated based on the correlation coefficient.

[0056] Example 11 is the method of examples 9-10, wherein determining the one or more causal relationships further comprises: generating, based on the first power consumption and the first power load, a linear regression model, wherein the mapping is generated based on the linear regression model.

[0057] Example 12 is the method of examples 8-11, wherein controlling the adjustment to the power load further comprises: identifying, based on the mapping, a power failure of the first switchgear; and automatically reallocating, based on the power failure, the power load from the first switchgear to a second switchgear in the set of switchgears.

[0058] Example 13 is the method of examples 8-12, wherein controlling the adjustment to the power load further comprises: determining a power limit for a power distribution unit that comprises the set of switchgears; determining, based on the mapping and the power limit, a power distribution to the individual electrical pumps via the individual switchgears; and automatically executing the power distribution to the individual electrical pumps.

[0059] Example 14 is the method of examples 8-13, wherein generating the mapping further comprises: determining that an uncertainty value for a first causal relationship between the first electrical pump and the first switchgear is lower than a predefined threshold.

[0060] Example 15 is a non-transitory computer-readable medium comprising program code that is executable by a processing device for causing the processing device to perform operations comprising: detecting, by a processing device, power data associated with a set of electrical pumps or a set of switchgears in a wellbore environment, wherein individual electrical pumps in the set of electrical pumps are electrically coupled to individual switchgears in the set of switchgears; determining, by the processing device and based on the power data, one or more causal relationships between one or more pairs of the individual electrical pumps and the individual switchgears; generating, by the processing device and based on the one or more causal relationships, a mapping indicating that a first electrical pump in the set of electrical pumps is electrically coupled to a first switchgear in the set of switchgears; and controlling, by the processing device and based on the mapping, an adjustment to a power load provided to the first electrical pump via the first switchgear.

[0061] Example 16 is the non-transitory computer-readable medium of example 15, further comprising program code that is executable by the processing device for causing the processing device to detect the power data associated with the set of electrical pumps or the set of switchgears by: modifying a pump rate of the first electrical pump in the set of electrical pumps; and subsequent to modifying the pump rate, sampling a first power consumption of the first electrical pump and a first power load provided by the first switchgear.

[0062] Example 17 is the non-transitory computer-readable medium of example 16, further comprising program code that is executable by the processing device for causing the processing device to determine the one or more causal relationships by: determining a correlation coefficient between the first power consumption and the first power load, wherein the mapping is generated based on the correlation coefficient.

[0063] Example 18 is the non-transitory computer-readable medium of examples 16-17, further comprising program code that is executable by the processing device for causing the processing device to determine the one or more causal relationships by: generating, based on the first power consumption and the first power load, a linear regression model, wherein the mapping is generated based on the linear regression model.

[0064] Example 19 is the non-transitory computer-readable medium of examples 15-18, further comprising program code that is executable by the processing device for causing the processing device to control the adjustment to the power load by: identifying, based on the mapping, a power failure of the first switchgear; and automatically reallocating, based on the power failure, the power load from the first switchgear to a second switchgear in the set of switchgears.

[0065] Example 20 is the non-transitory computer-readable medium of examples 15-19, further comprising program code that is executable by the processing device for causing the processing device to control the adjustment to the power load by: determining a power limit for a power distribution unit that comprises the set of switchgears; determining, based on the mapping and the power limit, a power distribution to the individual electrical pumps via the individual switchgears; and automatically executing the power distribution to the individual electrical pumps.

[0066] The foregoing description of certain examples, including illustrated examples, has been presented only for the purpose of illustration and description and is not intended to be exhaustive or to limit the disclosure to the precise forms disclosed. Numerous modifications, adaptations, and uses thereof will be apparent to those skilled in the art without departing from the scope of the disclosure.

Claims

1. A system comprising:a set of electrical pumps in a wellbore environment;a set of switchgears, wherein individual electrical pumps in the set of electrical pumps are electrically coupled to individual switchgears in the set of switchgears;a processing device communicatively coupled to the set of switchgears and the set of electrical pumps; anda memory device that includes instructions executable by the processing device for causing the processing device to:detect power data associated with the set of electrical pumps or the set of switchgears;determine, based on the power data, one or more causal relationships between one or more pairs of the individual electrical pumps and the individual switchgears;generate, based on the one or more causal relationships, a mapping indicating that a first electrical pump in the set of electrical pumps is electrically coupled to a first switchgear in the set of switchgears; andcontrol, based on the mapping, an adjustment to a power load provided to the first electrical pump via the first switchgear.

2. The system of claim 1, wherein the memory device further includes instructions executable by the processing device for causing the processing device to detect the power data associated with the set of electrical pumps or the set of switchgears by:modifying a pump rate of the first electrical pump in the set of electrical pumps; andsubsequent to modifying the pump rate, sampling a first power consumption of the first electrical pump and a first power load provided by the first switchgear.

3. The system of claim 2, wherein the memory device further includes instructions that are executable by the processing device for causing the processing device to determine the one or more causal relationships by:determining a correlation coefficient between the first power consumption and the first power load,wherein the mapping is generated based on the correlation coefficient.

4. The system of claim 2, wherein the memory device further includes instructions that are executable by the processing device for causing the processing device to determine the one or more causal relationships by:generating, based on the first power consumption and the first power load, a linear regression model,wherein the mapping is generated based on the linear regression model.

5. The system of claim 1, wherein the memory device further includes instructions executable by the processing device for causing the processing device to control the adjustment to the power load by:identifying, based on the mapping, a power failure of the first switchgear; andautomatically reallocating, based on the power failure, the power load from the first switchgear to a second switchgear in the set of switchgears.

6. The system of claim 1, wherein the memory device further includes instructions executable by the processing device for causing the processing device to control the adjustment to the power load by:determining a power limit for a power distribution unit that comprises the set of switchgears;determining, based on the mapping and the power limit, a power distribution to the individual electrical pumps via the individual switchgears; andautomatically executing the power distribution to the individual electrical pumps.

7. The system of claim 1, wherein the memory device further includes instructions executable by the processing device for causing the processing device to generate the mapping by:determining that an uncertainty value for a first causal relationship between the first electrical pump and the first switchgear is lower than a predefined threshold.

8. A method comprising:detecting, by a processing device, power data associated with a set of electrical pumps or a set of switchgears in a wellbore environment, wherein individual electrical pumps in the set of electrical pumps are electrically coupled to individual switchgears in the set of switchgears;determining, by the processing device and based on the power data, one or more causal relationships between one or more pairs of the individual electrical pumps and the individual switchgears;generating, by the processing device and based on the one or more causal relationships, a mapping indicating that a first electrical pump in the set of electrical pumps is electrically coupled to a first switchgear in the set of switchgears; andcontrolling, by the processing device and based on the mapping, an adjustment to a power load provided to the first electrical pump via the first switchgear.

9. The method of claim 8, wherein detecting the power data associated with the set of electrical pumps or the set of switchgears further comprises:modifying a pump rate of the first electrical pump in the set of electrical pumps; andsubsequent to modifying the pump rate, sampling a first power consumption of the first electrical pump and a first power load provided by the first switchgear.

10. The method of claim 9, wherein determining the one or more causal relationships further comprises:determining a correlation coefficient between the first power consumption and the first power load,wherein the mapping is generated based on the correlation coefficient.

11. The method of claim 9, wherein determining the one or more causal relationships further comprises:generating, based on the first power consumption and the first power load, a linear regression model,wherein the mapping is generated based on the linear regression model.

12. The method of claim 8, wherein controlling the adjustment to the power load further comprises:identifying, based on the mapping, a power failure of the first switchgear; andautomatically reallocating, based on the power failure, the power load from the first switchgear to a second switchgear in the set of switchgears.

13. The method of claim 8, wherein controlling the adjustment to the power load further comprises:determining a power limit for a power distribution unit that comprises the set of switchgears;determining, based on the mapping and the power limit, a power distribution to the individual electrical pumps via the individual switchgears; andautomatically executing the power distribution to the individual electrical pumps.

14. The method of claim 8, wherein generating the mapping further comprises:determining that an uncertainty value for a first causal relationship between the first electrical pump and the first switchgear is lower than a predefined threshold.

15. A non-transitory computer-readable medium comprising program code that is executable by a processing device for causing the processing device to perform operations comprising:detecting, by a processing device, power data associated with a set of electrical pumps or a set of switchgears in a wellbore environment, wherein individual electrical pumps in the set of electrical pumps are electrically coupled to individual switchgears in the set of switchgears;determining, by the processing device and based on the power data, one or more causal relationships between one or more pairs of the individual electrical pumps and the individual switchgears;generating, by the processing device and based on the one or more causal relationships, a mapping indicating that a first electrical pump in the set of electrical pumps is electrically coupled to a first switchgear in the set of switchgears; andcontrolling, by the processing device and based on the mapping, an adjustment to a power load provided to the first electrical pump via the first switchgear.

16. The non-transitory computer-readable medium of claim 15, further comprising program code that is executable by the processing device for causing the processing device to detect the power data associated with the set of electrical pumps or the set of switchgears by:modifying a pump rate of the first electrical pump in the set of electrical pumps; andsubsequent to modifying the pump rate, sampling a first power consumption of the first electrical pump and a first power load provided by the first switchgear.

17. The non-transitory computer-readable medium of claim 16, further comprising program code that is executable by the processing device for causing the processing device to determine the one or more causal relationships by:determining a correlation coefficient between the first power consumption and the first power load,wherein the mapping is generated based on the correlation coefficient.

18. The non-transitory computer-readable medium of claim 16, further comprising program code that is executable by the processing device for causing the processing device to determine the one or more causal relationships by:generating, based on the first power consumption and the first power load, a linear regression model,wherein the mapping is generated based on the linear regression model.

19. The non-transitory computer-readable medium of claim 15, further comprising program code that is executable by the processing device for causing the processing device to control the adjustment to the power load by:identifying, based on the mapping, a power failure of the first switchgear; andautomatically reallocating, based on the power failure, the power load from the first switchgear to a second switchgear in the set of switchgears.

20. The non-transitory computer-readable medium of claim 15, further comprising program code that is executable by the processing device for causing the processing device to control the adjustment to the power load by:determining a power limit for a power distribution unit that comprises the set of switchgears;determining, based on the mapping and the power limit, a power distribution to the individual electrical pumps via the individual switchgears; andautomatically executing the power distribution to the individual electrical pumps.

Images