Method for estimating at least one power consumption by a subset

Abstract

Method for estimating at least one power consumed by a subset. Method for determining the electrical power consumed by a subset of a group (G) comprising at least one subset, each subset of the group (G) comprising at least one electrical equipment from a set (E) of electrical equipment, during a period comprising a plurality of elementary periods, the method being implemented by computer and comprising: estimating the electrical power consumed by the subset using: individual elementary operating times of each subset of the group (G) during the respective elementary periods, and total elementary energy consumptions of the set (E) during the respective elementary periods. Figure for the abstract: Fig. 2

Description

Title of the invention: Method for estimating at least one power consumption by a subset Scope of the invention

[0001] The field of the invention is that of monitoring the power consumed by a set of equipment. One purpose of this type of monitoring is to identify power deviations in order to be able to act on these deviations to improve the energy efficiency of the set of equipment.

[0002] The invention applies to any industrial installation comprising several energy-consuming pieces of equipment where the energy consumption share is comparable between the pieces of equipment. For example, the invention can be applied to drinking water production units, waste sorting, recovery and processing units, and wastewater treatment plants, also referred to as WWTPs in this patent application.

[0003] For example, at present, most wastewater treatment plants are equipped with electricity meters to monitor energy consumption globally at the plant level, i.e., of all the equipment in the plant.

[0004] In order to identify the most power-consuming equipment and to detect power drifts of the respective equipment, it is necessary to be able to monitor the electrical consumption at the level of each of the equipment.

[0005] However, installing an electricity meter on each piece of equipment in a wastewater treatment plant (WWTP) is a considerable investment. Indeed, monitoring the individual consumption of the equipment in a WWTP requires an average of 20 electricity meters (between 5 and 80 per WWTP), and the installation of an electricity meter costs on average 1000 euros. State of the art

[0006] We know of solutions for estimating the power consumed by the respective equipment solely from the nominal powers of this equipment which are given by the suppliers, by providing a margin on these powers, just as proposed in the document “Energy consumption of intensive wastewater treatment in France: state of affairs and factors of variation” -Sticker et al, December 2017, IRSTEA.

[0007] However, these solutions do not allow for the identification of power consumption deviations by the different equipment.

[0008] One object of the invention is to limit at least one of the aforementioned disadvantages. Summary of the invention

[0009] To this end, the invention relates to a method for estimating the electrical power consumed by a subset of a group of at least one subset, each subset of the group comprising at least one electrical device from a set of electrical devices, during a period comprising a plurality of elementary periods, the method being implemented by computer and comprising: - Estimate the electrical power consumed by the subset using: - individual elementary operating times of each subset of the group during their respective elementary periods and, - the total elementary energy consumption of the whole during the respective elementary periods.

[0010] Advantageously, the process comprises: - determine the individual elementary operating times of each subset of the group during the respective elementary periods, - determine the total elementary energy consumption of the whole during the respective elementary periods.

[0011] Each of these steps can consist of receiving the elementary total energy consumption values ​​and / or elementary individual operating times and / or calculating the elementary total energy consumptions and / or elementary individual operating times from received values ​​and / or received measurements.

[0012] Advantageously, the electrical power estimation step comprises: - determining, from the total elementary energy consumptions and the individual elementary operating times, a set of at least one parameter of a parametric model modeling: - a distribution, over the elementary periods, of values ​​of individual elementary power consumed, during the respective elementary periods, of each subset of the group, - for each elementary period, the total elementary energy consumption during the elementary period, by a sum of a possible constant and the individual elementary energy consumption of each subset of the group during the elementary period.

[0013] Advantageously, at least when a number of activation / deactivation of at least one subset of the group during the set of elementary periods is greater than a principal threshold, the model is a probabilistic graphical model.

[0014]

[0015]

[0016]

[0017]

[0018]

[0019]

[0020]

[0021] Advantageously, the parametric model models the values ​​of the individual elementary powers consumed, during the respective elementary periods: - of each subset of a first subgroup of the group by a multimodal distribution and / or - of each subset of a second subgroup of the group by a unimodal distribution. Advantageously, the process includes the following steps: - group subsets of the group so that the first subgroup consists of each subset of the group with an activation / deactivation number during the set of elementary periods greater than a predetermined main threshold and the second subgroup consists of each subset with an activation / deactivation number during the set of elementary periods less than or equal to the main threshold. Advantageously, the process includes the following step: - determine a number of subsets of the first subgroup such that the model is a probabilistic graphical model only when the first subgroup is non-empty. Advantageously, at least when no subset of the group has an activation / deactivation number during the set of elementary periods greater than a predetermined principal threshold, the parametric model is a linear model. Advantageously, the process includes the following step: - determine a number of subsets exhibiting a number of activation / deactivations during the set of elementary periods greater than the main threshold, such that the parametric model is linear only when no subset of the group exhibits a number of activation / deactivations during the set of elementary periods greater than the main threshold. Advantageously, the process includes a preliminary grouping step of the equipment in the set according to a correlation criterion between the states of the equipment, using state information of the respective equipment, so as to form said group of at least one subset. Advantageously, the process includes an initial estimation step of the energy consumption of another set of at least one other piece of equipment based on a power rating of the other piece of equipment and status information of the other piece of equipment. Advantageously, the process includes an initial verification step implemented in work for each piece of equipment in a global set including each piece of equipment in the set, consisting of checking whether the equipment meets a set of at least one importance criterion using a predetermined rated power of the equipment and / or equipment status information, the other set of at least one other piece of equipment being made up of each piece of equipment in the set not meeting the set of at least one importance criterion.

[0022] Advantageously, the method includes, prior to the estimation step, a step of identifying each piece of equipment in the overall assembly having an individual total operating time less than or equal to a predetermined maximum portion or greater than or equal to a predetermined minimum portion of the duration T, and a step of removing each piece of equipment identified during the step of identifying the overall assembly.

[0023] The invention also relates to a computer program product stored in a non-transient, computer-readable medium, said computer program product comprising code instructions which, when the program is executed by a computer, cause the computer to perform the process according to the invention.

[0024] The invention also relates to a data processing device comprising a processor configured to execute a process according to the invention.

[0025] The invention also relates to an industrial system comprising: - a set of equipment comprising a group of at least one subset, each subset of the group comprising at least one electrical piece of equipment from a set of electrical equipment, - an electricity meter, - an electrical equipment control unit capable of activating and deactivating each piece of equipment in the system, - a computing unit configured to implement the method according to the invention, in order to estimate the electrical power consumed by a subset of the group,

[0026] the total elementary energy consumptions of the individual elementary operating times of each subset of the group during the elementary periods being derived from energy measurements delivered by the electric meter and the individual elementary operating times of each subset of the group during the respective elementary periods being derived from the control unit. Brief description of the figures

[0027] Figure 1 schematically represents the equipment of a wastewater treatment plant according to an example of implementation,

[0028] Figure 2 schematically represents an example of an industrial system according to the invention.

[0029] Figure 3 represents a flowchart of the steps of a process according to an example of an embodiment of the invention,

[0030] Figure 4 schematically represents an example of a Bayesian network modeling elementary energy consumption and individual elementary powers individually and in relation to each other.

[0031] Figure 5 shows a flowchart of steps for a stochastic expectation-maximization approximation algorithm according to an example implementation. Detailed description

[0032] The present invention relates to a computer-implemented method for estimating the electrical consumption of equipment in a global set EG of equipment during a predetermined monitoring period denoted T.

[0033] In this patent application, power means electrical power. Industrial equipment and system

[0034] The global set EG of equipment EQm with m an integer and m between 1 and M includes, for example, equipment from an industrial system, for example a STEP or a subset of equipment from a STEP.

[0035] A wastewater treatment plant (WWTP) comprises several pieces of equipment and functional units that treat municipal and / or industrial wastewater by intensifying natural processes. These pieces of equipment vary depending on the size of the treatment plant, the level of treatment required, and the specific technologies used. The overall EG assembly performs this function.

[0036] A wastewater treatment plant (WWTP) typically includes a pretreatment unit (PTU) designed to remove solid debris, coarse materials, and undesirable elements from the raw water before proceeding to the main treatment stages. The pretreatment stages and equipment may vary depending on the specific design of the treatment plant; for example: a pump Ei supplying equipment E2 via a pumping station, including, for example, a screen to remove different types of debris of varying sizes and / or a grit / oil separator to separate sand from floating matter (oils, greases, and / or hydrocarbons) and / or a sand washer and / or a biological grease treatment device.

[0037] A wastewater treatment plant advantageously, but not necessarily, includes a primary treatment unit (PTU). This stage conventionally removes finer suspended solids through flocculation / coagulation / sedimentation processes and flotation - with the injection of chemical reagents according to the desired degree of treatment using, for example, a decanter.

[0038] A wastewater treatment plant classically includes a secondary treatment unit (STU) used to carry out wastewater treatment by biological and / or physicochemical means, exploiting the ability of certain bacteria or biomass to eliminate pollutants dissolved in the water obtained at the outlet of the primary treatment unit, such as carbon pollution and / or nitrogen compounds and / or phosphorus compounds.

[0039] The secondary treatment unit UTS includes, for example, at least one source of pressurized air, for example a blower E3 configured to inject air into one of the biological treatment basins of the secondary treatment unit UTS to adapt the oxygen supply to variations in pollution loads, and to the needs of the biomass for the treatment of pollution.

[0040] Biomass is thus processed in one or more biological treatment basins under various conditions (anoxic, aerobic, anaerobic, etc.) suitable for its metabolism. The biomass develops as free-floating biological sludge (activated sludge process) or as a biofilm (biomass supported by biofilm supports or self-supporting, i.e., granular sludge). The secondary treatment unit (STU) also includes at least one agitator E4 for mixing the water and, for example, several brush aerators E5, E6 for the sludge.

[0041] The tertiary treatment unit (UTT) implements a separation step for the mixture from the biological and / or physicochemical treatment basin(s). It thus separates sludge from treated water. It includes a separator E7, which can take the form of a flotation system, a filter, a membrane integrated into the biological treatment basin, or a settling tank external to the biological treatment basin.

[0042] The treated water can undergo post-treatment (for example filtration, UV, etc.) or be used directly from the separator outlet, or even discharged into the natural environment.

[0043] The wastewater treatment plant (WWTP) typically includes a sludge treatment unit (UB) configured to thicken the sludge extracted from the units (optional PTU), STU, and TTU) by increasing its concentration. The sludge thickener can be static (gravity-fed) or dynamic. This thickener can, for example, take the form of a dewatering table, a centrifugation system, a gravity thickener, a drum, or a flotation device.

[0044] The thickened sludge from the sludge treatment unit UB can be treated, for example, using means such as a thermal hydrolyzer, a digester, dewatering equipment such as centrifuges, belt filters, filter presses, followed or not by chemical stabilization (liming) and / or biological stabilization (composting) and / or thermal drying and / or incineration.

[0045] The wastewater treatment plant advantageously includes an odor treatment unit (UTO) for odors from the secondary treatment unit (UTS) and sludge (UB). This odor treatment unit (UTO) includes, for example, at least one fan (E8) and / or one deodorization tower (E9) and / or one reagent station (Ei0).

[0046] The STEP may also include a UC air conditioning unit to regulate the temperature of the STEP premises, for example offices.

[0047] The STEP includes UE lighting equipment, allowing the STEP premises to be illuminated.

[0048] Alternatively, the STEP includes some of the aforementioned equipment.

[0049] The STEP may include other equipment.

[0050] The invention applies to equipment in other types of plants. Without limitation, the plant may be an energy recovery unit. An energy recovery unit is a plant that supplies a heat network or produces electricity through waste incineration.

[0051] Such a unit comprises one or more waste incineration furnaces. Each furnace includes a burner to ensure the combustion chamber reaches the incineration conditions required for heating. The furnace may be gas-fired or electric, and in the latter case, consume electrical energy during start-up.

[0052] The heat from the gases and fumes from combustion (temperature between 850 °C and 1000 °C) is advantageously transferred, via at least one transfer equipment including for example a fan, to a heat transfer fluid (generally water) circulated, via a circulation system, in a recovery unit, including for example at least one boiler and / or a turbine to recover the heat energy and utilize it, for example in the form of electricity or heat.

[0053] The energy recovery unit advantageously includes a flue gas treatment unit from the incineration unit to capture pollutants contained in the flue gases before the treated flue gases are released into the atmosphere.

[0054] Each of these units advantageously includes at least one fan and / or at least one pump for circulating a fluid in the energy recovery unit. This equipment consumes electrical energy.

[0055] The energy recovery unit advantageously includes a bottom ash recovery unit, which recovers the solid residue from waste combustion. This unit typically includes mechanical transfer equipment for this bottom ash, for example, conveyor belts, which consume electrical energy.

[0056] Just like wastewater treatment plants, an energy recovery unit typically includes an air conditioning unit to regulate the temperature of the unit's premises energy recovery, for example, offices and a lighting unit, allowing the lighting of premises in the recovery unit.

[0057] In [Fig. 2], an example of a global set EG of equipment EQm (m an integer with m = 1 to M) of an industrial system SL is shown.

[0058] This overall set EG includes, for example, equipment from a STEP, for example the equipment of the secondary treatment unit UTS, the equipment EQ i, EQ2, EQ3, EQ4 corresponding, for example, respectively to the equipment E3, E4, E5, E6 of the [Fig.1] and the lighting unit UE of the [Fig.1] marked EQ5 on the [Fig.2].

[0059] In the global set EG of equipment EQm with m = 1 to M, we consider a set E of equipment EQ; with i = 1 to N, N being less than or equal to M, taken from the equipment EQm of the global set EG.

[0060] In the non-limiting example of [Fig.2], M is equal to 5 and N is equal to 4.

[0061] In the method according to the invention, a group G of at least one sub- is considered set SEj, with j an integer and j = 1 to J, J being greater than or equal to 1 and less than or equal to N.

[0062] Each subset SEj includes at least one piece of equipment from set E.

[0063] Each piece of equipment EQ; belongs to only one of the subsets SEj. In other words, the subsets SEj are disjoint.

[0064] In the non-limiting example of [Fig.2], J = 2.

[0065] Furthermore, in the non-limiting example of [Fig.2], the EQm equipment is the EQ equipment; for m= 1 to 4.

[0066] The industrial system SI includes, for example, an electric meter CE, a control unit UCO and a computing unit UCA.

[0067] The CE electric meter is capable of making ME(k) measurements of an energy representative of the total energy consumption during different elementary periods Tk of a period T.

[0068] The period, denoted T, comprises K elementary periods denoted Tk of the same elementary duration Is, with K an integer greater than 1.

[0069] Advantageously, the period T consists of the K elementary periods Tk.

[0070] More generally, the period T comprises K elementary periods Tk.

[0071] In one variant, the duration of period T is greater than the sum of the durations of the elementary periods.

[0072] For example, at least two elementary periods of period T are temporally separated from each other.

[0073] K may depend on the period of supply of the information used in the process according to the invention.

[0074] In a non-limiting example, the period T is 1 month and the elementary duration is 10 minutes.

[0075] The elementary duration is adapted by a person skilled in the art to the equipment of the overall assembly and in particular to the average frequency of change of state (i.e. activation / deactivation) of this equipment.

[0076] The UCO control unit is capable of controlling each piece of equipment in assembly E to switch it from an activated (i.e., running) state to a deactivated (i.e., off) state, and vice versa. This UCO control unit is configured to issue activation / deactivation commands for the respective pieces of equipment or, at least, subsets of equipment in assembly E, so as to individually activate / deactivate the respective pieces of equipment.

[0077] Advantageously, the UCO control unit is capable of regulating the operating level of the equipment in assembly E, for example the speed of a motor, or the power level of a blower (maximum power or not).

[0078] Advantageously, the UCA computing unit has individual elementary operating times aj(k) of the respective equipment subsets SEj over the respective elementary periods Tk.

[0079] These elementary operating times aj(k) can be calculated by the UCA calculation unit from status information that allows the calculation of these individual elementary operating times aj(k) received by the UCA calculation unit. This status information is, for example, transmitted to the UCA calculation unit from the UCO control unit.

[0080] These state information are for example activation / deactivation times {tcm} of the equipment EQm or the activation / deactivation times {tCj} of the respective subsets SEj of the set E are transmitted to the computing unit UCA from the control unit UCO and the computing unit UCA is configured to calculate the elementary operating times tkj from the considered activation / deactivation times.

[0081] The activation moments of a piece of equipment or a subset of equipment are understood to be the moments when the equipment transitions from its inactive state to its active state, and the deactivation moments of the equipment are understood to be the moments when the equipment transitions from its active state to its inactive state. The activation / deactivation moments of a piece of equipment are understood to be the moments when the equipment is activated and the moments when it is deactivated. This also applies to subsets of equipment.

[0082] In another example, the state (active or inactive) of each piece of equipment or each subset of equipment SEj in the set E is transmitted at regular time intervals (shorter than the elementary periods Tk) to the computing unit UCA throughout the duration T and constitutes the state information. The computing unit UCA calculates the individual elementary operating times aj(k) from these states.

[0083] Alternatively, the UCA calculation unit directly receives the elementary durations of operation aj(k) of the equipment subsets SEj, over the elementary period Tk.

[0084] The UCA computing unit is configured to implement the process according to the invention from elementary total energy consumptions CET(k) and elementary individual operating times aj(k) of the respective SEj subsets.

[0085] Advantageously, the individual elementary operating times aj(k) are derived from the control unit UCO.

[0086] Advantageously, the elementary total energy consumptions CET(k) are the elementary measurements ME(k) or are determined, for example by the calculation unit UCA, from respective elementary measurements ME(k) taken by the electricity meter CE during the respective elementary periods Tk.

[0087] For example, the UCA calculation unit is configured to estimate the elementary total energy consumptions CET(k) from the respective elementary measurements ME(k) delivered by the CE meter. These estimates are then the elementary total energy consumptions CET(k) used in the process according to the invention. Process according to the invention

[0088] As can be seen in [Fig.3], the method according to the invention comprises an EPIND step for estimating at least one power consumed by at least one subset SEj of group G, from: - individual elementary operating durations aj(k) of each subset SEj of the group G during respective elementary periods Tk of the period T, - and total elementary energy consumption CET(k) during the respective elementary periods Tk.

[0089] This method does not require the use of a frequency behavior of a voltage measured across the terminals of the assembly E nor of a current flowing through this assembly E.

[0090] In other words, this method uses individual elementary operating times aj(k) and total elementary energy consumptions CET(k), for example elementary energy consumption measurements, without using the frequency behavior of a voltage across the equipment set or of a current flowing through this equipment set to determine individual powers consumed by subsets SEj of equipment composing this set E. An advantage is to allow the distinction between the powers consumed by different subsets of equipment or equipment having similar operating principles (compressor, motor, pump) which give rise to similar frequency signatures.

[0091] This process is precise, inexpensive, and particularly suited to equipment assemblies such as factory equipment, such as wastewater treatment plants.

[0092] Indeed, this process only requires the presence of an electric meter CE allowing the generation of ME(k) measurements representative of the total elementary energy consumptions CET(k) of the set E during the respective elementary periods Tk or allowing the calculation unit UCA to estimate the total elementary energy consumptions CET(k) of the set E during the respective elementary periods Tk and the disposition, by the calculation unit UCA of the individual elementary operating times aj(k) of the equipment subsets SEj.

[0093] The invention takes advantage of the activation / deactivation times of the different equipment in the assembly, allowing the calculation of the individual elementary operating times aj(k) classically available in a factory in which the equipment is controlled automatically, to estimate the elementary powers of the equipment or sub-assemblies of equipment.

[0094] Another advantage of the method is that the EPIND estimation step of the process can be implemented without knowing the rated power of each sub-assembly.

[0095] In other words, in a particular embodiment, the EPIND estimation step advantageously does not use rated equipment powers or equipment subsets from set E.

[0096] This invention also makes it possible to detect a degradation in the energy efficiency of equipment sub-assemblies.

[0097] In the following description, assembly E is considered to comprise several subassemblies, each comprising at least one piece of equipment, which will be called equipment subassemblies even if each of them may comprise only one piece of equipment. The invention also applies when assembly E comprises a single subassembly and / or when at least one subassembly comprises only one piece of equipment.

[0098] The method advantageously, but not necessarily, includes a step of calculating at least one elementary individual energy consumption of at least one subset SEj during an elementary period Tk, from the individual power consumed during the elementary period and the individual elementary operating time aj(k) of the subset SEj during an elementary period Tk.

[0099] Advantageously, this step includes, for each subset SEj, the calculation of the individual elementary energy consumptions of this subset during the respective elementary periods Tk. Disintegration of consumed energy

[0100] Advantageously, during the EPIND estimation step, a parametric model is used metric modeling the total elementary energy consumption CET(k) during each elementary period Tk as a linear combination of the elementary energy consumptions of the respective equipment subsets SEj during the elementary period Tk considered.

[0101] For example, the value CET(k) of the total elementary energy consumption during each elementary period Tk is modeled by a sum of a possible constant CST and the individual elementary energy consumptions CEj(k) of the respective subsets SEj, during the elementary period Tk.

[0102] The model models the individual elementary energy consumption CEj(k) of a subset SEj by a product between an elementary power consumed by the subset SEj during the period Tk and the individual elementary operating time aj(k) of the subset during the elementary period Tk.

[0103] In other words, the model models the elementary individual energy consumption CEj(k) as follows:

[0104] CEjk) =

[0105] By individual elementary power Pj(k) consumed by a subset of equipment SEj, we mean the electrical power consumed by the subset of equipment SEj during the elementary period Tk.

[0106] This refers, for example, to the electrical power absorbed by this subset during this elementary period Tk.

[0107] This individual elementary power consumed is considered to be fixed during the elementary period Tk

[0108] The constant CST is, for example, the energy generated by equipment whose state remains substantially the same over the entire duration of the period T.

[0109] In order to distribute the total elementary energy consumptions CET(k) over the different subsets SEj, it is advantageous to make, during the EPIND step, an a priori on the distributions of the individual elementary powers consumed Pj(k), over the elementary periods Tk, by the subsets SEj.

[0110] In other words, the parametric model models the distributions of the individual elementary powers consumed Pj(k), over the elementary periods Tk, by the respective subsets SEj.

[0111] The determination of the elementary powers consumed Pj(k) by the respective equipment subsets SEj therefore includes the determination of the parameters of the parametric model which optimizes, according to a predetermined criterion, the distribution of the total elementary energy consumptions CET(k) during the elementary periods Tk.

[0112] In summary, each elementary total energy consumption CET(k) is distributed among the different subsets SEj using the elementary durations of function operation aj(k) of the different subsets SEj and by determining the parameters of a parametric model modeling: - the distributions of the individual elementary powers Pj(k) of the subsets SEj by at least one parameter of the model, - and each total elementary energy consumption CET(k) by a sum of a possible constant CST and the individual elementary energy consumptions CEj(k) of the respective subsets SEj, during the elementary period Tk.

[0113] This step will be described in more detail later in the text.

[0114] Modeling of total energy consumption

[0115] The model models the total elementary energy consumption CET(k) during each elementary period Tk by a sum of a possible constant CST and the individual elementary energy consumptions CEj(k) of the respective subsets SEj, during the elementary period Tk.

[0116] In other words, the total elementary energy consumption CET(k) is defined as follows: [°117] CET(k) = Y^Pjik) *aj(k) + CST = L^CE^k) + CST

[0118] The value of the total elementary energy consumption CET(k) during the elementary period Tk is an input data. It is, for example, measured by the electricity meter CE or estimated based on a measurement from the meter CE as explained previously. Initial check

[0119] A non-limiting example of an embodiment of the process according to the invention is shown in [Fig.3].

[0120] The method advantageously includes an initial verification step VERI, implemented for each piece of equipment EQm of the global set EG for integer m from 1 to M, consisting of verifying compliance with a set of at least one important criterion in terms of power and / or number of activation / deactivation and, if at least one criterion of the set of equipment is not met by said piece of equipment EQm, an initial estimation step EST1 of the energy consumption CEm of the piece of equipment EQm.

[0121] The initial verification VERI of compliance with at least one importance criterion uses a predetermined rated power PNm of the equipment EQm and / or status information of the equipment EQm during the period T or the elementary periods Tk. The rated power PNm is typically provided by the manufacturer or available in the supplier's documentation.

[0122] In the non-limiting example of [Fig.2], the initial verification VERI includes a first verification VERIa of compliance with a first criterion of importance in terms of power based on the nominal power PNm of the equipment EQm.

[0123] The power importance criterion, noted Cia in this application, is, for example, met only when the rated power PNm of the equipment EQm is greater than or equal to a predetermined power threshold SP.

[0124] Advantageously, the predetermined power threshold, denoted SP in this patent application, is between 1% and 2% of the average rated power of the equipment EQm in the overall set EG. This makes it possible to exclude from set E, and therefore from accurate power calculations, equipment that has little impact on energy consumption drift due to its low rated power.

[0125] For example, in the example of [Fig.2], the lighting unit is not very powerful by compared to the other equipment in the overall EG system and therefore does not meet this Cia criterion.

[0126] In a non-limiting example of embodiment, the threshold is set at 2 kW.

[0127] In the non-limiting example of [Fig.2], the initial verification VERI includes, only when the first importance criterion is met, a second VERIb check of compliance with an importance criterion in terms of the number of state changes, from state information, for example activation / deactivation times of the EQm equipment during the period T or during the elementary periods Tk.

[0128] The importance criterion in terms of the number of activation / deactivation of states Clb is, for example, met only when a number of state changes, i.e. the number of activation / deactivation, of the equipment EQm during the period T or during all periods Tk, is greater than or equal to a predetermined initial threshold SI.

[0129] The number of activations / deactivations of a device during a period corresponds to the number of state changes between the activated state and the deactivated state during the entire duration of the same period. It is the sum of the number of activations and the number of deactivations obtained during the entire duration of the same period.

[0130] The number of activation / deactivation of a piece of equipment during the set of elementary periods Tk is the sum of the activation / deactivation numbers corresponding to the different elementary periods Tk.

[0131] Advantageously, the initial threshold SI is between 5 and 10. This avoids including in set E equipment for which the number of state changes is not sufficient to guarantee good performance of statistical calculations.

[0132] Alternatively, the initial VERI check comprises only one of the two VERIa or VERIb checks. Alternatively, the order of the two check steps is reversed.

[0133] Other criteria can of course be considered, as an alternative or in addition, depending on the information available.

[0134] Alternatively, the process is devoid of the initial VERI verification. Initial estimate

[0135] The initial estimation EST1 is implemented for each piece of equipment Em that does not meet the set of at least one importance criterion.

[0136] These equipment forms a set called remaining and noted ER of MR residual equipment, MR being an integer between 0 and Ml.

[0137] In the example of [Fig.2], the residual set ER consists of the lighting unit UE.

[0138] This step is therefore, for example, implemented only when the remaining set ER is not empty.

[0139] The initial estimate EST1 of the energy consumption CEm of a piece of equipment EQm uses the rated power PNm of the equipment EQm and a total operating time Tm of the equipment EQm during which the equipment in question is in the active state for all elementary periods Tk.

[0140] The total operating time is, for example, calculated from the activation / deactivation times of the equipment EQm during the period T or from elementary operating times of the equipment during the different elementary periods Tk.

[0141] The total operating time Tm of a piece of equipment EQm is, for example, given by the following formula:

[0142] T _ y*

[0143] where att{k) is the elementary operating time during which the equipment EQm is in the active state, during the kth elementary period Tk, and Is is the elementary duration of each elementary period Tk.

[0144] The initial estimation EST1 therefore includes the calculation CD of the total individual operating time T m of the equipment EQm from state information, for example activation / deactivation times, relating to the equipment EQm.

[0145] The initial estimation EST1 then includes a CPI calculation of a product of a predetermined correction factor FC, the rated power PNm of the equipment EQm, and the operating time Tm of the equipment EQm during the period T or the set of elementary periods Tk. In other words, the energy consumption of the equipment CEm during the period T or during the set of elementary periods Tk is, for example, estimated in step EST1 using the following formula:

[0146] CEm = FC*PNm*Tm

[0147] The correction factor FC is a constant between 0.5 and 1 corresponding to a factor between the power actually consumed and the nominal power.

[0148] The correction factor is, for example, equal to 0.85. Alternatively and / or in addition, the estimation step includes the estimation of the individual elementary energy consumption CEm(k) of the equipment EQm for at least one elementary period Tk.

[0149] The following formula is advantageously used:

[0150] CEm(k) = FC^PN^a^k)

[0151] The initial estimate EST1 has the advantage of being computationally inexpensive and fast.

[0152] Furthermore, this initial estimate allows for the consideration of the power consumption of equipment that consumes relatively little power compared to other equipment in the overall system, and whose power consumption can be estimated using a linear or probabilistic regression model. Indeed, when the variation in power generated by one piece of equipment is less than the random variation in the value generated by another piece of equipment, these models are unable to differentiate between these two variations.

[0153] Advantageously, the initial estimate EST1 uses the rated power of each piece of equipment.

[0154] Advantageously the process then includes an EST_CET step of estimating the total elementary energy consumptions CET(k) by the set E from the measurements ME(k) and the individual elementary energy consumptions CE^k) of the equipment EQm of the remaining set ER.

[0155] The total elementary energy consumption CET(k) by the assembly E during the elementary period Tk is then the energy consumption measured during this elementary period Tk from which is subtracted the sum of the elementary energy consumptions of the equipment of the remaining assembly ER, that is to say:

[0156] CET(k\ = -ZMR, CEdk] Set E

[0157] The set E of equipment EQ; with i = 1 to N, N being less than or equal to M, advantageously includes, when the first verification step VERI is implemented, only the equipment of the overall set EG which complies with the set of at least one criterion of importance in terms of power and / or number of activation / deactivation Cia, Clb.

[0158] Thus, assembly E includes only equipment with significant power in view of the equipment assembly and / or which have characteristics risk factors of state change, and more specifically dynamics, are necessary for a good estimation of their power from their state change information.

[0159] In the non-limiting example of [Fig.2], assembly E does not include the lighting unit UE.

[0160] Alternatively, set E includes all the equipment EQm, with m = 1 to M. In other words, set E is set EG. For example, the process lacks the initial verification step VERI. REGI Pre-Grouping

[0161] Advantageously, the method includes, as shown in the non-limiting example of [Fig.3], a prior grouping REGI of the equipment EQ; of the set E according to a predetermined prior grouping criterion so as to form the group G composed of at least one subset SEj with j an integer from 1 to J, J being less than or equal to N.

[0162] Each subset SEj of group G includes at least one piece of equipment EQ; from set E.

[0163] This preliminary REGI grouping is carried out from the status information of the EQ equipment; of the E set.

[0164] The prior grouping criterion is advantageously a correlation criterion between the states of the equipment EQ; of the set E during the entire duration of the set of elementary periods Tk or of the period T.

[0165] For example, for each pair of equipment in assembly E, a correlation coefficient r(X, Y) is calculated, given by: [° 166 ] LJ CMH \ ' /

[0167] where X and Y are the lists of states Xt, and respectively Yt, of a first equipment and respectively of a second equipment during the period T or the set of elementary periods Tk.

[0168] These n states Xt and Yt, indexed t, with t an integer from 1 to n, are, for example, taken at regular time intervals. The time interval is less than the duration of the elementary periods. Each state Xt or Yt takes the value 0 when the equipment is inactive and the value 1 when the equipment is active.

[0169] One advantage is to allow the estimation of an individual elementary power consumed and therefore the identification of power drifts of a set of equipment operating almost simultaneously and therefore difficult to distinguish, as we will see later.

[0170] In the non-limiting example of [Fig.2], at the end of the grouping step REGI prior applied to the global set E composed of equipment EQi to EQ4, we obtain two subsets SEi and SE2 composed respectively of equipment EQi to EQ3 and equipment EQ4 corresponding for example respectively to equipment E3 to E5 and E6 of a secondary processing unit UTS. State information of a SE subset

[0171] According to one embodiment, the state information of a subset SEj is the state information of a piece of equipment in the subset.

[0172] For example, the number of state changes of a subset SEj during the duration T or during an elementary period Tk is the number of state changes of a piece of equipment in the subset during the period considered.

[0173] Alternatively, the state information of a subset SEj is obtained from state information of several pieces of equipment in the subset SEj, for example from all the pieces of equipment in the subset SEj.

[0174] For example, the averages of the equipment status information of the SEj subset.

[0175] The same applies to each elementary operating time of a subset SEj during an elementary period Tk which can be, without limitation, an average of the operating times of the equipment of the subset during the same elementary period Tk or the elementary operating time of one of the equipment of the subset SEj during the elementary period.

[0176] The total individual operating time Tj of a piece of equipment EQj is, for example, given by the following formula: [0177> 7-.,.=

[0178] where a / k) is the elementary operating time during which the equipment subset SEj is in the active state, during the kth elementary period Tk.

[0179] The same applies to the number of activation / deactivation of each subset SEj during a given period which may be, without limitation, an average of the number of activation / deactivation of the equipment of the subsets of equipment which compose it during this period or a number of activation / deactivation of one of the equipment which it includes during this period.

[0180] The method advantageously includes a step of determining a number of activation / deactivations, during the period T or during all the periods Tk, of at least one piece of equipment from the state information of that equipment.

[0181] The method advantageously includes a step of determining a number of activation / deactivations, during the period T or during the set of periods Tk, of at least a subset of equipment from the state information of at least one of its equipment.

[0182] Distribution of individual elementary powers

[0183] The parametric model includes a set 6 of parameters comprising a first set of parameters modeling the respective distributions of the values ​​of the individual elementary powers Pj(k) of the respective subsets SEj.

[0184] The EPIND estimation step includes the determination of the parameters of the parametric model.

[0185] The probabilistic graphical model has the advantage of not requiring, in order to obtain accurate estimates of the different individual powers, a strict prior on the distribution of the values ​​of individual elementary powers in the sense that it allows the use of general distributions such as unimodal or multimodal distributions.

[0186] In particular, the probabilistic model does not require us to consider that the individual elementary powers of each of the equipment are fixed, that is to say, are the same over the whole period T. It therefore makes it possible to detect drifts taking place over shorter periods than over a period T. The powers of the subsets SEj are hidden variables (that is to say, unknown variables of the probabilistic graphical model).

[0187] The model is also defined by the fact that when the subset SEj is deactivated for the entire duration of the period T or of the set of elementary periods Tk, the individual elementary power Pj(k) of the corresponding subset SEj is equal to zero.

[0188] By a subset SEj deactivated for the entire duration of the period T, we mean a subset SEj whose individual total operating time Dj is zero.

[0189] When the subset SEj is activated for at least part of the period T or of the set of elementary periods, that is to say when its operating time is non-zero over this period or set of periods, the distribution of the values ​​of individual elementary powers Pj(k) of this subset SEj is modeled by a parametric graphical model whose parameter values ​​we seek to determine.

[0190] The distributions of the values ​​of the individual elementary powers P j(k) of the respective subsets SEj can be multimodal or unimodal.

[0191] The unimodal distribution is defined by a set of parameters called unimodal.

[0192] An example of a unimodal distribution of the values ​​of the individual powers of a The subset of equipment SEj is a Gaussian or normal distribution mP, a Y Vf P

[0193] where the unimodal parameters are Pj which is a mean of the normal distribution and which is a standard deviation of the normal distribution.

[0194] Another example of a unimodal distribution of the values ​​of individual powers of a subset of equipment SEj is a gamma distribution or gamma law r(a,j, fij) defined by the following unimodal parameters: fi.

[0195] is the shape parameter of the gamma distribution associated with the SEj subset

[0196] fij is the intensity parameter of the gamma distribution associated with the subset SEj.

[0197] An example of a multimodal distribution defined by so-called multimodal parameters is a mixture of gamma laws j tV « i where l is an integer and L is an integer greater than 1 and corresponds to the number of modes of the mixture of gamma laws. In other words, in general, the multimodal distribution is a mixture of distributions of different modes where l is an integer with ? ranging from 1 to L.

[0198] The mixture of gamma laws is, for example, defined by a set of the following so-called multimodal parameters: alJ, ffij.

[0199] al,j is the shape parameter of the distribution of the mode / , that is to say of the mode of order l, of the distribution associated with the subset SEj.

[0200] fiij is the intensity parameter of the mode distribution of order l of the distribution associated with the subset SEj.

[0201] is the mode weight parameter of order / in the distribution associated with the subset SEj. Distribution of total elementary energies

[0202] Advantageously, the set 6 of parameters also includes a second set of at least one parameter defining a distribution of the total elementary energy consumptions CET(k) for k = 1 to K by one or more parameters and advantageously at least one parameter of this distribution is defined during the step of determining the parameters of the model.

[0203] This distribution is, for example, a Gaussian distribution defined by the following two parameters: a standard deviation 0 and a mean of the elementary energy consumption W

[0204] The values ​​of the total elementary energy consumptions CET(k) are therefore defined by a normal law ;y ^E(k) rr-j depending on these two parameters.

[0205] A parameter modeling the distribution of the values ​​of the total elementary energy consumption CET(k) may be predetermined, for example while the other parameter(s) are estimated during the estimation of the model parameters or all the parameters may be estimated during the estimation of the model parameters.

[0206] Types of distribution other than Gaussian can of course be en- faceted.

[0207] One can, for example, define a gamma distribution or a mixture of gammas. Probabilistic graphical model

[0208] At least when a number of activation / deactivation of at least one subset SEj during the set of elementary periods Tk is greater than a predetermined principal threshold, the parametric model is a probabilistic graphical model.

[0209] It should be noted that when the period T consists of the elementary periods Tk, the number of activation / deactivation of the subset SEj during the set of elementary periods Tk is the number of activation / deactivation during the period T, which is not the case when the period T includes a set of elementary periods whose duration is less than the total duration (for example when they are disjoint or when they do not cover the entire duration T).

[0210] In the embodiment of [Fig.3], the parametric model is a probabilistic graphical model only when a number of activation / deactivation of at least one subset SEj during the set of elementary periods Tk is greater than a main threshold.

[0211] Advantageously, the main threshold is greater than the initial threshold, as we shall see later.

[0212] Alternatively, the main threshold is the initial threshold.

[0213] Alternatively, the main threshold is zero. In other words, a graphical model is used. probabilistic, regardless of the number of activation / deactivation of the different SEj subsets.

[0214] The probabilistic graphical model is, for example, a Bayesian network such as that shown in Figure 4, in which the hidden variables Pj(k), the parameter set, and the individual elementary operating times and the total elementary energy consumption are the nodes NO of the network. These nodes NO are connected in pairs by arcs A such as those shown in [Fig. 4] so as to define the parametric model described above.

[0215] Advantageously, the EPIND estimation step includes a step denoted AL of implementation of a stochastic approximation of expectation-maximization algorithm also called SAEM, an acronym for the Anglo-Saxon expression “Stochastic Approximation of Expectation-Maximization”.

[0216] This type of algorithm is known to a person skilled in the art and will be briefly described in the patent application.

[0217] The implementation of the SAEM algorithm includes the following step: - initialize IN the set 0 of parameters, that is to say the values ​​of the model parameters and the individual elementary powers consumed For k= 1 to K and for j= 1 to J by the equipment subsets SEj, that is to say the values ​​of the hidden variables.

[0218] The value of each individual elementary power P,(k) for k= 1 to K of a given subset SEjest, for example, initialized to a sum of a constant and the nominal powers of the equipment constituting the subset SEj.

[0219] The constant can be zero.

[0220] Alternatively, the values ​​of the individual elementary powers are initialized to values ​​within a predetermined power range, for example, to the same power value. This initialization is, for example, performed randomly.

[0221] The following parameters can, without limitation, be initialized in the following manner during the IN initialization step.

[0222] For each subset SEj whose distribution of individual elementary power values ​​is modeled by a mixture of gamma defined by the following parameters: ,, al,j, these parameters are initialized using the equations following:

[0223] H

[0224] .2-2¾ “ / V

[0225] where ^ij is the expectation of the distribution of the mode / of the subset SEj and whose value is initialized to the nominal power of the subset SEj by multiplying by a variable having a value within a predetermined interval.

[0226] The predetermined interval extends, for example, from 0.7 to 1.3.

[0227] The value is, for example, fixed randomly within the interval.

[0228] is the standard deviation of the distribution of the mode Z of the subset SEj and is initialized to a constant, for example 1.

[0229] . = 1 / Nmode where Nmode is the number of modes of the gamma mixture.

[0230] and P} j are calculated using the equations above and the initial values ​​of and

[0231] For each subset SEj whose distribution of individual elementary power values ​​is modeled by a Gaussian distribution: ai , ^j.

[0232] is initialized to a value A*PNomj where 2 is a predetermined constant, for example 0,1 and where PNoïîlj is the nominal power of the subset SEj.

[0233] The rated power of SEj is either known or calculated from the rated powers of the equipment constituting SEj. It is, for example, the sum of these rated powers.

[0234] For the distribution of the total elementary energy consumption values: cr2 is, for example, initialized to 1.

[0235] The value of is, for example, initialized to the sum of the individual elementary consumptions estimated by the subsets SEj during the elementary period Tk, calculated from the initial values ​​of these individual elementary powers P / k)- [02361 êw =

[0237] The constant CST can be initialized to a predetermined percentile of an elementary energy consumption CET(k).

[0238] The constant CST is, for example, fixed at the 5th percentile of the energy consumption CET(k).

[0239] The AL step of implementing the stochastic approximation algorithm with expectation maximization comprises the following set of steps repeated EE, as long as a stopping criterion is not met by the current values ​​of the parameters: - generate GEN a set P of values ​​of the hidden variables distributed, over the set of elementary periods Tk, according to the distributions defined by the current values ​​of the parameters, - calculate CAE, the expected likelihood of the model defined by the current values ​​of the parameter set 0, from these samples, - implement EMA a maximum likelihood estimator of the parameters so as to update the current values ​​of the parameters.

[0240] During the first implementation of the EE step set, the current values ​​of the parameters are the initial values ​​of the parameters defined during the initialization step.

[0241] The set P generated during the generation step GEN comprises for each subset SEj, a set of K values ​​of individual elementary powers P / (k) distributed according to the distribution defined by the current values ​​of the parameters CET(k), , al,j, Pij and Pj'(k) for all j' * j and being an integer between 1 and J.

[0242] This step is, for example, implemented by a Markov chain Monte Carlo algorithm also called MCMC (acronym for the English expression “Markov chain Monte Carlo”), for example a Hamiltonian Monte Carlo algorithm, also known as Hybrid Monte Carlo, to generate samples of the hidden variables distributed, over the set of elementary periods Tk, according to the distributions defined by the values ​​of the current parameters.

[0243] In an exemplary embodiment, during the GEN step, an MCMC algorithm (where Q is an integer greater than zero) is implemented Q times in order to generate Q sets P of values ​​of the hidden variables and the set P generated during the GEN step is an average of the Q generated sets.

[0244] The likelihood of the model L(ff) defined by the parameter set 9 is given by the following formula: 102451 =n* ^4(4)444 l 4)4-44 / 144 - 44)

[0246] where J is the number of equipment subsets SEj.

[0247] K is the number of elementary periods.

[0248] is the set of distribution parameters that model the distribution of individual elementary powers of SEj.

[0249] / 4 / 4) is an a priori probability of the set of parameters 4-

[0250] j^P^k) | 6*4) is a posterior probability of a set of powers knowing the parameters 9j of the distributions of the subset SEj. ^4(0 is a posterior probability of an elementary power consumed during the elementary period Tk knowing the elementary powers P / tk) of the different equipment during the elementary period Tk.

[0251] The expected likelihood E((L((9)) is, for example, calculated using the following formula:

[0253] where Q is the number of implementations of the MCMC algorithm, is the likelihood calculated during the qth implementation of the MCMC algorithm to generate the powers with q an integer from 1 to Q.

[0254] At the end of the EMA step, the current parameter values ​​are those that maximize the likelihood, according to the implemented estimator. In other words, the current parameter values ​​are those that allow obtaining the highest possible likelihood value by implementing the estimator.

[0255] It should be noted that the implementation of the AL algorithm is both a step of determining the values ​​of the model parameters, i.e. a step of parameterizing the model, and of the values ​​of the hidden variables.

[0256] These model parameter values ​​are the latest current parameter values ​​generated during the expectation-maximization algorithm. In other words, they are the parameter values ​​obtained during the last implementation of the EMA step.

[0257] The values ​​of the individual elementary powers Pj{k} are also the latest current values ​​of these powers, i.e. the values ​​obtained during the last implementation of the GEN step.

[0258] The stopping criterion is, for example, met when the set EE of steps has been implemented a number of times equal to a predetermined maximum number, this number being an integer greater than 1.

[0259] In one variant, the stopping criterion is a difference criterion between the two likelihoods calculated during the last implementation of the set of steps and during the previous implementation, less than or equal to a predetermined threshold.

[0260] In one variant, the stopping criterion is a difference criterion between the two likelihoods calculated during the last implementation of the set of steps and during the previous implementation less than or equal to a predetermined threshold, for a minimum number of successive implementations of the set of steps.

[0261] The minimum number is advantageously greater than or equal to 2. REG2 Grouping

[0262] In a particular embodiment, the EPIND step includes a secondary grouping REG2 of the SEj subsets of group G: - in a first subgroup G1 consisting of each subset having a number of activations / deactivations, during the set of elementary periods Tk, greater than a principal threshold, - and in a second subgroup G2 consisting of each subset having a number of activation / deactivations, during the set of elementary periods Tk, is less than or equal to the main threshold.

[0263] This REG2 step is carried out using the activation / deactivation numbers, during the set of elementary periods Tk, of the respective subsets SEj of the group G.

[0264] Each of these groups Gl, G2 can be empty or consist of all the subsets SEj of the group G.

[0265] Advantageously, the distribution of the values ​​of the individual elementary powers consumed by each subset of the first group Gl is modeled by a multimodal distribution and the distribution of the values ​​of the power of each subset of the second group G2 is modeled by a unimodal distribution.

[0266] These distributions are, for example, used in the model and therefore during the implementation of the expectation maximization algorithm to determine the values ​​of the parameters and hidden variables of the model.

[0267] Alternatively, the method is devoid of secondary grouping. In this latter case, the distributions of the individual elementary power values ​​of all the equipment used in the model can be unimodal or multimodal. REGL linear regression model

[0268] In the non-limiting embodiment of [Fig.2], the process includes a DNB step for determining the number of subsets SEj exhibiting an activation / deactivation number during the set of elementary periods Tk, greater than the main threshold.

[0269] For example, we determine the number of subsets included in the first group Gl.

[0270] When no subset SEj of group G has a number of activations / deactivations during the set of elementary periods Tk greater than the main threshold, i.e. when the first group Gl is empty, the parametric model is a linear regression model.

[0271] The EPIND estimation step includes the REGL implementation of a parameter estimation algorithm for the linear regression model.

[0272] The use of the linear model makes it possible to estimate the individual elementary powers even in the case where the number of information (number of activation / deactivation) of the respective subsets is limited.

[0273] Furthermore, using this linear model only when no subset meets the criterion for the number of state changes has the advantage of not degrading the power estimates of the multimodal subsets. Moreover, the parameter estimation algorithms for a linear regression model are relatively easy to implement, which limits computational costs and allows for essentially the same results as using an algorithm to determine the parameters of a probabilistic graphical model when the equipment is unimodal.

[0274] In this type of parametric model, it is assumed that the individual elementary powers are considered to be fixed over the duration T, that is to say that the individual elementary powers of each subset are the same during all the elementary periods, that is to say for any K. In other words, each subset SEj has a fixed individual power Pj over the set of elementary periods or during the whole duration T.

[0275] In an example embodiment, the linear regression model models the total energy consumed during the elementary period Tk by a sum of a constant and the energies consumed:

[0276] CET = ) + CST

[0277] where CST is a constant, and a^k) is the operating time of the SEj subset during the elementary period Tk

[0278] The parameters of the linear model are P j and CST.

[0279] The algorithm for estimating the parameters of the linear regression model is, by

[0280]

[0281]

[0282]

[0283]

[0284]

[0285]

[0286]

[0287]

[0288]

[0289]

[0290]

[0291]

[0292]

[0293]

[0294] For example, an algorithm for solving the linear regression model using a least squares method or a least squares algorithm. This algorithm is an optimization algorithm that calculates, for the subsets SEj, an estimate of their individual powers Pj, which minimize the following quantity Gj: Gj^JCETik) - L^Pfajtk)} The method is, for example, a non-negative least squares method, also called "Non-negative least squares" or NNLS in Anglo-Saxon terminology. In this method, the value of the individual power Pj is constrained to be a positive value. Alternatively, the value of the individual power Pj is constrained to be within a predetermined interval: Pnomj < Pj < n2*Pnomj Advantageously, the least squares method is underconstrained. This method is also called "constraint least squares" in Anglo-Saxon terminology. This allows us to limit the solution space. Pnom, is a predetermined nominal power of the subset SE. ni and n2 are predetermined positive parameters such that n2 is greater than ni. ni is positive and less than or equal to 1 and n2 is positive and greater than 1. The values ​​are set according to the ability of each sub-assembly to operate at a power far from its rated power. For example, ni is equal to 0.5 and n2 is equal to 2. The EPIND step advantageously, but not necessarily, includes an ESTE calculation step of the elementary energies Ej consumed by the respective subsets SEj from the individual powers Pj and the individual total operating times Dj of the subsets SEj during the period T. The elementary energy Ej consumed by each subset SEj, during the period T, is given by the following formula: SEj= PfDj Alternatively, the method omits the DNB verification step and includes the REGL implementation of the linear regression algorithm to estimate the individual powers of the SEj subsets of group G and optionally the ESTE step described above. However, the previously described embodiment is more advantageous, or a drawback of the linear model lies in the assumption of unimodality of the equipment subsets for equipment that may exhibit multiple operating modes or whose power is intended to vary. continuously over a range of values. Variant

[0295] Alternatively, the method includes a step of determining the parameters of a linear regression model that models, for each elementary period, the total elementary energy by a sum of a constant CST and the individual elementary energies consumed by the equipment subsets of the second group. Each individual elementary energy corresponds to a product of a fixed individual power and an elementary operating time of the equipment over the elementary period.

[0296] The EPIND estimation includes an estimate of the total energy consumed by the subsets of the second group G2 from the elementary energies Ej of the subsets of the second group G2.

[0297] The EPIND estimation then includes a correction step for each value of CET(k) by subtracting the estimate of the total energy consumed by the subsets of the second group G2 from the corresponding measure of energy consumption.

[0298] The EPIND estimation then includes a step of determining a set of parameters of a probabilistic graphical model modeling the distributions of the values ​​of the corrected elementary total energy consumption CET(k) and the distributions of the values ​​of the individual elementary powers of the respective subsets SEj of the first group G1 during the respective elementary periods Tk by multimodal distributions.

[0299] The method according to the invention is independent of the values ​​of energy consumption and operating times of the equipment during at least one period prior to period T. Only energy and activation / deactivation time measurements of the equipment obtained during period T are used.

[0300] Such a method is more generic, that is to say, applicable to sets E or global sets EG of equipment that are very different from each other.

[0301] Detection of devices being almost always in the same state

[0302] Advantageously, the method includes a step of identifying equipment which, in the overall set EG, has a substantially identical state (activated or deactivated) throughout the period T.

[0303] For this purpose, each piece of equipment is identified, for example, having an individual total operating time (i.e., a total operating time during the period T) less than or equal to a predetermined maximum portion or greater than or equal to a predetermined minimum portion of the duration T.

[0304] The maximum portion is for example between 0.1% and 1% and the minimum portion is, for example, between 99% and 99.9%.

[0305] The process also advantageously includes a step of removing each identified piece of equipment from the overall EG assembly.

[0306] These steps are advantageously implemented before the EPIND estimation step. This allows the removal, from this step, of equipment likely to distort the model. The energy consumed by this equipment is found in the constant CST.

[0307] These steps are, for example, implemented in addition to or instead of the VERI, EST1 and EST_CET steps. Material

[0308] From a hardware point of view, the UCA computing unit can be seen as a computer interacting with a computer program product.

[0309] The computing unit includes at least one computer, for example, a microcomputer, a computer network, an electronic component, a tablet, a smartphone or a personal digital assistant (PDA). The computing unit includes a memory set in which the computer program is stored.

[0310] The memory assembly includes, for example, a computer-readable medium. The computer-readable medium is a tangible device readable by the reader of the computing unit, capable of storing electronic instructions and of being coupled to communication means of the computing unit.

[0311] In other words, the computer-readable medium is a tangible medium. That is to say, it is not a transient signal in itself, such as radio waves or other freely propagating electromagnetic waves, such as light pulses or electronic signals. Such a computer-readable storage medium is, for example, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof.

[0312] By way of example, the readable medium is an optical disc, a magneto-optical disc, a read-only memory (ROM), an erasable and programmable read-only memory (EPROM), an electrically erasable and programmable read-only memory (EEPROM), a random access memory (RAM), a magnetic card, or an optical card. The memory assembly may include an operating system and load the programs according to the invention. It includes registers adapted to store parameter variables created and modified during the execution of the aforementioned programs. A computer program containing software instructions is then stored on the readable medium.

[0313] The computing unit includes a data processing unit comprising at least one electronic circuit designed to manipulate and / or transform data presented by electronic or physical quantities in registers of the evaluation system and / or memories in other similar data corresponding to physical data in the memories of registers or other types of display devices, transmission devices or storage devices.

[0314] The data processing unit includes, for example, memories for storing data, operationally coupled to the data processing circuit and a reader adapted to read the computer-readable media.

[0315] Each function of the computing unit is executed by causing the data processing unit to read a predetermined program on hardware such as the memory set so that the data processing circuit performs calculations, controls communications and reads and / or writes data into the memory set.

[0316] The process is carried out on a single computer or on a system distributed among several computers (in particular via the use of cloud computing).

[0317] The data processing unit comprises at least one of the following elements: a set of one or more processors (for example a central processing unit (CPU), a graphics processing unit (GPU), a microcontroller and a digital signal processor (DSP) capable of interpreting instructions in the form of a computer program; a programmable logic circuit, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a programmable logic device (PLD), programmable logic arrays (PLA), a system-on-chip (SoC), and / or an electronic board in which steps of the process according to the invention are implemented in hardware elements.

[0318] The product-program may include the computer-readable recording medium.

[0319] Alternatively, the program instructions are obtained from an external source and downloaded via a network. This is particularly the case for applications. In this case, the computer program product includes a computer-readable data carrier on which the program instructions are stored or a data carrier signal on which the program instructions are encoded.

[0320] The invention relates to a computer program product comprising the computer-readable medium containing instructions which, when executed by the processing circuit, cause the computer processing unit to implement the steps of the process according to the invention.

[0321] The form of program instructions is, for example, a form of source code, a computer-executable form, or any intermediate form between source code and a computer-executable form, such as the form resulting from the conversion of the source code via an interpreter, assembler, compiler, linker, or a locator. Alternatively, program instructions are microcode, firmware instructions, state definition data, integrated circuit configuration data (e.g., VHDL), or object code. Program instructions are written in any combination of one or more programming languages, for example, an object-oriented programming language (C++, Java, Python), a procedural programming language (e.g., C).

[0322] The communication means enable communication between the elements of the computing unit and optionally between at least one element of the computing unit and a device external to that computing unit, for example the control unit. The communication means may establish a physical link between elements of the system and / or between an element of the system and a device external to the system and / or a remote (wireless) communication link between elements of the system and / or between an element of the system and a device external to the system.

[0323] The means of communication advantageously allow the transmission of data between the control unit UCO and / or the electric meter CE and the calculation unit UCA.

Claims

1.

2.

3. Claims Method for estimating an electrical power consumed by a subset (SEj) of a group (G) comprising at least one subset (SEj), each subset (SEj) of the group (G) comprising at least one electrical equipment of a set (E) of electrical equipment, during a period (T) comprising a plurality of elementary periods (Tk), the method being implemented by computer and comprising: estimate (EPIND) the electrical power consumed by the subset (SEj) using: - individual elementary operating durations (aj(k)) of each subset (SEj) of the group (G) during the respective elementary periods (Tk) and, - the total elementary energy consumption (CET(k)) of the whole (E) during the respective elementary periods (Tk). Method according to the preceding claim, comprising: determine the individual elementary operating durations (aj(k)) of each subset (SEj) of the group (G) during the respective elementary periods (Tk), determine the total elementary energy consumptions (CET(k)) of the set (E) during the respective elementary periods (Tk). Method according to any one of the preceding claims, in which estimating (EPIND) the electrical power (Pj(k)) comprises: determine, from the total elementary energy consumption and the individual elementary operating times (aj(k)), a set of at least one parameter of a parametric model modeling: a distribution, over the elementary periods (Tk), of values of individual elementary powers consumed, during the respective elementary periods (Tk), of each subset (SEj) of the group (G), - for each elementary period (Tk), the total elementary energy consumption during the elementary period (Tk), by a sum of a possible constant (CST) and the individual elementary energy consumption (CEj(k)) of each subset (SEj) of the group (G) during the elementary period (Tk).

4. Method according to the preceding claim, in which at least when a number of activation / deactivation of at least one subset (SEj) of the group (G) during the set of elementary periods (Tk) is greater than a main threshold, the model is a probabilistic graphical model.

5. Method according to claim 4, in which the parametric model models values of the individual elementary powers consumed, during the respective elementary periods (Tk): - of each subset of a first subgroup (Gl) of the group (G) by a multimodal distribution, and / or - of each subset of a second subgroup (G2) of the group (G) by a unimodal distribution.

6. Method according to claim 5, comprising: - grouping (REG) subsets (SEj) of the group (G) so that the first subgroup (Gl) consists of each subset of the group (G) having a number of activations / deactivations during all the elementary periods (Tk) greater than a predetermined main threshold and the second subgroup (G2) consists of each subset having a number of activations / deactivations during all the elementary periods (Tk) less than or equal to the main threshold.

7. Method according to claim 5, comprising: - determining a number of subsets (SEj) of the first subgroup (Gl) so that the model is a model probabilistic graph only when the first subgroup (Gl) is non-empty.

8. Method according to any one of claims 3 to 7, in which, at least when no subset of the group (G) has a number of activation / deactivation during the set of elementary periods (Tk) greater than a predetermined main threshold, the parametric model is a linear model.

9. Method according to claim 8, comprising: - determining a number of subsets (SEj) having a number of activation / deactivation during the set of elementary periods (Tk) greater than the main threshold, so that the parametric model is linear only when no subset of the group (G) has a number of activation / deactivation, during the set of elementary periods (Tk), greater than the main threshold.

10. Method according to any one of the preceding claims, comprising a step of prior grouping (REGI) of the equipment of the set (E) according to a correlation criterion between states of the equipment (EQ;), using state information of the respective equipment, so as to form said group (G) of at least one subset (SEj).

11. Method according to any one of the preceding claims, comprising a step of initial estimation (EST1) of the energy consumption of another set of at least one other equipment from a nominal power of the other equipment and status information of the other equipment.

12. Method according to the preceding claim, comprising an initial verification step (VERI) implemented for each equipment of a global set (EG) comprising each equipment of the set (E), consisting of verifying whether the equipment complies with a set of at least one importance criterion (Cia, Clb) using a predetermined nominal power (P;) of the equipment and / or state information of the equipment, the other set of at least one other equipment being made up of each equipment of the set (E) not complying the set of at least one importance criterion.

13. Method according to any one of the preceding claims comprising, prior to the estimation step, a step of identifying each piece of equipment in the global set (EG) having a total individual operating time less than or equal to a predetermined maximum portion or greater than or equal to a predetermined minimum portion of the duration T, and a step of removing each piece of equipment identified during the identification step from the global set (EG).

14. A computer program product stored in a non-transitory computer-readable medium, said computer program product comprising code instructions which, when the program is executed by a computer, cause the computer to perform the method of any preceding claim.

15. A data processing device comprising a processor configured to execute a method according to any one of claims 1 to

16. 13. Industrial system comprising: - a set (E) of electrical equipment (EQ;) comprising a group (G) comprising at least one subset (SEj), each subset (SEj) of the group (G) comprising at least one electrical equipment of the set (E) of electrical equipment, - an electrical meter (CE), - a control unit (UCO) of the electrical equipment capable of activating and deactivating each equipment of the set (E), - a calculation unit (UCA) configured to implement the method according to any one of claims 1 to 13a, to estimate an electrical power consumed by a subset (SEj) of the group (G), the total elementary energy consumptions of the individual elementary operating durations (aj(k)) of each subset (SEj) of the group (G) during the elementary periods (Tk) being derived from energy measurements delivered by the electrical meter (CE) and the individual elementary operating durations (aj(k)) of each subset (SEj) of the group (G) during the respective elementary periods (Tk) coming from the control unit (UCO).

Images