AU2020103307A4 - Machine Learning-Based Power Quality Improvement System For Micro-Grid - Google Patents

Abstract

"MACHINE LEARNING BASED POWER QUALITY IMPROVEMENT SYSTEM FOR MICRO-GRID " Exemplary aspects of the present disclosure are directed towards the Machine Learning Based Power Quality Improvement System for Micro-Grid consists of the plurality of Smart Line Monitoring & Control System (SMCS) 101 connected to Central Monitoring & Control System (CMCS) 103 through Communication-Network 102. SMCS 101 is an integration of microcontroller 101a with advanced power-management chip 101b, Six potential-transformers 101d, Six current-sensors 101c, Circuitry for Circuit-Breaker 10le control, and Capacitor-Banks 101f. SMCS 101 uses the Random Forest-based Machine-Learning (ML) algorithm to predict power quality issues and operates respective Capacitor-Banks 101f for mitigating voltage and frequency profiles. All the power data received by CMCS 103 is normalized and fed to relevant ML algorithm to identify and predict, load, line stress and power quality issues and mitigate the problems. Based on mitigation CMCS 103 isolates the section if necessary by operating the concerned Circuit-Breaker 101e. Page 1 103 102 C S102 101 104-n CS-/7 le01e 101 105y 104-2 104-3 FIG1 POWER DISTRIBUTION MANAGEMENT SYSTEM

Description

102 C S102 101

104-n CS-/7

le01e 101 105y

104-2 104-3

FIG1 POWER DISTRIBUTION MANAGEMENT SYSTEM

TITLE OF THE INVENTION

Machine Leaming-Based Power Quality Improvement System For Micro-Grid

PREAMBLE TO THE DESCRIPTION

The following specification particularly describes the invention and the manner in which it is to be performed

DESCRIPTION TECHNICAL FIELD

[0001] The present disclosure generally relates to the field of Electrical Engineering, more precisely monitoring, protection, Power management and method thereof for resolving power quality issues in a micro grid system.

BACKGROUND

[0002] In wake of modern power systems, Micro-Grid system is predomnently deployed due to its advantages. The micro grid systems consists of one or more power generating sysytems and one or more load systems. In other words, a microgrid is a self reliant energy system that serves a discrete geographic footprint, such as a college campus, hospital complex, business center, or small towns/residents. In a microgrid are one or more distributed enery stations (solar panels, wind turbines, combined heat & power, generators) that produce required power are installed. In addition, many newer microgrids contain energy storage, typically from batteries. Some also now have electric vehicle charging stations.

[0003] Though Microgrids provide low cost, clean energy to limited geographic localities improving their energy stability and operations, they suffer from some drawbacks such as load islanding, load balancing and PQ issues. Wherein, the major problems relate to PQ issues which results in unreliable and unbalanced power which may lead to grid failure.

[0004] Power Quality (PQ) issues are usually reported in the categories of Voltage dips and swells, Short interruptions, Long interruptions, Harmonics, Surges and transients, and lastly in the category of Flicker, unbalance, earthing and electromagnetic compatibility (EMC) problems. Most of the microgrids are loosely monitored and they lack sophisticated monitoring or control system to avert the PQ issues.

[0005] Though several inventors and researchers have overcome the disadvantages by implementing machine learning and other artificial intelligence-based algorithms in existing microcontroller architecture but weren't able to integrate all the protection systems efficiently and unable to integrate with the total power distribution system.

[0006] Numerous prior arts have made attempts to automate the grid with numerous prototyping but haven't achieved a more desirable feature in a single unit for the power distribution network.

[0007] Similarly, several prior art disclosures have ascertained that power quality issues particularly Voltage Sag and Swell tend to malfunction or failure of equipment which can cause large financial losses to various manufacturers. When dealing with such a PQ issue their deeper understanding assists us to ascertain their impact and mitigate the issues effectively. Voltage dips and swells are defined in different manners based on their characteristics and they are Instantaneous, Interruption and Momentary sag and swells.

[0008] In the prior art KR101778772B1, with title The System and Method of Detecting Events by Checking Frequency in Microgrid explained A method for detecting a microgrid anomaly by an anomaly detection system, the method comprising: collecting frequency information per unit time relating to a voltage of each power facility constituting a microgrid; Measuring a frequency change per unit time through the collected information; Calculating overtime when the frequency change per unit time exceeds a threshold of any of a plurality of thresholds, And determining that an abnormal phenomenon corresponding to any one of the thresholds has occurred in the microgrid when the calculated excess time is equal to or longer than a predetermined time, And a predetermined time of the microgrid abnormality detecting method.

[0009] Another prior art US20200313430A1, titled Configuring, optimizing, and managing micro-grids ascertained methods and systems for controlling electrical distribution grids. The method includes determining premises in an electrical distribution grid that include an energy resource. The method further includes determining a configuration of the electrical distribution grid including a micro-grid, the micro-grid including the one or more premises. The method further includes electrically isolating, monitoring and controlling the micro-grid from the electrical distribution grid through the use of a micro-grid manager.

[0010] Another Prior art document US9455577B2 by Gopal K. BHAGERIAJean Gael F. REBOUL, titled Managing devices within micro-grids - explained An approach to provide power from power supply devices to power-consuming devices based on characteristics of the power consuming devices and/or the power supply devices. The approach includes a method that includes receiving information of a power-consuming device from an energy management system that determines criticality of the power consuming device. The method further includes receiving power supply information of one or more power supply devices associated with an electric grid. The method further includes receiving a power request from the power-consuming device. The method further includes determining that the power-consuming device receives power from the power supply device, based on the information and the power supply information.

[0011] Similar prior art US9960637B2 .with title Renewable energy integrated storage and generation systems, apparatus, and methods with cloud distributed energy management services- discloses A software platform in communication with networked distributed energy resource energy storage apparatus, configured to deliver various specific applications related to offset demand monitoring, methods of virtual power plant and orchestration, load shaping services, methods of reducing demand at aggregated level, prioritizing computer programs related to virtual energy pool, energy cloud controllers methods, charge discharge orchestration plans of electric vehicles, distributed energy resources, machine learning predictive algorithms, value optimizing algorithms, autonomous sensing event awareness, mode selection methods, capacity reservation monitoring, virtual power plant methods, advanced DER-ES apparatus features, energy management system for governing resources and methods, aggregated energy cloud methods, load shaping methods, marginal cost cycle-life degradation, load shaping API, forward event schedule, on-demand request, and load service state request methods.

[0012] In Prior art document US20060158037A1 by Douglas Danley et al, with title Fully integrated power storage and supply appliance with power uploading capability disclosed a Systems, methods and devices for integrating alternative energy sources and energy storage components into a single device with systems for control and safety monitoring to provide for use of the generated power on the premises, resale of power to the utility, and for power supply from storage and/or the alternative energy sources in the event of an interruption of supply from a utility's power grid.

[0013] Another prior art document US20170228479A1 describes a Systems and methods for real-time modelling of a microgrid are disclosed. An analytics server communicatively connected to a microgrid. The analytics server comprises a virtual system modelling module, an analytics module; a simulation module; and a communications module. The virtual system modelling module is operable to generate predicted data for the microgrid utilizing a virtual system model of the microgrid. The analytics module is operable to initiate a calibration and synchronization operation to update the virtual system model based on a difference between the predicted data and real-time data from the microgrid. The simulation module is operable to forecast at least one aspect of the microgrid. The communications module is operable to provide at least one forecasted aspect to a microgrid operator and a microgrid operator.

[0014] Another prior art document US8751421B2 by Roger N. Anderson Et al disclosed an invention Machine learning for power grid wherein he proposed A machine learning system for ranking a collection of filtered propensity to failure metrics of like components within an electrical grid that includes a raw data assembly to provide raw data representative of the like components within the electrical grid; (b) a data processor, operatively coupled to the raw data assembly, to convert the raw data to more uniform data via one or more data processing techniques; (c) a database, operatively coupled to the data processor, to store the more uniform data; (d) a machine learning engine, operatively coupled to the database, to provide a collection of propensity to failure metrics for the like components; (e) an evaluation engine, operatively coupled to the machine learning engine, to detect and remove non-complying metrics from the collection of propensity to failure metrics and to provide the collection of filtered propensity to failure metrics; and (f) a decision support application, operatively coupled to the evaluation engine, configured to display a ranking of the collection of filtered propensity to failure metrics of like components within the electrical grid.

[0015] Referring to another document US10599175B1, discloses a Time synchronized frequency and voltage regulation of electric power balancing areas. Wherein Systems, methods, and computer program products are described for controlling power of a balancing area having a plurality of distributed energy resources of a power system. A high frequency controller having a memory and at least one data processor of one distributed energy resource of the balancing area continuously receives (i) data including a phasor data stream having time-synchronized phasor measurements derived from the plurality of distributed energy resources of the balancing area and (ii) real-time energy levels of the plurality of distributed energy resources.

[0016] US20150051856A1 document titled Method for estimating voltage stability discussed a method for estimating voltage stability includes establishing a multi-port equivalent model and the measurement-based equivalent impedance; calculating the reactive power response factor through two consecutive samples from wide-area phasor measurement unit measurement; finding the mitigation factor; constructing the modified coupled single port model with the modified impedance and voltage; and using the modified maximal loading parameter for voltage stability assessment.

[0017] CN104242462A presented an invention relates WAMS (wide-area measurement system) and SCADA (supervisory control and data acquisition) integrated data based grid forced oscillation source positioning method. The method includes: firstly, positioning general directions of the oscillation sources by adopting an energy flow function method based on 500kV grid WAMS data, then adopting different accurate oscillation source positioning methods according to properties of three common oscillation sources, computing tie lines of a local weak tie network by adopting a SCADA data-based oscillation extreme point judgment method, and judging whether oscillation exists in the weak tie network or not; adopting WAMS data of generator excitation voltage phase to judge whether oscillation is caused by a generator exciting system or not; adopting an extreme point computation method of SCADA data of valve or guide vane opening of a generator set to judge whether grid oscillation is caused by a unit prime mover or not.

[0018] In an early document CN102323494B, The invention relates to a novel method for distinguishing multiple harmonic sources, which can be used for providing a theoretical foundation for positioning a disturbance source in a multiple harmonic source system, managing harmonic waves, rewarding or punishing the harmonic waves and the like and has a broad application prospect and favourable social and economic benefits. The method comprises the following steps of (1) defining a harmonic influence index; (2) solving the harmonic influence index; (3) acquiring and pre-processing data; and (4) selecting and analyzing the data.

[0019] In a prior document CN102221655A, The invention discloses a random-forest model-based power transformer fault diagnosis method, which comprises the following steps of: acquiring transformer state overhauling data, training a random forest model by utilizing the transformer state overhauling state, checking the sensitivity of the random forest model, and diagnosing a fault of a transformer by using the trained and checked random forest model. The method provided by the invention is high in adaptability and interpretability, and criticality between normality and the fault is separated by utilizing a k-means clustering method, and a system is endowed with fault early warning capability.

[0020] In an invention stated in a document CN102377180B, disclosed an invention relates to a power system load modelling method based on an electric energy quality monitoring system, belonging to the field of power system measurement and load model identification.

[0021] The present invention provides an effective maintenance system for a microgrid system with the integration of the plurality of the Smart Line Monitoring &

Control System (SMCS). Whereas SMCS can work alone with Machine Learning Algorithm and as well as in coordination control with other plurality of SMCS and CMCS. Wherein CMCS on a whole can execute advanced Machine Learning Algorithms to ascertain PQ issues and stress on the lines and isolate the faulty or overloaded systems.

[0022] The present invention addresses the shortcomings mentioned above of the prior art.

[0023] All publications herein are incorporated by reference to the same extent as if each publication or patent application were specifically and individually indicated to be incorporated by reference. Where a definition or use of a term in an incorporated reference is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies, and the definition of that term in the reference does not apply.

SUMMARY

[0024] The following presents a simplified summary of the disclosure in order to provide a basic understanding of the reader. This summary is not an extensive overview of the disclosure, and it does not identify key/critical elements of the invention or delineate the scope of the invention. Its sole purpose is to present some concepts disclosed herein in a simplified form as a prelude to the more detailed description that is presented later.

[0025] Exemplary embodiments of the present disclosure are directed towards the Machine Leaming-Based Power Quality Improvement System For Micro-Grid.

[0026] An exemplary object of the present disclosure is directed towards a system that monitors and controls the PQ issues especially Voltage Sag And Swells in a Microgrid system.

[0027] Another exemplary object of the present disclosure is directed towards the integration of microcontroller 101a with Power IC 101b and capacitor banks to make Smart Line Monitoring & Control System (SMCS) 101. Whose primary function is to monitor vital bus parameters especially voltages, currents, frequency waveforms.

[0028] Another exemplary object of the present disclosure is directed towards the integration of microcontroller 101a with a capacitor bank which can switch on required capacitance on-demand to mitigate the voltage issues.

[0029] An exemplary aspect of the present subject matter is directed towards the implementation of the Machine Learning Algorithm in microcontroller 10la for ascertaining the type of PQ issue that occurred in the particular bus where the SMCS is connected.

[0030] An exemplary aspect of the present subject matter is directed towards the use of the Machine Learning Algorithm in microcontroller 101a for predicting the PQ issues that may be caused by excess loading and pre-fault conditions.

[0031] An exemplary aspect of the present subject matter is directed towards the implementation of the Machine Learning Algorithm in microcontroller 10la for predicting the PQ event and finding suitable mitigation method.

[0032] Another exemplary aspect of the present disclosure is directed towards the integration of the plurality of SMCS with CMCS through WiFi Mesh Network. Where in each SMCS acts as a node and trans-receive the WiFi signals.

[0033] Another exemplary aspect of the present disclosure is directed towards the implementation of the Machine Learning Algorithm in SMCS for supporting decisions of the plurality of SMCS during PQ anomaly and as well as fault conditions and prediction of failures.

[0034] Another exemplary aspect of the present disclosure directed towards the implementation of the Machine Learning Algorithm in SMCS for determining the stress on line and loading capacity.

[0035] Another exemplary aspect of the present disclosure directed towards the removal of the faulty section or transformer from the system to avert total system failure.

BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In the following, numerous specific details are set forth to provide a thorough description of various embodiments. Certain embodiments may be practiced without these specific details or with some variations in detail. In some instances, certain features are described in less detail so as not to obscure other aspects. The level of detail associated with each of the elements or features should not be construed to qualify the novelty or importance of one feature over the others.

[0037] FIG.1 is a diagram depicting the100 Machine Leaming-Based Power Quality Improvement System for Micro-Grid, according to an exemplary embodiment of the present disclosure.

[0038] FIG. 2 is a Block diagram 101 Smart Line Monitoring & Control System (SMCS) 101 according to an exemplary embodiment of the present disclosure.

[0039] FIG. 3 is an actual representation of the microcontroller 101a, according to an exemplary embodiment of the present disclosure.

[0040] FIG. 4 is an actual representation of Custom Made PCB for POWER IC (ADE7861), according to an exemplary embodiment of the present disclosure.

[0041] FIG. 5 is a flow chart 500 depicting the Process executed on SMCS.

[0042] FIG. 6 is a flow chart 600 depicting the process carried in CMCS.

[0043] Fig 7 depicts the actual representation of Two Step Capacitor Bank Array

DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0044] It is to be understood that the present disclosure is not limited in its application to the details of construction and the arrangement of components outlined in the following description or illustrated in the drawings. The present disclosure is capable of other embodiments and of being practiced or of being carried out in various ways. Also, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting.

[0045] The use of "including", "comprising" or "having" and variations thereof herein is meant to encompass the items listed thereafter and equivalents thereof as well as additional items. The terms "a" and "an" herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced item. Further, the use of terms "first", "second", and "third", and the like, herein do not denote any order, quantity, or importance, but rather are used to distinguish one element from another.

[0046] The nomenclature used hereafter for ease of understanding grouped and termed here as follows. Microgrid system means a plurality of loads and a source connected in a ring main to maintain continuous supply to all the loads by deriving the power from one or more power sources. Microcontroller means a microcomputer capable of executing Artificial intelligence and machine language algorithms. Machine Learning Algorithm (MLA) implies a generalized term for the complete process of data collections, noise removal, data formatting, cleansing, usage of random forest method, training the model with -80 ration, model evaluation, parameter tuning, prediction, and weight adjustment. Power IC 101b is an advanced chip custom made to collect power data in a bus bar/connected terminals having a six-channel current sensor in which three connected in input side and another three connected to secondary of the particular bus. Powe quality issues which are mainly in discussions are Voltage Sag and Swell only. Another set of nomenclature used hereafter are defined when and where required.

[0047] Referring to FIG. 1 is a diagram depicting a Machine Learning Based Power Quality Improvement System for Micro-Grid. Which comprises of a Central Monitoring & Control System (CMCS) 103, a plurality of Smart Line Monitoring & Control System (SMCS) 101 connected through WiFi Mesh network 102 to CMCS 103 in a ring main microgrid system. CMCS is a central management unit capable of executing parallel and complex Machine Learning Algorithms (MLA) and calculations. All the SMCS 101 are enabled with WiFi mesh network which eliminates the necessity of any special routers or modems and this feature is an advanced IoT function that removes the redundancy and reliable data transfer.

[0048] Further to it, CMCS & SMCS uses a trained MLA based on a random forest model for predicting faults, line loading, load flow analysis, and PQ issue determination.

Data transmitted by the plurality of SMCS 101 is collected, labelled as per SMCS ID and time interval, and stored in the database. The power data thus received is cleansed and fed to the MLA for predicting stress on the feeder and line, the capacity of other components in the line as well as the components which might create PQ issues. And also, MLA predicts the faults and analyzes the fault events which take place in or outside the busbar and justifies the actions taken by SMCS 101. CMCS 103 is a centralized unit which typically consists of a computing device which is capable of interacting, acquiring the data, processing the data and sending necessary commands to the plurality of SMCS 101.

[0049] Additional to it, CMCS can isolate a faulty section or an overstressed section based on the prediction model. This feature enables the microgrid to maintain its stability and reliability through its operation time. For the said model, a five bus system is considered wherein four loads are connected to four busses and one bus is considered as power sources bus. Hence, it is to understand that, the generating bus is capable of supplying the required power demand from all the four loads. This system is considered by taking into account of a microgrid formed in cement industry.

[0050] During the islanding process and as well as uncertain loading conditions, PQ events may occur and which may create serious problems if not mitigated in time. For mitigating the PQ event we must act swiftly when an anomaly is found. For finding the PQ anomaly the placement of SMCS devices is much more important. Hence, five SMCS is considered and among them, two are connected between source bus bar 104n and load busbar 104-1 and well at 104-4. Remaining are connected across the load busbars as shown in fig 1.

[0051] SMCS 101-n has connected across the load bus and generator bus means, a set of the current transformers and three potential transformers from load-bus continuously compares the voltage and currents waveforms concerning source bus. Whereas remaining SMCS monitor only feeders connected to that concerned busbar. This configuration and assembly help in ascertaining exact PQ anomaly and pinpoint the place of origin. This process is executed by CMCS based on relevant trained MLA and data set.

[0052] In accordance with a non-limiting exemplary embodiment of the present subject matter, FIG. 2 is a representation of the Smart Line Monitoring & Control System (SMCS) 101. As depicted in the drawings of FIG 2, SMCS 101 consists of microcontroller 101a, Power IC (ADE7816) 101b, Current sensors 101c, Potential sensors 101d, embedded connection to Circuit breakers 101e controlled through relays, Temperature sensor 101f and Capacitor Bank 101g. Current sensors 101c divided into a set of three and connected to the two-lines adjoining concerned busbar. Similarly, Potential transformers 101d divided into a set of three and connected in the same fashion as that of current transformers 101c. The arrangement of Current sensors 101c forms a busbar protection system and also for identifying PQ events. The combinational performance analysis of temperature sensor 101f and current sensor 101c enables the relevant MLA to predict the future faults arising of core and oil temperature variations concerning the predicted and present load on a transformer. Microcontroller 101a controls the circuit breakers concerned with that transformer and busbar, which are arranged in incoming and outgoing lines, as indicated in FIG 1. Based on the output of MLA, Microcontroller 10la decided to operate concerned circuit breaker 101e for averting PQ anomaly and faults and disconnecting the faulty transformer or line. All the components of the SMCS concealed in a custom container with IP & IK protection norms and for ease of installation. Powered by solar, and as well as +12/+5 V DC supply, makes the SMCS more convenient for deployment.

[0053] Referring to FIG 3 is a diagram depicting the actual image of Microcontroller 101a, which acts as a backbone for the present invention. Tweaked with ZRAM and additional external storage system 101a-i makes the microcontroller 101a suitable for the present invention. In microcontroller 101a, Machine Learning Algorithms can be executed in parallel to validate several parameters of the microgrid.

[0054] In accordance with a non-limiting exemplary embodiment of the present subject matter, FIG. 4 is an actual image depicting the Custom Made PCB for POWER IC(ADE7816) 101b. The Power IC 101b- is a state of the art chip designed particularly for accurate power measurement and integrated with easy. By utilizing this feature, in the present invention, the same Power IC 10lb-i is developed on a custom size PCB to hold the required components such as power supply and sensor connectors and controller connectors. Custom PCB integrated with microcontroller 10la for busbar anomaly detection and mitigation. The Current Transformers 101c, which are split-core type connected to any sort of cables/wire up to 200A current rating. Three current transformers 101c form a group that is hooked up in either the primary or secondary side of the transformer and acts as a differential protection scheme. Power IC 10lb-i collects the sensor data and accurately measures and presents power data, which are Active Power, Reactive Power, Apparent Power, Individual phase and line currents and voltages, along with RMS and True values and concerned waveform.

[0055] According to a non-limiting exemplary embodiment of the present disclosure, FIG.5 is a flow chart 500 depicting Process for executed in SMCS 101. SMCS considered as principal protection and monitoring device for the busbar in the way it acts by monitoring its performance with sensors and power IC and controlling its operations when fault or PQ abnormality arises. The step 501 starts by acquiring Current and Voltage magnitudes from respective waveforms through Power IC 101b. Assign time stamping to the acquired values along with SMCS ID. Timestamping is done to the acquired value so that the occurrence can be known precisely for the present and future process. Whereas SMCS ID is attached to the data acquired as this data is further transmitted to CMCS for justification and prediction of the faults and other PQevents, and this SMCS ID makes the CMCS pinpoint the occurrence point in the system accurately. In successive step 502, microcontroller 101a compare waveforms of two currents and voltages at that bus and compute the change in waveforms of currents and voltages Al and AV. In a balanced system, when so anomaly is present then the Al and AV must be nearly zero. It is to be noted that, Al and AV may be the difference is busbar voltages and currents or maybe the difference between operating norms. Therefore, in step 503 microcontroller executes relevant Machine Learning Algorithm (MLA) to ascertain whether Al and AV values are in limits by comparing them with set values. For speedy of response, the microcontroller first compares the Al and AV values with user-defined set values to determine an ongoing anomaly or a fault. In step 504, then feed the values directly to the machine learning algorithm and predict the type of power quality issue alert the CMCS-MAIN and devise the mitigation strategy. The mitigation strategies which are not limited to but maybe energizing capacitor banks in a stepwise manner or eliminating the source which causes the PQ anomaly. And also communicating the anomaly to CMCS 103 by SMCS 101 may also lead to mitigation strategy which may be localized at that fault or maybe on overall prospective of the grid. The mitigation strategies at grid level which are not limited to but maybe increasing the generation, increasing the capacitor involvement or maybe removing a section.

[0053] Further to step 505, based on mitigation strategy, connect capacitors of the respective capacitor bank. This step is crucial for eliminating any false PQ issue indication arisen from several constraints. Any PQ event arose of any condition is mitigated away in this step. This is to be noted that, Power IC 101b s capable of identifying Voltage sag and Swell in 1 / 1 0 th of a cycle and the processor 101a is capable of executing the relevant MLA and mitigate the same in less than a half-power cycle. Next step 506 starts with microcontroller 101a acquire Al and AV after energies the capacitor banks and fed the values to respective MLA for determining their safe values. And in the following step 507, microcontroller 101a If the PQ issues persisting, then microcontroller 10la increase the capacitor bank values and again Acquire Al and AV through power IC 10lb. It is worthwhile to note that, capacitor bank 101g is a two-step value device, which is capable of delivering the required capacitance to mitigate the PQ event. The capacitance value may be designed exactly based on the grid parameters and predicted PQ events. Wherein step 508, a conclusion about the PQ event or anomaly which has aggrieved from step 507, and the microcontroller 101a then ascertain the type of PQ issues and intimate the CMCS with time stamping & SMCS ID and upload power data and type of PQ issue.

[0054] According to a non-limiting exemplary embodiment of the present disclosure, FIG.6 is a flow chart 600 depicting the process carried in CMCS, which starts at step 601 wherein CMCS acquire all the parameters of the Grid through respective SMCS and allocate time-stamping along with SMCS ID. Data is not restricted to sensors, but it also includes the MLA predicted outcome as well as other derivatives. As data collected from the plurality of SMCS, then the data cleansing should take place. Therefore in step 602. Data cleansed to meet the requirements of the MLA present in CMCS. In consecutive step 603, power data, that is Al, AV, AT, and APL of all the plurality of SMCS fed to the concerned machine learning algorithm MLA.

[0055] Further, in step 604, with the help of predicted outcome from one of the MLAs concerning current and voltage variations in all the lines, CMCS ascertains the exact load causing the concerned PQ issues and intimates the SMCS for deploying appropriate mitigation method. In consecutive step 605, if microcontroller in SMCS once received the mitigation method, it executes the necessary actions and intimates the same to CMCS through communication network 102. In step 606, CMCS monitor the actions of relevant SMCS and acquires new data of Al, AV, Af and APL of all the plurality of SMCS and feed to concerned MLA. Subsequently in step 607, If the concerned PQ issue is not resolved to improvise the mitigation strategy and send new mitigation command to concern SMCS. Step 608, CMCS execute the steps 605 to 607 till the PQ issues are resolved, else send a command to relevant SMCS to disconnect the concerned load.

[0056] In an embodiment, SMCS collects the data of transformers core and oil temperature through temperature sensor 101f. This data is normalized and fed to relevant MLA to predict the nearby fault conditions and stress on the core due to excessive currents or losses in a transformer. It is to note that, excessive heat lead to PQ issues due to saturated core and may result in fatal transformer failure. If predicted results show adverse loading condition and stress on the line, CMCS removes the faulty session or transformer.

[0057] In another embodiment, the capacitor banks 101g which are designed to just suit the requirements of the microgrid thus considered. The well-known fact that excessive power electronic components usage in microgrids introduces the excessive reactive power in the system and this results in inrush current during commencement and as well as load decommissioning. Hence, the capacitor bank 101g initially if required to mitigate this issue may be energized. This step is initiated by the CMCS 103 based on relevant MLA output. The relevant output predicts the initial condition based on its training model and the data provided.

Editorial Note 2020103307 There are only two pages of Claim

Claims (5)

1. STATEMENT OF CLAIMS

   We Claim:

   The Machine Learning-Based Power Quality Improvement System For Micro-Grid consisting of:

   A plurality of Smart Line Monitoring & Control System (SMCS) 101 connected to Central Monitoring & Control System (CMCS) 103 through Communication-Network 102; and Where in Smart Line Monitoring & Control System (SMCS) 101 is an integration of Microcontroller 101a, Power IC 101b, Current Sensors 101c, Potential Transformers 101d, circuitry for controlling Circuit Breaker 101e, Temperature sensor 101f and capacitor banks 101g; and SMCS 101 capable of running suitable Machine Learning Algorithms for predicting and ascertaining the type of PQ issue, fault and its timeline; and SMCS 101 capable of running suitable Machine Learning Algorithms for predicting fault and PQ events due to temperature variations in core and oil of the transformer; and CMCS is comprising a computer capable of acting as a server and parallel execution of different Machine Learning Algorithms to ascertain decisions taken by SMCS; and CMCS capable of executing a type of Machine Learning algorithm to predict the loading effect and can isolate the session based on PQ event in that section; and CMCS capable of running suitable Machine Learning Algorithms on data acquired from plurality of SMCS 101 for predicting the origin of PQ event and send appropriate mitigation method; and SMCS is capable of mitigating the PQ event by one or more methods which may include the introduction of capacitor banks or isolation of the PQ event causing agent.
2. 2. The device as claimed in claim 1, wherein a combination of a plurality of SMCS 101 and CMCS 103 employed for monitoring and mitigating the PQ event in a microgrid by employing capacitor banks 101g else isolation of the component causing that PQ event.
3. 3. The device as claimed in claim 1, wherein the SMCS contains the integration of Microcontroller 101a and Power IC (ADE7816) 10lb capable of making a protection scheme for the busbar and determine/ predict PQ events by using suitable Machine Learning Algorithm.
4. 4. The device as claimed in claim 1, wherein CMCS using Machine Learning Algorithm, determine the PQ event causing component and isolates the section.
5. 5. The device as claimed in claim 1, wherein SMCS 101 use Machine Learning Algorithm to mitigate the concerned PQ event by connecting capacitor bank 101g and reviewing the capacity of capacitor bank 101g till PQ event is averted.

   103

   CMCS

   102 102 101 2020103307

   101 104-n

   SMCS1

   101e 101e 101 101 105

   SMCS4

   104-2 104-3

   FIG 1 POWER DISTRIBUTION MANAGEMENT SYSTEM

   101a 101b 101c 2020103307

   CT1

   CT2 MICRO ADE7816 CONTROLLER POWER IC

   CT6

   PT

   101d 1-6

   101e 101g CIRCUIT BREAKERS 101f

   101 TRANSFORMER MONITORING SYSTEM (TMS)

   FIG 3 101a-1 101a

   101c 2020103307

   101b-1

   FIG 4- Custom Made PCB with POWER IC ADE7816

   500 09 Nov 2020

   501

   Acquire Current and Voltage magnitudes from respective wave forms through Power IC 101b. Assign time stamping to the acquired values along with SMCS ID 502 Compare waveforms of two sets of currents and voltages at that bus and compute the change in currents and voltages ΔI and ΔV. 2020103307

   503 Using relevant machine learning algorithm, ascertain whether ΔI and ΔV values are in limits in comparison them with set values and.

   504 If ΔI and ΔV are very high, then feed the values directly to machine learning algorithm and predict the type of power quality issue alert the CMCS-MAIN and devise the mitigation strategy. 505

   Based on mitigation strategy, connect capacitors of the respective capacitor bank. 506

   Acquire ΔI and ΔV after energies the capacitor banks and fed the values to respective MLA for determining and predicting their safe values. 507

   If the PQ issues persisting, then increase the capacitor bank 101g values and again Acquire ΔI and ΔV

   508 If ΔI is high and persistent after the step 507, then ascertain the type of PQ issues and intimate the CMCS with time stamping & SMCS ID and upload power data and type of PQ issue.

   FIG 5 500 Process for Executed in SMCS

   600 601

   Acquire all the parameters of the Grid through respective SMCS and assign time stamping along with SMCS ID

   602

   Segregate the PQ data concerning its type and arrange them in sequence and 2020103307

   place of occurrence and perform data cleansing.

   603

   Feed the cleansed data of ΔI, ΔV, Δf and ΔPL of all the plurality of SMCS to the Concerned machine learning algorithms.

   604

   Machine learning algorithm predicts and determines the exact load causing the concerned PQ issues and intimates the SMCS for mitigation method.

   605 SMCS once received the mitigation method, it executes the necessary actions and intimate the same to CMCS through communication network 102. 606

   CMCS monitor the actions of relevant SMCS and acquires new data of ΔI, ΔV, Δf and ΔPL of all the plurality of SMCS and feed to concerned MLA. 607

   If the concerned PQ issue is not resolved improvise the mitigation strategy and send new mitigation command to concern SMCS.

   608 Execute the steps 605 to 607 till the PQ issues are resolved, else send command to relevant SMCS to disconnect concerned load.

   FIG 6; 600 Process carried in CMCS

   2020103307 7

   Fig 7. A Two Step Capacitor Bank Array