Characterization for the optimization of the electrical consumption of a set of equipment connected to an electrical network

Abstract

Characterization for optimizing the electrical consumption of a set of equipment (E1, E2, E3, …, En) located in a room (L), comprising the transformation of a measurement stream of overall electrical consumption, provided by a measuring device (C), into a time series, which is provided as input to at least one first predictive model (MP1) adapted to provide consumption data for a piece of equipment and at least one second predictive model (MP2) adapted to provide activation data for a piece of equipment, wherein the second predictive model (MP2) comprises a first sub-model (MP1') corresponding to the first predictive model and a second sub-model (CC) adapted to determine an activation probability (P) from the output of the first sub-model. Figure for the abstract: Fig. 1

Description

Title of the invention: Characterization for the optimization of the electrical consumption of a set of equipment connected to an electrical network. FIELD OF THE INVENTION

[0001] The present invention relates to the non-intrusive determination of the electrical consumption of electrical equipment located in a specified room.

[0002] The invention relates more particularly to a method of disaggregating the load curve of a fleet of equipment in order to determine individual consumptions and to detect periods of activation of the equipment.

[0003] It thus enables the optimization of electricity consumption for users (premises managers) and of electricity production for the supplier or distributor.

[0004] These premises, whether domestic or business premises, contain a growing number of electrical equipment whose nature and behavior are extremely diverse, both in terms of consumption and activation rate per period of time.

[0005] In a residential building, one can typically find electrical equipment such as a connected television, lighting systems, household appliances, connected sockets, water heaters, charging stations, electrical panels, inverters, etc.

[0006] However, optimizing electricity consumption, or more generally energy consumption, may become increasingly important for economic and environmental reasons. Such optimization can only be achieved through knowledge of the individual electrical behavior of each piece of equipment.

[0007] Generally, there is no way to measure the electricity consumption of each piece of equipment. Such an approach would require installing an electricity meter for each piece of equipment, which is undesirable due to the additional cost involved. Furthermore, such a solution would likely not be acceptable to users.

[0008] Non-intrusive load monitoring (or NILM for “Non-Intrusive Load Monitoring”) approaches have been proposed.

[0009] Load curve disaggregation aims to estimate the individual energy consumption of each appliance or piece of equipment, and / or the activation of the on / off state, using only the aggregated total load curve (apparent power consumed for a dwelling). This aggregated total load curve is available via a smart electricity meter.

[0010] Load curve disaggregation was initially addressed as a linear combination problem. Early research investigated the use of combinatorial optimization algorithms with the aim of estimating the proportion of energy consumption at each time step and for each active device. Subsequently, hidden Markov models were the preferred approach for several years.

[0011] In recent years, proposals have been made based on neural networks and deep learning.

[0012] One of the first publications relating to this family of approaches is the article by Kelly, J., & Knottenbelt, W. “Neural nilm: Deep neural networks applied to energy disaggregation”, in Proceedings of the 2nd ACM international conference on embedded Systems for energy-efficient built environments (pp. 55-64), 2015.

[0013] Other approaches are based on convolutional neural networks, such as the one described in Zhang, Chaoyun et al. “Sequence-to-point learning with neural networks for nonintrusive load monitoring” in AAAI Conference on Artificial Intelligence (2016).

[0014] More recently, a new approach has emerged based on "transformer" technology. This type of algorithm was introduced in the article by Vaswani, Ashish et al., "Attention is AU you Need." In Neural Information Processing Systems (2017).

[0015] An example of such an algorithm “BERT4NILM” is described in the article by Zhenrui Yue, Camilo Requena Witzig, Daniel Jorde, and Hans-Amo Jacobsen “BERT4NILM: A Bidirectional Transformer Model for Non-Intrusive Load Monitoring” in Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring (NILM'20). Association for Computing Machinery, New York, NY, USA, 89-93. https: / / doi.org / 10.1145 / 3427771.3429390.

[0016] This mechanism allows a partial disaggregation of the load curve: the individual load (or consumption) of certain types of equipment can be determined, but this proves impossible, or too imprecise for other types of equipment.

[0017] It has also been proposed to focus on determining the activity of a piece of equipment (i.e. whether it is switched on or not) over a unit of time, rather than on the disaggregation of its load curve.

[0018] There is therefore a need to improve current proposals of the state of the art. Summary of the invention

[0019] The invention aims to combine the approaches of load curve disaggregation and equipment activation determination. In particular, it aims to integrate both approaches optimally, that is, by minimizing the resources needed.

[0020] To this end, according to a first aspect, the present invention can be implemented by a method for characterizing the electrical consumption of a set of equipment located in a given room, comprising the transformation of a stream of measurement values ​​of the overall electrical consumption of said set, provided by a measurement device associated with said given room, into a time series, said time series being provided as input to at least a first predictive model adapted to provide consumption data for at least one respective piece of equipment from a first subset of said set and to at least a second predictive model adapted to provide activation data for at least one respective piece of equipment from a second subset of said set,in which said at least one second predictive model comprises a first sub-model corresponding to said at least one first predictive model and a second sub-model adapted to determine an activation probability from the output of said first sub-model, and in which said at least one predictive model is trained on a predetermined training set and said at least one second predictive model is trained from said first predictive model, by transfer, and then from a second training set.

[0021] According to preferred embodiments, the invention comprises one or more of the following features which can be used separately or in partial combination with each other or in total combination with each other: - said at least one first predictive model is a neural network comprising an embedding module, a transformer module and a multilayer perceptron module; - said second sub-model comprises two fully connected dense layers; - control commands intended for said equipment are determined by an optimization module based on said consumption data and said activation data. These control commands can then be transmitted to the equipment by means of interfaces and protocol adaptations or to devices adapted for equipment control; - said consumption and activation data are transmitted, in an anonymized form, to a concentrator of a second service platform, adapted to establish statistics on the consumption of a set of determined premises, in order to adapt the electricity production of an electricity supplier; - a training module, comprising said at least one first and second predictive models, is stored in a secure structure within a gateway, and in which a training phase includes the transmission of said module to a service platform through a telecommunications network, the execution of said training module by said service platform, in order to train said predictive modules, and then the transmission of said predictive models to said gateway; - a classification module for learning is adapted to select said learning sets based on equipment present in said specified room: - during the training of said second predictive model from said second training set, only said second sub-model is adapted; - during the training of said second predictive model from said second training set both said first sub-model and said second sub-model are adapted.

[0022] Another aspect relates to a computer program comprising instructions for implementing a process as previously described, when said process is implemented on an information processing platform.

[0023] Another aspect relates to a gateway comprising a processor adapted to implement a process as previously described, optionally in collaboration with a service platform through a telecommunications network.

[0024] Other features and advantages of the invention will become apparent from the following description of a preferred embodiment of the invention, given by way of example and with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE FIGURES

[0025] The attached drawings illustrate the invention: Figure 1 schematically illustrates a context of use of a proposed method. Figure 2 schematically represents a functional view of a system comprising a gateway in collaboration with a service platform, according to an embodiment of the invention.

[0027] Figure 3 schematically illustrates a functional view of a gateway and the use of predictive models for characterizing electrical consumption, according to one embodiment.

[0028] Fig. 4 illustrates an implementation of a predictive model architecture based on the "BERT4NILM" network, according to one embodiment.

[0029] Figure 5 illustrates an example of a functional architecture for a predictive model of a second type, according to one embodiment.

[0030] Fig. 6 illustrates one embodiment of a learning phase according to one embodiment.

[0031] DETAILED DESCRIPTION OF EMBODIMENT METHODS OF THE INVENTION

[0032] Figure 1 shows a set of equipment, Eb E2, E3, ..., En, located in a specific room L.

[0033] The defined location L may correspond to a geographically limited space within which a given user can have and control the connected objects. This space may correspond to a personal dwelling (apartment, house, etc.), or to the premises of a company, a store, etc.

[0034] The determined premises may possibly have extensions outside of a limited space, when for example certain connected objects are remote: a charging station for an electric car may be located in a garage, a garden, or even open onto the road, and be outside the main space corresponding to the dwelling, while being within the user's control perimeter.

[0035] The equipment can be of different kinds. Generally speaking, it refers to any equipment connected to an electrical energy distribution network NE and consuming this energy continuously or not.

[0036] For example, one could cite: - household appliances (ovens, refrigerators, hobs) heated...), - lighting systems, - heating and thermal regulation systems, - security systems (motion detectors, surveillance cameras, etc.

[0037] A device C is associated with the specified room L, and is adapted to provide measurement data of a global load, or consumption, for all the equipment associated with the specified room L. This device can measure the energy consumed on the distribution network NEinside the specified room L. The measured values ​​can typically represent apparent power.

[0038] This device is typically a so-called "smart" electricity meter, that is to say, one adapted to provide such data, generally in the form of a stream of numerical values. It could be, in particular, a Linky™ type electricity meter in France, for example.

[0039] A suitable GTW gateway may also be provided to communicate with the measuring device C, in order to acquire a stream of measurement values ​​of overall electrical consumption provided by the measuring device C.

[0040] The GTW gateway may include data processing means. It may also have interfaces with the measuring device C and a telecommunications network N.

[0041] The interface with the measuring device C can be a radio interface, in order to minimize wired connections within the room L and for ergonomic reasons. To achieve this, a radio module may need to be connected to the measuring device C to ensure radio connectivity between it and the GTW gateway. This module can be a local radio transmitter (LRT) using the Zigbee™ protocol, for example.

[0042] According to a particular embodiment, the GTW gateway may include a Raspberry Pi type microprocessor, RAM memory (between 4 GB and 8 GB, for example), and mass storage, for example of the eMMC type, of about 16 GB.

[0043] The interface to the N telecommunications network can be wired (Ethernet) or wireless (Wi-Fi, etc.). More precisely, this telecommunications network can be composed of a local network to which a telecommunications gateway is connected in order to allow access to the public telecommunications network (the Internet). The N telecommunications network can therefore be viewed as a set of subnets.

[0044] The telecommunications network N allows the GTW gateway to communicate with a service platform S.

[0045] Different role sharing arrangements between the GTW gateway and the S services platform can be envisaged.

[0046] The S service platform can be in charge of managing the GTW gateway, including software updates, fault management, etc.

[0047] Data and processing can also be transmitted from the GTW gateway to the S service platform. This processing and data may correspond to tasks that cannot be performed locally, particularly because the computing power of an S service platform is required. The S service platform can be deployed on a server farm or, abstracted as a cloud computing server. Its computing power can be adapted according to the task to be performed, as submitted by the GTW gateways.

[0048] These treatments may correspond to the training of predictive models on training sets.

[0049] According to one embodiment, as illustrated by the example in [Fig. 2], a secure digital structure (SEC) is provided within the GTW gateway. The security is designed to prevent any third party without the appropriate keys from reading the contents of the digital structure.

[0050] According to one embodiment, the training module can be stored in this SEC secure structure within said gateway.

[0051] This training module may include a set of predictive models, MP, typically multilayer artificial neural networks, and computer code, MI, enabling the implementation of the training steps.

[0052] During a training phase, this training module can be transmitted to the service platform S through the telecommunications network, in an SI step.

[0053] In a step S2, the training module is executed by the service platform S. The transmitted predictive models MP are thus trained on the basis of training sets (described later).

[0054] In an S3 step, the training module, or only the predictive MP models, are transmitted to the GTW gateway.

[0055] The S2 training step is costly in terms of computing power and execution memory. It is therefore advantageously executed on a service platform S which can be adequately sized for this type of processing, whereas the GTW platform can only have limited resources since it is a device intended to be deployed at users' premises: it therefore meets strong cost and sizing constraints.

[0056] It should be noted, however, that only the training phase is implemented on the service platform S. As will be seen later, the use of the predictive models MP to characterize the overall consumption of the dwelling L can be carried out entirely locally by the GTW gateway.

[0057] In the event that access to the N telecommunications network is interrupted, the GTW gateway can continue to operate for prediction. Training can also be implemented, but since the resources of the GTW gateway are limited, the time required for learning convergence will necessarily be longer.

[0058] The process therefore allows for optimized mixed collaboration between cloud computing and local edge computing.

[0059] This training module can be included in a "container," which is a data structure containing computer code and elements dependent on that code, adapted to be executed on a virtual machine. Thus, among other advantages, the code can be executed independently of the operating system and hardware infrastructure of the equipment on which it is to be executed: the same code can therefore be executed on the GTW gateway or on the S services platform.

[0060] These containers, stored in the secure digital structure SEC, also make it possible to protect the predictive models MP and the associated computer code MI from possible theft and hacking.

[0061] Fig. 3 illustrates one embodiment of the use of predictive models for the characterization of the electrical consumption of all the equipment located in the determined room L.

[0062] As mentioned previously, the GTW gateway can acquire measurement value streams (or measurement streams, by abuse of language) of an overall electrical consumption of the set of equipment connected to the NE electrical network of the premises L.

[0063] The GTW gateway may include an MT preprocessing module (for example in the SEC secure digital structure) adapted to transform this flow of measurement values ​​into a time series.

[0064] This time series is constructed to be provided as input to predictive models MPI, MP2, of the multilayer neural network type.

[0065] This time series can represent a time window in which each value represents a measurement value for an interval of this time window.

[0066] For example, we can have a time interval, or no time, of 15 seconds, and a time series of 480 values, which represents in total a time window of 480x15 = 2 hours.

[0067] Within the time series, the value assigned to a time interval can correspond to a resampling of the values ​​in the measurement stream. For example, if more than one value in the measurement stream is available for the same time interval, the MT preprocessing module can establish an average value (for example) in order to construct the output time series.

[0068] Each predictive model is adapted for a particular type of equipment. Indeed, each type of equipment has its own specific electrical behavior. As will be seen later, each predictive model is specifically trained on a training set corresponding to a type or class of equipment, so that at the end of this training phase, the model is adapted for that type of equipment.

[0069] These predictive models can be divided into two subsets: - a first subset of predictive models, MPI, is adapted to provide consumption data for equipment from a first subset of equipment (among the set of equipment); - a second subset of predictive models, MP2, is adapted to provide activation data for equipment from a second subset of equipment (among the equipment set).

[0070] In other words, depending on their type, equipment connected to the NE electrical network can be classified into two categories, depending on whether it is possible to determine disaggregated electrical consumption from the overall acquired consumption via the measurement device C, or if we can only determine their activation, that is, whether they are on or off, for each time step considered.

[0071] This distribution into a first class, corresponding to the first subset of predictive models, MPI, or into a second class, corresponding to the second subset of (second) predictive models, MP2, can be done according to a profile of the individual load curve of the equipment.

[0072] Such a classification was, for example, proposed in the article by George W. Hart, "Nonintrusive Appliance Load Monitoring", in Proceedings of the IEEE, December 1992, pp. 1870-1891. The proposed classification is as follows: - uses with permanent consumption: this category includes uses consuming a constant power, 24 hours a day and 7 days a week. These include, for example, fire alarm or security devices, telecommunications devices such as modems, internet access gateways, etc. - On / Off appliances: This category consists of devices with only two states. An OFF state (or off) where they consume no power, and an ON state (or on) where they consume approximately constant power. Many common household appliances belong to this category. Examples include kettles, light bulbs, refrigerators, freezers, toasters, coffee makers, microwave ovens, conventional ovens, some heating systems, etc. - Uses with a finite number of states: this category includes uses that go through several distinct states where they consume constant power for each state. This is typically the case for equipment following an automatic cycle made up of a succession of states. Examples include washing machines, dryers, dishwashers, etc. - Uses with an infinite number of states: this category includes equipment whose power consumption can vary continuously over a certain range of values, generally according to a user setting. Examples include vacuum cleaners with variable power, etc.

[0073] It is also possible to define a finer, or different, classification than these categories.

[0074] For example, in the case of heating systems, considered above in the ON / OFF usage category, it may be easier to extract the load curve of a heat pump than that of an electric convector heater. Therefore, each can be considered to belong to a different class.

[0075] Depending on the type of equipment, a first or second subset of predictive models (respectively first, MPI, and second, MP2, predictive models) are used.

[0076] This choice of directing a type of equipment towards one or the other of the subsets of predictive models can be made according to a parameterization, which can be set by the supplier of the GTW platform and / or the predictive models MPI, MP2.

[0077] It may depend on the ability of the predictive models of the first subset to provide consumption data for this given type of equipment based on overall consumption data (disaggregation). This ability can be assessed by the designer of the predictive model in question, and this assessment can allow this predictive model to be assigned to this type of equipment, or, if the assessment is not considered sufficiently positive, to a predictive model of the second subset.

[0078] This configuration can evolve over time. For example, new predictive models may become available (e.g., due to new training). It is possible that new predictive models from the first subset may offer better capabilities for disaggregating overall consumption curves. In this case, it may be necessary to change the assignment of a type of equipment from the second subset to the first subset of predictive models. This change can be implemented by updating the MT preprocessing module, for example, by downloading computer code or configuration parameters from the S service platform.

[0079] According to one embodiment, the MT pretreatment module can be provided to define a first subset of equipment and a second subset of equipment, the two subsets being disjoint and forming a partition of the total set of equipment.

[0080] The MT preprocessing module can provide the time series of a piece of equipment as input to a predictive model corresponding to that equipment. This predictive module belongs - to the first subset of (first) predictive models MPI if the equipment belongs to the first subset of equipment, or, - to the second subset of (second) predictive models MP2, if the equipment belongs to the second subset of equipment.

[0081] According to one embodiment, the MT preprocessing module may include a table associating each piece of equipment or each type of equipment with a predictive model in one or the other of the subsets.

[0082] According to one embodiment, load curve disaggregation is implemented only for ON / OFF uses. It is also possible, as As previously indicated, to distinguish only a sub-part of this equipment for load curve disaggregation.

[0083] In other words, according to this embodiment, the MT preprocessing module can be provided to (by means of a preconfigured table, for example) provide the received time series to a predictive module of the first subset of predictive models MPI if the equipment belongs to certain types of equipment for use ON / OFF, and to a predictive module of the second subset MP2 in other cases.

[0084] As mentioned previously, the predictive models MPI, MP2 can be artificial neural networks.

[0085] According to one embodiment, the predictive models of the same subset, MPI, MP2, can be structurally identical. They differ in their internal state (synaptic weights of the different constituent layers) which are fixed during the learning phase: as will be seen later, each predictive model is trained on a specific training set.

[0086] According to one embodiment, a neural network comprising an embedding module, a transformer module and a multilayer perceptron module.

[0087] Figure 4 illustrates an implementation of such an architecture based on the BERT4NILM network. This type of network was introduced in the article by Zhenrui Yue, Camilo Requena Witzig, Daniel Jorde, and Hans-Arno Jacobsen, “BERT4NILM: A Bidirectional Transformer Model for Non-Intrusive Load Monitoring,” in Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring (NILM'20). Association for Computing Machinery, New York, NY, USA, 89–93. https: / / doi.org / 10.1145 / 3427771.3429390

[0088] A BERT4NILM architecture is based on the well-known BERT architecture described in the article by Devlin, Jacob, Chang, Ming-Wei, Lee, Kenton, et al. “Bert: Pre-training of deep bidirectional transformers for language understanding”, arXiv preprint arXiv: 1810.04805, 2018.

[0089] A BERT4NILM network consists of an immersion module M1, a transformer module M2 and a multilayer perceptron module M3, linked sequentially.

[0090] The embedding module Ml includes an extraction of features from the input Ll, which increases the dimensionality of the data. A pooling operation is then applied in an L3 layer.

[0091] The output of this layer L3 is then added to a position embedding matrix L4, in the resultant, L5, can form the input of the transformers L6, L7 ..., L11, of the transformer module M2.

[0092] The transformer module is formed of several layers, each layer having several attention heads. This concept of attention in an artificial neural network was introduced by Vaswani, Ashish, Noam M. Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin. “Attention is All You Need.” in Neural Information Processing Systems (2017).

[0093] The M3 multilayer perceptron module includes a deconvolution layer L12, and two linear layers L13, L14, in order to provide an output vector of the same dimension as the input.

[0094] The input of the predictive model MPI is a time series obtained from a stream of measurement values ​​of overall electrical consumption.

[0095] This time series represents the flow of measured values ​​for the overall electrical consumption of all equipment connected to the electrical distribution network. The L14 output of the predictive model corresponding to a given piece of equipment is also a time series, but this one represents a flow of measured values ​​for the predicted (or estimated) electrical consumption of that given piece of equipment.

[0096] In other words, the predictive MPI model makes it possible to extract a consumption curve of a given piece of equipment from the consumption curve of all the equipment.

[0097] These consumption data provided by the predictive model MPI can be of the same dimension as the input vector Ll, i.e. represent a time window of the same length with an identical step.

[0098] By continuously aggregating consumption data, a consumption curve can be obtained for a given piece of equipment. The beginning and end of this curve correspond to the start and stop of the prediction process just described. In one embodiment, preferably, this process is implemented continuously, or at least over long periods, in order to determine results usable by the MO optimization module.

[0099] The same time series, obtained from the measurement stream provided by the measurement device C, can be supplied to a plurality of predictive models from the first set of predictive models, MPI. Each model, trained for a particular type of equipment, will determine consumption data for equipment belonging to that type. In other words, a plurality of load curves are obtained as output.

[0100] Furthermore, the MT preprocessing module can be provided to (by means of a preconfigured table, for example) provide the received time series to a predictive module of the second subset MP2, in the cases previously described.

[0101] These second predictive models MP2 are structurally different from the first models MPI since they aim to perform a classification and not a regression.

[0102] Fig. 5 illustrates an example of a functional architecture for an MP2 predictive model of the second subset.

[0103] This second predictive model MP2 includes a first sub-model MPI' corresponding to the first predictive model MPI and a second sub-model CC adapted to determine an activation probability P from the output of the first sub-model, MPI'.

[0104] The first MPI' sub-model can be structurally identical to the first predictive MPI model: same number of layers, same number of neurons per layer, etc. Thus, both can correspond to the implementation illustrated in [Fig. 4]. However, they can differ in their internal state, determined by the learning phase. In other words, depending on the embodiment, the synaptic weights can differ between the two MPI and MPI' models.

[0105] The second sub-model CC may comprise two fully connected dense layers. They aim to summarize the information of the representation obtained as output from the first sub-model MPI' in order to obtain a classification probability P.

[0106] This classification P represents the probability of activation of a given piece of equipment within the time window corresponding to the input data, that is, whether this equipment is switched on (i.e., consuming electrical energy) or not. As previously explained, a plurality of predictive MP2 models can be predicted, each corresponding to a given type of equipment.

[0107] This probability can be simply thresholded to provide a binary activation, i.e. an estimate of whether the equipment is on or off during the corresponding time period.

[0108] The outputs of the different predictive models, of the two subsets, are transmitted to a characterization module MC which is responsible for processing its individual results of each predictive model to provide a usable result, for example by an optimization module MO.

[0109] This MC characterization module aggregates the outputs of the different predictive modules and can also be designed to handle the temporal aspect by serializing the different outputs as a function of time.

[0110] For example, it can reconstruct a consumption curve from the outputs of the predictive models of the first subset which correspond to time windows. It can do this by joining them together.

[0111] It can also construct an activation curve by matching the output of the predictive models of the second subset to each corresponding time interval.

[0112] It is thus possible to obtain a series of curves, either of consumption or of activation, corresponding to the different equipment connected to the electrical distribution network.

[0113] In general, the predictive models MPI, MP2 together allow for a characterization of the electrical consumption of a set of equipment Eb E2, E3, ..., En located in a specific room L connected to the electrical network, from a flow of values ​​of overall electrical consumption measurements provided by a measurement device C associated with the specific room L.

[0114] The characterization of the electrical consumption for a room L is important for various reasons, and can be exploited in different ways.

[0115] From a general point of view, this characterization has great interest, both from a purely scientific point of view and from a technological point of view.

[0116] In particular, it helps to manage energy consumption from the perspective of the consumer, the energy supplier, and the environment as a whole. This last point addresses current and future requirements regarding the environmental impact of users' energy consumption (both residential and industrial).

[0117] Furthermore, in order to design smart buildings, more efficient distribution systems, etc., it is important for the scientific community to have more precise and numerous metrics. Such a mechanism for characterizing the electricity consumption of a household or a business can contribute to building a knowledge base to facilitate research and development in these areas.

[0118] The characterization of electricity consumption can be used for the optimization of energy production by the electricity energy supplier.

[0119] The characterizations of a large number of end consumers can be transmitted, in anonymized form, to a concentrator which can compile consumption statistics. This concentrator can be an application module on a service platform accessible to the energy supplier.

[0120] As an example, it is possible to establish an average consumption, or activation, curve per type of equipment.

[0121] Based on these statistics, the energy supplier can adapt its production network. In particular, it can build a reliable prediction of customer usage and thus anticipate increases in load at its production points or, conversely, decreases in load, thereby allowing it to reduce its exposure to speculative risks in the inter-producer electricity market.

[0122] The characterization process can therefore enable energy suppliers to optimize energy production, in particular to avoid waste by overproduction, thanks to the transmission of characterization data to a service platform accessible to the energy supplier.

[0123] Also, an optimization module MO can be provided in the GTW gateway or in the S service platform, in order to allow the optimization of the equipment fleet Eb E2, E3, ..., En located in a determined room L according to the consumption data and activation data obtained from the predictive models (via the characterization module).

[0124] Preferably, the MO optimization module is embedded (as a software or application module) within the GTW gateway. This allows optimization to be performed based on locally available information, thus minimizing data transmission to the Internet, which is beneficial for managing personal data and conserving bandwidth and network resources. Furthermore, optimization can continue even if the link to the telecommunications network and the S service platform is interrupted.

[0125] The optimization module can determine control orders for one or more pieces of equipment among those connected to the network in order to respond to these internal or external constraints of the specified room L, or of the building to which the specified room L belongs.

[0126] In particular, a possible constraint may be to balance consumption, or at least to constrain fluctuations in consumption to already a given threshold.

[0127] Thus, in the event of a consumption peak (detectable from the consumption curve provided by the measurement device C), characterizing the electrical consumption across the equipment fleet can help determine a probable cause of this peak (either through consumption data or, failing that, through activation data). It is then possible to determine control commands to smooth out electrical consumption.

[0128] For example, some equipment can be momentarily switched off or forced into a less power-consuming state, for a duration corresponding to an activity of the equipment that is the source of the peak consumption.

[0129] As an illustrative example, a kitchen heating system can be lowered when an oven is switched on: its operating time is limited so that lowering the heating is not very detrimental to the inhabitants.

[0130] Furthermore, characterizing consumption makes it possible to identify the share of energy consumption per piece of equipment and thus to provide an energy cost for each. Specific actions for reducing energy consumption per piece of equipment can then be proposed to the user, and a precise return on investment can be provided, since it is possible to know the energy share and financial associated with each piece of equipment: it is therefore possible to indicate a possible saving on their energy bill by lowering the heating by one degree.

[0131] Similarly, the characterization of electrical equipment over a given time window can be one of the inputs to a load control model based on energy predictions that take this characterization as input. For example, this control model could send commands to switch electrical devices on or off according to the past characterization performed.

[0132] Furthermore, the MO optimization module can provide the user with a representative overview of consumption and activation data for all equipment. This data can be aggregated and consolidated to provide a comprehensive view of its electricity usage.

[0133] The optimization module can detect optimization opportunities and, possibly after validation by a user from local L, transmit suitable command orders.

[0134] For example, it can detect standby equipment and electricity consumers: plugged-in household appliances, for instance. It can also identify heating systems used at night. In some cases, it may be beneficial to limit these uses, and the MO optimization module can suggest control commands aimed at reducing this consumption, which should not impact the comfort of the occupants (or at least present an energy savings / comfort loss ratio greater than one).

[0135] Obviously, other optimization scenarios can be implemented by the optimization module, MO, by taking advantage of the detailed knowledge of the electrical uses of the premises obtained by the characterization process described.

[0136] Various other use cases are also described in the scientific or commercial literature related to non-intrusive load characterization (NILM).

[0137] It is clear that the characterization obtained by the GTW gateway allows the optimization of the electricity consumption of consumers and the optimization of the electricity production of electricity suppliers.

[0138] As indicated, this characterization process is based on MPI, M2 predictive models, which have undergone a training phase.

[0139] During this: - The first MPI predictive model(s) of the first set are trained on a predetermined training set, - the second predictive model(s) MP2 of the second set are trained from the first predictive models, MPI, by transfer, then from a second training set.

[0140] Fig. 6 illustrates one way of carrying out this learning phase.

[0141] In this embodiment, the learning is deployed on the S service platform. As described previously, in one embodiment, a training module can be transmitted from the GTW gateway to the S service platform through the telecommunications network (dotted arrows).

[0142] A database DB contains a predetermined training set for the first predictive models MPI and a second training set for the second predictive models MP2.

[0143] This training set associates time series corresponding to flows of measured values ​​of overall electrical consumption with - consumption data, in the case of the first training set (i.e., corresponding to the first predictive models) - Activation data, in the case of the second training set

[0144] . This consumption and activation data corresponds to labels representative of a reality. The training sets can be constructed by conducting experimental studies in the laboratory or in real user premises, using measuring equipment to record the consumption and / or activation of individual devices.

[0145] Public training databases exist and can be used, such as the REDD, UK-DALE, or REFIT databases. These three databases present consumption values ​​at fine time steps (5-10 seconds) for overall load curves and household appliances. REDD offers data from 6 US homes collected in 2011, UK-DALE from 5 UK homes collected from 2012 to 2015, and REFIT from 23 UK homes collected from 2015 to 2017.

[0146] According to one embodiment, a classification module for learning, MCA, is provided for selecting training sets from the content of the training sets contained in the database DB.

[0147] The selection can be made based on the equipment contained in the determined room L. The examples selected from the database to constitute the training sets correspond to those with a strong resemblance to the determined room L. This resemblance is estimated from the types of the main equipment (which can be provided by a list), but also by other impacting elements: surface area, detached house or apartment, etc.

[0148] Non-electrical equipment may also be taken into account. For example, the presence of a fireplace or stove can impact electricity consumption for heating-related uses.

[0149] This selection therefore allows us to consider in the learning process only examples relevant to the determined location L. We thus obtain models Predictive MPI, MP2 adapted to the local determined L, which allows for more relevant predictions.

[0150] A predictive model is trained for each piece of equipment, i.e. for each label, whether it is formed of consumption data (for a given piece of equipment) or of activation (also for a given piece of equipment).

[0151] A predictive MPI model is trained for each of the equipment connected to the electrical network of the determined room L.

[0152] In the case where the first predictive models are of the BERT4NILM type, the training of these can be carried out in accordance with the article describing this type of architecture, in particular in terms of cost function (or “loss function” in English).

[0153] The second predictive models are trained once by transfer, meaning that the internal state of the first predictive models is copied to form the respective second predictive models. In other words, the knowledge acquired during the first training phase (captured by the state of the first predictive models) is reused, or transferred, to the second predictive models MP2.

[0154] Then, the second training set mentioned above is used for a second "sub-phase" of training. This second training aims to specialize the second predictive models in the task of determining (or predicting) activation data.

[0155] In other words, it aims to train primarily the second subnetwork CC designed to summarize the information produced by the first subnetwork into an activation probability P.

[0156] For this training, a BCE (Binary Cross Entropy) cost function can be used between the output activation probability P and the label provided by the second training set (as selected by the MCA training classification module, if applicable). The BCE cost function is a very common function, defined as a measure of the difference between two probability distributions.

[0157] This training allows the internal state of the second predictive models to converge in order to specialize them in a classification task (determination of an activation P). In particular, it seeks to fix the state of the second CC subnetwork constituting the second predictive models MP2.

[0158] According to one embodiment, the internal state of the first subnetwork MPI' is fixed during this training and therefore remains the same as that of the first corresponding MPI model. In other words, only the second CC sub-model is adapted during training.

[0159] According to another, alternative embodiment, the internal state of the first MPI' subnetwork is not fixed during this training. In other words, both the first MPI' submodel and the second CC submodel are adapted during training.

[0160] Experimental studies have demonstrated the effectiveness of the proposed approach. In particular, the proposed method for characterizing electrical consumption offers superior quality measurements (accuracy, recall rate, etc.) compared to prior art proposals for a range of different types of electrical equipment.

[0161] Some prior art proposals may achieve better results for certain types of equipment, but insofar as a given room L includes equipment of various types, these specialized mechanisms are not satisfactory.

[0162] The proposed process, on the contrary, makes it possible to achieve high performance in the case of a set of equipment of various types (refrigerator, freezer, heating system, computer, microwave ovens, washing machine...).

[0163] In particular, the proposed method allows for high performance in the case of refrigeration equipment (freezers, refrigerators, etc.) for obtaining consumption data per unit. It also allows for high performance in obtaining activation data for household appliances.

[0164] Of course, the present invention is not limited to the examples and embodiment described and illustrated, but is defined by the claims. In particular, it is susceptible of numerous variations accessible to those skilled in the art.

Claims

Demands

1. A method for characterizing the electrical consumption of a set of equipment (Eb E2, E3, En) located in a specific room (L), comprising transforming a stream of measured values ​​of the overall electrical consumption of said set, provided by a measuring device (C) associated with said specific room (L), into a time series, said time series being provided as input to at least one first predictive model (MPI) adapted to provide consumption data for at least one respective piece of equipment from a first subset of said set and to at least one second predictive model (MP2) adapted to provide activation data for at least one respective piece of equipment from a second subset of said set,in which said at least one second predictive model (MP2) comprises a first sub-model (MPI') corresponding to said at least one first predictive model and a second sub-model (CC) adapted to determine an activation probability (P) from the output of said first sub-model, and in which said at least one predictive model (MPI) is trained on a predetermined training set and said at least one second predictive model (MP2) is trained from said first predictive model, by transfer, and then from a second training set.

2. Method according to the preceding claim wherein said at least one first predictive model (PPM) is a neural network comprising an embedding module (M1), a transformer module (M2) and a multilayer perceptron module (M3).

3. Method according to the preceding claim, wherein said second submodel (CC) comprises two fully connected dense layers.

4. A method according to any one of the preceding claims wherein control commands for said equipment are determined by an optimization module (MO) based on said consumption data and said activation data.

5. A method according to any one of the preceding claims, wherein a training module, comprising said at least one first and second predictive models, is stored in a secure structure (SEC) within a gateway (GTW), and wherein a phase training includes the transmission of said module to a service platform (S) through a telecommunications network (N), the execution of said training module by said service platform, in order to train said predictive modules, and then the transmission of said predictive models to said gateway (GTW).

6. A method according to any one of the preceding claims, wherein a classification module for learning (MCA) is adapted to select said learning sets based on equipment present in said specified room (L).

7. A method according to any one of the preceding claims, wherein in training said second predictive model (MP2) from said second training set, only said second sub-model (CC) is fitted.

8. A method according to any one of claims 1 to 6 wherein, during the training of said second predictive model (MP2) from said second training set, both said first sub-model (MPI') and said second sub-model (CC) are fitted.

9. A computer program comprising instructions for implementing a method according to any one of the preceding claims, when said method is implemented on an information processing platform.

10. Gateway (GTW) comprising a processor adapted to implement a method according to any one of claims 1 to 8, optionally in collaboration with a service platform (S) through a telecommunications network (N).

Images