WO2020053846A2 - A system and method for analysis of smart meter data - Google Patents
A system and method for analysis of smart meter data Download PDFInfo
- Publication number
- WO2020053846A2 WO2020053846A2 PCT/IB2020/050108 IB2020050108W WO2020053846A2 WO 2020053846 A2 WO2020053846 A2 WO 2020053846A2 IB 2020050108 W IB2020050108 W IB 2020050108W WO 2020053846 A2 WO2020053846 A2 WO 2020053846A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- clusters
- electricity
- cluster
- new
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R22/00—Arrangements for measuring time integral of electric power or current, e.g. electricity meters
- G01R22/06—Arrangements for measuring time integral of electric power or current, e.g. electricity meters by electronic methods
- G01R22/061—Details of electronic electricity meters
- G01R22/063—Details of electronic electricity meters related to remote communication
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2613—Household appliance in general
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2639—Energy management, use maximum of cheap power, keep peak load low
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B70/00—Technologies for an efficient end-user side electric power management and consumption
- Y02B70/30—Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
- Y02B70/3225—Demand response systems, e.g. load shedding, peak shaving
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
- Y04S20/20—End-user application control systems
- Y04S20/222—Demand response systems, e.g. load shedding, peak shaving
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/20—Information technology specific aspects, e.g. CAD, simulation, modelling, system security
Definitions
- the present invention relates to the analysis of smart meter data.
- the present invention relates to the development of an incremental clustering algorithm for the analysis of smart meter data and the system thereof.
- load prediction is be performed based on historical data and behaviour of power consumption of users may be analysed in order to plan load shedding cycles.
- Load prediction may be vital for planning in the power management system and provides a basis for economic operation of the power management system.
- Clustering analysis is commonly used to categorize the electricity consumption of a household and further classify the pattern of the load.
- a multidimensional dataset may be divided into groups, with points in each group being similar to one another, and points from different groups differ from one another as much as possible.
- a similarity may be determined by clustering according to a geometric average distance (such as Euclidean distance, etc.) K-Means clustering is used most widely today.
- K-value K-value
- a method such as Gaussian mixture model, self-organizing map (SOM), hierarchical clustering, time sequence analysis, etc., may apply as well for clustering smart meter data.
- none of the methods is ideal for capturing and generating the hidden pattern of energy consumption based on the day time and night time, season wise, planned and unplanned load shedding, etc.
- the US Patent 9190844B2 discloses a system for detecting individual appliance energy loads from a building composite load profile that includes an electric meter for capturing building composite load profile.
- the present invention consider the electricity consumptions of entire home (including all electrical appliance and their utilization) and not the individual appliances connected at home using incremental clustering and learning approach.
- the US Patent USl000l389Bl discloses a smart metering system that receives time series data from resource consumption nodes at regular intervals to find the anomalous behaviour of the consumption node.
- the present invention able to mine hidden patterns of the load cycle of consumer.
- the clustering based improvement of non-parametric functional time series forecasting of intra-day household-level load curves uses hierarchical algorithm to identify the patterns of energy consumption such as load profiles/consumption during a season wise, time (day /night), etc.
- the said algorithm suffers from the order sensitivity issue; also, the boundary of a cluster depends on radius or diameter.
- instant invention does not require any user intervention/inputs at all, as this proposed algorithm is completely parameter free and hence maintains the quality of the clusters always.
- a Bayesian Information Criterion is used to select the number of clusters for the constrained based Gaussian mixture model, which integrates the type of day (Saturday, Sunday and weekdays).
- the cited reference fail to explicitly disclose the analysis of the load shedding patterns in both planned and unplanned scenarios.
- the intra-building clustering used a Gaussian mixture model-based clustering to identify the typical daily electricity usage profiles of each individual building.
- the inter-building clustering used an agglomerative hierarchical clustering to identify the typical daily electricity usage.
- the instant invention consider the electricity consumptions of the entire home and not the building and uses Semi-Supervised Machine Learning Techniques and Incremental Learning approach.
- the inputs required from the end users may be the number of clusters to be formed, distance measure to be used, the assumption of centroids etc. in addition to inputting raw data set for forming the clusters.
- the end user needs to be completely aware of the nature of raw dataset. If the user is not aware of the dataset then there is a possibility of entering wrong details to the clustering algorithm. If wrong details are entered, then the quality of clusters can be hampered. Therefore, the need exists for a system wherein the dependency on the end user is completely removed.
- the main object of the present invention is to provide a new system and method thereof for analysing smart meter data to optimize electricity load management.
- Another objective of the present invention is to determine the load shedding patterns by using the said new system and method thereof for analysing smart meter data systematically by capturing and generating the hidden patterns of electricity consumption during the day-time, night-time and season in both planned and unplanned scenarios.
- Still another objective of the present invention is to provide a simple system and method thereof for analysing smart meter data to optimize electricity load management in an efficient manner and the said system and method would be easy to implement on commercial scale.
- the present invention relates to analysis of electric energy consumption data of individual households.
- This consumption data is captured by the smart meter and analysed by using the proposed incremental clustering algorithm of the present invention.
- the proposed incremental clustering algorithm is able to capture and generate the hidden pattern of consumption based on the day-time and night-time, season wise, as well as during planned and unplanned load shedding. These analysed details are useful for a generation unit to predict required energy in future and take further decisions. Further, the same analysis may also be performed at the electricity generation side too, for analysis of electricity generation related pattern analysis.
- the system enables a Closeness based Gaussian Mixture Incremental Clustering Algorithm (CGMICA) for analysing load shedding patterns in both planned and unplanned scenarios.
- CGMICA Closeness based Gaussian Mixture Incremental Clustering Algorithm
- the incremental clustering algorithm is configured to process raw dataset and automatically generate clusters. As a result, the quality of clusters is always maintained.
- the semi- supervised machine learning techniques and incremental learning approach enabled by the invention does not require user intervention or input.
- the proposed system identifies the change in residential energy consumption and provides the valuable data to help utility companies optimize the electricity load management. The invention thereby assists the government to efficiently plan for its economic and energy needs of the growing population.
- a method for analysing smart meter data to optimize electricity load management may comprise steps for receiving raw dataset from each smart meter of a set of smart meters.
- the method may comprise steps for dynamically generating a set of clusters from the raw dataset by pre-processing raw dataset to generate normalized data, generating a set of basic cluster(s) by processing the normalized data, and incrementally clustering new data, received from the set of smart meters, by selectively updating the set of basic cluster(s) or adding new cluster(s) to the set of basic cluster(s) based on the influx of the new data.
- the method may comprise steps for analysing each cluster from the set of clusters for determining load shedding patterns during planned and unplanned electricity outages to optimize the electricity load management.
- a system for analysing smart meter data to optimize electricity load management comprising a memory and a processor, wherein the processor is configured to execute programmed instructions stored in the memory for receiving raw dataset from each smart meter of a set of smart meters. Further, the processor may be configured to dynamically generating a set of clusters from the raw dataset by pre-processing raw dataset to generate normalized data, generating a set of basic cluster(s) by processing the normalized data, and incrementally clustering new data, received from the set of smart meters, by selectively updating the set of basic cluster(s) or adding new cluster(s) to the set of basic cluster(s) based on the influx of the new data. The processor may be further configured for analysing each cluster from the set of clusters for determining load shedding patterns during planned and unplanned electricity outages to optimize the electricity load management.
- Figure 1 illustrates an implementation 100 of a system 101 for regulating electrical energy consumption by performing clustering-based analysis of smart meter data acquired from a set of smart meters, in accordance with an embodiment of the present invention.
- FIG. 2 illustrates the system 101 and components of the system 101, in accordance with the embodiment of the present invention.
- Figure 3 illustrates a method 300 for regulating electrical energy consumption by performing clustering-based analysis of smart meter data acquired from a set of smart meters, in accordance with an embodiment of the present invention.
- Figure 4 illustrates a flowchart for regulating electrical energy consumption by performing incremental clustering-based analysis of smart meter data acquired from a set of smart meters, in accordance with an embodiment of the present invention.
- the network implementation (100) includes a set of smart meters (103) that record and collect the electricity consumption for household.
- the set of smart meters (103) are connected to the said system (101) through a network (102).
- the said network (102) communicates the data acquired by the smart meters (103) to the said system (101).
- the said system (101) is accessed by the electricity generation units for regulating electrical energy management, enabling reduced load shedding and thereby indirectly reduction in energy consumption and carbon emission.
- the referred network (102) may be a wireless network, a wired network or a combination thereof.
- the said network (102) can be accessed by the said system (101) using wired or wireless network connectivity means including updated communications technology.
- the said network (102) can be implemented as one of the different types of networks, such as intranet, local area network (LAN), wide area network (WAN), the internet, and the like.
- the said network (102) may either be a dedicated network or a shared network.
- the shared network represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Intemet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like, to communicate with one another.
- the network (102) may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, and the like.
- the said system (101) may comprise at least one processor (201), an input/output (I/O) interface (202), a memory (203), modules (204) and data
- At least one said processor (201) is configured to fetch and execute computer-readable instructions stored in the memory (203).
- the said I/O interface (202) may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like.
- the said I/O interface (202) may allow the system (101) to interact with the said operator devices (103).
- the said I/O interface (202) may enable the said operator device (103) to communicate with other computing devices, such as web servers and external data servers.
- the said I/O interface (202) can facilitate multiple communications within a wide variety of network and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite.
- the said I/O interface (202) may include one or more ports for connecting to another server.
- the said memory (203) may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and memory cards.
- volatile memory such as static random access memory (SRAM) and dynamic random access memory (DRAM)
- non-volatile memory such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and memory cards.
- ROM read only memory
- erasable programmable ROM erasable programmable ROM
- the modules include routines, programs, objects, components, data structures, etc., which perform particular tasks, functions or implement particular abstract data types.
- the modules may include an incremental clustering module (205), a cluster analysis module (206), a pattern identification module (207), and energy management module (208).
- the other modules may include programs or coded instructions that supplement applications and functions of the user device.
- the said data (209) may comprise repository
- the repository (209) may be configured to store data processed, received, and generated by one or more of the modules (204).
- the repository (210) may store database of the one or more smart meters.
- the said other data (211) may include data generated as a result of the execution of one or more modules.
- the said incremental clustering module (205) performs the task of clustering the smart meter data collected by the said set of smart meters (103).
- the said incremental clustering module (205) enables an incremental clustering algorithm for dynamically analyse the smart meter data and group related data series together. Incremental clustering algorithms start with the creation of basic clusters with initial dataset available.
- incremental clustering algorithm effectually accommodates the new data and either appends the existing clusters or forms new cluster(s) automatically.
- these clusters may observe the change in their individual structures. Every cluster's representative may change the threshold range of cluster may affect with the new data addition.
- the said incremental clustering module (205) captures all these details and learns from every iteration of the addition of new data, which is termed as incremental learning. With every new learning details, the augmentation of knowledge is achieved.
- the said cluster analysis module (206) analyses the clusters formed by the said incremental clustering module (205).
- the analysis step generates electricity consumption patterns for households.
- the consumption pattern implies patterns observed during planned and unplanned load shedding scenarios.
- (208) regulates the electrical energy by mining and locating the hidden patterns of electricity energy consumption such as load composition during a particular season, time (day/night) specific, etc.
- the method (300) for regulating electrical energy consumption in a household by performing incremental clustering-based analysis of smart meter data acquired from a set of smart meters is illustrated.
- the method (300) includes the steps of: Data acquisition (302), Data pre-processing (304), Incremental clustering (306) and Load shedding pattern analysis (308) for improving electrical energy consumption in households.
- the said method (300) is further elaborated with respect to the flowchart of figure 4
- step (402) the data acquisition of raw dataset from a set of smart meters is diligently performed.
- the raw dataset is pre-processed to produce noise free normalized data.
- the ‘Closeness based Gaussian Mixture Incremental Clustering Algorithm (CGMICA)’ enabled by the said system (101) is ran on the normalized data. Further, the CGMICA forms basic clusters using the normalized data.
- the said CGMICA also updates the existing clusters on the arrival of the new data. If the new data cannot be classified into the existing clusters, new clusters are generated.
- the formed clusters are stored in the cluster database.
- the said clusters stored in the database are further analysed for identification of the load shedding patterns.
- the cluster characteristics and load shedding patterns are further fed into the network of the set of smart meters, which are further used as dataset for pre-processing and so on for incremental clustering for incremental learning.
- a Gaussian mixture model/clustering is a parametric approximation to a probability distribution via a weighted combination of Gaussian components.
- a traditional approach to Gaussian mixture learning is the Expectation-Maximization (EM) algorithm.
- EM Expectation-Maximization
- the EM algorithm is slow, especially when the number of samples is large and therefore it has limitations, which are bypass by the proposed instant invention.
- it is not adaptive in the number of Gaussian components in the mixture model, and the local maximum likelihood solution it depends heavily on the initial guess. Choosing the correct attributes (initial guess) is potentially the most important aspect of a successful clustering, which motivates the present inventors to pursue the instant invention, moreover the smart meter generates a large amount of data incrementally.
- the present invention proposes CGMICA that combines Closeness Factor Based Algorithm (CFBA) with the EM algorithm by feeding the output of CFBA to the EM algorithm as its initial guess.
- CFBA Closeness Factor Based Algorithm
- the informed initial guess is often close to a maximum likelihood estimate and thus needs fewer EM iterations, which make the EM algorithm, fast enough for large datasets.
- the quality of the informed initial guess potentially improves the accuracy of the EM output. Therefore, the said proposed CGMICA or model thereof excels at both accuracy and efficiency for large datasets.
- the semi-supervised approach performs selective update of the formed clusters and exhibits its scalable nature with new cluster generation.
- the incremental clustering process begins on arrival of new data series, the data turns out to be labelled.
- the incoming data is unlabelled still and need to be clustered, append in existing clusters or form the new clusters.
- This is the combination of labelled and unlabelled concepts, which is applied and hence it is called as semi- supervised approach.
- This incremental clustering algorithm always remains in semi- supervised mode as it accommodates incoming data in real time mode always.
- Step l.Data acquisition The collection of smart electricity meter data from network.
- the smart meter data may include active power, reactive power, a voltage, a current, a power factor etc.
- the load may be an active power reading.
- Step 2 In the direction of increasing the detection accuracy cleaning of data, normalization, and remove noise by using statistic techniques.
- Incremental Clustering Closeness based Gaussian Mixture Incremental Clustering Algorithm, which incrementally clusters the influx of new data. The computation of different values is done to update the existing clusters or to form the new clusters.
- Step 4. Analysing the load shedding patterns which includes the day wise, area wise, season wise in both planned and unplanned scenarios.
- I x ⁇ I xi , I x2 , ... , I xn ⁇ a set of n d- dimensional time series smart meter raw datasets, Mi ter : a maximum number of iterations, converge criteria(e) for loglikelihood.
- I xn (l) is the point 1 in series n.
- Sum(l) is the total of the corresponding parameters of the series considered.
- the referred incremental clustering approach for smart meter analysis may be implemented in electricity units, electricity utility companies, households, residential areas, etc.
- a method for analysing smart meter data to optimize electricity load management described above may have following advantages including but not limited to:
- the method and system of the present invention is a simple, economic, reliable, accurate, user-friendly and thereby lowering of labour.
- the present invention does not require any form of user intervention/inputs to form clusters.
- the present invention involves Closeness based Gaussian Mixture Incremental Clustering (CGMIC) Algorithm, which is cluster-first approach and not the centre-first as implemented in other conventional algorithms.
- CGMIC Gaussian Mixture Incremental Clustering
- the incremental learning is achieved via incremental clustering using knowledge augmentation, wherein cluster ranking is performed by the algorithm during iterations.
- the incremental learning is achieved via CGMIC algorithm and to utilize updated and clustered smart meter data as knowledge for further mining.
- the present invention helps the better balancing for the household customer, utility provider, and the environment. Household customers will be able to monitor and improvise electricity consumption patterns. Utility providers will be able to access monthly meter reading online quickly, accurately, and in real time mode. Utility providers hence will be able to reduce power outage and will be able to avoid capital expenses of building new plants.
- the proposed instant invention is extremely useful for maintaining the environment by reducing pollution via carbon production by power plants (as pollution is hazardous to health). Also helps in reducing pollution by individual vehicles used for driving to the individual customer’s meters for manual reading.
Abstract
The present invention discloses a method for improving energy management, enabling reduced energy consumption and load shedding based on analysis of smart electricity meter data. The method discloses an intelligent system, wherein it precisely estimates residential electricity demand by using dynamically generated smart meter data using incremental clustering algorithm. The disclosed invention redesigns and develops a parameter-free incremental clustering algorithm for mining the hidden patterns of electricity load shedding such as season-wise, time (day/night) specific patterns.
Description
TITLE OF INVENTION:
A SYSTEM AND METHOD FOR ANALYSIS OF SMART METER DATA
FIELD OF INVENTION
The present invention relates to the analysis of smart meter data. In particular, the present invention relates to the development of an incremental clustering algorithm for the analysis of smart meter data and the system thereof.
BACKGROUND OF INVENTION
In a power/ electricity management system, load prediction is be performed based on historical data and behaviour of power consumption of users may be analysed in order to plan load shedding cycles. Load prediction may be vital for planning in the power management system and provides a basis for economic operation of the power management system. Clustering analysis is commonly used to categorize the electricity consumption of a household and further classify the pattern of the load.
With clustering analysis, a multidimensional dataset may be divided into groups, with points in each group being similar to one another, and points from different groups differ from one another as much as possible. In clustering analysis, a similarity may be determined by clustering according to a geometric average distance (such as Euclidean distance, etc.) K-Means clustering is used most widely today. However, different initial partitions (K-value) can result in different final clusters. A method such as Gaussian mixture model, self-organizing map (SOM), hierarchical clustering, time sequence analysis, etc., may apply as well for clustering smart meter data. However, none of the methods is ideal for capturing and generating the hidden pattern of energy consumption based on the day time and night time, season wise, planned and unplanned load shedding, etc.
The US Patent 9190844B2 discloses a system for detecting individual appliance energy loads from a building composite load profile that includes an electric meter for capturing building composite load profile. However, the present invention consider the electricity consumptions of entire home (including all electrical appliance and their utilization) and not the individual appliances connected at home using incremental clustering and learning approach.
The US Patent USl000l389Bldiscloses a smart metering system that receives time series data from resource consumption nodes at regular intervals to find the anomalous behaviour of the
consumption node. However, the present invention able to mine hidden patterns of the load cycle of consumer.
According to the disclosure of IEEE Transactions on Smart Grid, 2014 the clustering based improvement of non-parametric functional time series forecasting of intra-day household-level load curves. The said system uses hierarchical algorithm to identify the patterns of energy consumption such as load profiles/consumption during a season wise, time (day /night), etc. The said algorithm suffers from the order sensitivity issue; also, the boundary of a cluster depends on radius or diameter. However, instant invention does not require any user intervention/inputs at all, as this proposed algorithm is completely parameter free and hence maintains the quality of the clusters always.
According to the disclosure of Energies, 2017 a Bayesian Information Criterion is used to select the number of clusters for the constrained based Gaussian mixture model, which integrates the type of day (Saturday, Sunday and weekdays). However, the cited reference fail to explicitly disclose the analysis of the load shedding patterns in both planned and unplanned scenarios.
According to the disclosure of Applied Energy, 2018 the two levels of clustering, i.e. intra building clustering and inter-building clustering. The intra-building clustering used a Gaussian mixture model-based clustering to identify the typical daily electricity usage profiles of each individual building. The inter-building clustering used an agglomerative hierarchical clustering to identify the typical daily electricity usage. However, the instant invention consider the electricity consumptions of the entire home and not the building and uses Semi-Supervised Machine Learning Techniques and Incremental Learning approach.
Further, conventional clustering algorithms require the end user to input various details. The inputs required from the end users may be the number of clusters to be formed, distance measure to be used, the assumption of centroids etc. in addition to inputting raw data set for forming the clusters. To enter all these details as input to the clustering algorithm, the end user needs to be completely aware of the nature of raw dataset. If the user is not aware of the dataset then there is a possibility of entering wrong details to the clustering algorithm. If wrong details are entered, then the quality of clusters can be hampered. Therefore, the need exists for a system wherein the dependency on the end user is completely removed.
OBJECTIVES OF THE INVENTION
The main object of the present invention is to provide a new system and method thereof for analysing smart meter data to optimize electricity load management.
Another objective of the present invention is to determine the load shedding patterns by using the said new system and method thereof for analysing smart meter data systematically by capturing and generating the hidden patterns of electricity consumption during the day-time, night-time and season in both planned and unplanned scenarios.
Yet another objective of the present invention wherein, the said system and method using incremental learning is useful for electricity generation units to regulate and reduce the un planned load-shedding pattern, thereby fixing such a problem instantaneously.
Still another objective of the present invention is to provide a simple system and method thereof for analysing smart meter data to optimize electricity load management in an efficient manner and the said system and method would be easy to implement on commercial scale.
SUMMARY OF THE INVENTION
This summary is provided to introduce concepts related to incremental clustering-based analysis of smart meter data. The object and advantages of the embodiments will be realized and achieved at least by the elements, features, and combinations particularly pointed out in the claims. It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of the invention, as claimed.
The present invention relates to analysis of electric energy consumption data of individual households. This consumption data is captured by the smart meter and analysed by using the proposed incremental clustering algorithm of the present invention. The proposed incremental clustering algorithm is able to capture and generate the hidden pattern of consumption based on the day-time and night-time, season wise, as well as during planned and unplanned load shedding. These analysed details are useful for a generation unit to predict required energy in future and take further decisions. Further, the same analysis may also be performed at the electricity generation side too, for analysis of electricity generation related pattern analysis.
In one embodiment wherein, the system enables a Closeness based Gaussian Mixture Incremental Clustering Algorithm (CGMICA) for analysing load shedding patterns in both planned and unplanned scenarios. The incremental clustering algorithm is configured to process raw dataset and automatically generate clusters. As a result, the quality of clusters is always maintained. The semi- supervised machine learning techniques and incremental learning approach enabled by the invention does not require user intervention or input. The proposed system identifies the change in residential energy consumption and provides the valuable data to help utility companies optimize the electricity load management. The invention thereby assists the government to efficiently plan for its economic and energy needs of the growing population.
In another embodiment of the present invention wherein, a method for analysing smart meter data to optimize electricity load management is disclosed. The method may comprise steps for receiving raw dataset from each smart meter of a set of smart meters. The method may comprise steps for dynamically generating a set of clusters from the raw dataset by pre-processing raw dataset to generate normalized data, generating a set of basic cluster(s) by processing the normalized data, and incrementally clustering new data, received from the set of smart meters, by selectively updating the set of basic cluster(s) or adding new cluster(s) to the set of basic cluster(s) based on the influx of the new data. The method may comprise steps for analysing each cluster from the set of clusters for determining load shedding patterns during planned and unplanned electricity outages to optimize the electricity load management.
In yet another embodiment of the present invention wherein, a system for analysing smart meter data to optimize electricity load management is disclosed. The system comprising a memory and a processor, wherein the processor is configured to execute programmed instructions stored in the memory for receiving raw dataset from each smart meter of a set of smart meters. Further, the processor may be configured to dynamically generating a set of clusters from the raw dataset by pre-processing raw dataset to generate normalized data, generating a set of basic cluster(s) by processing the normalized data, and incrementally clustering new data, received from the set of smart meters, by selectively updating the set of basic cluster(s) or adding new cluster(s) to the set of basic cluster(s) based on the influx of the new data. The processor may be further configured for analysing each cluster from the set of clusters for determining load shedding patterns during planned and unplanned electricity outages to optimize the electricity load management.
BRIEF DESCRIPTION OF DRAWINGS
The detailed description is described with reference to the accompanying Figures. In the Figures, the left-most digit(s) of a reference number identifies the Figure in which the reference number first appears. The same numbers are used throughout the drawings to refer like features and components.
Figure 1 illustrates an implementation 100 of a system 101 for regulating electrical energy consumption by performing clustering-based analysis of smart meter data acquired from a set of smart meters, in accordance with an embodiment of the present invention.
Figure 2 illustrates the system 101 and components of the system 101, in accordance with the embodiment of the present invention.
Figure 3 illustrates a method 300 for regulating electrical energy consumption by performing clustering-based analysis of smart meter data acquired from a set of smart meters, in accordance with an embodiment of the present invention.
Figure 4 illustrates a flowchart for regulating electrical energy consumption by performing incremental clustering-based analysis of smart meter data acquired from a set of smart meters, in accordance with an embodiment of the present invention.
DETAILED DESCRIPTION OF THE INVENTION
Reference throughout the specification to“various embodiments,”“some embodiments,”“one embodiment,” or“an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in various embodiments,” “in some embodiments,” “in one embodiment,” or“in an embodiment” in places throughout the specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments.
The words "comprising," "having," "containing," and "including," and other forms thereof, are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items or meant to be limited to only the listed item or items. It must be noted that the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise.
Various modifications to the embodiment may be readily apparent to those skilled in the art and the generic principles herein may be applied to other embodiments. However, one of ordinary skill in the art may readily recognize that the present invention is not intended to be limited to the embodiments illustrated but is to be accorded the widest scope consistent with the principles and features described herein.
Referring to figure 1, a network implementation (100) of a system (101) for regulating electrical energy consumption by performing incremental clustering-based analysis of smart meter data acquired from a set of smart meters is illustrated, in accordance with an embodiment of the present subject matter. As shown in figure 1, the network implementation (100) includes a set of smart meters (103) that record and collect the electricity consumption for household. The set of smart meters (103) are connected to the said system (101) through a network (102). In another embodiment of the present invention, wherein the said network (102) communicates the data acquired by the smart meters (103) to the said system (101). In another embodiment of the present invention, wherein the said system (101) is accessed by the electricity generation units for regulating electrical energy management, enabling reduced load shedding and thereby indirectly reduction in energy consumption and carbon emission.
In another implementation of the present invention, wherein the referred network (102) may be a wireless network, a wired network or a combination thereof. The said network (102) can be accessed by the said system (101) using wired or wireless network connectivity means including updated communications technology. The said network (102) can be implemented as one of the different types of networks, such as intranet, local area network (LAN), wide area network (WAN), the internet, and the like. The said network (102) may either be a dedicated network or a shared network. The shared network represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Intemet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like, to communicate with one another. Further the network (102) may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, and the like.
Although the instant invention is explained considering that the referred system (101) is implemented as on a server, it may be understood that the said system (101) may also be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a workstation, a mainframe computer, a server, a network server, and the like. It will be understood that the said system (101) may be accessed by multiple electricity generating units or electricity utility companies.
Now referring to figure 2, components of the said system (101) are illustrated in accordance with an embodiment of the present invention. The said system (101) may comprise at least one processor (201), an input/output (I/O) interface (202), a memory (203), modules (204) and data
(209). In another embodiment of the present invention, at least one said processor (201) is configured to fetch and execute computer-readable instructions stored in the memory (203).
In another embodiment, the said I/O interface (202) may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The said I/O interface (202) may allow the system (101) to interact with the said operator devices (103). Furthermore, the said I/O interface (202) may enable the said operator device (103) to communicate with other computing devices, such as web servers and external data servers. The said I/O interface (202) can facilitate multiple communications within a wide variety of network and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. The said I/O interface (202) may include one or more ports for connecting to another server.
In another implementation of the instant invention, wherein the said memory (203) may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and memory cards. The said memory (203) may include the said modules (204) and data (209).
The modules include routines, programs, objects, components, data structures, etc., which perform particular tasks, functions or implement particular abstract data types. In another implementation of the present invention wherein, the modules may include an incremental clustering module (205), a cluster analysis module (206), a pattern identification module (207), and energy management module (208). The other modules may include programs or coded instructions that supplement applications and functions of the user device.
In another embodiment of the present invention, the said data (209) may comprise repository
(210) and other data (211). In another exemplary embodiment of the present invention, wherein the repository (209) may be configured to store data processed, received, and generated by one or more of the modules (204). In another exemplary embodiment of the present invention, wherein the repository (210) may store database of the one or more smart meters. The said other data (211) may include data generated as a result of the execution of one or more modules.
In another embodiment of the present invention, wherein the said incremental clustering module (205) performs the task of clustering the smart meter data collected by the said set of smart meters (103). The said incremental clustering module (205) enables an incremental clustering algorithm for dynamically analyse the smart meter data and group related data series together. Incremental clustering algorithms start with the creation of basic clusters with initial dataset available. Once the basic clusters are ready, on arrival of the new data, incremental clustering algorithm effectually accommodates the new data and either appends the existing clusters or forms new cluster(s) automatically. In another embodiment of the present invention, on arrival of new data every time, these clusters may observe the change in their individual structures. Every cluster's representative may change the threshold range of cluster may affect with the new data addition. Hence, the said incremental clustering module (205) captures all these details and learns from every iteration of the addition of new data, which is termed as incremental learning. With every new learning details, the augmentation of knowledge is achieved.
In another embodiment of the present invention, wherein the said cluster analysis module (206) analyses the clusters formed by the said incremental clustering module (205). The analysis step generates electricity consumption patterns for households. The consumption pattern implies patterns observed during planned and unplanned load shedding scenarios.
In another embodiment of the present invention, wherein the said pattern identification module
(207) assists in identifying and locating the type of outages occurring at the households, which includes the planned and unplanned outages. In the planned load shedding, electricity office informs the users about the shut down in advance; therefore predefined depending on a locality. But to locate unplanned shutdown it is more important to check "no electricity utilization" indication details given by the smart meter data. Hence, the said pattern identification module locates the type of outage in the household area.
In yet another embodiment of the present invention, wherein the said energy management module
(208) regulates the electrical energy by mining and locating the hidden patterns of electricity energy consumption such as load composition during a particular season, time (day/night) specific, etc.
According to the figure 3, the method (300) for regulating electrical energy consumption in a household by performing incremental clustering-based analysis of smart meter data acquired from a set of smart meters is illustrated. In another embodiment of the present invention, wherein the method (300) includes the steps of: Data acquisition (302), Data pre-processing (304), Incremental clustering (306) and Load shedding pattern analysis (308) for improving electrical
energy consumption in households. The said method (300) is further elaborated with respect to the flowchart of figure 4
According to figure 4, wherein the flowchart (400) of the proposed incremental clustering algorithm for smart meter data analysis is illustrated.
According to the present invention, wherein at step (402), the data acquisition of raw dataset from a set of smart meters is diligently performed.
According to the present invention, wherein at step (404), the raw dataset is pre-processed to produce noise free normalized data.
According to the present invention, wherein at step (406), the‘Closeness based Gaussian Mixture Incremental Clustering Algorithm (CGMICA)’ enabled by the said system (101) is ran on the normalized data. Further, the CGMICA forms basic clusters using the normalized data.
According to the present invention, wherein at step (408), the said CGMICA also updates the existing clusters on the arrival of the new data. If the new data cannot be classified into the existing clusters, new clusters are generated.
According to the present invention, wherein at step (410), the formed clusters are stored in the cluster database.
According to the present invention, wherein at step (412), the said clusters stored in the database are further analysed for identification of the load shedding patterns.
According to the present invention, wherein at step (414), the cluster characteristics and load shedding patterns are further fed into the network of the set of smart meters, which are further used as dataset for pre-processing and so on for incremental clustering for incremental learning.
Furthermore, it must be noted that a Gaussian mixture model/clustering is a parametric approximation to a probability distribution via a weighted combination of Gaussian components. A traditional approach to Gaussian mixture learning is the Expectation-Maximization (EM) algorithm. As an iterative optimization method, the EM algorithm is slow, especially when the number of samples is large and therefore it has limitations, which are bypass by the proposed instant invention. Also, it is not adaptive in the number of Gaussian components in the mixture model, and the local maximum likelihood solution it depends heavily on the initial guess. Choosing the correct attributes (initial guess) is potentially the most important aspect of a successful clustering, which motivates the present inventors to pursue the instant invention, moreover the smart meter generates a large amount of data incrementally.
Thus, the present invention proposes CGMICA that combines Closeness Factor Based Algorithm (CFBA) with the EM algorithm by feeding the output of CFBA to the EM algorithm as its initial guess. The informed initial guess is often close to a maximum likelihood estimate and thus needs fewer EM iterations, which make the EM algorithm, fast enough for large datasets. Also, the quality of the informed initial guess potentially improves the accuracy of the EM output. Therefore, the said proposed CGMICA or model thereof excels at both accuracy and efficiency for large datasets.
In building incremental learning systems, various aspects are needed to be taken care of. The scarcity of the labelled data is one of the concern factors for the researchers while developing incremental systems. The tremendous availability of the unlabelled data can very well be utilized in bringing up incremental systems with the new classes. The proposed invention considered these factors and recommends semi-supervised incremental approach along with selective learning.
The semi-supervised approach performs selective update of the formed clusters and exhibits its scalable nature with new cluster generation.
Once the basic clusters are formed with their respective-cluster members, the incremental clustering process begins on arrival of new data series, the data turns out to be labelled. The incoming data is unlabelled still and need to be clustered, append in existing clusters or form the new clusters. This is the combination of labelled and unlabelled concepts, which is applied and hence it is called as semi- supervised approach. This incremental clustering algorithm always remains in semi- supervised mode as it accommodates incoming data in real time mode always.
Broadly, the whole development process of the proposed incremental clustering algorithm and system thereof can be segregated into the following steps:
Step l.Data acquisition: The collection of smart electricity meter data from network. The smart meter data may include active power, reactive power, a voltage, a current, a power factor etc. The load may be an active power reading.
Step 2. Pre-Processing: In the direction of increasing the detection accuracy cleaning of data, normalization, and remove noise by using statistic techniques.
Step 3. Incremental Clustering: Closeness based Gaussian Mixture Incremental Clustering Algorithm, which incrementally clusters the influx of new data. The computation of different values is done to update the existing clusters or to form the new clusters.
Step 4. Analysing the load shedding patterns which includes the day wise, area wise, season wise in both planned and unplanned scenarios.
Further, the proposed CGMICA is as disclosed below:
Input: Ix = { Ixi, Ix2, ... , Ixn} a set of n d- dimensional time series smart meter raw datasets, Miter: a maximum number of iterations, converge criteria(e) for loglikelihood.
Output: A series of the cluster stored in clusterdb
Outcome: Incremental learning of load shedding patterns day wise, time wise, season-wise Phase I: Formation of Basic Clusters
1) WHILE change in loglikelihood(llh) is greater than e and Mlter has not been reached DO: a) for i = 1 to n
i) Consider every two time series Ixi and Ix2, Ixn(l) is the point 1 in series n. Sum(l) is the total of the corresponding parameters of the series considered.
ii) The Relationship Probability(RP) of Ixi is calculated as ratio of first series to the sum of the corresponding parameters
iii) Closeness(CN) between series are CN=[(Er(l))2 * sqrt(Sum(l) )] [ sqrtfS u m(l) J 1 wherein Er(l) = [RP*Sum(l) - Ixn(l)] [sqrt(Sum(l) * RP * (l-RP))] 1
iv) number of cluster (k), Mean (m), Variance (å) are stored in clusterdb
endfor
b) Initialize: Set m, å, k, prior probability(Il) by using output of previous step(a). llh= -co c) for i = 1 to n
for j = 1 to k
Wherein, PP(Ixi | pj, åj)=[exp(-l/2 (Ic,- m , / Xf 'dxi- pj)]/[(2n)d/2 |å,| i/2] endfor
endfor d) for i = 1 to k
llh = llh + logiPRPtf PRPOxi/Ci)
endfor
Phase II: On influx of new data either updation of existing cluster(s) or formation of new cluster(s)
In another exemplary embodiment the proposed invention, the referred incremental clustering approach for smart meter analysis may be implemented in electricity units, electricity utility companies, households, residential areas, etc.
According to yet another embodiment the present invention wherein, a method for analysing smart meter data to optimize electricity load management described above may have following advantages including but not limited to:
• The method and system of the present invention is a simple, economic, reliable, accurate, user-friendly and thereby lowering of labour.
• The present invention does not require any form of user intervention/inputs to form clusters.
• The present invention involves Closeness based Gaussian Mixture Incremental Clustering (CGMIC) Algorithm, which is cluster-first approach and not the centre-first as implemented in other conventional algorithms.
• In the present invention the incremental learning is achieved via incremental clustering using knowledge augmentation, wherein cluster ranking is performed by the algorithm during iterations.
• In the present invention the incremental learning is achieved via CGMIC algorithm and to utilize updated and clustered smart meter data as knowledge for further mining.
• In the present invention it is possible to learn from the influx of new data always, without discarding the previously acquired knowledge.
• Analysis of load shedding patterns in unplanned scenarios are feasible, so as to inform these updates and details to generation unit for further actions.
The present invention helps the better balancing for the household customer, utility provider, and the environment. Household customers will be able to monitor and improvise electricity consumption patterns. Utility providers will be able to access monthly meter reading online quickly, accurately, and in real time mode. Utility providers hence will be able to reduce power outage and will be able to avoid capital expenses of building new plants. The proposed instant invention is extremely useful for maintaining the environment by reducing pollution via carbon production by power plants (as pollution is hazardous to health). Also helps in reducing pollution by individual vehicles used for driving to the individual customer’s meters for manual reading.
The embodiments, examples and alternatives of the preceding paragraphs or the description and drawings, including any of their various aspects or respective individual features, may be taken independently or in any combination thereof. Features described in connection with one embodiment are applicable to all embodiments, unless such features are incompatible.
Claims
1. A method for analysing smart meter data to optimize electricity load management, the method comprising:
receiving raw dataset from each smart meter of a set of smart meters (103);
dynamically generating a set of clusters from the raw dataset by:
pre-processing raw dataset to generate normalized data;
generating a set of basic cluster(s) by processing the normalized data;
incrementally clustering new data, received from the set of smart meters (103), by selectively updating the set of basic cluster(s) or adding new cluster(s) to the set of basic cluster(s) based on the influx of the new data; and analysing each cluster from the set of clusters for determining load shedding patterns during planned and unplanned electricity outages to optimize the electricity load management.
2. The method as claimed in claim 1, wherein the raw dataset includes at least one parameter selected from active power, reactive power, a voltage, a current, and a power factor.
3. The method as claimed in claim 1, wherein pre-processing includes data normalization, cleaning of data, and noise removal by utilizing statistical techniques.
4. The method as claimed in claim 1, wherein the incremental clustering algorithm operates in a semi- supervised mode for accommodating new incoming data in real time, wherein semi- supervised mode performs selective update of the formed clusters by appending the existing clusters or forming new clusters by using the combination of labelled and unlabelled data.
5. The method as claimed in claim 1, wherein the electricity consumption by individual household is determined by capturing and generating the hidden patterns of electricity consumption during day-time, night-time, and season.
6. A system (101) for analysing smart meter data to optimize electricity load management, the system (101) comprising:
a memory (203); and
a processor (201), wherein the processor (201) is configured to execute programmed instructions stored in the memory (203) for:
receiving raw dataset from each smart meter of a set of smart meters (103);
dynamically generating a set of clusters from the raw dataset by:
pre-processing raw dataset to generate normalized data;
generating a set of basic cluster(s) by processing the normalized data; incrementally clustering new data, received from the set of smart meters, by selectively updating the set of basic cluster(s) or adding new cluster(s) to the set of basic cluster(s) based on the influx of the new data; and
analysing each cluster from the set of clusters for determining load shedding patterns during planned and unplanned electricity outages to optimize the electricity load management.
7. The system (101) as claimed in claim 6, wherein the raw dataset includes at least one parameter selected from active power, reactive power, a voltage, a current, and a power factor.
8. The system (101) as claimed in claim 6, wherein pre-processing includes data normalization, cleaning of data, and noise removal by utilizing statistical techniques.
9. The system (101) as claimed in claim 6, wherein the incremental clustering algorithm operates in a semi- supervised mode for accommodating new incoming data in a real time, wherein semi- supervised mode performs selective update of the formed clusters by appending the existing clusters or forming new clusters by using the combination of labelled and unlabelled data.
10. The system (101) as claimed in claim 6, wherein the electricity consumption by individual household is determined by capturing and generating the hidden patterns of electricity consumption during day-time, night-time, and season.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
IN201921047841 | 2019-11-22 | ||
IN201921047841 | 2019-11-22 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2020053846A2 true WO2020053846A2 (en) | 2020-03-19 |
WO2020053846A3 WO2020053846A3 (en) | 2020-04-30 |
Family
ID=69778383
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/IB2020/050108 WO2020053846A2 (en) | 2019-11-22 | 2020-01-08 | A system and method for analysis of smart meter data |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2020053846A2 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111754116A (en) * | 2020-06-24 | 2020-10-09 | 国家电网有限公司大数据中心 | Credit assessment method and device based on label portrait technology |
CN112103956A (en) * | 2020-09-18 | 2020-12-18 | 福州大学 | Distribution network state estimation method based on intelligent electric meter dynamic measurement point |
CN114841832A (en) * | 2022-07-04 | 2022-08-02 | 国网湖北省电力有限公司营销服务中心(计量中心) | Power consumer portrait label establishing method based on secondary clustering of power loads |
CN114915667A (en) * | 2022-04-08 | 2022-08-16 | 华立科技股份有限公司 | Method for storing data file in electricity consumption information acquisition terminal |
US11899516B1 (en) | 2023-07-13 | 2024-02-13 | T-Mobile Usa, Inc. | Creation of a digital twin for auto-discovery of hierarchy in power monitoring |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108009938B (en) * | 2016-11-02 | 2021-12-03 | 中国电力科学研究院 | System load clustering and load period pattern recognition method based on shape |
-
2020
- 2020-01-08 WO PCT/IB2020/050108 patent/WO2020053846A2/en active Application Filing
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111754116A (en) * | 2020-06-24 | 2020-10-09 | 国家电网有限公司大数据中心 | Credit assessment method and device based on label portrait technology |
CN111754116B (en) * | 2020-06-24 | 2023-10-17 | 国家电网有限公司大数据中心 | Credit evaluation method and device based on label portrait technology |
CN112103956A (en) * | 2020-09-18 | 2020-12-18 | 福州大学 | Distribution network state estimation method based on intelligent electric meter dynamic measurement point |
CN114915667A (en) * | 2022-04-08 | 2022-08-16 | 华立科技股份有限公司 | Method for storing data file in electricity consumption information acquisition terminal |
CN114841832A (en) * | 2022-07-04 | 2022-08-02 | 国网湖北省电力有限公司营销服务中心(计量中心) | Power consumer portrait label establishing method based on secondary clustering of power loads |
US11899516B1 (en) | 2023-07-13 | 2024-02-13 | T-Mobile Usa, Inc. | Creation of a digital twin for auto-discovery of hierarchy in power monitoring |
Also Published As
Publication number | Publication date |
---|---|
WO2020053846A3 (en) | 2020-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020053846A2 (en) | A system and method for analysis of smart meter data | |
US20230334599A1 (en) | Methods and systems for machine-learning for prediction of grid carbon emissions | |
Pineda et al. | Data-driven screening of network constraints for unit commitment | |
US11204591B2 (en) | Modeling and calculating normalized aggregate power of renewable energy source stations | |
Buddhahai et al. | An energy prediction approach for a nonintrusive load monitoring in home appliances | |
Khan et al. | Incremental density-based ensemble clustering over evolving data streams | |
Alghamdi et al. | A survey of preprocessing methods used for analysis of big data originated from smart grids | |
Xu et al. | Adaptive DE algorithm for novel energy control framework based on edge computing in IIoT applications | |
Pawar et al. | Smart electricity meter data analytics: A brief review | |
Markovič et al. | Data-driven classification of residential energy consumption patterns by means of functional connectivity networks | |
Bidoki et al. | Comparison of several clustering methods in the case of electrical load curves classification | |
Tiwari et al. | Machine learning-based model for prediction of power consumption in smart grid. | |
Dong et al. | Forecasting smart meter energy usage using distributed systems and machine learning | |
Grigoras et al. | Processing of smart meters data for peak load estimation of consumers | |
Haq et al. | Classification of electricity load profile data and the prediction of load demand variability | |
Liu et al. | Learning task-aware energy disaggregation: a federated approach | |
Ramos et al. | A data mining framework for electric load profiling | |
CN109858667A (en) | It is a kind of based on thunder and lightning weather to the short term clustering method of loading effects | |
Shahoud et al. | Descriptive statistics time-based meta features (DSTMF) constructing a better set of meta features for model selection in energy time series forecasting | |
Radha et al. | Energy Management based on K-Nearest Neighbour Approach in Residential Application | |
Eskandarnia et al. | A taxonomy of smart meter analytics: Forecasting, knowledge discovery, and power management | |
Chakravorty et al. | A distributed gaussian-means clustering algorithm for forecasting domestic energy usage | |
CN111815022A (en) | Power load prediction method based on time-delay coordinate embedding method | |
Oyinlola | Energy prediction in edge environment for smart cities | |
Bâra et al. | Intelligent systems for predicting and analyzing data in power grid companies |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20710752 Country of ref document: EP Kind code of ref document: A2 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20710752 Country of ref document: EP Kind code of ref document: A2 |