Method and processing system for commissioning a supervisory control and data acquisition system (SCADA)

Abstract

Techniques useful for commissioning a Supervisory Control and Data Acquisition (SCADA) system (40) of an electric power system are provided, with commissioning being performed at an installation site (18) of the SCADA system after the SCADA system has been tested at a test site different from the installation site. Baseline data that is based on observations collected by a processing system (70) during testing of the SCADA system at the test site is used to perform an abnormality detection in which monitoring data collected by the processing system (70) at the installation site (18) is evaluated based on the baseline data.

Description

[0001] METHOD AND PROCESSING SYSTEM FOR COMMISSIONING A SUPERVISORY CONTROL AND DATA ACQUISITION SYSTEM (SCADA)

[0002] TECHNICAL FIELD

[0003] Embodiments of the invention relate to processing systems and methods useful in commissioning a Supervisory Control and Data Acquisition (SCADA) system. Embodiments of the invention relate in particular to processing systems and methods for commissioning a SCADA system for an electric power system, such as a high voltage direct current (HVDC) system. Embodiments of the invention also relate to techniques of performing control actions related to an electric power system.

[0004] BACKGROUND

[0005] Systems that comprise devices and a Supervisory Control and Data Acquisition (SCADA) system for monitoring and coordinating these devices are widely used. Such devices and SCADA systems may be implemented in an automation control system, such as an automation control system for use in electric power system automation (e.g. substation automation systems) or other infrastructure automation systems.

[0006] SCADA systems for electric power systems are complex and may comprise a significant number of devices and function instances executed on these devices. Commissioning such a SCADA system is, thus, a complex task which may involve hardwiring and interconnections done by humans that are prone to errors. Occurrence of such errors subsequently delays the commissioning activities, as it adds more tasks for scrutiny and testing before a station can start field operation.

[0007] The complexity of the commissioning task is exacerbated by the large number of potential root causes of errors, such as incorrect hardwiring, device name changes, network configuration changes, hardware changes between factory testing and commissioning or other similar changes that were not adequately considered, or incorrect settings of logics of the SCADA system, such as incorrect softwiring. Conventionally, such errors are fixed only on manual detection and thorough checks performed by site engineers during the testing phase that can span a few months (e.g., two or more months). Moreover, theses checks are conventionally done with a rules based approach, that is closely tied to the domain knowledge.

[0008] Thus, there is a need for techniques useful in commissioning a SCADA system for an electric power system.

[0009] US 11 016 475 B2 discloses techniques for automatically commissioning an electrical system in industrial / commercial settings. Automated data collection devices can collect commissioning data related to electrical and other characteristics of electrical equipment. Automation software can access commissioning data from the automated data collection devices over a computer network. However, conventional techniques of assisting or automatically performing commissioning tasks may not adequately reflect the complexity and potential root causes for commissioning errors encountered in electric power systems, such as high voltage direct current (HVDC) systems. In particular, there is an ongoing need in the art of methods and processing systems useful in commissioning a SCADA system for an electric power system that is first tested at a test site and that is rewired at an installation site at which the SCADA system is being commissioned.

[0010] SUMMARY

[0011] It is an object of the invention to provide methods and processing systems that provide enhanced commissioning techniques applicable in association with an electric power system. It is in particular an object of the invention to provide methods and processing systems that can be used in association with a Supervisory Control and Data Acquisition (SCADA) system that first undergoes factory tests, then is disassembled and shipped to an installation site, and which is then rewired at the installation site to bring it back to a tested and accepted / approved state before the shipment to installation site. It is in particular an object of the invention to provide methods and processing systems that can leverage knowledge obtained during testing at the test site in commissioning of the SCADA system.

[0012] According to exemplary embodiments, methods and systems as recited in the claims are provided.

[0013] According to an aspect of the invention, there is provided a method of commissioning a SCADA system or useful in commissioning of an electric power system at an installation site of the SCADA system after the SCADA system has been tested at a test site different from the installation site. The method comprises monitoring, by a processing system, the SCADA system after rewiring of the SCADA system at the installation site, comprising collecting monitoring data during commissioning of the SCADA system at the installation site. The processing system comprises a storage system having stored therein baseline data for SCADA system behavior, the baseline data being based on data captured by the processing system during testing of the SCADA system at the test site. The method comprises performing, by the processing system, an abnormality detection to detect abnormalities during commissioning, wherein the abnormality detection comprises using the baseline data to evaluate the collected monitoring data. The method comprises generating, by the processing system, output based on a result of the abnormality detection.

[0014] Various effects and advantages are associated with the method. By providing the processing system that performs the abnormality detection, using baseline data that depend on data captured by the processing system during testing of the SCADA system at the test site, discrepancies between the SCADA system rewired at the installation site can be detected by comparing SCADA system behavior post-rewiring to SCADA system behavior pre-rewiring. Depending on the baseline data, any one or any combination of various types of abnormalities can be detected, such as abnormalities caused by incorrect hardwiring or abnormalities caused by incorrect softwiring, such as incorrect logics connections of the SCADA system.

[0015] Generating the output may comprise generating output indicating the presence of an abnormality.

[0016] Thereby, the presence of an abnormality may be indicated automatically and without requiring manual interventions during commissioning.

[0017] Generating the output may comprise generating output indicating a root cause of the abnormality and / or devices of the SCADA system affected by the abnormality.

[0018] Thereby, the processing system aids a commissioning engineer in the task of identifying the root cause and / or affected devices, making it easier to take appropriate corrective action.

[0019] The collected monitoring data may comprise data from a first SCADA subsystem and data from a second SCADA subsystem , wherein the first and second SCADA subsystems are comprised by or associated with a same station (e.g., a local station). The first and second SCADA subsystems may be so-called "A" or "active" and "B" or "standby" subsystems. The second SCADA subsystem may comprise a redundant implementation of the first SCADA subsystem. The abnormality detection may use the baseline data to evaluate both the data from the first SCADA subsystem (e.g., the "A" or "active" subsystem) and the data from the second SCADA subsystem (e.g., the "B" or "standby" subsystem).

[0020] Thereby, the processing system is operative to assist in commissioning of SCADA systems having redundant subsystems, in which case the commissioning is particularly challenging and error-prone due to the large number of devices required to provide redundancy.

[0021] Commissioning the SCADA system may comprise commissioning the first SCADA subsystem and the second SCADA subsystem to ensure availability of the SCADA systems to control and operate the main station functions.

[0022] Thereby, the processing system is useful for commissioning the first and second SCADA subsystems that are intended to operate in a manner which allows a change-over to be performed between the first and second SCADA subsystems during field operation^

[0023] The first SCADA subsystem (e.g., the "A" or "active" subsystem for a station) may be operative to perform control and protection functions for a first (e.g., the "A" or "active") electric power subsystem. The second SCADA subsystem (e.g., the "B" or "standby" subsystem for the same station) may be operative to perform control and protection functions for a second electric power subsystem(e.g., the "B" or "standby" of a same station as the first electric power subsystem). The second electric power subsystem may be a backup system for the first electric power subsystem. The first electric power subsystem and the second electric power subsystem may be comprised by a same station (e.g., a station at a near end or a remote end of a line). Thereby, the processing system is useful for commissioning tasks in association with electric power systems that comprise both main electric power system equipment and backup electric power system equipment, with the backup electric power system equipment providing a backup electric power subsystem for the main electric power subsystem. Such implementations are beneficial in terms of continuous operation, while making commissioning more challenging in view of the increased complexity of the SCADA system. This challenge is mitigated by the processing system that assist in the identification of abnormalities during commissioning.

[0024] The SCADA system may comprise a change-over logic operative to trigger switching between the first electric power subsystem and the second electric power subsystem to ensure continuous operation of inverter / converter stations, wherein the processing device is operative to detect an abnormality related to the change-over logic.

[0025] Thereby, the processing system is useful for commissioning tasks in association with electric power systems that comprise both main electric power system equipment and backup electric power system equipment. This is of particular relevance to a SCADA system that needs to be rewired at the installation site.

[0026] Performing the abnormality detection may comprise detection of an incorrect installation of physical wires between SCADA system devices at the installation site. The detection of the incorrect installation may comprise errors with interchanged connections with ferrule numbering, without being limited thereto.

[0027] Thereby, abnormalities caused by incorrect hardwiring may be detected using the baseline data.

[0028] Performing the abnormality detection may comprise verifying an operation logics of the SCADA system.

[0029] Thereby, abnormalities caused by incorrect operation logics may be detected using the baseline data. This is of particular relevance to a SCADA system that needs to be rewired at the installation site, in which case changes in hardware of SCADA devices may take place upon rewiring.

[0030] Verifying the operation logics may comprise detecting an incorrect softwiring in SCADA system engineering data at the installation site.

[0031] Thereby, abnormalities caused by incorrect softwiring may be detected using the baseline data. This is of particular relevance to a SCADA system that needs to be rewired at the installation site, in which case changes in softwiring may have to be made due to, e.g., name changes desired by the operator of the electric power system.

[0032] Verifying the operation logics may comprise detecting an incorrect data flow configuration between function instances of the SCADA system at the installation site.

[0033] Thereby, abnormalities caused by incorrect data flow configurations may be detected using the baseline data. This is of particular relevance to a SCADA system that needs to be rewired at the installation site, in which case changes in data flow configuration may have to be made due to, e.g., name changes desired by the operator of the electric power system. The baseline data may be such that they include all positive accepted test data obtained at the test site. The baseline data may be such that they do not include negative, i.e. rejected, test data obtained at the test site.

[0034] Performing the abnormality detection comprises detecting one, several, or all of the following: changes in hardware configuration at the installation site as compared to the test site; changes in names at the installation site as compared to the test site; changes in network ports at the installation site as compared to the test site.

[0035] Thereby, the processing system can assist in the detection of various types of abnormalities.

[0036] The collected monitoring data (i.e., the data collected during commissioning at the installation site post-rewiring) may comprise timeseries data. The abnormality detection may comprise automated processing the timeseries data.

[0037] Thereby, the processing system can efficiently perform abnormality detection based on timeseries data, which are indicative of dynamic system behavior.

[0038] The collected monitoring data may comprise data from a first SCADA subsystem and data from a second SCADA subsystem. The second SCADA subsystem may comprise a redundant implementation of the first SCADA subsystem for a same station of the electric power system. The data from the first SCADA subsystem may comprise first timeseries data. The data from the second SCADA subsystem may comprise second timeseries data. The abnormality detection may comprise processing the first timeseries data and the second timeseries data in parallel or otherwise processing the first timeseries data and the second timeseries data jointly. The abnormality detection may comprise or may provide basic checks that include all aspects of configuration, wiring, and / or settings etc. and functional checks that involve checks related to logics and functionality driven aspects.

[0039] Thereby, the processing system can efficiently perform abnormality detection based on the dynamic behavior of the first and second SCADA subsystems. Deviations from a desired operation can be detected, taking into consideration the baseline data.

[0040] The baseline data may comprise baseline timeseries data captured by the processing system during testing of the SCADA system at the test site. The abnormality detection may comprise using the baseline timeseries data to process the monitoring data collected at the installation site.

[0041] Thereby, the abnormality detection can be performed in an efficient manner based on a comparison of timeseries, with one timeseries being captured when tests are performed during commissioning at the installation site and the other timeseries being captured during testing at the test site.

[0042] The abnormality detection may comprise comparing: the baseline timeseries data captured at the test site by the processing system during when a test system inputs a test scenario to the SCADA system to the timeseries data included in the monitoring data, with the timeseries data included in the monitoring data being captured by the processing system when the SCADA system is subjected to the test scenario at the installation site.

[0043] Thereby, abnormality detection can be performed in a versatile manner applicable to a wide variety of different devices and test scenarios.

[0044] The timeseries data captured at the test site and the timeseries data included in the monitoring data may respectively comprise measurements, such as measurements relating to one, several or all of electric characteristics (voltages, currents, phasors), temperatures, insulation, moisture in insulation, dissolved gas analysis (DGA) results, components comprising power semiconductor devices, such as power semiconductor devices having a control gate (e.g., thyristors or Insulated Gate Bipolar Transistors (IGBTs)), thyristor or IGBT valves of a converter / inverter, other converter / inverter characteristics, without being limited thereto.

[0045] Thereby, abnormality detection can be performed in a versatile manner applicable to a wide variety of different devices and test scenarios.

[0046] The baseline timeseries data may comprise first baseline timeseries data captured for a first SCADA subsystem at the test site by the processing system when a test system inputs a test scenario to the first SCADA subsystem, with the baseline timeseries data further comprising second baseline timeseries data captured for a second SCADA subsystem at the test site by the processing system when the test system inputs the test scenario to the second SCADA subsystem, wherein the second SCADA subsystem is a redundant implementation of the first SCADA subsystem. The timeseries data included in the monitoring data may comprise first timeseries data captured for the first SCADA subsystem at the installation site by the processing system when the first SCADA subsystem is subject to the test scenario during commissioning, with the timeseries data included in the monitoring data further comprising second timeseries data captured for the second SCADA subsystem at the test site by the processing system when the second SCADA subsystem is subjected to the test scenario during commissioning. The abnormality detection may comprise comparing the first baseline timeseries data to the first timeseries data included in the monitoring data and comparing the second baseline timeseries data to the second timeseries data included in the monitoring data. An abnormality can be detected responsive to a difference between the first baseline timeseries data to the first timeseries data included in the monitoring data fulfilling an abnormality criterion (such as a threshold criterion) and / or a difference between the second baseline timeseries data to the second timeseries data included in the monitoring data fulfilling the abnormality criterion (such as a threshold criterion). Thereby, abnormality detection can be performed in a versatile manner applicable to a wide variety of different devices and test scenarios when the SCADA system has first and second SCADA subsystems.

[0047] The baseline data may comprise parameters of an artificial intelligence (Al) model. The Al model(s) may define several processing techniques that receive, at their input, the monitoring data obtained from the SCADA system at the test site and provide, at their output, data indicative of a hardwiring, softwiring, and / or configuration issue.

[0048] Performing the abnormality detection may comprise processing at least part of the monitoring data using the Al model. The Al model has an input operative to receive an Al model input that comprises or is otherwise based on at least part of the monitoring data collected at the installation site, one or several hidden Al model layers, and an output operative to provide an Al model output. An abnormality detection result may be based on the Al model output.

[0049] Thereby, the processing system may harness observations made during testing of the SCADA system at the test site for performing the abnormality detection, by using an Al model that depends on these observations made during testing at the test site. During commissioning, the processing system can apply the Al model to the monitoring data. This allows abnormality detection to be performed efficiently. Storage space requirements in the system storage are reduced as compared to storing the complete timeseries data captured during the testing at the test site.

[0050] The processing system may be operative to use a set of supervised, semi-supervised , unsupervised or self-supervised techniques that are applicable based on a context of the monitoring data and / or availability of ground truth labels. Processing implementations such as long short term memory (LSTM), convolutional neural network (CNN), autoencoders and / or other can be used in association with these techniques.

[0051] Thereby, the processing system may harness observations made during testing of the SCADA system at the test site for performing the abnormality detection.

[0052] The processing system may be operative such that various machine learning (ML) techniques may be applied to parse data, learn from useful data aggregated during tests to support detection of abnormal decision making based on learning over a period. Variations includes the structuring of the Al-based processing techniques in layers to create an "artificial neural network" that can learn and support intelligent decisions making.

[0053] Thereby, the processing system may harness observations made during testing of the SCADA system at the test site for performing the abnormality detection, by using ML techniques that depend on these observations made during testing at the test site.

[0054] The processing system may be operative such that the Al model is operative to process timeseries data. Thereby, the processing system can identify abnormalities based on the SCADA system dynamics as reflected by the timeseries data.

[0055] Alternatively or additionally, the processing system may be operative such that the Al model comprises long short term memory (LSTM) cells and / or gated recurrent units (GRUs) to process timeseries data and / or may comprise other approaches with autoencoders or its variations using ensemble methods that are proven to be also effective depending on whether the ground truth labels are available or not.

[0056] Thereby, the processing system can identify abnormalities based on the SCADA system dynamics as reflected by the timeseries data.

[0057] Alternatively or additionally, the processing system may be operative such that the Al model comprises at least one attention mechanism, such as a self-attention mechanism, a cross-attention mechanism, a multi-head self or cross-attention mechanism, without being limited thereto.

[0058] Thereby, the processing system can identify abnormalities based the local or global context of the monitoring data indicative of the SCADA system behavior.

[0059] Alternatively or additionally, the processing system may be operative such that the Al model comprises a stack of self-attention mechanisms.

[0060] Thereby, the processing system can identify abnormalities based the local or global context of the monitoring data indicative of the SCADA system behavior.

[0061] Alternatively or additionally, the processing system may be operative such that the Al model comprises an Al-transformer model.

[0062] Thereby, the processing system can identify abnormalities based the local or global context of the monitoring data indicative of the SCADA system behavior.

[0063] Alternatively or additionally, the processing system may be operative such that the Al model comprises a convolutional neural network (CNN).

[0064] Thereby, the processing system can identify abnormalities in a data-driven manner.

[0065] In any of the above cases, the processing system may be operative such that the Al model is trained based on the observations captured during testing of the SCADA system at the test site.

[0066] Thereby, the processing system can identify abnormalities in a data-driven manner, eliminating the risk of human judgment error.

[0067] The Al model may comprise an autoencoder, wherein an encoder of the autoencoder is operative to receive the Al model input and to output a code, wherein the Al model comprises a decoder operative to receive the code and provide the Al model output.

[0068] Thereby, the processing system can identify abnormalities in a data-driven manner using an encoder-decoder structure, eliminating the risk of human judgment error. The Al model output may be dependent on a reconstruction loss. The encoder may comprise a first stack of attention mechanisms and the decoder may comprise a second stack of attention mechanisms.

[0069] Thereby, the processing system can identify abnormalities in a data-driven manner based the local or global context of the monitoring data indicative of the SCADA system behavior.

[0070] The Al model may comprise a trained Al-transformer.

[0071] Thereby, the processing system can identify abnormalities in a data-driven manner based the local or global context of the monitoring data indicative of the SCADA system behavior.

[0072] The method may comprise training the Al model based on observations captured by the processing system during testing of the SCADA system at the test site.

[0073] Thereby, the logic applied by the SCADA system can be generated in a data-driven manner, mitigating the risk of human-induced error.

[0074] The SCADA system may be or may comprise a high voltage direct current (HVDC) system SCADA system.

[0075] Thereby, the commissioning of the SCADA system is facilitated in the context of a HVDC system SCADA system, where commissioning may be particularly complex. All features relating to the provision of redundant subsystems are particularly applicable in the HVDC context where such redundancy is often provided.

[0076] The SCADA system may comprise control and protection devices for HVDC power system assets. The HVDC power system assets may comprise one, several, or all of: an inverter / converter asset; a cooling system for an inverter / converter asset; a transformer comprising three single-phase transformers or a single 3-phase transformer operated under control of the control and protection devices.

[0077] Thereby, the commissioning of the SCADA system is facilitated in the context of a HVDC system SCADA system, where commissioning may be particularly complex. All features relating to the provision of redundant subsystems are particularly applicable in the HVDC context where such redundancy is often provided.

[0078] The SCADA system may be operative to monitor secondary devices in the SCADA system. Monitoring the secondary devices may comprise monitoring hardware usage of the secondary devices that perform control and protection functions.

[0079] Thereby, the commissioning of the SCADA system is facilitated when the SCADA system also monitors the secondary devices.

[0080] According to another aspect of the invention, there is provided a method of operating an electric power system using a Supervisory Control and Data Acquisition (SCADA) system. The method comprises commissioning the SCADA system, comprising performing any one of the commissioning techniques disclosed herein, and performing, by the SCADA system, control and protection operations for the electric power system.

[0081] Thereby, operation and control of the electric power system is attained using a SCADA system that is commissioned in a manner that reduces the risk of errors during commissioning, as explained herein in detail. The risk of SCADA system malfunction with potentially catastrophic consequences is reduced.

[0082] According to another aspect of the invention, there is provided a processing system operative for use in commissioning a Supervisory Control and Data Acquisition, SCADA, system of an electric power system at an installation site of the SCADA system after the SCADA system has been tested at a test site different from the installation site. The processing system comprises a storage system having stored therein baseline data for SCADA system behavior, the baseline data being based on data captured by the processing system during testing of the SCADA system at the test site. The processing system comprises at least one processing circuit operative to monitor the SCADA system at the installation site, comprising collecting monitoring data during commissioning of the SCADA system at the installation site, perform an abnormality detection to detect abnormalities during commissioning, wherein the abnormality detection comprises using the baseline data to evaluate the collected monitoring data, and cause output to be provided based on a result of the abnormality detection.

[0083] Various effects and advantages are attained by the processing system. The processing system is operative such that it performs the abnormality detection, using baseline data that depend on data captured by the processing system during testing of the SCADA system at the test site. Thus, discrepancies between the SCADA system rewired at the installation site can be detected by comparing SCADA system behavior post-rewiring to SCADA system behavior pre-rewiring. Depending on the baseline data, any one or any combination of various types of abnormalities can be detected, such as abnormalities caused by incorrect hardwiring or abnormalities caused by incorrect softwiring, such as incorrect logics settings of the SCADA system.

[0084] The at least one processing circuit is further operative to perform monitoring of the SCADA system during testing at the test site and to generate the baseline data based on the monitoring of the SCADA system.

[0085] Thereby, the processing system is operative to generate the baseline data required for subsequent processing of the monitoring data after rewiring of the SCADA system to perform the abnormality detection.

[0086] The at least one processing circuit may be operative to store in the storage system baseline data comprising baseline timeseries data obtained by the processing system while the SCADA system is installed at the installation site for use in performing the abnormality detection. Thereby, the abnormality detection can be performed in a versatile manner using the information included in the dynamic SCADA system behavior both at testing at the test site and during commissioning at the installation site.

[0087] The at least one processing circuit may be operative to store in the storage system baseline data comprising parameters of at least one Al model, with the parameters of the at least one Al model being based on observations of SCADA system behavior while the SCADA system is installed at the test site. The at least one processing circuit may be operative to perform the abnormality detection by generating Al model input from the monitoring data and providing Al model input to the at least one Al model, and to generate the output based on an Al model output of the at least one Al model.

[0088] Thereby, the abnormality detection can be performed in an efficient manner, using an Al model that is generated in a data-driven manner. This reduces the risk in human-induced error.

[0089] The processing system may be operative to perform the method of any aspect or embodiment. Similarly, the method of any aspect of embodiment may be performed by or using the processing system disclosed herein.

[0090] According to another aspect, there is provided an electric power system comprising primary power system equipment, a SCADA system operative to perform control and protection functions for the primary power system equipment, and the processing system of any aspect or embodiment disclosed herein.

[0091] The electric power system provides the effect that the processing system can identify abnormal SCADA system behavior indicative of incorrect hardwiring or softwiring at the installation site, as compared to a previously observed SCADA system behavior at the test site.

[0092] The SCADA system may comprise a first SCADA subsystem (e.g., an "A" or "active" subsystem of a station) and a second SCADA subsystem (e.g., a "B" or "standby" subsystem of the same station). The second SCADA subsystem may comprise a redundant implementation of the first SCADA subsystem.

[0093] Thereby, the processing system is operative to assist in commissioning of SCADA systems having redundant subsystems (also referred to as "A" and "B" or "active" and "standby" subsystems), in which case the commissioning is particularly challenging and error-prone due to the large number of devices required to provide redundancy.

[0094] The first (e.g., "A" or "active") SCADA subsystem may be operative to perform control and protection functions for a first sub-set of the primary power system equipment and the second (e.g., "B" or "standby") SCADA subsystem may be operative to perform control and protection functions for a second sub-set of the primary power system equipment. The first sub-set may comprise a redundant implementation of the second sub-set within a same station (e.g., a local or remote station).

[0095] Thereby, the processing system is useful for commissioning tasks in association with electric power systems in which the primary power system equipment comprises both main electric power system equipment and backup electric power system equipment within a same station (e.g., local or remote), with the backup electric power system equipment providing a backup electric power subsystem for the main electric power subsystem. Such implementations are beneficial in terms of continuous operation, while making commissioning more challenging in view of the increased complexity of the SCADA system. This challenge is mitigated by the processing system that assist in the identification of abnormalities during commissioning.

[0096] The SCADA system may comprise a change-over logic operative to trigger switching between the first electric power subsystem and the second electric power subsystem to ensure continuous operation of inverter / converter stations, wherein the processing device is operative to detect an abnormality related to the change-over logic.

[0097] Thereby, the processing system is useful for commissioning tasks in association with electric power systems that comprise both main electric power system equipment and backup electric power system equipment. This is of particular relevance to a SCADA system that needs to be rewired at the installation site.

[0098] The primary power system equipment may comprise high voltage direct current (HVDC) power system equipment.

[0099] Thereby, the commissioning of the SCADA system is facilitated in the context of a HVDC system SCADA system, where commissioning may be particularly complex. All features relating to the provision of redundant subsystems are particularly applicable in the HVDC context where such redundancy is often provided.

[0100] The SCADA system may comprise control and protection devices for HVDC power system assets. The primary power system equipment may comprise the HVDC power system assets. The HVDC power system assets may comprise one, several, or all of: an inverter / converter asset; a cooling system for an inverter / converter asset; a transformer comprising three single-phase transformers synchronously operated under control of the control and protection devices.

[0101] Thereby, the commissioning of the SCADA system is facilitated in the context of a HVDC system SCADA system, where commissioning may be particularly complex. All features relating to the provision of redundant subsystems are particularly applicable in the HVDC context where such redundancy is often provided.

[0102] According to another aspect of the invention, there is provided machine-readable instruction code comprising machine-readable instructions which, when executed by at least one processing circuit, cause the at least one processing circuit to perform the method according to an aspect or embodiment of the invention.

[0103] The effects attained by the machine-readable instruction code correspond to the effects disclosed in association with the methods and processing systems according to various embodiments. According to another aspect of the invention, there is provided non-transitory storage medium having stored thereon machine-readable instruction code comprising machine-readable instructions which, when executed by at least one processing circuit, cause the at least one processing circuit to perform the method according to an aspect or embodiment of the invention.

[0104] The effects attained by the non-transitory storage medium correspond to the effects disclosed in association with the methods and processing systems according to various embodiments.

[0105] Various effects and advantages are attained by embodiments of the invention. For illustration, the methods and processing provide enhanced commissioning techniques applicable in association with an electric power system. The methods and processing systems are applicable to a Supervisory Control and Data Acquisition (SCADA) system that first undergoes factory tests, then is disassembled and shipped to an installation site, and which is then rewired at the installation site. The methods and processing systems leverage observations of SCADA system behavior obtained during testing at the test site in commissioning the SCADA system.

[0106] The processing systems and methods can be used in association with a HVDC power transmission system or subsystems thereof, such as a power system substation (e.g., an inverter / converter, components of such an inverter / converter, such as power semiconductor devices, such as power semiconductor devices having a control gate (e.g., thyristors or Insulated Gate Bipolar Transistors (IGBTs)), a valve hall comprising valves including thyristors or IGBTs), without being limited thereto.

[0107] BRIEF DESCRIPTION OF THE DRAWINGS

[0108] Embodiments of the invention will be described with reference to the drawings in which similar or identical reference signs designate elements with similar or identical configuration and / or function.

[0109] Figure 1 is a schematic diagram of an electric power system comprising a Supervisory Control and Data Acquisition (SCADA) system and a processing system operative to perform an abnormality detection during commissioning when installed at an installation site.

[0110] Figure 2 is a block diagram of the processing system.

[0111] Figure 3 is a block diagram of the SCADA system and the processing system when installed at a test site different from the installation site.

[0112] Figure 4 is a flow chart of a method.

[0113] Figure 5 is a block diagram of a logic of the processing system.

[0114] Figure 6 is a block diagram illustrating a configuration of logics of the SCADA system.

[0115] Figure 7 is a schematic representation of the SCADA system and the processing system.

[0116] Figure 8 is a schematic representation of timeseries data monitored by the processing system at the installation site.

[0117] Figure 9 is a block diagram of a logic of the processing system. Figure 10 is a schematic representation of an Al model cell that can be executed by the processing system to perform the abnormality detection.

[0118] Figure 11 is a schematic representation of an Al model that can be executed by the processing system to perform the abnormality detection.

[0119] Figure 12 shows a control and protection device of the SCADA system, with the processing system being operative to facilitate commissioning of the SCADA system comprising the control and protection device.

[0120] Figure 13 shows a further control and protection device of the SCADA system, with the processing system being operative to facilitate commissioning of the SCADA system comprising the further control and protection device.

[0121] Figure 14 shows a yet further control and protection device of the SCADA system, with the processing system being operative to facilitate commissioning of the SCADA system comprising the yet further control and protection device.

[0122] Figure 15 is a flow chart.

[0123] DETAILED DESCRIPTION OF EMBODIMENTS

[0124] Embodiments of the invention will be described with reference to the drawings. In the drawings, similar or identical reference signs designate elements with similar or identical configuration and / or function.

[0125] Embodiments relate to methods and processing systems that facilitate commissioning of a Supervisory Control and Data Acquisition (SCADA) system at an installation site in which the SCADA system equipment is operatively associated with primary power system equipment.

[0126] While embodiments will be described in detail primarily in association with SCADA systems for high voltage direct current (HVDC) power system, in particular HVDC power transmission system, the embodiments are not limited thereto.

[0127] Commissioning of SCADA systems is a complex task, which is made more complex with increasing complexity of SCADA systems (e.g., with increasing number of devices, control and protection function instances, etc.).

[0128] The process of providing a SCADA system can involve, for example, the following stages:

[0129] Factory system tests (FST) of the SCADA system are performed. After completion of the FST, the SCADA system is delivered to its installation site and rewired at the installation site.

[0130] Commissioning at the installation site can start after all SCADA system components have been received at the installation site, quality checked, verified and reassembled for hardware connections and set ready for testing the logics. Commissioning of the SCADA system involves various tests that are carried out at the installation site. This may comprise validating hardware connections after re-assembly at the installation site from the FST phase. A number of test cases to be validated can be, e.g., in excess of 100 test cases. During validation in the commissioning, it is possible that multiple trip events are triggered due to errors and the issue is fixed and re-validated. This cycle is repeated until all cases are validated. It is also possible that human errors in hardware connections are caught as a trip event. This is more a reactive approach.

[0131] The commissioning, and in particular the system validation in the commissioning, is thus a challenging task. This is exacerbated when the SCADA system first undergoes FST (with test scenarios being provided by a test system) and is rewired for commissioning comprising validation at the installation site (with the SCADA system devices being operatively associated with primary power system equipment).

[0132] The techniques disclosed herein are operative to identify abnormal situations in SCADA system behavior after rewiring at the installation site, e.g. during test scenarios in validation performed during commissioning. The abnormal situations are identified by using baseline data that is based on observations of SCADA system behavior during testing at the test site. The abnormality detection is performed by processing, by a processing system, monitoring data captured at the installation site (e.g., during validation in the commissioning process) and using the baseline data to evaluate the monitoring data. Thereby, discrepancies between the desired behavior at the end of the FST and the SCADA system behavior at the installation site after rewiring can be detected, which are indicative of an abnormality caused by human errors in rewiring or softwiring.

[0133] Thus, embodiments of the invention provide techniques useful in commissioning of a SCADA system after rewiring. Embodiments of the invention provide methods and processing systems for performing an abnormality detection during commissioning after a SCADA system has been rewired at the installation site.

[0134] As used herein, the term "rewiring" encompasses hardwiring (physical connections between devices) and softwiring (such as logic configurations, e.g., data flow between control and protection function instances executed by the same or different control and protection devices). Methods and processing systems disclosed herein may be operative to detect errors in hardwiring, softwiring, or both.

[0135] As used herein, the term "SCADA system" encompasses in particular a control and protection system, e.g., a control and protection system of a HVDC system.

[0136] As used herein, the term "installation site" refers to a site at which SCADA system devices are operatively associated with primary electric power system equipment. As used herein, the term "test site" refers to a site different from the installation site and at which the SCADA system is tested prior to being disassembled for shipment and rewiring at the installation site.

[0137] The techniques disclosed herein may involve the application of artificial intelligence (Al) models. The Al-based techniques may comprise the use of machine learning (ML) techniques and / or deep learning (DL) techniques. As used herein, the term Al is intended to encompass ML techniques and DL techniques, without being limited thereto. The techniques may comprise or may be supervised, semisupervised , unsupervised or self-supervised techniques to process data captured at the installation site, using data previously captured at the test site.

[0138] The techniques disclosed herein may use subsystems, in the primary and / or secondary system parts, which are referred to as "first" and "second" subsystems herein. Such subsystems are also referred to as "A" and "B" subsystems or as "active" and "standby" subsystems in the art. The "first" and "second" subsystems may in particular be subsystems of or for a same station (e.g., a station at a local end or at a remote end). Thus, the first" and "second" subsystems are distinguished from subsystems provided in separate stations (e.g., stations at a local and remote end). It will be appreciated that the techniques disclosed herein with relation to the "first" and "second" subsystems of a station may equally be applied to each one of the two stations. e., the techniques disclosed herein may be applied to a first station (which may have its first and second subsystems) and a second station provided on an opposite end of a line as the first station, with the second station optionally having its own first and second subsystems.

[0139] The techniques disclosed herein are performed using or by a processing system. The processing system may be a dedicated processing system for detecting abnormalities during SCADA system commissioning at the installation site after rewiring. The processing system may be a processing system that does not perform any control and protection functions during live field operation of the electric power system with which the SCADA system is associated. This allows the processing system to be disassembled from the SCADA system after completion of commissioning. In other implementations, the processing system may remain installed after completion of the commissioning and may be operative to, e.g., perform monitoring functions during field use of the electric power system with which the SCADA system is associated.

[0140] Thus, the processing system may be a processing system operative to be deinstalled from the SCADA system after commissioning without adversely affecting SCADA system operation.

[0141] The processing system is operative to be communicatively coupled with SCADA system devices to capture data both during testing at the test site (pre-rewiring) and the commissioning at the installation site (post-rewiring). The processing system may be operative such that the captured data comprise measurements (such as measurements relating to one, several or all of electric characteristics (voltages, currents, phasors), temperatures, insulation, moisture in insulation, dissolved gas analysis (DGA) results, power semiconductor devices (e.g., power semiconductor devices having a control gate), thyristor or Insulated Gate Bipolar Transistor (IGBT) valves of a converter / inverter, other converter / inverter characteristics, without being limited thereto) and / or event-based messages or signals.

[0142] The methods and processing systems disclosed herein implement the abnormality detection in a data-driven manner. As used herein, this means in particular that the processing system is operative to perform the abnormality detection in a manner that uses and is based on observations of the SCADA system behavior at the test site, as compared to the SCADA system behavior at the installation site.

[0143] The methods and processing systems disclosed herein are particularly useful in association with HVDC systems. The HVDC system may comprise or may be a HVDC power transmission system. A power transmission line of the HVDC system may have a length of at least 100 km, at least 200 km, at least 300 km, or at least 400 km. HVDC transmission systems offer various advantages, in particular for power transmission over longer distances. HVDC transmission systems are gaining popularity for, e.g., power transmission from a renewable energy source to an area that may be remote from the location of the renewables energy source. Thus, the techniques disclosed herein are particularly useful in association with a transition to more environmentally friendly electric power systems that comprise renewables energy source and HVDC transmission systems.

[0144] As used herein, the term "power" refers to electric power unless explicitly stated otherwise.

[0145] Figure 1 is a schematic representation of an electric power system 10 comprising a processing system 70 according to an embodiment. The electric power system 10 comprises a primary system (i.e., a system that carries the currents and has the voltages for electric power transmission performed as part of an international, national, or regional power grid). The primary system comprises a high voltage direct current (HVDC) system 20. The primary system may comprise a first AC system 11, a first transformer 13 (e.g., a step-up transformer 13), a second transformer 14 (e.g., a step-down transformer), and a second AC system 15, with the HVDC system 20 being operative to provide DC power transmission between the first and second AC systems 15.

[0146] The HVDC system 20 may comprise first and second converters 21, 22 located on opposite ends relative to a DC transmission line 23, 23'. The converters 21, 22 are also referred to as converter / inverter assets in the art, as they can perform not only inversion but also other conversion functions. Each or both of the converters 21, 22 may be or may comprise a line-commutated current-sourced converter (LCC). The LCC may comprise thyristor valves. Each or both of the converters 21, 22 may be or may comprise a Voltage Source Converter (VSC). The VSC may comprise Insulated Gate Bipolar Transistor (IGBT) valves. The inverter / converter 21, 22 may have other configurations that may include power semiconductor devices (e.g., power semiconductor devices having a control gate). The HVDC system 20 may comprise equipment controllable to protect the HVDC system 20. This equipment may comprise grounding switches 24, 25, 24', 25' for DC protection and / or AC / DC circuit breakers (CBs).

[0147] The HVDC system 20 may provide a redundant system implementation having subsystems of the primary system that include a main system and a backup system. This may be implemented in such a manner that continuous converter operation can be ensured.

[0148] There does not have to be a redundant implementation for all primary system components. Redundancy may be provided for at least part of the primary system components, with the respective implementations being referred to as first / active / "A" and second / backup / "b" subsystems of the primary system herein. The first and second primary system subsystems may be comprised by a same station, i.e., they may be both arranged at a same line relative to an HVDC transmission line or cable.

[0149] As will be described in more detail herein, different SCADA subsystems may be associated with the different primary system subsystems to provide redundant implementations, with the different SCADA subsystems operating during field operation to ensure availability of the SCADA systems to control and operate the main station functions.

[0150] The electric power system 10 comprises a SCADA system 40. The SCADA system 40 comprises a plurality of SCADA system devices 41-43, 45-49. The SCADA system devices may comprise control and protection devices 41-43, 45-47 and sensors 48, 49. The control and protection devices 41-43, 45-47 may be communicatively coupled, via physical connections or signal transmission, and / or via wireless links (such as wireless point-to-point links) to the sensor devices 48, 49 to receive measurements therefrom. The control and protection devices may also be communicatively coupled, via wired or wireless links, to a central control and protection system 50, which may provide a control and protection human machine interface (HMI).

[0151] The control and protection devices 41-43, 45-47 and the central control and protection system 50 may be operative to perform control and protection functions, such as valve control of converter valves, grounding switch control, AC / DC CB control, without being limited thereto.

[0152] The SCADA system 40 comprises a communication system 60. The communication system 60 may comprise wired communication links and / or wireless communication links. For illustration, the communication system 60 may comprise RS-485, CAN, etherCAT, Ethernet, modbus, IEEE 61850 wired connections and / or wireless communication links with a carrier bandwidth in, e.g., the sub-1 GHz range, without being limited thereto. The communication system 60 may comprise at least some physical connections between one or several of the sensors 48, 49, control and protection devices 41- 43, 45-47, a communication switch device 61 or edge device, and the central control and protection system 50. The electric power system 10 comprises a processing system 70 according to an embodiment. The processing system 70 is operative to detect abnormal SCADA system behavior when the SCADA system 40 is subjected to tests during validation in the commissioning at an installation site 18, at which the SCADA system devices are operatively associated with the primary system equipment of the electric power system 10. The processing system 70 is operative to capture monitoring data during at least the tests performed at the installation site 18, after the SCADA system 10 has been rewired at the installation site. The monitoring data may comprise data (such as measurements and / or event-based messages or signals) relating to the SCADA system behavior and / or to primary system equipment (such as temperature measurements in insulation fluid of primary system equipment or moisture measurements in insulation of primary system equipment).

[0153] The processing system 70 performs the abnormality detection in a data-driven manner, by processing the monitoring data using baseline data. The baseline data stored in a storage system of or accessible to the processing system 70 comprises or is based on observations of at least SCADA system behavior made by the processing system 70 during tests of the SCADA system 40 at a test site (i.e., prior to rewiring of the SCADA system 40 at the installation site 18, e.g., in a final phase of the factory system tests, which is sometimes also referred to as FST 3 in the art). Thereby, the abnormality detection is performed in an objective manner, which is less susceptible to human judgment error than abnormality detection logics established by a human expert without using observations.

[0154] The processing system 70 may in particular be operative to collect and process timeseries data. The processing system 70 may be operative to compare these monitored timeseries data captured with the SCADA system 40 installed at the installation site (i.e., post-rewiring of the SCADA system) to baseline timeseries data captured with the SCADA system 40 installed at the test site (i.e., pre-rewiring of the SCADA system). Alternatively or additionally, the processing system 70 may be operative to process these monitored timeseries data captured with the SCADA system 40 installed at the installation site (i.e., post-rewiring of the SCADA system) using an abnormality detection logic that has one or several parameters set in dependence on the dynamic SCADA system behavior observed by the processing system 70 during several test scenarios while the SCADA system 40 is installed at the test site (i.e., pre-rewiring of the SCADA system).

[0155] For referencing the timeseries data to a consistent reference time, the SCADA system 40 may comprise a clock device 61. Timeseries data may be referenced, by the processing system 70, to the reference time to ensure consistency of received measurements, decision logic outputs, and other monitoring data.

[0156] Figure 2 is a block diagram of the processing system 70. The processing system 70 comprises at least one interface 71, a storage system 72, and at least one processing circuit 80. The at least one processing circuit 80 may be operative to perform the operations disclosed below in several processing layers.

[0157] The at least one interface 71 is operative to receive monitoring data 75 while the SCADA system 40 (and optionally also at least part of the primary system) is subject to various test scenarios during validation as part of the commissioning at the installation site 18. The monitoring data 75 may comprise measurements relating to the SCADA system 40 (such as sensor output that is input to at least one decision logic of at least one control and protection device), data relating to internal states of the control and protection devices (such as a at least one decision logic output of at least one control and protection device or event based messages or signals indicative of the at least one decision logic output of at least one control and protection device), and measurements relating to the primary system (such as measurements of electric characteristics, temperature measurements, dissolved gas analysis (DGA) results, insulation moisture measurements, etc.), without being limited thereto. The monitoring data 75 may comprise timeseries data, e.g., timeseries data relating to a timeseries of a sensor output that is input to at least one decision logic of at least one control and protection device and / or a timeseries of measurements relating to the primary system (such as measurements of electric characteristics, temperature measurements, dissolved gas analysis (DGA) results, insulation moisture measurements, etc.). The monitoring data 75 captured while the SCADA system 40 and optionally also the primary system) is subject to various test scenarios during validation as part of the commissioning at the installation site 18 is processed to perform the abnormality detection, as will be described in more detail.

[0158] The at least one interface 71 may be operative to receive configuration data 74 defining a configuration of the SCADA system 40 and the primary system with which it is associated. The configuration data may comprise a standardized configuration language (SCL) configuration description and / or a proprietary configuration description, which is machine-readable. The processing system 70 may be operative to use the configuration data 74 to perform the abnormality detection, e.g., by associating measurements with control and protection devices (e.g., by determining which sensor outputs are provided to which function instance of which control and protection device).

[0159] The storage system 72 is operative to store therein at least part of the received monitoring data 74. The processing system 70 may be operative such that a selection of the received monitoring data 75 and / or other preprocessing (such as filtering out part of the received monitoring data 75) is performed by the at least one processing circuit 80 to determine which part of the received monitoring data 75 or data derived therefrom is to be stored in the storage system 72.

[0160] The storage system 72 is operative to store therein baseline data 73. The baseline data 73 may comprise or may otherwise be dependent on observations of the SCADA system 40 performed by the processing system 70 while the SCADA system 40 was tested at the test site different from the installation site 18 (pre-rewiring). The baseline data 73 may comprise baseline data (such as baseline timeseries data) representing observations (such as measurements or decision logic outputs) captured while the SCADA system 40 was tested at the test site different from the installation site 18 (prerewiring). The baseline data 73 may comprise parameters defining an abnormality detection logic (such as by providing trained parameters of an Al model) that were determined in a data-driven manner using observations (such as measurements or decision logic outputs) captured while the SCADA system 40 was tested at the test site different from the installation site 18 (pre-rewiring).

[0161] The at least one processing circuit 80 may be operative to perform a first set of operations 81, 82, 83 when the processing system 70 is interfaced with the SCADA system 40 installed at the installation site 18. The at least one processing circuit 80 may be operative to perform a second set of at least one operation 90 when the processing system 70 is interfaced with the SCADA system 40 installed at the test site different from the installation site 18. The processing system 70 may be operative to receive information on whether it is to perform the operations for test site operation or the operations for installation site operation via the interface 71. The processing system 70 may comprise a dedicated HMI interface element, such as a physical actuation element, that is actuable to indicate whether the processing system 70 is to perform the operations for test site operation or the operations for installation site operation via the interface 71. The processing system 70 may be operative to control an HMI to enable an engineer to specify whether the processing system 70 is to perform the operations for test site operation or the operations for installation site operation via the interface 71.

[0162] The output 79 may comprise control data to control an HMI to indicate that an abnormality has been detected. The output 79 may optionally comprise control data to control the HMI to indicate which device(s) of the SCADA system 40 are affected and / or a possible root cause (e.g., hardwiring vs. softwiring issue) and / or recommendations for resolving the issue (e.g., recommendation to correct a logic flow and / or to correct an incorrect physical connection).

[0163] Alternatively or additionally, the output 79 may comprise control data to control a communication circuit to transmit data indicative of the detected abnormality to a terminal device, such as a cellular phone of a commissioning engineer. The output 79 may optionally comprise control data to control the communication circuit to transmit data to indicate which device(s) of the SCADA system 40 are affected and / or a possible root cause (e.g., hardwiring vs. softwiring issue) and / or recommendations for resolving the issue (e.g., recommendation to correct a logic flow and / or to correct an incorrect physical connection).

[0164] Alternatively or additionally, the output 79 may comprise control data that act on devices of the SCADA system 40, e.g., to perform a mitigating or corrective action in response to detecting the abnormality. When the processing system 70 is set for test site operation, the at least one processing circuit 80 is operative to obtain baseline data by observing SCADA system behavior during at least a final test phase (such as FST 3) of the SCADA system 40 at the test site. The at least one processing circuit 80 is operative to determine which baseline data are to be stored (e.g., by selecting timeseries of measurements and / or associated decision logic states for inclusion in the baseline data 73) and / or to process the observations to generate the baseline data 73 (e.g., by performing an Al model training to obtain baseline data 73 that includes parameters of at least one trained Al model).

[0165] The at least one processing circuit 80 may comprise any one or any combination of integrated circuits, integrated semiconductor circuits, processors, controllers, application specific integrated circuits (ASICs), circuit(s) including quantum bits (qubits) and / or quantum gates, without being limited thereto, to perform the mentioned functions.

[0166] Figure 3 is a schematic representation of the SCADA system 40 installed at the test site 19 different from the installation site. The SCADA system 40 comprises the control and protection devices 41-43, 45-47, the sensors 48, 49, the control and protection system 50 and communication system 60 as intended for installation at the installation site 18.

[0167] The processing system 70 is communicatively interfaced with the SCADA system 40 via communication system 60. When the processing system 70 is communicatively interfaced with the SCADA system 40 as installed at the test site 19, the processing system 70 is operative to obtain baseline data by observing SCADA system behavior during at least a final test phase (such as FST 3) of the SCADA system 40 at the test site 19. The processing system 70 is operative to determine which baseline data are to be stored (e.g., by selecting timeseries of measurements and / or associated decision logic states for inclusion in the baseline data 73) and / or to process the observations to generate the baseline data 73 (e.g., by performing an Al model training to obtain baseline data 73 that includes parameters of at least one trained Al model).

[0168] The observations may comprise timeseries data to capture the dynamic SCADA system behavior during testing at the test site 19 (i.e., pre-rewiring). The baseline data may comprise or may be dependent on the timeseries data acquired by the processing system 70 during testing of the SCADA system 40 at the test site 19. For referencing the timeseries data to a consistent reference time, the processing system 70 may be operative to reference the various timeseries to a reference time provided by the clock device 62.

[0169] At the test site 19, a test system 16 generates test scenarios and supplies input data 17 representative of the test scenario to the SCADA system 40 as inputs. The input data 17 may reflect dynamic changes in measurements in accordance with the respective test scenario.

[0170] Figure 4 is a flow chart of a method 100. The method 100 may be performed automatically by or using the processing system 70. At process block 101, the processing system 70 performs monitoring of the SCADA system 40 while the SCADA system 40 is installed at the test site 19 (i.e., pre-rewiring). The monitoring at the test site 19 may comprise acquiring data (such as decision logic outputs of control and protection devices) as the SCADA system 40 is subjected to tests at the test site 19. During these tests, the test system 16 may generate test scenarios and supplies input data 17 representative of the test scenario to the SCADA system 40 as inputs. SCADA system behavior is observed for these various tests, at least in a final test phase at the test site 19 (e.g., shortly prior to disassembly and shipment of the SCADA system 40).

[0171] At process block 102, the processing system 70 stores the baseline data. This may comprise selecting which of the observed timeseries or other data acquired at process block 101 are to be stored and / or setting parameters of at least one Al model based on the observations at process block 101. Setting the parameters of the at least one Al model may comprise Al model training.

[0172] At process block 103, the processing system collects monitoring data while the SCADA system 40 is installed at the installation site 18 and is subject to tests at the installation site 18, where the SCADA system 40 is operatively associated with the primary system of the electric power system (in the sense that the SCADA system 40 can perform control operations that directly affect primary system equipment). Collecting the monitoring data at the installation site 18 may comprise collecting timeseries data, such as timeseries of measurements, associated timeseries of decision logic states of control and protection devices, timeseries of environmental condition data (such as weather data), without being limited thereto.

[0173] At process block 104, the processing system 70 uses the baseline data from process block 102 to evaluate the monitoring data from process block 103. The evaluation is performed to detect an abnormality that may be caused by, e.g., errors in hardwiring or softwiring that may have occurred during rewiring at the installation site. Such errors may also be caused by changes in hardware and / or changes in naming.

[0174] At process block 105, the processing system 70 generates output based on a result of the processing at process block 104. The generated and provided output may comprise control data to control an HMI to indicate that an abnormality has been detected. The generated and provided output may optionally comprise control data to control the HMI to indicate which device(s) of the SCADA system 40 are affected and / or a possible root cause (e.g., hardwiring vs. softwiring issue) and / or recommendations for resolving the issue (e.g., recommendation to correct a logic flow and / or to correct an incorrect physical connection). Alternatively or additionally, the generated and provided output may comprise control data to control a communication circuit to transmit data indicative of the detected abnormality to a terminal device, such as a cellular phone of a commissioning engineer. The generated and provided output may optionally comprise control data to control the communication circuit to transmit data to indicate which device(s) of the SCADA system 40 are affected and / or a possible root cause (e.g., hardwiring vs. softwiring issue) and / or recommendations for resolving the issue (e.g., recommendation to correct a logic flow and / or to correct an incorrect physical connection). Alternatively or additionally, the generated and provided output may comprise control data that act on devices of the SCADA system 40, e.g., to perform a mitigating or corrective action in response to detecting the abnormality.

[0175] Figure 5 is a block diagram of the at least one processing circuit 80. The at least one processing circuit 80 may be operative to perform an abnormality detection 82 that comprises a detection 84 of hardwiring issues and a detection 85 of softwiring issues. The at least one processing circuit 80 may be operative to detect, based on the monitoring data captured while the SCADA system 40 is installed at the installation site 18 (i.e., post-rewiring) as evaluated using the baseline data, issues relating to incorrect logics configurations and issues relating to incorrect physical wires. Issues relating to incorrect logics configurations may be caused by naming inconsistencies, incorrect assignment of incoming signals of a control and protection device to inputs of a control and protection function instance executed on the control and protection device, incorrect wireless communication setup, and others. The at least one processing circuit 80 may optionally be operative to determine whether an issue is likely a hardwiring issue (as indicated by, e.g., incorrect control and protection function output of a control and protection device that should be coupled to a sensor and concurrent correct control and protection function output of another control and protection device coupled to the same sensor) or a softwiring issue (as indicated by, e.g., control and protection function output resulting from incorrect naming or incorrect data flow configurations).

[0176] Figure 6 is a schematic representation 110 of control and protection devices 111, 112, 113 of the SCADA system 40. The control and protection devices perform various control and protection functions related to a switch (such as function instance CSWI1 of control and protection device 111), to transformers Cl, C2 (such as function instance PTR Cl and PTR C2 of control and protection devices 111, 112), to a circuit breaker (such as function instance XCBR1 of control and protection device 113), and to a converter.

[0177] A logics configuration of the SCADA system 40 defines data flows 114, 115 between logical function instances. For illustration, the logics configuration may define which incoming signal of a control and protection device is used as what input of a control or protection function instance executed by that control and protection device. Errors in the logics configuration are softwiring issues. The processing system 70 may be operative to detect such softwiring issues based on the processing disclosed herein.

[0178] The operations performed by the processing system 70 make the processing system 70 suitable for use in association with a SCADA system 40 that comprises several redundant subsystems. The redundant SCADA subsystems may be operative to operate during field operation to ensure availability of the SCADA system to control and operate main station functions of the electric power system 10 comprising the SCADA system 40. The redundant SCADA subsystems may comprise a first SCADA subsystem for performing control and protection functions for a first subsystem of the primary system, and a second SCADA subsystem for performing control and protection functions for a second subsystem of the primary system. The first subsystem of the primary system and the second subsystem of the primary system may provide redundant implementations of each other. As noted above, the primary system may comprise assets or other equipment for which there is no redundant implementation. Le., the primary system of, e.g., a station may comprise the first subsystem of the primary system, the second subsystem of the primary system, and additional assets and / or equipment.

[0179] A change-over logic may be operative to cause switching over from the first subsystem of the primary system and its associated first SCADA subsystem to the second subsystem of the primary system and its associated second SCADA subsystem, and vice versa. The change-over logic may be implemented to ensure continuous operation of the HVDC system, e.g., continuous operation of the converters including the valves thereof.

[0180] Figure 7 is a schematic representation diagram of a SCADA system 40 comprising a first SCADA subsystem 121 and a second SCADA subsystem 125. The fist SCADA subsystem 121 comprises a first set of control and protection devices 123. The control and protection devices of the first set 123 may be operative to perform control and protection functions for a first subsystem of, e.g., an HVDC transmission system. The fist SCADA subsystem 121 comprises a first set of sensors 124. The control and protection devices of the first set may be operative to perform the control and protection functions for the first subsystem of the HVDC transmission system based on sensor output of sensors included in the first set 124 and independently of sensor output of sensors included in a second set 127 that will be described below.

[0181] The second SCADA subsystem 125 comprises a second set of control and protection devices 126. The control and protection devices of the second set 126 may be operative to perform control and protection functions for a second subsystem of, e.g., an HVDC transmission system. The second SCADA subsystem 125 comprises a second set of sensors 127. The control and protection devices of the second set 126 may be operative to perform the control and protection functions for the second subsystem of the HVDC transmission system based on sensor output of sensors included in the second set 127 and independently of sensor output of sensors included in the first set 124.

[0182] The SCADA system 40 comprises the change-over logic operative to cause operation to switch between the first SCADA subsystem 121 and its associated first subsystem of the HVDC system and the second SCADA subsystem 126 and its associated second subsystem of the HVDC system.

[0183] The processing system 70 disclosed herein may be operative to perform monitoring of both the first SCADA subsystem 121 and the second SCADA subsystem 125 while tests are performed during commissioning while the SCADA system 40 is installed at the installation site, with the first SCADA subsystem 121 being operatively coupled to the first subsystem of the HVDC and the second SCADA subsystem 125 being operatively coupled to the second subsystem of the HVDC system. Similarly, prerewiring and while the first SCADA subsystem 121 and the second SCADA subsystem 125 are installed at the test site where they are not operatively coupled to the primary system equipment of the first and second HVDC subsystems, the processing system 70 is operative to observe the behavior of both the first SCADA subsystem and the second SCADA subsystem 125 and generate the baseline data based thereon.

[0184] In this case, the baseline data may comprise first baseline data generated based on observations of the behavior of the first SCADA subsystem 121 during testing at the test site 19 and second baseline data generated based on observations of the behavior of the second SCADA subsystem 121 during testing at the test site 19.

[0185] The processing system 70 may be operative such that the abnormality detection performed for the SCADA system 40 during commissioning at the installation site (i.e., post-rewiring) may comprise processing the monitoring data obtained for the first SCADA subsystem using the first baseline data and processing the monitoring data obtained for the second SCADA subsystem using the second baseline data. Thus, inconsistencies between the behavior of each of the subsystems between the test site operation and the installation site operation may be detected, causing an output to be provided responsive thereto.

[0186] Additionally or alternatively, processing system 70 may be operative such that the abnormality detection performed for the SCADA system 40 during commissioning at the installation site (i.e., postrewiring) may comprise processing the monitoring data obtained for the first SCADA subsystem using the second baseline data and / or processing the monitoring data obtained for the second SCADA subsystem using the first baseline data. This is possible as the various subsystems, both in the SCADA system and in the primary system (e.g., the HVDC primary system), provide redundant implementations. Thus, both inconsistencies between the behavior of each of the subsystems between the test site operation and the installation site operation and inconsistencies caused by different behavior of the fist subsystem and the second subsystem can be detected.

[0187] Irrespective of whether or not the processing system 70 is operative for use in association with a SCADA system having several redundant subsystems, the processing system 70 may be operative to use various techniques, in isolation or in combination, to process the monitoring data captured during validation upon commissioning based on baseline data captured during testing prior to installation of the SCADA system at the installation site where it is operatively coupled to primary system equipment. The processing system 70 may be operative to compare monitoring data, in particular timeseries data, to baseline timeseries data (Figure 8) and / or may process the monitoring data using an abnormality 1 detection logic that is based, at least in part, on observed SCADA system behavior captured by the processing system at the test site.

[0188] Figure 8 illustrates baseline data comprising baseline timeseries data 128. Figure 8 also illustrates monitoring data comprising timeseries data 129. The processing system 70 may be operative to determine, based on a metric quantifying a difference between the timeseries data 129 and the baseline timeseries data 128, to determine whether there is an abnormality.

[0189] It will be appreciated that, in a realistic setting, the processing system 70 may be operative to compare a plurality of timeseries representing SCADA system behavior at the installation site 18 to a plurality of baseline timeseries representing SCADA system behavior at the test site 19. An abnormality may be detected responsive to a time-integral over a modulus of a difference of corresponding timeseries and / or a L2-norm or a LN-norm of the difference of corresponding timeseries reaching or exceeding a threshold. The timeseries for which the deviation is detected may also be indicative of the root cause of the abnormality, in particular affected devices and / or whether the abnormality is considered to be caused by incorrect hardwiring or incorrect logics configurations, such as incorrect softwiring. As used herein, softwiring encompasses changes in logic configurations (such as name changes, changes in assignment of data received by a control device to a function input of a function instance (a process also referred to as binding in the art), and other data flow configurations, without being limited thereto).

[0190] Figure 9 illustrates logics of the at least one processing circuit 80 when the processing system 70 is operative to determine parameters of an abnormality detection logic based on SCADA system behavior observed by the processing system 70 when the SCADA system is tested at the test site, where it is not operatively coupled to the primary power system equipment.

[0191] The at least one processing circuit 80 is operative to perform a module 90 of obtaining baseline data and / or controlling storage of the baseline data. The at least one processing circuit 80 may be operative to implement a data collection module 91 to collect data (such as control and protection function outputs, which may be available as timeseries data) during testing of the SCADA system 40 at the test site, e.g., during a final phase of factory site testing (e.g., FST 3). The at least one processing circuit 80 may be operative to implement a logics generation and / or update module 92 to generate and / or update an abnormality detection logic based on the data collected by the data collection module 91. The at least one processing circuit 80 may be operative to implement a storage module 93 to store parameters and / or hyperparameters of the abnormality detection logic as generated by the logics generation and / or update module 92.

[0192] The generation and / or update of the abnormality detection logic is performed based on the data collected during testing of the SCADA system 40 at the test site 19. Thus, the generation and / or update of the abnormality detection logic is performed in a data-driven manner, which makes the abnormality detection logic more objective than, e.g., human expert based logic designs.

[0193] The large number of tests (e.g., more than 100 test scenarios) and the large number of SCADA system components have the effect that large data amounts are available for generating and / or updating the abnormality detection logic. The collected data (e.g., the collected timeseries data) may be partitioned into a training set, a test set, and a validation set. For illustration rather than limitation, the training set may be, e.g., 70% of the collected data, the test set may be, e.g., 15% of the collected data, and the validation set may be, e.g., 15% of the collected data. Data augmentation may be performed if desired to, e.g., have a more balanced set of cases with and without abnormality.

[0194] The split of available data for training, testing and validations can be performed based on the volume of data available, computing power of the device doing the processing. There are various possible implementations, such as using small batches for training that can also accommodate online batches to update the models or in offline mode. When there is static data, a 70 to 30% split considering all the type of methods ( supervised, unsupervised and semi-supervised methods) can be applied, without being limited thereto.

[0195] The generation and / or updating of the abnormality detection logic may comprise setting decision thresholds in a data-driven manner. More complex techniques, such as techniques using at least one Al model to perform abnormality detection, may be used. The at least Al model may comprise at least one Al model operative to process timeseries data, which may comprise timeseries data of measurements and / or timeseries of control and protection function outputs.

[0196] The abnormality detection logic has generated or updated may be used by the abnormality detection 82 when the processing system 70 monitors the SCADA system 40 installed at the installation site 18 where it is operatively coupled to the primary system equipment of the electric power system.

[0197] The abnormality detection logic may comprise a long short term memory (LSTM) cell.

[0198] Figure 10 shows the LSTM cell 130. The processing system 70 may be operative such that the baseline data comprises parameters of the LSTM cell 130. The processing system 70 may be operative to process the monitoring data using an Al model that comprises at least one LSTM cell 130, optionally a plurality of LSTM cells.

[0199] In Figure 10, C designates a cell state. The parameter h designates a hidden state. The parameter x designates an input. The subscript respectively designates the time. The subscript t designates the time of the input processed by the cell illustrated in Figure 11. The subscript t - 1 designates the preceding time.

[0200] During training, parameters of the LSTM cell or of several LSTM cell arranged in a stacked structure may be trained. The training may comprise training of a forget gate (designated by ft), an input gate (designated by it) and an output gate (designated by ot). Training the various gates may comprise training the weight parameters and bias parameters of each of the gates of the LSTM cell.

[0201] As previously explained, the LSTM cell(s) may be trained using observations of SCADA system behavior while the SCADA system 40 is tested with test scenarios provided by the test system 16.

[0202] During inference, the LSTM cell(s) or an Al model comprising the LSTM cell(s) and optional pre- and / or post-processing (such as a normalization layer, a feed forward neural network, a convolutional neural network, a recurrent neural network, and / or another deep learning (DL) or shallow learning model used in combination with the LSTM cell(s)) is used to process the monitoring data captured when the SCADA system 40 is at the installation site and operatively coupled to the primary system equipment during validation in commissioning the SCADA system 40. The Al model may comprise an Al model input operative to receive the monitoring data or input data based on the monitoring data (e.g., obtained by filtering, normalization, or other preprocessing) and an Al model output, with the at least one processing circuit 80 being operative to generate the output indicative of an abnormality detection result based on the Al model output. For illustration, the LSTM cell 130 may have an input operative to receive the monitoring data or input data based on the monitoring data (e.g., obtained by filtering, normalization, or other preprocessing) and an LSTM cell output, with the at least one processing circuit 80 being operative to generate the output indicative of an abnormality detection result based on the LSTM cell model output.

[0203] The abnormality detection logic may comprise an Al model having at least one attention mechanisms, e.g., a self-attention mechanisms, a cross-attention mechanism, a multi-head selfattention mechanisms, and / or a multi-head cross-attention mechanism. The Al model may comprise an Al-transformer comprising a stack of Al-transformer model blocks (also referred to as attention blocks), each comprising at least one attention mechanisms. In the art, such a model is also known as a "transformer." To clearly distinguish the Al model from the physical entity of a power system transformer, the term "Al-transformer" is used to refer to the Al model comprising one or several attention mechanisms.

[0204] Figure 11 shows the Al-transformer which may comprise an Al-transformer encoder 140 and / or an Al-transformer decoder. The processing system 70 may be operative such that the baseline data comprises parameters of the Al-model transformer. The processing system 70 may be operative to process the monitoring data using an Al model that comprises at least one Al transformer, optionally an Al-transformer encoder and / or decoder having a plurality 142 of Al-transformer blocks 143. The plurality of Al-transformer blocks may be stacked so that the output of one Al-transformer block is input to the subsequent Al-transformer block.

[0205] Each Al transformer block 143 comprises at least one attention mechanisms 145, e.g., a selfattention mechanisms, a cross-attention mechanism, a multi-head self-attention mechanisms, and / or a multi-head cross-attention mechanism. Each Al transformer block 143 may comprise pre- and / or post-processing (such as a normalization layer 144, a feed forward neural network 146, a convolutional neural network, a recurrent neural network, and / or another deep learning (DL) or shallow learning model).

[0206] The Al-transformer encoder and / or decoder may comprise a token generation 141 that processes the Al-transformer input to a token. The token processing 141 may map a sequence of input values (such as datapoints of a timeseries) to query (Q), key (K) and value (V) of a QKV transformer model.

[0207] During training, at least parameters of the processing 141 (such as parameters that define how the Al model input is mapped to the Q, K, and V values of the Al-transformer model) may be trained.

[0208] As previously explained, the Al model comprising the Al transformer encoder and / or decoder 140 may be trained using observations of SCADA system behavior while the SCADA system 40 is tested with test scenarios provided by the test system 16.

[0209] During inference, the Al-transformer model(s) or an Al model comprising the Al-transformer model(s) and optional pre- and / or post-processing (such as a normalization layer, a convolutional neural network, a recurrent neural network, and / or another deep learning (DL) or shallow learning model used in combination with the LSTM cell(s)) is used to process the monitoring data captured when the SCADA system 40 is at the installation site and operatively coupled to the primary system equipment during validation in commissioning the SCADA system 40. The Al model may comprise an Al model input operative to receive the monitoring data or input data based on the monitoring data (e.g., obtained by filtering, normalization, or other preprocessing) and an Al model output, with the at least one processing circuit 80 being operative to generate the output indicative of an abnormality detection result based on the Al model output. For illustration, the Al-transformer encoder 140 and / or an Al-transformer decoder may have an input operative to receive the monitoring data or input data based on the monitoring data (e.g., obtained by filtering, normalization, or other preprocessing) and Al-transformer output, with the at least one processing circuit 80 being operative to generate the output indicative of an abnormality detection result based on the Al-transformer output.

[0210] Various pre-processing techniques may be applied to monitoring data before the monitoring data are input to a trained Al model or other abnormality detection logic. For illustration, any one or any combination of filtering, zero padding, normalization, or other techniques may be used to bring the monitoring data to a format suitable for processing by the trained Al model or other abnormality detection logic.

[0211] The processing system 70 may be operative to be used in association with a SCADA system 40 for a HVDC electric power system, e.g., a HVDC transmission system. The processing system 70 may be operative to receive, as monitoring data when the SCADA system 40 is operatively coupled to the HVDC system at the installation site 18 measurements relating to the primary system equipment of the HVDC system, measurements relating to the SCADA system 40, and / or outputs of control and protection functions performed by control and protection devices of the SCADA system 40 and / or the central control and protection system 50. The processing system 70 may be operative to process this data (such as control and protection function inputs in association with control and protection function outputs), using the baseline data as previously explained. Thereby, an abnormal situation indicative of hardwiring and / or softwiring issues can be detected.

[0212] Exemplary SCADA system components with which the processing system 70 can be used in a technically beneficial manner are described in association with Figure 12, Figure 13, and Figure 14.

[0213] Figure 12 shows a converter / inverter asset 160 comprising power semiconductor devices having a gate electrode. For illustration, and as shown in Figure 12, the converter / inverter asset 160 may comprise thyristor valves 161, 162, 163, 164 that each may comprise a plurality of thyristors. More complex configurations may be used, such as 12 pulse configurations or even more complex configurations. The converter / inverter asset 160 may be operative to convert AC to DC and / or vice versa. The converter / inverter asset 160 may be operative to provide bidirectional AC / DC conversion.

[0214] The SCADA system 40 comprises a control and protection device 151. The control and protection device 151 comprises a valve control function 152 (optionally a valve control function for each thyristor valve). In field operation, the control and protection device 151 may be operative to perform the valve control function 152responsive to sensor outputs of sensors 154, 155.

[0215] The processing system 70 may be operative to monitor an output of the valve control function 152. When the SCADA system 40 is installed at the installation site and operatively coupled to the primary power system equipment, the processing system 70 may additionally monitor the inputs to the valve control function 152. Thus, the monitoring data may comprise the output and the inputs of at least one of the valve control function 152. To establish the baseline data, the processing system 70 may be operative to at least acquire the output of at least one of the valve control function 152. The processing system 70 may optionally also acquire the values provided by the test system 16 as inputs for the various test scenarios (e.g., as timeseries data or otherwise).

[0216] Using the baseline data, the processing system 70 is operative to perform the abnormality detection that processes the monitoring data to detect incorrect hardwiring and / or incorrect softwiring of the control and protection device 150.

[0217] Figure 13 shows a converter / inverter asset 180 comprising power semiconductor devices having a gate electrode. For illustration, and as shown in Figure 13, the converter / inverter asset 180 may comprise IGBT valves 181, 182, 183, 184 that each may comprise a plurality of IGBTs. More complex configurations may be used. The converter / inverter asset 180 may be operative to convert AC to DC and / or vice versa. The converter / inverter asset 180 may be operative to provide bidirectional AC / DC conversion. The SCADA system 40 comprises a control and protection device 171. The control and protection device 171 comprises a valve control function 172 (optionally a valve control function for each IGBT valve). In field operation, the control and protection device 171 may be operative to perform the valve control function 172 responsive to sensor outputs of sensors 154, 155.

[0218] The processing system 70 may be operative to monitor an output of the valve control function 172. When the SCADA system 40 is installed at the installation site and operatively coupled to the primary power system equipment, the processing system 70 may additionally monitor the inputs to the valve control function 172. Thus, the monitoring data may comprise the output and the inputs of at least one of the valve control function 172. To establish the baseline data, the processing system 70 may be operative to at least acquire the output of at least one of the valve control function 172. The processing system 70 may optionally also acquire the values provided by the test system 18 as inputs for the various test scenarios (e.g., as timeseries data or otherwise).

[0219] Using the baseline data, the processing system 70 is operative to perform the abnormality detection that processes the monitoring data to detect incorrect hardwiring and / or incorrect softwiring of the control and protection device 170.

[0220] Figure 14 shows a DC grounding switch 190.

[0221] The SCADA system 40 comprises a control and protection device 191. The control and protection device 191 comprises a DC protection function 192. In field operation, the control and protection device 191 may be operative to perform the DC protection function 192 responsive to sensor outputs of at least one sensor 193.

[0222] The processing system 70 may be operative to monitor an output of the DC protection function 192. When the SCADA system 40 is installed at the installation site and operatively coupled to the primary power system equipment, the processing system 70 may additionally monitor the inputs to the DC protection function 192. Thus, the monitoring data may comprise the output and the inputs of the DC protection function 192. To establish the baseline data, the processing system 70 may be operative to at least acquire the output of the DC protection function 192. The processing system 70 may optionally also acquire the values provided by the test system 18 as inputs for the various test scenarios (e.g., as timeseries data or otherwise).

[0223] Using the baseline data, the processing system 70 is operative to perform the abnormality detection that processes the monitoring data to detect incorrect hardwiring and / or incorrect softwiring of the control and protection device 191.

[0224] Figure 15 is a flow chart of a method 200 according to an embodiment. The method 200 may be performed automatically by a system that comprises the SCADA system 40 and the processing system

[0225] 90. At process block 201, the processing device 90 operates to detect abnormalities during at least validation in commissioning of the SCADA system 40.

[0226] At process block 202, the commissioned SCADA system 40 performs control and protection functions that affect primary power system equipment, such as primary power system equipment of a HVDC transmission system.

[0227] As explained with reference to Figure 1 to Figure 15, the invention provides processing systems and methods operative to detect abnormalities after a SCADA system has been rewired. Thus, the invention addresses the need for detecting errors in hardwiring and / or softwiring. Such errors can occurs when the SCADA system is rewired after a thorough factory system testing phase in which detailed system engineering tests and logic tests are performed and, at least in a final test phase, recorded by the processing system 70.

[0228] The methods and processing systems are thus operative to allow validation and verification of all logics in the SCADA system to be performed more efficiently. Human errors that can occur in rewiring can be detected more efficiently.

[0229] Thus, the methods and processing systems provide a novel approach of applying a data-drive method with a goal to optimize and reduce effort involved in commissioning. The techniques may be applied at least to a control and protection portion of the SCADA system. The control and protection portion is where all the sensors / devices are assembled according to the approved and accepted architecture in the communication network. The control and protection portion is responsible for fetching all real measurements from the sensors mounted on the field devices. The logics and rules of operations are built in here for validation of the entire system operation.

[0230] This processing system 70 is operative to capture data continually (i.e., in an ongoing basis) during FST including the tests done with real-time simulation devices of the test system 16. This is the baseline of the data with or without labels. At the installation site (i.e., post-rewiring), the data collection continues, with the baseline data being used as a reference context for next real site tests or operations.

[0231] The processing of the monitoring data may use pattern, trend and / or similarity detection techniques from a machine learning (ML) library. This enables the processing system 80 to detect abnormal patterns that point to hardware connection issues (for e.g., interchange of wires for inlet temperature to outlet temperature or vice-versa). In this context, the application of machine learning to detect errors is useful for, e.g., commissioning tests. With help of quick dashboards on parameters in each area of the control and protection system, it is possible to assist in identifying issues, possibly without even having to run any logic conditions. Thus, the risk of human error is reduced, identification of human errors is facilitated, and the risk of incorrect commissioning is mitigated. The processing system 70 and methods performed using the processing system 70 use the hardware of the processing system 70 to both store the baseline data (based on SCADA system observations in the test phase) and to analyze monitoring data captured after rewiring and when the SCADA system 40 is operatively coupled to the primary power system equipment.

[0232] Various effects and advantages are attained by the processing system and method according to embodiments. The processing system and method provide enhanced techniques of detecting incorrect hardware connections and / or incorrect softwiring (e.g. incorrect logic flow configurations) of a SCADA system that are applicable in association with an electric power system. The methods and processing systems are applicable to a Supervisory Control and Data Acquisition (SCADA) system that first undergoes factory tests, then is disassembled and shipped to an installation site, and which is then rewired at the installation site. The methods and processing systems leverage observations of SCADA system behavior obtained during testing at the test site in commissioning the SCADA system.

[0233] While embodiments have been described in detail with reference to the drawings, various modifications may be implemented in other embodiments. For illustration rather than limitation:

[0234] • While embodiments have been described in which the SCADA system is a SCADA system for an HVDC electric power system, the techniques can also be applied to a SCADA system for another electric power system, a legacy AC power generation, transmission, and / or distribution system, for a microgrid or for a distributed energy resource (DER) .

[0235] • While embodiments have been described in which a control and protection system is operatively associated with primary system assets such as converter / inverter assets and / or other primary system equipment such as valves, CBs, etc., the techniques disclosed herein are applicable when the SCADA system is operative to perform control and protection functions to other equipment, such as, without limitation: o a heating, ventilation, air conditioning (HVAC) system; o another auxiliary system of a station; o motors, pumps, and / or other components of primary system equipment or auxiliary systems.

[0236] • While embodiments have been described in which the SCADA system performs control and / or monitoring function for primary system assets or other primary system equipment, the SCADA system may alternatively or additionally be operative to perform monitoring and / or control functions for secondary system devices (e.g., for central processing unit (CPU) usage, communication bandwidth usage, etc. of devices comprised by the SCADA system). • While embodiments have been described in which a converter / inverter comprises thyristors or IGBTs, the converter / inverter may have other configurations, in particular configurations comprising controllable power semiconductor devices.

[0237] • While embodiments have been described in which the processing system 70 itself is operative to determine parameters of an abnormality detection logic, the determination of these parameters may also be performed by a separate computing system (e.g., by a server system that performs Al model training).

[0238] • While embodiments have been described in which the processing system 70 is a dedicated system that can be disassembled from the SCADA system 40 after commissioning without adversely affecting SCADA system operation, the processing system 70 may also be operative to continue monitoring after commissioning has been completed. Thus, the processing system 70 may perform functions of a monitoring device in the SCADA system 40.

[0239] • The components of the processing system 70 may be integrated into a housing of a device, facilitating assembly and disassembly of the processing system 70. The processing system 70 may also be implemented as a distributed system having several devices that are interfaced with each other.

[0240] Embodiments may be used in association with a power grid comprising a HVDC power transmission system, without being limited thereto.

[0241] This description and the accompanying drawings that illustrate aspects and embodiments of the present invention should not be taken as limiting-the claims defining the protected invention. In other words, while the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative and not restrictive. Various mechanical, compositional, structural, electrical, and operational changes may be made without departing from the spirit and scope of this description and the claims. In some instances, well- known circuits, structures, and techniques have not been shown in detail in order not to obscure the invention. Thus, it will be understood that changes and modifications may be made by those of ordinary skill within the scope and spirit of the following claims. In particular, the present invention covers further embodiments with any combination of features from different embodiments described above and below.

[0242] The disclosure also covers all further features shown in the Figures individually although they may not have been described in the afore or following description. Also, single alternatives of the embodiments described in the Figures and the description and single alternatives of features thereof can be disclaimed from the subject matter of the invention or from disclosed subject matter. The disclosure comprises subject matter consisting of the features defined in the claims or the embodiments as well as subject matter comprising said features.

[0243] The term "comprising" does not exclude other elements or process blocks, and the indefinite article "a" or "an" does not exclude a plurality. A single unit or process block may fulfil the functions of several features recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. Components described as coupled or connected may be electrically or mechanically directly coupled, or they may be indirectly coupled via one or more intermediate components. Any reference signs in the claims should not be construed as limiting the scope. A machine-readable instruction code may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via a wide area network or other wired or wireless telecommunication systems. Furthermore, a machine-readable instruction code can also be a data structure product or a signal for embodying a specific method such as the method according to embodiments.

Claims

CLAIMS1. A method of commissioning a Supervisory Control and Data Acquisition, SCADA, system of an electric power system at an installation site of the SCADA system after the SCADA system has been tested at a test site different from the installation site, the method comprising: monitoring, by a processing system, the SCADA system after rewiring of the SCADA system at the installation site, comprising collecting monitoring data during commissioning of the SCADA system at the installation site, wherein the processing system comprises a storage system having stored therein baseline data for SCADA system behavior, the baseline data being based on data captured by the processing system during testing of the SCADA system at the test site; performing, by the processing system, an abnormality detection to detect abnormalities during commissioning, wherein the abnormality detection comprises using the baseline data to evaluate the collected monitoring data; and generating, by the processing system, output based on a result of the abnormality detection.

2. The method of claim 1, wherein the collected monitoring data comprises data from a first SCADA subsystem and data from a second SCADA subsystem, wherein the second SCADA subsystem comprises a redundant implementation of the first SCADA subsystem, wherein the abnormality detection uses the baseline data to evaluate both the data from the first SCADA subsystem and the data from the second SCADA subsystem.

3. The method of claim 2, wherein commissioning the SCADA system comprises commissioning the first SCADA subsystem and the second SCADA subsystem to ensure availability of the SCADA systems to control and operate station functions.

4. The method of claim 2 or claim 3, wherein the first SCADA subsystem performs control and protection functions for a first electric power subsystem of a station, wherein the second SCADA subsystem performs control and protection functions for a second electric power subsystem of the station, wherein the second electric power subsystem is a backup system for the first electric power subsystem.

5. The method of any one of the preceding claims, wherein performing the abnormality detection comprises detection of an incorrect installation of physical wires between SCADA system devices at the installation site.

6. The method of any one of the preceding claims, wherein performing the abnormality detection comprises verifying an operation logics of the SCADA system.

7. The method of claim 6, wherein verifying the operational logics comprises detecting one or both of: an incorrect softwiring in SCADA system engineering data at the installation site; an incorrect data flow configuration between function instances of the SCADA system at the installation site.

8. The method of any one of the preceding claims, wherein performing the abnormality detection comprises detecting one, several, or all of the following: changes in hardware configuration at the installation site as compared to the test site; changes in names at the installation site as compared to the test site; changes in network ports at the installation site as compared to the test site.

9. The method of any one of the preceding claims, wherein the collected monitoring data comprises timeseries data, wherein the abnormality detection comprises processing the timeseries data.

10. The method of claim 9 when dependent on any one of claims 2 to 4, wherein the data from the first SCADA subsystem comprises first timeseries data, wherein the data from the second SCADA subsystem comprises second timeseries data, wherein the abnormality detection comprises processing the first timeseries data and the second timeseries data.

11. The method of any one of the preceding claims, wherein the baseline data comprise baseline timeseries data captured by the processing system during testing of the SCADA system at the test site, wherein the abnormality detection comprises using the baseline timeseries data to process the monitoring data collected at the installation site.

12. The method of any one of the preceding claims, wherein the baseline data comprises parameters of an artificial intelligence, Al, model, wherein performing the abnormalitydetection comprises processing at least part of the monitoring data using the Al model, wherein the Al model has an input operative to receive an Al model input that comprises at least part of the monitoring data collected at the installation site, one or several hidden Al model layers, and an output operative to provide an Al model output, wherein an abnormality detection result is based on the Al model output.

13. The method of claim 12, wherein at least one of the following applies: the Al model is operative to process timeseries data; the Al model comprises long short term memory, LSTM, cells and / or gated recurrent units, GRUs, to process timeseries data; the Al model comprises at least one attention mechanism; the Al model comprises at least one self-attention mechanism; the Al model comprises a stack of self-attention mechanisms; the Al model comprises an Al-transformer model; the Al model comprises one or several autoencoders, and / or a convolutional neural network, CNN.

14. The method of claim 12 or claim 13, wherein the Al model comprises an encoder operative to receive the Al model input and to output a code, wherein the Al model comprises a decoder operative to receive the code and provide the Al model output.

15. The method of claim 14, wherein the encoder comprises a first stack of attention mechanisms and the decoder comprises a second stack of attention mechanisms.

16. The method of any one of claims 12 to 15, wherein the Al model comprises a trained transformer model.

17. The method of any one of the preceding claims, wherein the SCADA system is or comprises a high voltage direct current, HVDC, system SCADA system.

18. The method of claim 17, wherein the SCADA system comprises control and protection devices for HVDC power system assets, wherein the HVDC power system assets comprise one, several, or all of: an inverter / converter asset; a cooling system for an inverter / converter asset;a transformer comprising three single-phase transformers; a single 3-phase transformer ; a heating, ventilation, air conditioning, HVAC, system; other auxiliary systems of stations; motors, pumps, and / or other components of primary system equipment or auxiliary systems; respectively operated under control of the control and protection devices.

19. The method of any one of the preceding claims, wherein the SCADA system is operative to monitor secondary devices in the SCADA system, optionally including monitoring hardware usage of the secondary devices that perform control and protection functions.

20. A method of operating an electric power system using a Supervisory Control and Data Acquisition, SCADA, system, the method comprising: commissioning the SCADA system, comprising performing the method of any one of the preceding claims; performing, by the SCADA system, control and protection operations for the electric power system.

21. A processing system operative for use in commissioning a Supervisory Control and Data Acquisition, SCADA, system of an electric power system at an installation site of the SCADA system after the SCADA system has been tested at a test site different from the installation site, the processing system comprising: a storage system having stored therein baseline data for SCADA system behavior, the baseline data being based on data captured by the processing system during testing of the SCADA system at the test site; at least one processing circuit operative to monitor the SCADA system at the installation site, comprising collecting monitoring data during commissioning of the SCADA system at the installation site, perform an abnormality detection to detect abnormalities during commissioning, wherein the abnormality detection comprises using the baseline data to evaluate the collected monitoring data; and cause output to be provided based on a result of the abnormality detection.

22. The processing system of claim 21, wherein the at least one processing circuit is further operative to perform monitoring of the SCADA system during testing at the test site and to generate the baseline data based on the monitoring of the SCADA system.

23. The processing system of claim 21 or claim 22, wherein the processing system is operative to perform the method of any one of claims 1 to 19.

24. An electric power system, comprising primary power system equipment; a SCADA system operative to perform control and protection functions for the primary power system equipment; and the processing system of any one of claims 21 to 23.

25. The electric power system of claim 24, wherein the SCADA system comprises a first SCADA subsystem and a second SCADA subsystems, wherein the second SCADA subsystem comprises a redundant implementation of the first SCADA subsystem.

26. The electric power system of claim 25, wherein the first SCADA subsystem is operative to perform control and protection functions for a first sub-set of the primary power system equipment and the second SCADA subsystem is operative to perform control and protection functions for a second sub-set of the primary power system equipment, wherein the first subset comprises a redundant implementation of the second sub-set.

27. The electric power system of any one of claims 24 to 26, wherein the primary power system equipment comprises high voltage direct current, HVDC, power system equipment.

28. Machine-readable instruction code comprising machine-readable instructions which, when executed by at least one processing circuit, cause the at least one processing circuit to perform the method of any one of claims 1 to 20.

29. Non-transitory storage medium having stored thereon machine-readable instruction code comprising machine-readable instructions which, when executed by at least one processing circuit, cause the at least one processing circuit to perform the method of any one of claims 1 to 20.

Images