Method and system for monitoring a power cable of an electrical power system

Abstract

The present disclosure relates to a method (100) for monitoring a power cable of an electrical power system, the power cable extending between a first and a second transformer unit, the method comprising obtaining (101) data, from said electrical power system. Further, the method comprises obtaining (102) characteristics of said power cable, characteristics comprising default cable dimensions, cable material, default capacitance of said cable and default inductance of said cable, the characteristics being indicative of a default power transferring capability of said power transmission cable. Further, the method comprises determining (103), based on the data and the characteristics, a power transferring capability of said power cable. There is also provided a system (1) for monitoring a power cable (10) of an electrical power system (15).

Description

[0001] METHOD AND SYSTEM FOR MONITORING A POWER CABLE OF AN ELECTRICAL POWER SYSTEM

[0002] TECHNICAL FIELD

[0003] The present disclosure relates to a method and system for monitoring a power cable of an electrical power system.

[0004] BACKGROUND

[0005] Power lines / cables are utilized to transfer electrical energy generated at a power plant, to e.g. residential and commercial buildings. In other words, power cables are utilized in electrical power systems for transmission and distribution of electrical energy. The power cables extend between transformer units being part of the electrical power system.

[0006] The power lines have a specific power transferring capability dependent on the power line characteristics. The power transferring capability determines the amount of electrical energy the power line can transfer / distribute. However, factors such as environmental factors can influence the power lines power transferring capability. Accordingly, a specific default power transferring capability may be increased / decreased based on environmental factors. In other words, the power transferring capability of a power line is variable based on different factors. If a power line transfers e.g., more electrical energy than it possibly should, there could be serious damage to the cable or in worst case cause outages. Based on this, the power transfer levels may be adapted or adjusted if such an increase / decrease occurs in order to avoid disturbances of faults to the electrical power system. Thus, it is of importance to continuously monitor power cables in electrical power systems to be able to proactively control the transfer of electrical energy in a safe and efficient manner.

[0007] However, systems and methods in the present art fail to in an efficient and reliable manner monitor power cables of electrical power systems. Specifically, systems and methods in the present art require expensive and unreliable measurement methods and devices that are challenging to scale.

[0008] Based on the above, there is in the present art room for improvements in order to have methods and systems that allow for monitoring a power cable of an electrical power system in a more efficient manner.

[0009] Thus, there is room for methods and devices in the present art to explore the domain of providing improved methods and systems for monitoring a power cable of an electrical power system. Specifically, the methods and devices should be efficient. Even though some currently known solutions work well in some situations it would be desirable to provide a method and system that specifically fulfils requirements relating to efficiency when monitoring power cables of electrical power systems.

[0010] SUMMARY

[0011] It is therefore an object of the present disclosure to provide a method and system to mitigate, alleviate or eliminate one or more of the above-identified deficiencies and disadvantages.

[0012] This object is achieved by means of a method and a system as defined in the appended claims.

[0013] The present disclosure is at least partly based on the insight that by providing an improved and system, power cables can be monitored more efficiently. Specifically, power cables can be monitored in a reliable and cost-efficient manner. Further, the system and method provided by the present disclosure provides improved scalability compared to conventional solutions.

[0014] The present disclosure provides a method for monitoring a power cable of an electrical power system, the power cable extending between a first and a second transformer unit. The transformer units may be substations. The method comprises the steps of obtaining data, from said electrical power system, the data being associated to at least a first point / portion of said power cable, the first point being at a first portion of the power cable. Moreover, the method comprises the step of obtaining (or in some aspects determining) characteristics of said power cable, characteristics comprising default cable dimensions, cable material, default capacitance of said cable and default inductance of said cable, the characteristics being indicative of a default power transferring capability of said power transmission cable. Determining, based on the data and the characteristics, a power transferring capability of said power cable.

[0015] An advantage of the method is that it is able to determine a power transferring capability of the power cable efficiently without the need of superfluous hardware devices.

[0016] It should be noted that the method may be for monitoring a plurality of power cables of electrical power systems. Thus, each method step may be performed for each power cable of said system or for one power cable if parameters of all power cables are common.

[0017] Moreover, the method may in step of determining power transferring capability comprise deriving, based on said data and characteristics, a cable sag of the power cable, wherein said power transferring capability is determined based on said cable sag. An advantage of this is that the method provides a further improvement in efficiency of the method as the power transferring capability is determined based on a single parameter (the cable sag), thus there is no need for special expensive sensors such as camera devices.

[0018] Further, the step of determining power transferring capability may comprise determining a capacitance and inductance alteration / change relative said default capacitance and inductance. Moreover, the step of determining may comprise determining a cable sag relative said default cable dimensions. Further, the step of determining may comprise deriving, from inputting said cable sag into a signal processing unit or a machine learning component, said power transferring capability. The method may also determine the loss and temperature of the cable based on the cable sag. In some aspects, the method may determine the capacitance and inductance alteration and based on said alteration directly allow the signal processing unit or machine learning component derive the power transferring capability.

[0019] The step of determining capacitance and inductance may comprise deriving phase shift from said data, the phase shift being derived from a comparison of data associated to said first point and a second point being at a second end portion of said cable, or, from a comparison of data measured at different time points at one of said first and second points. In other words, the data (e.g. current and voltage data) of two different points may be compared so to derive phase shift from said data.

[0020] Accordingly, based on the phase shift, the cable sag may be determined.

[0021] The data may comprise at least one of voltage and current data, thus the data may represent current and voltage values over a time period. The data may be represented as a plot, specifically sinus plots representing data over the time period. The current may be alternating current (AC).

[0022] The power cable may be a transmission and distribution cable. Moreover, the cable dimension is at least one of cable diameter, cable length and minimum distance of cable to ground.

[0023] Further, at least the step of determining a power transferring capability may comprise utilizing a machine learning component.

[0024] There is also disclosed a system for monitoring a power cable of an electrical power system, the system comprising control circuitry comprising a machine learning component, the control circuitry being configured to oobtain data associated to at least a first point of said power cable, the first point being at a first end portion of the power cable. Moreover, the control circuitry is configured to obtain, from said machine learning component or from a signal processing unit associated to said cable, characteristics of said power cable, characteristics comprising default cable dimensions, cable material, default capacitance of said cable and default inductance of said cable. The characteristics being indicative of a default power transferring capability of said power transmission cable. Further, the control circuitry is configured to determine, based on the data and the characteristics, a power transferring capability of said power cable.

[0025] The system herein provides the corresponding advantages and benefits as the method according to the present disclosure.

[0026] The control circuitry may be configured to, when determining power transferring capability, derive, based on said data and characteristics, a cable sag of the power cable, wherein the machine learning component is configured to determine a power transferring capability based on said cable sag.

[0027] Accordingly, the method may be further increased in efficiency.

[0028] Moreover, the machine learning component may be configured to use / apply a learning model indicating / defining a correlation between cable sag and power transferring capability.

[0029] Accordingly, based on the determined cable sag, the power transferring capability may be determined. Thereby, the system allows for the system to monitor variations in power transferring capability and thereby adapt the distribution of power through said cables in accordance with the power transferring capability being present.

[0030] The machine learning component may be configured to use / apply a learning model indicating a correlation between said data and said characteristics for obtaining the characteristics of said cable based on said data. Accordingly, the machine learning component may obtain data e.g. current and voltage data, and based on said data derive the characteristics of said cable. In other words, the machine learning component may, based on a specific set of data, determine that the cable length is X and that the cable diameter is Y.

[0031] An advantage of this is that the machine learning component may be less dependent on external data and may derive power transferring capabilities on little input.

[0032] It should be noted that the machine learning component may use a combination of several learning models according to any aspect herein. Moreover, the machine learning component defined in the system may be several machine learning components. Further, it should be appreciated that the machine learning components utilized in the system may be utilized in the method as well. For example, the step of determining, based on the data and the characteristics, a power transferring capability of said power cable may be performed at least a machine learning component in accordance with any machine learning component of the system. The phrase “machine learning component” may be interchanged with “machine learning module”, “machine learning agent”, “artificial intelligence agent” or any other suitable phrase.

[0033] Generally, all terms used in the description are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to “a / an / the [element, device, component, means, step, module etc.]” are to be interpreted openly as referring to at least one instance of said element, device, component, means, step, etc., unless explicitly stated otherwise.

[0034] BRIEF DESCRIPTION OF THE DRAWINGS

[0035] These and other features and advantages of the present disclosure will now be further clarified and described in more detail, with reference to the appended drawings;

[0036] Figure 1 illustrates schematically a system 1 for monitoring a power cable 10;

[0037] Figure 2 schematically illustrates an electrical power system in accordance with some aspects herein;

[0038] Figure 3 schematically illustrates a part of an electrical power system 15 in accordance with some aspects herein;

[0039] Figure 4 schematically illustrates a part of an electrical power system 15 and cable sag alteration thereof over a time period;

[0040] Figure 5 schematically illustrates different modules utilized in the control circuitry 2 for determining power transferring capability; and

[0041] Figure 6 illustrates in the form of a flowchart, a method 100 for monitoring a power cable-

[0042] DETAILED DESCRIPTION

[0043] In the following detailed description, some embodiments of the present disclosure will be described. However, it is to be understood that features of the different aspects are exchangeable between the aspects and may be combined in different ways, unless anything else is specifically indicated. Even though in the following description, numerous specific details are set forth to provide a more thorough understanding of the present disclosure, it will be apparent to one skilled in the art that the present disclosure may be practiced without these specific details. In other instances, well known constructions or functions are not described in detail, so as not to obscure the present disclosure. Figure 1 schematically illustrates a system 1 for monitoring a power cable 10 of an electrical power system 15, the system 1 comprising control circuitry 2 The control circuitry 2 being configured to obtain data 3 associated to at least a first point 3a of said power cable 10, the first point 3a being at a first end portion 3b of the power cable 10. Moreover, the system 1 is configured to obtain, from a machine learning component or from a signal processing unit associated to said cable 10, characteristics 4 of said power cable 10. Characteristics 4 of said power cable 10 comprises default cable dimensions, cable material, default capacitance of said cable 10 and default inductance of said cable 10. The characteristics 4 being indicative of a default power transferring capability of said power transmission cable 10. Further, the control circuitry 2 is configured to determine, based on the data 3 and the characteristics 4, a power transferring capability of said power cable 10.

[0044] By deriving a power transferring capability, the system 1 may communicate / transmit the realtime power transferring capability of the cable to the power system 15, thereby allowing the power system 15 to adjust the power levels in accordance with the current power transferring capability.

[0045] The characteristics 4 may be obtained e.g from a processing unit associated to said cable 10. The signal processing unit may measure / store the default capacitance, default inductance, material and default cable dimensions. The signal processing unit may be coupled to the power system / station that supplies power from the cable. However, in some aspects herein, the characteristics 4 may be obtained from a machine learning component of said control circuitry

[0046] The machine learning component may, based on the obtained data 3 derive the characteristics of the cable 10.

[0047] The term “default” as utilized herein may refer to e.g. an average (e.g. at an average temperature) or expected cable dimension or cable dimension according to specifications when initiating the system.

[0048] The term “power transferring capability” may refer to the amount of power that can be transferred from a first end of the power cable 10 to an opposing second end of the power cable 10.

[0049] The system 1 may further comprise at least one memory device 6, an input / output interface (not shown) and optionally at least one communication interface (not shown).

[0050] The at least one memory device 6 may comprise any form of volatile or non-volatile computer readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used.

[0051] The control circuitry 2 may be arranged to run instruction sets in the memory device 6 for operating a method for monitoring a power cable (e.g. as illustrated in Figure 6). The control circuitry 2 may be any suitable type such as a microprocessor, digital signal processor (DSP), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), or a combination of these, or other similar processing means arranged to run instruction sets. The computer readable storage medium may be of non-volatile and / or volatile type and transitory or non-transitory type; for instance RAM, EEPROM, flash disk and so on. It should be noted that the memory device 6 may be integrated with the control circuitry 2.

[0052] The communication interface may be of any suitable type such as Ethernet, I2C bus, RS232, CAN bus, wireless communication technology such as IEEE 802.11 based or cellular based technologies, or other communication protocols depending on application. The communication interface may be used for receiving signals from a power system or a signal processing unit of a power system. Furthermore, the communication interface may be used to communicate results, messages, status reports and similar to external devices and control units such as a control station or servers via a network, e.g. via public or private networks. The networks may be local or wide area networks depending on the use of system 1.

[0053] Memory device 6 may be used to store any calculations made by control circuitry 2 and / or any data received via output and input interfaces or power system associated to the cable 10. In some aspects, each control circuitry 2 and each memory device 6 may be considered to be integrated. In some embodiments, the memory device 6 and related data are stored in a cloud server accessible by the system 1.

[0054] Each memory device 6 may also store data that can be retrieved, manipulated, created, or stored by the control circuitry 2. The data may include, for instance, local updates, parameters, training data (e.g. historical data), trained learning algorithms (and / or the models, components, data utilized in said trained learning algorithms) and other data. Each memory device 6 may store characteristics of cable and power data correlated to said characteristics. As illustrated in Figure 1, the machine learning (ML) module 7, which may comprise one or more learning algorithms may be stored in the control circuitry 2. However, ML module may be stored in a cloud computing device accessible by the system 1. Preferably, the control circuitry 2 comprises the ML component 7 that based on data from the memory device 6 may implement at least one trained learning algorithm. The data can also be stored in one or more databases.

[0055] The one or more databases can be connected to the system 1 by a communication network.

[0056] The control circuitry 2 may include, for example, one or more central processing units (CPUs), graphics processing units (GPUs) dedicated to performing calculations, and / or other processing devices. Calculations may comprise e.g. determining power transferring capability based on inductance / capacitance and characteristics of the cable 10. The memory device 6 may comprise one or more computer-readable media and can store information accessible by the control circuitry 2, including instructions / programs (e.g. instruction for performing a method for monitoring the power cable 10) that can be executed by the control circuitry 2.

[0057] The instructions which may be executed by the control circuitry 2 may comprise instructions for implementing the trained learning algorithm according to any aspects of the present disclosure. It should be noted that in some aspects herein, the system 1 may comprise a signal processing module 8 in addition to, or instead of the ML module 7.

[0058] The control circuitry 2 may be configured to, when determining power transferring capability, derive, based on said data 3 and characteristics 4, a cable sag of the power cable, wherein the machine learning component 7 is configured to determine a power transferring capability based on said cable sag.

[0059] The machine learning component 7 may be configured to use a learning model indicating a correlation between cable sag and power transferring capability. The method may utilize at least one trained machine learning (ML) algorithm, preferably at least one of a Naive Bayes Classifier, Support Vector Machine (SVM) Linear Regression, Logistic Regression, Artificial Neural Network (ANN), Decision Trees, Random Forests, K-Nearest Neighbours (KNN) and K- means clustering.

[0060] It should be noted that ANN comprises (i) Multi-layer perceptron (MLP), (ii) Recurrent Neural Network, including Long-short term memory and Gated recurrent unit, (iii) Convolutional Neural Networks, and any combination thereof. Accordingly, after deriving the cable sag, the machine learning component 7 may based on correlation data stored in the memory device 6 derive power transferring capability of said cable 10. In other aspects, the signal processing unit 8 may derive the power transferring capability based on signal processing calculations.

[0061] The expression “cable sag” may refer to as a vertical difference in level between points of support (e.g. transmission towers) and the lowest point of the conductor (i.e. a point being closest to earth). In some aspects herein, the system / method may be configured to derive a cable sag difference from a default cable sag, accordingly, the system 1 may prior to determining cable sag derive a default cable sag.. Thus, the characteristics 4 may also comprise default cable sag. Moreover, the characteristics may also comprise transmission tower height from earth.

[0062] The machine learning component 7 may be configured to use a learning model indicating a correlation between said data 3 and characteristics 4 for obtaining the characteristics 4 of said specific cable 10 based on said data 3.

[0063] The data 4 may comprise at least one of voltage and current data. The data 4 may be, as illustrated in Figure 1, represented as sinus plots representing data over a time period. The time period may be shorter time periods of 1-24 hours or longer time periods of 1-10 days. In some aspects herein the time period may be continuous such that the data is obtain continuously.

[0064] Figure 2 illustrates an example of a power system 15, the power system 15 comprising power cables 10 connected in-between transformer units / substations 16 for transferring power. Further, the power cables 10 may comprise supports in the form of transmission towers 17. The power generated / supplied may stem from a power station 18. The characteristics 4 may be derived from the machine learning component 7 as illustrated in Figure 1 or a signal processing unit being associated to the cable 10, the signal processing unit may be an external signal processing unit part of the power system 15 or a signal processing unit / electronic device 8 part of the system 1 that is connected / coupled to the cable 10 for deriving said characteristics. The power system 15 may e.g. at implementation of the system 1 at the power system 15 transmit the characteristics 4 to the system 1, allowing the system 1 to gain knowledge of default values of the cable 10 when being initiated. Moreover, cable dimension of the cable 10 may be at least one of cable diameter, cable length and minimum distance of cable to ground / earth. Further, as illustrated in Figure 2, the power cable 10 may be a transmission and distribution power cable.

[0065] Figure 3 schematically illustrates a power cable 10 of a power system communicating with the system 1 herein. The system 1 may communicate with a signal processing device / electronic device 19 for obtaining data and characteristics. The signal processing device / electronic device 19 may comprise sensors / memory devices (not shown) recording and storing data / characteristics of the cable 10 and power system. In some aspects, the electronic device 19 may be one or more sensors. Figure 3 further illustrates an example circuitry of the cable 10. As shown in Figure 3, the cable 10 may comprise parameters of inductance L, capacitance C and resistance R. The inductance, resistance and capacitance L, C of said circuitry A may be equally distributed along the entire length of the line. It should be noted that dependent on the length of the cable, the circuitry may differ. Thus the method and system herein may determine the variation of capacitivity between cable and ground and inductivity of the cable over time.

[0066] Figure 4 schematically illustrates cable sag of power cables 10 over a time period. As illustrated in Figure 4, based on external factors (such as temperature changes) the cable sag increases. Thereby, the power transferring capability decreases. Accordingly, the amount of power transfer should be adjusted. Figure 4 illustrates that the cable sag caused the cable to alter with a distance d from ground. Accordingly, the control circuitry 2 may derive the cable sag alteration d.

[0067] Figure 5 illustrates schematically modules of the control circuitry 2 in accordance with some aspects herein. Figure 5 illustrates Modules 1-4, the modules 1-4 may correspond to the ML module 7 / signal processing module 8 as illustrated in Figure 1. Accordingly, in some aspects herein, the control circuitry 2 may comprise a first module, module 1 for deriving phase shifts and (but not limited to) resistivity from the obtained data. Moreover, the control circuitry 2 may comprise a second module module 2 for deriving capacitance, inductance and resistance alterations based on said phase shift. Moreover, the control circuitry 2 may comprise a third module, module 3 for deriving cable sag based on said phase shift. Furthermore, the control circuitry 2 may comprise a fourth module, module 4 for deriving power transferring capability, temperature and / or loss of the cable.

[0068] In some aspects, the system may derive the power transferring capability based on the data 3 By utilizing a single ML component. In other aspects, the system may sequentially derive phase shift based on the data and characteristics 3, 4, by signal processing utilized in module 1. Further, the control circuitry 2 may derive capacitance and inductance based on said signal processing in another (or in some aspects the same) module, module 2. Also, the control circuitry 2 may derive cable sag in the corresponding manner in module 3. Furthermore, the control circuitry 2 may utilize, in module 4, machine learning to derive the power transferring capability.

[0069] The arrows a1 indicate that in some aspects of the present disclosure, the control circuitry 2 may derive the power transferring capability by utilizing machine learning, thereby disregarding some modules by utilizing models in the machine learning module of module 4.

[0070] Figure 6 illustrates in the form of a flowchart, a method 100 for monitoring a power cable of an electrical power system, the power cable extending between a first and a second transformer unit, the method 100 comprising the steps of obtaining 101 data, from said electrical power system, associated to at least a first point of said power cable (as shown in e.g. Figure 1-3), the first point being at a first portion of the power cable. Further, the method 100 comprises the step of obtaining 102 characteristics of said power cable, characteristics comprising default cable dimensions, cable material, default capacitance of said cable and default inductance of said cable, the characteristics being indicative of a default power transferring capability of said power transmission cable. The characteristics may be obtained from the power system or by utilizing machine learning components in the method 100. Further, the method comprises the step of determining 103, based on the data and the characteristics, a power transferring capability of said power cable. Accordingly, the method 100 may determine a current power transferring capability of the cable as the default power transferring capability may have been altered (increased or reduced) after being affected by external factors.

[0071] The step of determining power transferring capability may comprise deriving, based on said data and characteristics, a cable sag of the power cable, wherein said power transferring capability is determined based on said cable sag. The expression cable sag may be interchanged with cable stretch.

[0072] Further, in some aspects of the method 100, the step of determining 103 power transferring capability comprises determining 103b a capacitance and inductance alteration relative said default capacitance and inductance. Further, determining 103c a cable sag relative said default cable dimensions. Further, the method 100 may derive 103d, from inputting said cable sag (i.e. cable sag values) into a signal processing unit or a machine learning component, said power transferring capability.

[0073] The step of determining 103a capacitance and inductance may comprise deriving 103a phase shift from said data, the phase shift being derived from a comparison of data associated to said first point and a second point being at a second end portion of said cable, or, from a comparison of data measured at different time points at one of said first and second points. Accordingly, the phase shift may be derived either by obtaining iteratively, data from said first point and comparing said data to derive the phase shift, or, by comparing data obtained from a first and opposing second point of the cable to each other.

[0074] In some aspects, the method may further comprise the step of transmitting (not shown) the determined current power transferring capability to the power system. Enabling the power system to adapt its power supply to the cable.

[0075] The present disclosure may also relate to a method for training a learning algorithm for monitoring a power cable of an electrical power system, the method may comprise the steps of obtaining data, from said electrical power system, associated to at least a first point of said power cable, the first point being at a first portion of the power cable. Further, the method may comprise the step of obtaining characteristics of said power cable, characteristics comprising default cable dimensions, cable material, default capacitance of said cable and default inductance of said cable, the characteristics being indicative of a default power transferring capability of said power transmission cable. Further, the method may comprise the step of training the learning algorithm to determine said characteristics based on said data. Further, the method may comprise the step of determining, based on the data and the characteristics, a power transferring capability of said power cable. Accordingly, the method further may comprise the step of training the learning algorithm to determine the power transferring capability based on the data and the characteristics.

Claims

CLAIMS1. A method (100) for monitoring a power cable of an electrical power system, the power cable extending between a first and a second transformer unit, the method comprising: obtaining (101) data, from said electrical power system, associated to at least a first point of said power cable, the first point being at a first portion of the power cable; obtaining (102) characteristics of said power cable, characteristics comprising default cable dimensions, cable material, default capacitance of said cable and default inductance of said cable, the characteristics being indicative of a default power transferring capability of said power transmission cable; determining (103), based on the data and the characteristics, a power transferring capability of said power cable.

2. The method (100) according to claim 1 , wherein said step of determining power transferring capability comprises deriving, based on said data and characteristics, a cable sag of the power cable, wherein said power transferring capability is determined based on said cable sag.

3. The method (100) according to claim 1 or 2, wherein the step of determining (103) power transferring capability comprises: i. determining (103b) a capacitance and inductance alteration relative said default capacitance and inductance; ii. determining (103c) a cable sag relative said default cable dimensions iii. deriving (103d), from inputting said cable sag into a signal processing unit or a machine learning component, said power transferring capability.

4. The method (100) according to claim 3, determining (103a) capacitance and inductance comprises: deriving (103a) phase shift from said data, the phase shift being derived from a comparison of data associated to said first point and a second point being at a second end portion of said cable, or, from a comparison of data measured at different time points at one of said first and second points.

5. The method (100) according to any one of the preceding claims, wherein the data comprises at least one of voltage and current data.

6. The method (100) according to any one of the preceding claims, wherein the power cable is a transmission and distribution power cable.

7. The method (100) according to any one of the preceding claims, wherein the data is represented as sinus plots representing data over a time period.

8. The method (100) according to any one of the preceding claims, wherein cable dimension is at least one of cable diameter, cable length and minimum distance of cable to ground.

9. The method (100) according to any one of the preceding claims, wherein at least the step of determining (103) a power transferring capability comprises utilizing a machine learning component.

10. A system (1) for monitoring a power cable (10) of an electrical power system (15), the system (1) comprising: control circuitry (2) being configured to: o obtain data (3) associated to at least a first point (3a) of said power cable (10), the first point (3a) being at a first end portion (3b) of the power cable (10); o obtain, from a machine learning component (7) or from a signal processing unit associated to said cable (10), characteristics (4) of said power cable (10), characteristics comprising default cable dimensions, cable material, default capacitance of said cable and default inductance of said cable, the characteristics being indicative of a default power transferring capability of said power cable (10); o determine, based on the data (3) and the characteristics (4), a power transferring capability of said power cable (10).

11. The system (1) according to claim 10, wherein the control circuitry (2) is configured to, when determining power transferring capability, derive, based on said data (3) and characteristics (4), a cable sag of the power cable (10), wherein the machine learning component (7) is configured to determine a power transferring capability based on said cable sag.

12. The system (1) according to claim 11, wherein the machine learning component (7) is configured to use a learning model indicating a correlation between cable sag and power transferring capability.

3. The system (1) according to any one of the claims 10-12, wherein the machine learning component (7) is configured to use a learning model indicating a correlation between said data and said characteristics for obtaining the characteristics of said cable based on said data (3).

Images