ENSURING SAFE SERVICING IN A LOW-VOLTAGE NETWORK OF THE ELECTRIC POWER DISTRIBUTION SYSTEM

• US 20200134761A1
• Filed: 10/30/2019
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: Electricitã© De France
• Original Assignee: Electricitã© De France
• Inventors: CHARPENTIER, Philippe, MEVEL, Camille
• Granted Patent: US 11,551,323 B2
• Time in Patent Office: Days
• CPC Class Codes: G01R 19/2513 Arrangements for monitoring electric power systems, e.g. power lines or loads; Logging
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/20 Administration of product repair or maintenance
• CPC Class Codes: G06Q 50/06 Energy or water supply
• CPC Class Codes: G06Q 50/265 Personal security, identity or safety
• CPC Class Codes: H02J 13/00 Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
• CPC Class Codes: H02J 2203/20 Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
• CPC Class Codes: H02J 2300/20 The dispersed energy generation being of renewable origin
• CPC Class Codes: H02J 3/003 Load forecast, e.g. methods or systems for forecasting future load demand
• CPC Class Codes: H02J 3/12 for adjusting voltage in ac networks by changing a characteristic of the network load
• CPC Class Codes: H02J 3/32 using batteries with converting means
• CPC Class Codes: H02J 3/381 Dispersed generators
• CPC Class Codes: H02J 3/388 Islanding, i.e. disconnection of local power supply from the network
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
• CPC Class Codes: Y02B 10/10 Photovoltaic [PV]
• CPC Class Codes: Y02B 90/20 Smart grids as enabling technology in buildings sector smart grids supporting the management or operation of end-user stationary applications in general, or like technologies with no associated climate change mitigation effect Y04S20/00
• CPC Class Codes: Y02E 10/56 Power conversion systems, e.g. maximum power point trackers
• CPC Class Codes: Y02E 60/00 Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
• CPC Class Codes: Y04S 10/50 : Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
• CPC Class Codes: Y04S 20/12 : Energy storage units, uninterruptible power supply [UPS] systems or standby or emergency generators, e.g. in the last power distribution stages
• CPC Class Codes: Y04S 40/20 : Information technology specific aspects, e.g. CAD, simulation, modelling, system security

Abstract

To ensure the safety of people needing to service a low-voltage network of an electric power distribution system, the dwellings connected to this network may include autonomous units for producing electricity (PV1, . . . , PVn), thus generating voltage and endangering the people servicing the work. A step is therefore provided for obtaining first data from consumption records from the meter (C1, . . . , Cn) of each dwelling, in regular time intervals, and second data (MET) which are meteorological data in the geographical area of these dwellings, in order to identify at least some weather conditions conducive to the production of energy by autonomous units. A model is then applied for detecting, based on the first and second data, a coincidence between periods of lower consumption measured by a meter and weather conditions conducive to electricity production by autonomous units during these periods. Information on the presence or absence of autonomous units in the dwelling equipped with this meter is thus deduced, this information being stored in a database (MEM) with a corresponding dwelling identifier, and the dwellings likely to include autonomous units are thus identified in the database.

Claims

1-13. -13. (canceled)

14. A method for ensuring the safety of persons needing to service a low-voltage network of an electric power distribution system, wherein:

the low-voltage network is connected to a substation supplying power to a plurality of dwellings within a geographical area,

the dwellings are equipped with meters configured to measure and communicate consumption by regular time intervals,

at least some of the dwellings are likely to comprise autonomous means of producing electricity using renewable energy, a placing in operation of said autonomous means generating voltage in the low-voltage network despite shutting down the substation during the work, thus endangering people during their servicing,

the method, implemented by a server communicating with the meters, comprising;

obtaining first data from consumption records from each meter by regular time intervals,

obtaining second data which are meteorological data in the geographical area, in order to identify at least some weather conditions conducive to the production of energy by said autonomous means,

for each meter, applying a model for detecting, based on at least the first and second data, a coincidence between periods of low consumption measured by the meter and weather conditions conducive to electricity production by said autonomous means during said periods, and deducing, from the application of the model, information on the presence of autonomous means in the dwelling equipped with this meter,

for each dwelling, storing in a database the information on the presence of autonomous means, with a corresponding identifier specific to the dwelling,

and, before performing the servicing work, identifying in the database the dwellings likely to comprise autonomous means.

15. The method according to claim 14, wherein the server further obtains an instantaneous measurement of the voltage in the low-voltage network before the servicing work, and the work is dependent on the server obtaining a zero-voltage measurement in the low-voltage network.

16. The method according to claim 15, wherein each meter is configured to be cut off remotely by a command from the server, and wherein the presence information is a probability score for the presence of autonomous means in the dwelling equipped with said meter, and the method further comprises:

establishing a list of the probability scores for the presence of autonomous means, with respective corresponding meter identifiers,

if a non-zero voltage is measured in the low-voltage network, using the meter identifier having the maximum score in said list to cut off that meter remotely, then removing that meter from the list and using again a next meter identifier having a new maximum score in said list to cut off that next meter until a zero-voltage measurement is obtained in the network.

17. The method according to claim 14, wherein the detection model is obtained by a “

tree boosting”

technique comprising;

a setting of variables in a learning sample composed of dwellings for which the consumption is analyzed,

a defining of explanatory variables of the correlation, taken from the variables set, and

an application of the tree boosting method to the explanatory variables in order to determine a model for calculating a probability score for the presence of autonomous means in a dwelling equipped with a meter measuring and communicating consumption in the dwelling by regular time intervals, said score corresponding to said presence information stored in the database.

18. The method according to claim 17, wherein a cross-validation is further applied in order to consolidate the determination of the calculation model.

19. The method according to claim 14, wherein the detection model is obtained by implementing a convolutional neural network, this implementation comprising:

a setting of variables in a learning sample composed of dwellings for which the consumption is analyzed,

a learning of the sample by the neural network, and

the determination by the neural network of a model for calculating a probability score for the presence of autonomous means in a dwelling equipped with a meter measuring and communicating consumption in the dwelling by regular time intervals, said score corresponding to said presence information stored in the database.

20. The method according to claim 17, wherein the variables to be set in the learning sample comprise, for each dwelling:

a predictive variable indicating whether or not the dwelling is equipped with autonomous production means;

the dwelling consumption, by regular intervals;

the weather conditions in the area of the dwelling, including an instantaneous temperature in this area.

21. The method according to claim 14, wherein the autonomous production means whose presence is to be detected is a photovoltaic panel, and wherein the weather conditions include at least the level of sunlight at a given moment.

22. The method according to claim 20, wherein the autonomous production means whose presence is to be detected is a photovoltaic panel, and the weather conditions include at least the level of sunlight at a given moment, and wherein each meter is arranged to measure and communicate consumption at an hourly or sub-hourly interval, said explanatory variables comprising at least one variable among:

an average ratio per meter between a consumption between 10 a.m. and 4 p.m. in a day and a total consumption over the same full day,

a slope of the regression line of the consumption between 12 p.m. and 2 p.m. versus level of sunlight,

a ratio between an average consumption over all meters between a.m. and 4 p.m. for the X days with higher levels of sunlight and that between 10 a.m. and 4 p.m. for the X days with lower levels of sunlight,

an average ratio per meter between the consumption between 10 a.m. and 4 p.m. and the degrees of temperature for the same day between 10 a.m. and 4 p.m.,

an average ratio of consumption per degree of temperature between 10 a.m. and 4 p.m. for the X days with higher levels of sunlight and consumption per degree of temperature between 10 a.m. and 4 p.m. for the X days with lower levels of sunlight.

23. The method according to claim 20, wherein the autonomous production means whose presence is to be detected is a photovoltaic panel, and wherein the weather conditions include at least the level of sunlight at a given moment, and wherein each meter is arranged to measure and communicate consumption at a daily interval, the explanatory variables comprising at least one variable among:

a ratio of consumption over one day to level of sunlight over the same day;

a ratio of consumption over one day to average level of sunlight between 10 a.m. and 4 p.m. of that day;

a ratio of consumption over one day to average level of sunlight between 12 p.m. and 2 p.m. of that day;

a ratio of consumption over one day to maximum level of sunlight between 10 a.m. and 4 p.m. of that day;

a ratio of consumption over one day to maximum level of sunlight between 12 p.m. and 2 p.m. of that day;

a ratio between the average daily consumption for the X days with higher levels of sunlight and the average consumption for the X days with lower levels of sunlight;

an average ratio of consumption per day per degrees of temperature;

an average ratio between consumption per day per degree of temperature for the X days with higher levels of sunlight and consumption per day per degree of temperature for the X days with lower levels of sunlight.

24. A non-transitory computer storage medium, storing instructions of a computer program causing the method according to claim 14 to be implemented, when said instructions are executed by a processor of a processing circuit.

25. A server for implementing the method according to claim 14, comprising a memory for storing the database and a processing circuit configured for applying the model for detecting autonomous production means in a dwelling, based on at least the first data on consumption from the meter of that dwelling and on the second data on weather conditions for the area of the dwelling.

26. A processing circuit of a server for implementing the method according to claim 14, comprising a memory for storing the database and a processing circuit configured for applying the model for detecting autonomous production means in a dwelling, based on at least the first data on consumption from the meter of that dwelling and on the second data on weather conditions for the area of the dwelling, the processing circuit being configured, for the purposes of implementing the method according to claim 14, to apply the model for detecting autonomous production means in a dwelling, based on at least the first data on consumption from the meter of the dwelling and the second data on weather conditions for the area of that dwelling.