Management of a power cut in a cellular radiocommunication network

Abstract

The invention relates to a method for managing a power cut in a site of a cellular radiocommunication network, the site being provided with an energy storage device, the method comprising: - receiving (300) a request to cut power from the site, the request indicating a requested cut duration; - predicting (302) an energy consumption of the site on the basis of at least one indicator representative of the operation of the site; - making a decision (305-308) concerning the request on the basis of a result based on a comparison between a calculated autonomy of the storage device and the requested cut duration, the calculated autonomy being based on the energy consumption prediction for the site.

Description

[0001]DESCRIPTION Title: Management of a power outage in a cellular radiocommunication network Field of the invention The field of the invention is that of cellular radiocommunication networks and more particularly the management of a power outage for voluntary load shedding in these networks. Prior art Electricity suppliers face variations in energy consumption in an electrical network depending on the time of day, and generally distinguish between peak hours, during which the energy consumption of the electrical network is high, and off-peak hours, during which the energy consumption on the electrical network is lower. A mobile cellular radiocommunication network consumes a significant amount of electricity due to the operation of sites comprising one or more base stations,antennas and other network infrastructure. The continuous need for data transmission places a high energy demand on the cellular radio network. Cellular radio networks continue to expand to support increased data traffic and new technologies, such as the generation of 5G networks. This results in an increase in the energy requirements of cellular radio networks. An existing solution to reduce the load imposed by a cellular radio network on an electrical grid, particularly during peak hours, is a load shedding technique, according to which at least one site of the cellular radio network is required to be temporarily disconnected from the electrical grid (thus cutting off the site's power) for an outage period, to be powered by an energy storage device at the site,such as a battery for example. To this end, an operator in charge of the cellular radiocommunication network can negotiate with an aggregator the conditions of the power outage, in particular the duration of the outage. An aggregator acts as an intermediary between actors (individuals or companies) who have load shedding capacities, as is the case for an operator of a cellular radiocommunication network, and an electricity grid manager. An aggregator thus allows the electricity grid manager to group together load shedding capacities of different consumers or electricity consumption sites. However, it is essential to keep in mind that an energy storage device has limits in terms of autonomy. Thus, if the outage duration is greater than the autonomy of the storage device,This results in an inevitable interruption of the services permitted by the cellular radiocommunication network. It is thus complex for the operator of the cellular radiocommunication network to know in advance the autonomy permitted by the storage device of a site, which depends on the activity of the site, which is variable and which is not known in advance. This results in an inability for the network operator to be able to evaluate whether the duration of the outage in the context of voluntary load shedding is acceptable or not, that is to say whether it will impact or not the quality of the services provided by a site of a cellular radiocommunication network. Purpose and summary of the invention One of the aims of the invention is to remedy at least one of the drawbacks of the aforementioned state of the art by proposing a new technique for managing the power outage of a cellular radiocommunication site, which makes it possible to take a decision to accept or not the outage,depending on the autonomy allowed by a storage device of the site. It is thus possible to accept a greater number of power outage requests, which facilitates the balancing of the electrical network, in particular during peak hours, while guaranteeing stable performance for users of the communication services managed by the cellular radiocommunication site. To this end, an object of the present invention relates to a method for managing a power outage in a site of a cellular radiocommunication network according to claim 1. Claims 2 to 11 describe preferred embodiments of said method. The site is provided with an energy storage device. The method may comprise: - receiving a power outage request from the site, the request indicating a required outage duration; - predicting an energy consumption of the site for a future prediction horizon,based on indicators representative of operation of the site; - a calculation of an autonomy of the storage device of the site based on the prediction of energy consumption of the site; - a comparison between the calculated autonomy of the storage device and the required outage duration; - a decision on the request, based on a result of the comparison. Thus, the invention makes it possible to determine the actual autonomy of the storage device, which depends on the future energy consumption of the site. The decision to accept or not a request for power outage of the site is thus improved: it is thus possible to accept a greater number of power outage requests, which facilitates the balancing of the electrical network, in particular during peak hours, while guaranteeing stable performance for users of the communication services managed by the cellular radiocommunication site. Advantageously,the prediction of the energy consumption of the site is based on indicators representative of the operation of the site, such as for example key performance indicators or KPIs (in English, “Key Performance Indicator”), raw indicators (number of resources occupied per cell, quantity of data sent via the network, etc.), which allow an accurate prediction of the energy consumption for the prediction horizon. According to embodiments, the indicators representative of the operation of the site may comprise a history of past values ​​of an indicator of energy consumption of the site. Such a history allows the dynamic evolution of the energy consumption of the site to be taken into account, which improves the precision associated with the prediction of the energy consumption for the prediction horizon. In addition,the indicators representative of the operation of the site may further comprise at least one current value of at least one other indicator of operation of the site than the indicator of energy consumption of the site. Such additional indicators make it possible to improve the precision associated with the prediction of the energy consumption for the prediction horizon. The decision-making regarding the request is thus improved. In addition or as a variant, the prediction of the energy consumption of the site may be based on a predictive model defined by parameters associated respectively with past values ​​of the historical energy consumption indicator and / or at least one current value of at least one other indicator of operation of the site. Thus, it is made possible to weight, by parameters,the contributions of each of the operating indicators in predicting the energy consumption of the site for the prediction horizon, which improves the accuracy of the prediction, and makes it possible to determine a predictive model specific to a given site. In addition, the parameters can be defined by machine learning, from a training data set and a test data set. Thus, the accuracy enabled by the predictive model is improved. In addition, when the training and test data are collected on the site, the predictive model developed is specific to the site. According to embodiments, the operating indicators of the site can be global operating indicators of an entire site. It is thus made possible to directly predict the energy consumption of the overall site, without differentiating between the elements making up the site. Alternatively,the site may operate according to at least one frequency band and / or at least one generation of cellular communication network, and the site operation indicators may be indicators associated with the at least one frequency band and / or the at least one generation of cellular communication network. For example, the site operation indicators may be associated with respective “Remote Radio Units”, RRUs, each RRU corresponding to a group of cells which operate on the same frequency band with different network generations (2G and 3G on the 900 MHz band for example). Thus,a predictive model is provided to determine the energy consumption of each frequency band and / or a network generation and / or an RRU. The energy consumption of the site is then obtained by summing the energy consumption predictions of all the frequency bands and / or network generations and / or RRUs of the site. According to embodiments, if the autonomy of the storage device is less than the required outage duration, the decision may be a refusal of the power outage. Thus, the request for a power outage is refused so as not to degrade the quality of service of users of the cellular radiocommunication network. Alternatively, if the autonomy of the storage device is less than the required outage duration, the decision may be a transmission of a power outage proposal indicating a new outage duration less than the autonomy of the storage device. Thus, load shedding is made possible,but over a shorter period which makes it possible to maintain the quality of service provided to users of the cellular radiocommunication network. As a further variant, the site may operate according to at least one frequency band and / or at least one generation of cellular communication network, and, if the autonomy of the storage device is less than the required outage duration, the decision comprises an acceptance of the power outage for the required outage duration. The method may further comprise, at the time of the power outage: - an activation of the storage device, - a calculation of a time of deactivation of said at least one frequency band or of said at least one generation of network, said calculation being implemented according to a criterion for optimizing the energy stored in the storage device, - a deactivation, at said calculated deactivation time,of said at least one frequency band or said at least one network generation. Such a variant makes it possible to accept more power outage requests, while optimally preserving the storage resources of the storage device, for the duration of the power outage, by scheduling a time for deactivating said at least one frequency band or said at least one network generation of the cellular radiocommunication site. Thus, thanks to this variant, the storage device avoids discharging too quickly, for the benefit, during the power outage, of maintaining the quality of service or QoS perceived by users, whose communications received or transmitted from their communication terminals pass through the cellular radiocommunication site. The site can then be quickly restored to full capacity once the power outage is over. In addition,when said site operates according to at least two frequency bands and / or at least two generations of cellular radiocommunication network, the method may comprise, at the time of the power cut, once the storage device is activated: - a calculation, according to said optimization criterion, of at least two successive instants of deactivation of respectively said at least two frequency bands or of respectively said at least two generations of network, - a deactivation, at said at least two calculated instants of deactivation, of respectively said at least two frequency bands or of respectively said at least two generations of network. Such an embodiment is based on an effective strategy implementing a progressive reduction of the frequency bands or of the generations of cellular radiocommunication network used on the site,thus reducing energy consumption and increasing the time during which the storage device can take over during the power outage. Thus, for example, in the case where a radio site uses four cells, such as for example LTE-2600, LTE-800, 3G-2100 and 2G-900, when a power outage is required with an outage duration greater than the autonomy of the storage device, rather than keeping these four cells active throughout the outage period, the site implements a gradual reduction strategy. At a first moment, it is for example the 2100 MHz frequency band of the 3G-2100 cell which is deactivated, which reduces the consumption of the site and extends the autonomy of the storage device. Other frequency bands can then be gradually deactivated. By following this progressive approach,the radio site extends the duration during which the storage device can support the services, while optimizing the use of the energy stored at the storage device. The invention also relates to a power outage management device in a cellular radio communication site according to claim 12. The power outage management device can be configured to: - receive a request for power outage from the site, the request indicating a required outage duration; - predict an energy consumption of the site for a future prediction horizon, based on indicators representative of an operation of the site; - calculate an autonomy of the storage device of the site based on the prediction of energy consumption of the site; - compare the calculated autonomy of the storage device and the required outage duration; - make a decision on the request,depending on a result of the comparison. Such a device is in particular configured to implement the aforementioned control method, according to one or other of its embodiments. The invention also relates to a computer program comprising instructions for implementing the power outage management method according to the invention, according to any one of the particular embodiments described above, when said program is executed by a processor. Such instructions can be stored permanently in a non-transitory memory medium of the power outage management device implementing the power outage management method according to the invention. This program can use any programming language, and be in the form of source code, object code, or intermediate code between source code and object code, such as in a partially compiled form,or in any other desirable form. The invention also relates to a recording medium or information medium readable by a computer, and comprising instructions of a computer program as mentioned above. The recording medium can be any entity or device capable of storing the program. For example, the medium can comprise a storage means, such as a ROM, for example a CD ROM or a microelectronic circuit ROM, or a magnetic recording means, for example a mobile medium, a hard disk or an SSD. On the other hand, the recording medium can be a transmissible medium such as an electrical or optical signal, which can be conveyed via an electrical or optical cable, by radio or by other means, so that the computer program it contains is remotely executable. The program according to the invention can in particular be downloaded over a network,for example an Internet-type network. Alternatively, the recording medium may be an integrated circuit in which the program is incorporated, the circuit being adapted to execute or to be used in the execution of the aforementioned power outage management method. According to an exemplary embodiment, the present technique is implemented by means of software and / or hardware components. With this in mind, the term "device" or "module" may correspond in this document to a software component, a hardware component or a set of hardware and software components. Brief description of the drawings Other characteristics and advantages will appear on reading particular embodiments of the invention, given as illustrative and non-limiting examples, and the appended drawings,among which: - Figure 1 represents an architecture in which the method for managing a power outage of a cellular radiocommunication network is implemented, according to a particular embodiment of the invention, - Figure 2 represents a device for managing a power outage of a cellular radiocommunication network, according to an embodiment of the invention; - Figure 3 represents the main steps implemented in the method for managing a power outage, according to an embodiment of the invention, as implemented in the architecture of Figure 1; - Figure 4 represents a device for controlling the consumption of a cellular radiocommunication network during a power outage, according to a particular embodiment of the invention; - Figure 5 represents additional steps for controlling the consumption of the cellular radiocommunication network,implemented in the method for managing a power outage of a radiocommunication network, according to a particular embodiment of the invention; - Figure 6 represents a curve of the evolution, in a real situation, of the energy consumption of an element of the cellular radiocommunication network, as a function of time; - Figure 7A represents the main actions implemented during one of the complementary steps of the method for managing a power outage of a cellular radiocommunication site, as illustrated in Figures 3 and 5, according to one embodiment; - Figure 7B represents the main actions implemented during one of the complementary steps of the method for managing a power outage of a cellular radiocommunication site, as illustrated in Figures 3 and 5,according to another embodiment; - Figure 8 represents a schematic curve illustrating the strategy for deactivating RRUs of the cellular radiocommunication network, in accordance with the other embodiment of Figure 7B. Detailed description of an embodiment of the invention Figure 1 represents an architecture in which a method for managing a power outage PO is implemented in the context of voluntary load shedding, according to an embodiment of the invention. Such an RC network is for example of the 3G, 4G, 5G, etc. type. Such an architecture comprises: - a power outage management device DIS,configured to receive a power outage request REQ from a site S installed at a given geographical location and comprising the equipment necessary for the transmission and reception of communication data via the RC network. The request REQ is received as part of voluntary load shedding and can identify a time of start of outage t0 as well as a required outage duration Te. The request REQ is received, prior to the power outage PO, from an entity EN_PR which may be a management entity of an electricity network in charge of supplying electricity to the site S, or which may belong to an aggregator, which is an intermediary between actors who have load shedding capabilities and the manager of the electricity network; - an energy storage device STO capable of storing energy in a given form, and of restoring electrical energy, on command,at site S. The storage device STO may for example be an electric battery. Alternatively, the storage device STO may be a generator, an inertial flywheel, or any other storage device capable of storing energy in a given form and of restoring electrical energy on command. The maximum value of the energy stored in the storage device STO is noted Emax. Before the power cut PO (or during reception of the request REQ), the energy stored in the storage device STO has an initial value E0, which is less than or equal to Emax. According to certain embodiments of the invention,the architecture may optionally comprise: - a calculation device DME configured to estimate the total energy consumed by the site S; - a device DCC configured to control the energy consumption of the site S during a power outage PO. The devices DME and DCC are described in the following with reference to certain embodiments of the invention. According to the invention, the outage management device DIS is configured to predict the energy consumption PR of the site S over a future period of duration ^^ for a prediction horizon H (i.e. expiring with a duration H in the future after a current instant),and to deduce therefrom a maximum duration Δ^^ during which the storage device STO can serve the site S before the device STO is completely discharged. The maximum duration Δ^^ thus corresponds to the autonomy of the storage device STO. From the deduced maximum duration Δ^^ and from the required outage duration Te indicated in the request REQ coming from the entity EN_PR, the outage management device DIS is configured to take a decision DEC to accept or not the power outage PO, the decision DEC being transmitted in return to the entity EN_PR, and being described in the following. The outage management device DIS is for example a server, a platform, for example of the CSON type (“Centralized - self-organizing networks” in English), intelligent controller RIC (“Radio access network Intelligent Controller” in English) or OSS (“Operations Support System” in English),etc. It can be installed on site S or remotely. Site S is composed of K elements EL1, EL2, …, Ek, …, ELK of the same nature. The RC network being a cellular radiocommunication network, the K elements EL1, EL2, …, ELK can be respectively K different frequency bands, for example 1800 MHz and 2100 MHz or at least two different generations of cellular network, for example 3G and 4G, in the case for example where K=2. The elements EL1 to ELK can also be K RRUs (in English "Remote radio Unit") each operating on a different frequency band. Conventionally, an RRU corresponds to a group of cells which operate on the same frequency band with different network generations (2G and 3G on the 900 MHz band for example). We will now describe, with reference to Figure 2,the simplified structure of the DIS outage management device. The DIS outage management device comprises: - a first communication interface COM1 configured to communicate, via the RC network of figure 1 or another network, with in particular the DME calculation device and the DCC device; - a second communication interface COM2 configured to communicate, via the RC network or another network, with the EN_PR entity described previously; - a module COL1 for collecting DR data relating to the operation of said RC network, including in particular indicators representative of the operation of the site S; - a module COB1 for controlling activation / deactivation of the STO storage device; - a module PRED1 for predicting the PR energy consumption of the site S for a prediction horizon H,according to the indicators representative of the operation of the site S included in the data DR; - a module CALC1 for calculating the maximum duration Δ^^ described previously, during which the storage device STO can serve the site S before the device STO is completely discharged, according to the energy consumption PR for the prediction horizon H; - a module COMP1 for comparing the maximum duration Δ^^ and the required outage duration Te; - a module DEC1 for making a decision DEC according to the result of the comparison from the module COMP1. At initialization, computer program code instructions PG1 are for example loaded into a RAM memory (not shown) before being executed by a processor PROC1 of the outage management device DIS. The processor PROC1 of the processing unit UTR1 notably implements the following actions, within the framework of the method for managing the power outage of the site S,which will be described below, according to the instructions of the computer program PG: - receive, from the entity EN_PR, the request REQ requesting a power outage and indicating a required outage duration Te as well as an outage time t0; - collect the data DR relating to the operation of the network RC, in particular of the site S; - receive from the storage device STO, the value of the energy E0 stored before the power outage PO; - predict the energy consumption PR of the site S for the prediction horizon H; - calculate the maximum duration Δ^^, or autonomy, described previously; - compare the maximum duration Δ^^ and the required outage duration Te; - take the decision DEC, based on the comparison between the maximum duration Δ^^ and the required outage duration Te; - transmit the decision DEC, following receipt of the request REQ,to the entity EN_PR; - control the activation of the storage device STO according to the decision DEC. Optionally, according to certain embodiments, and according to the decision DEC, the power outage management device DIS is configured to transmit the energy consumption prediction PR for the horizon H and the required power outage duration Te, to the control device DCC. We now describe, in relation to FIG. 3, together with FIGS. 1 and 2, the sequence of a method for managing a power outage of the cellular radiocommunication network, according to a particular embodiment of the invention. Such a power outage may for example be requested by the entity EN_PR in the request PR. In a step 300, the power outage management device DIS receives the request REQ from the entity EN_PR, the request REQ requesting a power outage PO of the site S, in the context of voluntary load shedding, the request REQ indicating the required power outage duration Te,and the outage time t0. In a step 301, the outage management device DIS receives, or collects, the operating data DR of the RC network, comprising indicators representative of the operation of the site S, at a current time, which is prior to the time t0 indicated in the request REQ. Such DR data may comprise raw indicators relating to the operation of the RC network, in particular of the site S, such as for example the number of resources occupied per cell covered by the site S, the quantity of data sent via the RC network, etc. Alternatively, such DR data may comprise performance indicators or KPIs relating to the RC network, in particular to the site S, such as for example, depending on the cellular network generation considered 2G, 3G, 4G, 5G, etc.: the traffic volume, the throughput for each cell, the average number of users for each cell, the cell load,etc. The energy consumption KPI is also collected by the outage management device DIS. Conventionally, such an energy consumption KPI is available for the radio site S, for each of the frequency bands or network generations of the radio site S. The KPIs are sent back to the DIS device with a granularity ^^ which is variable depending on the context of the modeling, which can for example be a time interval of 15 min, 30 min, 1 hour, etc. In a step 302, the outage management device DIS predicts the energy consumption PR of the site S for a prediction horizon H, from the indicators representative of the operation of the site S collected in the previous step 301. Steps 301 and 302 can be implemented in parallel with step 300 of receiving the request REQ. Thus, the request REQ can be received after the prediction step 302,as long as the required outage duration Te is less than a remaining duration before the end of the prediction horizon H, when the prediction horizon starts at the current time (the implementation of step 301). Alternatively, steps 301 and 302 are implemented following the reception of the request REQ in step 300. In the following, an example of prediction of the energy consumption PR of the site S for the prediction horizon H is described, for illustrative purposes. In this example, the prediction PR is a prediction of the total energy consumption of the site S. The prediction PR is based on ^^, ^^KPIs collected in step 301, which are denoted in which ^^ corresponds to a time index, in which 1 ≤ ^^ ≤ ^^^^ denotes an index of the KPI and in which the superscript (^^) refers to the entire site S. As previously indicated, the site S consists of ^^ RRUs, each RRU corresponding to a group of cells that operate on the same frequency band with different network generations (2G and 3G on the 900 MHz band for example). Step 302 may also comprise the prediction of the energy consumption of each RRU. For an RRU 1 ≤ ^^ ≤ ^^, ^^^^ KPIs are obtained in step 301, which are denoted in which ^^ corresponds to the time index, in which 1 ≤ ^^ ≤ ^^^^ denotes the KPI index and in which the exponent ( ^^ ) refers to the ^^ ^^è^^^^RRU of site S. For example, the KPIs considered may be any combination of the following indicators: - For 2G network generation: traffic volume and throughput for each cell; - For 3G network generation: traffic volume, throughput and average number of users for each cell; - For 4G network generation: traffic volume, cell load and average number of users for each cell. In this example, no indicator is considered for 5G network generation. However, according to the invention, indicators relating to 5G network generation may be taken into account for the prediction of the energy consumption PR of step 302.In addition, an energy consumption KPI is generally available per radio site and per RRU, which allows access to a current energy consumption value of the site and / or each RRU, but also to store a history of the energy consumption of the site S and / or each RRU. Such an energy consumption KPI is noted ^^(^^) (^^) ^. ^ for the entire S site and ^^ ^^ for the ^^ ^^è^^^^ RRU, in which ^^ refers to the time index of the measurement. As previously stated, all KPIs can be collected by the DIS outage management device with a granularity of ^^ (^^ = 15, 30, 60 min etc.). Thus,^^ ( ^^ ) ^ ^ , respectively ^^(^^) ^ ^, corresponds to the energy consumption of site S, respectively of the RRU, during the reference period ^^. To take into account the granularity of implementation of step 301, the index ^^ in the different KPIs is incremented every period ^^. Thus, if the value of the index ^^ = 10, then the measurements were taken at time ^^ = 10 ^^, expressed in minutes or hours. The prediction at the current time index ^^ (the current time of step 301) of the future energy consumption PR for a horizon ^^ = ℎ × ^^ , that is to say for a horizon ending at the time index ^^ + ℎ, is carried out by considering a history of the energy consumption (of the site S and of each RRU) as well as the current values ​​at time i of the KPIs according to the following prediction models: For the entire radio site For the ^^ ^^è^^^^ RRU In which (^^ (^^)^^+1−^^ , … , ^^(^^)^^ ) with (^^) = (^^) or (^^) is the history of the previous energy consumption values ​​of the site S or of the RRU of index k, the history being made up of ^^ previous measurements. To take into account the granularity of collection of the measurements of step 301, the prediction horizon H is preferably a multiple of ^^. If ℎ = = 60 ^^^^^^, then the prediction horizon ^^ = 60 ^^^^^^. If ℎ =4 ^^^^ ^^ = 30 ^^^^^^, then ^^ = 120 ^^^^^^ , etc. The prediction horizon H (and therefore the value h) can be determined from the cut-off time t0 indicated in the query, so as to estimate the energy consumption in a future period of duration ^^ including the cut-off time t0. In (1) and (2), the parameters are unknown, but can be obtained during a preliminary training phase, not shown in Figure 3. The preliminary phase may include machine learning of the parameters, based on an artificial intelligence-based technique such as linear regression, LASSO regression (for "Least Absolute Shrinkage and Selection Operation"), or any other technique. Machine learning can be performed on a training database, storing values ​​^^ (^^) and ^^ (^^), as well as (^^) ^^−^^ ^^,^^e the corresponding target values ​​^^ ^^+ℎ (the ground truth). Thus, during the learning phase, the future value ^^ (^^) ^ ^+ℎ (for the prediction horizon ℎ × ^^ ) is considered as the variable of interest. The history of energy consumption ^^ ( ^^ ) and the vale ( ^^ ) ^ ^−^^ current values ​​of other KPIs ^^ ^^,^^are predictor variables as shown in Table 1 where ^^ is the number of observations used during the training phase, i.e. the number of datasets in the training database. Predictor Variables Variable of Interest ^^ ( ^^ ) 1 ,1 … ^^ ( ^^ ) ( ^^ ) 1 ,^^^^ ^^ 2−^^ … ^^ ( ^^ ) ( ^^ ) 1 ^^ 1+ℎ ^^ ( ^^ ) ^^ ^^ ^^ ^ 2,1 … ^^ ( ) ( ) 2 ,^^^^ ^^ 3−^^ … ^^ ( ) 2 ^^ ( ^ ) 2 +ℎ . . . . . . . . . . . . . . . ^^ (^^) (^^) (^^) (^ ) ( ) ^ ^ … ^^ ^^ ^^ … ^^^ ^^ ^^ ,1 ^^,^^ ^^+1−^^ ^^ ^^+ℎTable 1 However, no restrictions are attached to the way in which the parameters are determined … , ), which can be obtained by a technique other than a technique based on machine learning. Following learning, the DIS cut-off management device stores the parameters ^^ and (^^ (^^) 1 , ^^(^^)2 , … , ) trained, and is thus able to implement, by the prediction module PRED1, a prediction of the energy consumption of the site S, or RRU by RRU. For the entire radio site, we obtain: The obtained value ^̂^ (^^) ^ ^+ℎ is a prediction of the energy consumption of site S (therefore corresponding to PR) over a period ^^ for the prediction horizon H, i.e. for a period of duration ^^ expiring at the end of the prediction horizon H. For the ^^ ^^è^^^^ RRU, we obtain: The obtained value ^̂^ (^^) ^ ^+ℎis a prediction of the energy consumption of the k-th RRU over a period ^^ for the prediction horizon H. According to a first embodiment of the invention, the power cut management device DIS stores the predictive model corresponding to equation (1) in the prediction module PRED1 described previously. The application of the model to the history of the energy consumption of the site S and to the current values ​​of the other thus makes it possible to predict the energy consumption PR of the site S over the period ^^ for the prediction horizon H. According to a second embodiment, the power cut management device DIS stores the predictive model corresponding to equation (2) for each RRU of the site S, and the prediction of energy consumption PR of the site S over the period ^^ for the prediction horizon H can be obtained by summing all the individual predictions ^̂^ (^^) ^ ^+ℎK RRUs of site S. According to another embodiment not described, the cut-off management device DIS stores a model for predicting the energy consumption for each network generation (2G, 3G, 4G, 5G for example) on site S, and the prediction of energy consumption PR of site S for a duration for the prediction horizon H can be obtained by summing all the individual predictions of the network generations of site S. The predictive models described above were tested, after parameter learning, on a set of real test data of a cellular radiocommunication network, for a prediction horizon H, with a granularity value ^^ of 60 minutes, and a horizon H of also 60 minutes (thus with h=1), in the case where the outage would occur at the outage time t0 which is less than one hour after the current time of index i. The test period includes data between 10 a.m. and 5 p.m. of a day d. The parameter learning period includes the two days preceding day d. A learning model is created per site for the predictive model (1) and per RRU for the predictive model (2).The results show that the predicted energy consumption values, per site or per RRU, are very close or even identical to the actual energy consumption values. A second experiment was conducted to evaluate the performance of the predictive model (2) per RRU as a function of the absolute value of the relative error RE, between the actual energy consumption values ​​from the test data and the predicted energy consumption values ​​obtained from the predictive model (2): actual − predicted value|. . actual value Table 2 below gives the obtained results expressed as a rate (or probability or percentage) that RE is less than 15% for several values ​​of the prediction horizon. Table 2 shows that the error on the prediction of the energy consumption per RRU is low. Table 2: Prediction horizon ^^ = 120 ^^^^^^ ^^ = 180 ^^^^^^ ^^ = 240 ^^^^^^Percentage that 91% 86% 81% RE<15% Thus, the predictive models (1) and (2) are particularly suitable for predicting the energy consumption of a site or an RRU, based on radio KPIs such as traffic, throughput, load and the number of active users.Referring again to Figure 3, the outage management method further comprises, following steps 300 to 302, a step 303 of calculation by the calculation module CALC1 of the maximum duration Δ^^ during which the storage device STO can serve the site S before the STO device is completely discharged, from the prediction of the energy consumption PR of the site S for the horizon H. In particular, the maximum duration Δ^^, or autonomy, is calculated from the value E0 of the energy stored in the storage device STO and the prediction of the electrical consumption PR of the site S during the period ^^ for the prediction horizon H. For example, the calculation module CALC1 applies the following formula to determine the maximum duration Δ^^:. We remind you that ^̂^ (^^) ^ ^+ℎis the prediction of the energy consumption resulting from the predictive model (1) or (2) over a period ^^ for the prediction horizon H. Alternatively, Δ^^ may be reduced by X% compared to the result obtained from the formula above, for example 10%, in order to take into account possible errors in the prediction. In a step 304, the comparison module COMP1 of the outage management device DIS is able to compare the maximum duration Δ^^ with the required outage duration Te in the request REQ. Depending on the result of the comparison, the decision module DEC1 is able to take a decision DEC, which is returned to the entity EN_PR in response to the request REQ. If the maximum duration Δ^^ is greater than the required outage duration Te, then the decision DEC may be an acceptance of the request REQ.The power outage management device therefore accepts the power outage PO at a step 305, and can activate the storage device STO following the power outage during this step 305. If the maximum duration Δ^^ is less than the required power outage duration Te, the power outage management device DIS can take one of the following decisions DEC: - either refuse the request REQ during a step 306; - or conditionally accept the request REQ, replacing the required power outage duration Te with a new duration less than the maximum duration Δ^^, during a step 307.In this case, the power cut management device DIS can transmit a power cut duration proposal indicating the new duration less than the maximum duration Δ^^; - either accept the request REQ during a step 308, then transmit, during a step 309, the required power cut duration Te, which has been accepted, to the control device DCC for implementation of the additional steps of the power cut management method, described with reference to the following figures, in particular to figure 5. The control device DCC and the calculation device DME are now described. As a reminder, such devices are optional, and are advantageous in the embodiments where the decision according to steps 308 and 309 is taken by the power cut management device DIS.According to these embodiments, the DCC control device is in particular configured to activate the storage device STO at the time of the power outage PO and to calculate, optimally from a quality of service point of view and in a single pass, K instants of deactivation of respectively K elements EL1, EL2, …, Ek, …, ELK of the same nature which make up the site S, such that 1≤k≤K. The DCC device is for example a server, a platform, for example of the CSON type (“Centralized - self-organizing networks” in English), intelligent controller RIC (“Radio access network Intelligent Controller” in English) or OSS (“Operations Support System” in English), etc. It can be installed on the site S or remotely. According to the invention, the DME calculation device is an artificial intelligence module which generates a mathematical modeling of the energy ^^. ^^consumed on site S, from the collection of DR data relating to the operation of the RC network. Such generation is implemented at time t0 at the start of the power outage, or just before such a time (for example a few minutes before t0), so as to have the most recent DR data. The DME calculation device is configured to transmit to the DCC calculation device the energy ^^ ^^ estimated according to the aforementioned modeling. Note that the energy ^^ ^^ corresponds to the energy consumed on the site at the time of the estimate, and is different from the energy consumption predictions implemented by the prediction module PRED1 of the power cut management device DIS. According to the invention, the DCC calculation device is configured to:- calculate K deactivation times Δ^^1, Δ^^2, … , of respectively the K elements EL1, EL2, …, ELK, as a function of the energy ^^ ^^ , of the value of energy ^^ ^^stored in the storage device at the time of the PO outage, the duration Te of the power outage, as well as DR data relating to the operation of the RC network, collected in a time interval preceding the PO outage, - control the deactivation of the K elements EL1, EL2, …, ELK, respectively at said K calculated deactivation times. We will now describe, with reference to Figure 4, the simplified structure of the DCC control device.The DCC device comprises: - a communication interface COM configured to communicate, via the RC network of figure 1 or another network, with in particular the calculation device DME, the cut-off management device DIS, and the site S, - a module COL for collecting data DR relating to the operation of said RC network, - a module COB for controlling activation / deactivation of the storage device STO, - a module CAL for calculating K deactivation instants Δ^^1, Δ^^2, … , Δ^^^^ or ^^1, ^^2, … , of respectively K elements EL1, EL2, …, ELK of the same nature which make up the site S, - a module COE for controlling the deactivation of the K elements EL1, EL2, …, ELK, at said K calculated deactivation instants. At initialization, the code instructions of the computer program PG are, for example, loaded into a RAM memory (not shown) before being executed by the processor PROC.The processor PROC of the processing unit UTR notably implements the following actions, within the framework of the complementary steps of the outage management method, which will be described below with reference to FIG. 5, according to the instructions of the computer program PG: - receive, from the outage management device DIS, information IPO indicating a power outage PO of the site S, as well as the duration Te of the power outage, accepted from the entity EN_PR during step 308; - command the activation of the storage device STO, such an activation capacity is optional, since the outage management device can itself activate the storage device STO when accepting the request REQ in step 308; - receive, from the calculation device DME, an estimated value of the energy ^^. ^^consumed by site S before the power outage PO, and / or receive, from the power outage management device DIS, the predicted energy consumption PR of site S; - receive, from a communication terminal associated with site S or from the storage device STO if the latter is equipped with a dedicated communication module, the value of the energy ^^ ^^stored in the storage device STO at the time of the power outage PO; - collect data DR relating to the operation of said RC network, - calculate K deactivation times Δ^^1, Δ^^2, … , Δ^^^^ or ^^1, ^^2, … , ^^^^ of respectively K elements EL1, EL2, …, ELK of the same nature which make up the site S. Optionally, the control device DCC is configured to: - control the deactivation of the storage device STO after power restoration, - control the activation of the K elements EL1, EL2, …, ELK, after power restoration. We now describe, in relation to Figure 5, together Figures 1 and 4, the complementary steps of a power outage management method, according to a particular embodiment of the invention following the decision of steps 308 and 309 described previously. The complementary steps may comprise a step S0 of estimating the energy ^^ ^^consumed on site S, from the collection of DR data relating to the operation of the RC network. Such a phase is implemented by the DME calculation device at the time of the outage, at the outage instant t0. These are therefore not the same DR data as those used in formulas (1) and (2) to predict the energy consumption of site S during the steps of Figure 3. The DR data correspond to the data collected for the instant t0 of the outage or shortly before the instant t0. As explained previously, the DR data may include raw indicators relating to the operation of the network, such as for example the number of resources occupied per cell covered by site S, the quantity of data sent via the RC network, etc. Alternatively, such DR data may include performance indicators or KPIs relating to the RC network, such as for example, depending on the generation of cellular network considered 2G, 3G, 4G, 5G, etc.: traffic volume, throughput for each cell, average number of users for each cell, cell load, etc. The energy consumption KPI is also collected by the DME computing device. Typically, such an energy consumption KPI is available for radio site S, for each of the frequency bands or network generations of radio site S. The KPIs are collected with a granularity of ^^ which is variable depending on the modeling context, for example a time interval of 15 min, 30 min, 1 hour, etc. The goal of the S0 phase is to accurately and reliably model the energy consumption ^^. ^^using an artificial intelligence technique. The accuracy of the modeling is crucial to avoid unwanted service interruptions. By having an accurate estimate of the power consumption, the strategies for deactivating the K elements EL1, EL2, …, ELK which will be detailed later in the description will be particularly suitable for selectively deactivating certain network generations or certain frequency bands, starting with those which are the least critical for QoS. According to the invention, the DME calculation device uses for the modeling of the energy consumption ^^ ^^a linear regression method, for example the LASSO method (in English, "Least Absolute Shrinkage and Selection Operator"), Ridge, etc. In the embodiment described below, it is the LASSO method which is considered, this type of method being particularly well adapted to the processing of indicators representative of the operation of the site, whether KPIs, or raw indicators (number of resources occupied per cell, quantity of data sent via the network, etc.). The LASSO regression which links the variable of interest, which is here the energy consumed ^^ ^^ , with the explanatory variables, which are here the KPIs or the raw indicators mentioned above, is expressed as follows: where: - ^^ ^^ is the total energy consumed by site S, - ^^ 1,^^corresponds to the energy consumed when there are no users on the radio site and therefore no traffic, - ^^ corresponds to a generation of cellular network used on site S, - ^^(^^) corresponds to a set of different frequency bands used on site S and corresponding to the generation of network ^^, - ^^(^^) is the number of KPIs considered for the generation of network ^^, - ^^ ^^,^^ is a linear regression coefficient that is trained in relation to an ith frequency band considered for a network generation ^^, such that 1≤i≤ ^^(^^), and for a jth KPI considered, such that 1≤j≤ ^^(^^). Note that the linear regression coefficients ^^ ^^,^^ are different from the coefficients ^^ ^^determined for the predictive models (1) and (2) described previously. In the example shown, three generations of network 2G, 3G, 4G are considered, such that ^^ ∈ {2,3,4}. It goes without saying that this number can be less than 3, for example 3G or 3G and 4G, or greater than 3, for example 2G, 3G, 4G, 5G. The expression of the energy consumed per generation of network ^^ is represented in the following form: where ^^ ^^^^ is the energy consumed when data traffic is zero or very low, as is the case for example at night. The expression of the energy consumed by a considered RRU ^^ or a considered frequency band ^^ is represented in the following form: where ^^ 1,^^represents the intercept which is a fixed value of the energy consumed for the RRU or the frequency band ^^. In a manner known per se, such a linear regression is subjected to a Lasso regularization which is a regularization technique to penalize the coefficients ^^ ^^,^^,^^ (expression (3)), ^^ ^^,^^ (expression (4)), ^^ ^^,^^ (expression (5)) of less important features, by bringing these coefficients to zero. Thus, Lasso regularization adds a penalty proportional to the absolute value of the coefficients to the loss function. Such regularization is applied during the processing of the model and when it processes new samples by going from i to i+1. Modeling the energy consumed ^^ ^^ , ^^ ^^^^ , ^^ ^^, according to the Lasso regression above is implemented based on a set of real data (KPIs or raw indicators mentioned above) collected according to a time interval ^^ , where, as a non-exhaustive example, ^^ = 60 min, according to this modeling. The performance indicator RE of the modeling of the consumed energy is expressed according to the relation (6) below, in the form of a ratio between the difference in absolute value of the real value of ^^ ^^ , ^^ ^^^^ or ^^ ^^ , and the estimated value of ^^ ^^ , ^^ ^^^^ or ^^ ^^ , and the actual value of ^^ ^^ , ^^ ^^^^ or ^^ ^^ , that is to say the relative error RE between the real and estimated values ​​of ^^ ^^ , ^^ ^^^^ or ^^ ^^ : Training the energy consumption estimation model ^^ ^^ , ^^ ^^^^ , ^^ ^^was performed for different metrics: mean RE(%) which represents the average of the RE values ​​over all test samples, RE<15% which represents the probability (or rate) that the RE value is less than 15% over all test samples, RE<10% which represents the probability (or rate) that the RE value is less than 10% over all test samples, considering the estimation of ^^ ^^ consumed by site S, the estimate of ^^ ^^^^ consumed for each of the 2G, 3G, 4G network generations and the estimate of ^^ ^^for an RRU operating at a low frequency, for example 800 MHz or 900 MHz, or a high frequency, for example 2100 MHz or 2600 MHz. The results of this training, as shown in Table 3 below, show that the error in the energy estimation is low, whether this energy is estimated per site, per network generation or per frequency band. Table 3: Relative error on the estimation of the consumed energy Site S 2G 3G 4G RRU Mean RE (%) 5.98 2.61 7.98 6.07 6.53 RE<15% (%) 97.83 100 90.83 99.57 96.92 RE<10% (%) 92.3 97.45 79.19 97.09 84.17 The results shown in Table 3 show that the error on the energy estimation is low. Thus, the modeling of the energy estimation based on the aforementioned Lasso regression is robust to accurately estimate the energy consumption based on the aforementioned KPIs or raw indicators.Lasso regression, which incorporates a regularization term as defined above, is particularly effective in dealing with multicollinearity of predictive values ​​of raw KPIs or indicators, i.e., the high correlation between these predictive values. In the context of the aforementioned modeling, based on linear regression with several raw KPIs or indicators, including traffic, with some raw KPIs or indicators being predominant compared to other considered raw KPIs or indicators, Lasso regression introduces a penalty term according to which some regression coefficients, trained for non-dominant raw KPIs or indicators, are pushed to reach exactly zero. Such a penalization is notably described in the paper PK Matthew, FA Chama, and NS Agog, “Penalization Techniques for Remedying Multicollinearity in Multiple Regression Model” KASU Journal of Mathematical Science, vol.3.1, pp.41-49, 2022.Thus, when Lasso regression is applied to a set of raw KPIs or indicators, it is likely to identify and retain one or more of the most relevant raw KPIs or indicators, for example the "traffic" KPI or the "amount of data sent" raw indicator, while forcing the regression coefficients associated with the least relevant or highly correlated raw KPIs or indicators to be zero. This not only improves the interpretability of the model, but also improves its performance by focusing on the most informative explanatory variables. We now describe, with reference to Figure 6, a curve representing the evolution, in a real situation, of energy consumption, for example per RRU, as a function of time and over several days "Day 1", "Day 2", "Day 3", "Day 4".It is found that the fixed value of energy, which does not depend on traffic, is quite high compared to the consumption linked to traffic. The accuracy of the intercept value ^^ is also found. 1,^^ in equation (5), since late at night, users do not transmit data via their mobile terminals and the energy consumed corresponds to ^^ 1,^^ . On the other hand, we notice that ^^ 1,^^ exceeds half of the energy consumption. Of course, correspondingly, the evolution, in real situations, of the energy consumption, per site S or generation of cellular radiocommunication network, as a function of time and over several days, can also be obtained to verify the accuracy of the values ​​^^ 1,^^ and ^^ ^^^^The representative curve in Figure 6 gives an indication of the deactivation strategy to be implemented, although the curves representing the evolution, in real situations, of the energy consumption, by site S or generation of cellular radiocommunication network, as a function of time and over several days, have not been shown. Indeed, this curve shows that it is not recommended to proceed with a cell-by-cell extinction of the RC network. Indeed, if one cell, for example 3G-2100 MHz, is deactivated, then another cell, for example 3G-1800 MHz, then yet another cell, for example 4G-2100 MHz, the energy management of the STO storage device is not optimal. The RRU operating at the 2100 MHz frequency remains functional even when the 3G-2100 MHz cell is deactivated, because the other 4G-2100 MHz cell is still switched on.This means that the fixed part of the RRU (intercept) still consumes energy even after the 3G-2100 MHz cell has been deactivated. And the intercept consumes a lot of energy. The optimal strategy to favor is to deactivate RRU by RRU or frequency band by frequency band, to save the energy of the fixed part, once the RRU is deactivated. Referring again to Figure 5, once the preliminary phase S0 of energy estimation ^^. ^^consumed on the site S has been implemented, the storage device STO is activated in S1 when the power outage PO begins following acceptance of step 308. The activation S1 is implemented by the aforementioned COB module of the control device DCC. Alternatively, step S2 can be implemented by the power outage management device DIS during step 308, in which case steps 308 and S2 are combined. The detection of the power outage PO can for example comprise a reception by the control device DCC, via its communication interface COM, of information IPO indicating the power outage PO, from the power outage management device DIS. The method continues by implementing, in S2, a calculation of K deactivation instants Δ^^1, Δ^^2, … , … , ^^^^ of respectively said K elements EL1,EL 2 , …, EL Kof the same nature which make up the site S. The calculation S2 is implemented by the aforementioned CAL module. In S3, said K elements EL1, EL2, …, ELK are then deactivated respectively at said K deactivation times Δ^^1, Δ^^2, … , Δ^^^^ or calculated, using the aforementioned COE control module. Step S3 can be implemented for a single element (K=1), in the case where the site S only comprises one frequency band or one network generation, as well as for several elements, i.e. at least two elements of the same nature. Thus, the complementary steps S0 to S3 which have just been described above can of course be applied to two, three, four, five etc. different frequency bands, different RRUs or different cellular radiocommunication network generations, which implies the calculation in S2 of respectively two, three, four, five, etc. deactivation times Δ^^2, Δ^^3, Δ^^4, Δ^^5, etc. or ^^2, ^^3, ^^4, ^^5, etc. We now describe, with reference to FIG. 7A, an embodiment of the step S2 of calculating said K deactivation instants Δ^^1, Δ^^2, … , Δ^^^^ .According to this embodiment, the calculation step S2 is implemented so as to maximize one of the aforementioned KPIs or raw indicators, for example according to the data volume, the amount of data sent via the RC network, etc. during the power outage PO. The first embodiment will be described by considering the maximization of the data volume passed by RRU of the radio site S. It is considered that the radio site S operates with ^^ RRUs, where K≥1 and (Δ^^1, Δ^^2, … , Δ^^^^) are the switching-off times of the ^^RRUs. According to the embodiment shown, the DCC control device is configured to determine the optimal switching-off times ∆^^1. ∗ , ∆^^2 ∗ , …, ∆^^ ^ ∗^ allowing to maximize the volume of traffic carried during the duration Te of the power outage PO. A set of data relating to the operation of the radio site S, as used in the calculation S2 comprises the following data: - ^^0 the energy stored in the storage device STO at the time of the power outage PO, - Te the duration of the power outage PO, indicated by the power outage management device DIS; - ^^^^ = ^^^^,2^^ + ^^^^,3^^ + ^^^^,4^^ the volume of traffic carried at the time of the power outage PO, for a kth RRU among K, during a time interval ^^ , where^^ ^^,^^^^ is the KPI corresponding to the volume of traffic of the network generation nG collected at the time of the outage, where ^^ is for example such that 2 ≤ ^^ ≤ 4.- ^^ ^^the total energy consumed by the site S, as estimated at S0. For this purpose, the method comprises, at the time of the power cut PO, a reception step S20, during which the control device DCC receives, via its communication interface COM: - an estimated value of the energy ^^ ^^ consumed by site S before or during the power cut PO at time t0, from the DME calculation device, - an energy value ^^ ^^ stored in the storage device STO at the time of the power outage PO, coming from a communication terminal associated with the site S or from the storage device STO if the latter is equipped with a dedicated communication module, - a value of the duration Te of the power outage PO, coming from the power outage management device DIS. Of course, as an alternative, the estimated value of the energy ^^ ^^ , the value of energy ^^ ^^and value of the duration Te of the power outage PO can be received simultaneously or each at different times. The method further comprises, at the time of the power outage PO, a step S21 of collecting data DR relating to the operation of said RC network, such as the value of the traffic volume ^^^^ = ^^^^,2^^ + ^^^^,3^^ + ^^^^,4^^, in the example shown, indicators of energy consumption associated with the k-th RRU, etc. During a step S22, the calculation module CAL solves the following optimization problem (7): subject to ∑^^ ′ ^^=1 ^^^^ ≤ ^^0,(7)∆^^^^ ≥ 0, for 1≤k≤K,^^ ^^ ≤^^ ^^,^^ , for 1≤k≤K,where ^^^^ = ^^^^,2^^ + ^^^^,3^^ + ^^^^,4^^ to be optimized here corresponds to the amount of traffic transmitted by the k-th RRU during the reference time interval ^^ and ^^ ^^,^^^^corresponds to the KPI of the traffic quantity of the k-th RRU of the network generation ^^^^ , in equation (5). Thus, ^^ is the total number of bits passed by the k-th RRU during the PO power outage. Note that if one or more RRUs is / are deactivated, its users will switch to the other RRUs still active. This results in a new distribution of traffic and users on the remaining bands after the deactivation of one or more RRUs. Thus, ^^ ^^ may vary due to traffic transfer from a powered-off RRU to another powered-on RRU. Furthermore, in optimization problem (7) above: - ^^ ^^ is the amount of traffic of the k-th RRU that is collected at the time of PO power outage, - ^^ ^^,^^ is the maximum amount of traffic that the k-th RRU can support, the maximum amount of traffic being obtained from the data collected in S21, - ^^ ^^is the corresponding energy consumed during the reference time interval ^^, is the energy consumed by the k-th RRU during Δ^^ ^^ , from the start of the PO power outage, when this k-th RRU transmits ^^ ^^ bits instead of ^^ ^^ , where ^^ ^^,^^ is the energy consumed when the k-th RRU transmits ^^ ^^ bits during the reference time interval ^^. ^^ ^^,^^ is calculated by considering the above expression (5) and using ^^ ^^,^^^^ instead of ^^ ^^,^^^^ . Remember that ^^ ^^,^^^^ and ^^ ^^,^^^^are used in (5) as the traffic KPIs of the technology ^^^^. For other KPI values ​​to be used in expression (5), it is sufficient to assume that they change proportionally in the same way as the traffic KPI or to create a learning model that links each KPI to the traffic. In order to solve the optimization problem (7), an energy efficiency metric, measured in bits / Joule, is defined for each RRU. For a k-th RRU, the energy efficiency metric, denoted ^^ ^^ , is expressed as follows: Without loss of generality, we assume for this approach that ^^1 ≥ ^^2 … ≥ ^^^^. Thus the calculation of ^^1 ≥ ^^2 … ≥ ^^^^ defines a priority order in which to successively deactivate the K elements by first deactivating the element ELK with the lowest energy efficiency and last deactivating the element EL1 with the highest energy efficiency. Note that ^^ ^^is not constant and varies from measurement to measurement in reality. However, from several experiments based on a real data set, it is found that when ^̅^ ^^ (the average value of ^^ ^^ ), such that 1≤i≤K, is significantly greater than^̅^^^, such that 1≤i≤K, then ^^^^ > ^^^^ almost all the time. The case where the means of ^̅^^^ and^̅^ ^^ are close does not pose a problem since the optimal solution will not differ much. Since the energy stored in the STO storage device is insufficient to electrically supply the site for the entire duration Te of the outage, it is no longer possible to keep all the RRUs functional for the entire duration Te of the PO power outage. It is clear that more ^^ ^^is high, the higher the volume of traffic transferred, because more bits are transmitted per unit of energy. Thus, the solution to optimization problem (7) is to keep the RRUs that have a high energy efficiency during the duration Te of the power outage PO. These RRUs that have a high energy efficiency will also transmit with their maximum capacity. Conversely, RRUs with a low energy efficiency are deactivated because they consume more and transmit fewer bits. Thus, the solution (9) to optimization problem (7) is as follows: ∆^^ ∗ ^^ = ^^^^, ^^∗^^ = ^^^^,^^, if 1≤k≤N-1 consumed by the k-th RRU during ^^ when it transfers ^^ ^^,^^ . Energy ^^ ^^,^^ is calculated using expression (5), when the traffic volume is equal to ^^ ^^,^^. We now describe, with reference to Figure 7B, another embodiment of the calculation step S2 of the K deactivation instants. According to this second embodiment, the calculation step S2 is implemented so as to optimize the autonomy of the storage device STO during the duration Te of the power outage PO, the order in which the K RRUs are deactivated being predefined by the manager of the network RC. For this purpose, a preliminary step SP2 is implemented, during which is defined from which threshold ^^ℎ of autonomy of the storage device STP, it is appropriate to turn off a first RRU, then a second and so on. The threshold ^^ℎ is defined in minutes in the embodiment shown. Of course, in other embodiments, the threshold ^^ℎ can be defined in hours.In the example shown, for reasons of simplification, it is defined that: - the first RRU, RRU1, is deactivated at t1, - the second RRU, RRU2, is deactivated at t2, - …, - the K-th RRU, RRUK, is deactivated at tK. It goes without saying that this example is not exhaustive. It could be defined for example that: - the third RRU, RRU3, is deactivated at t1, - the K-th RRU, RRUK, is deactivated at tK, - …, - the first RRU, RRU1, is deactivated at tK-1, - etc. In this other embodiment, it is considered that the radio site S operates with ^^RRUs, where K≥1 and. … , ^^^^) are the deactivation times of the ^^ RRUs. According to the embodiment shown, the DCC control device is configured to determine in a single pass the deactivation times (^^1, ^^2, … , , at the time of the power outage PO, making it possible to maximize the autonomy of the storage device during the duration Te of the power outage PO. As in the embodiment of FIG. 7A, a set of data relating to the operation of the radio site S, as used in the calculation S2, comprises the following data: - ^^0 the energy stored in the storage device STO at the time of the power outage PO, - Te the duration of the power outage PO, indicated by the power outage management device DIS, - ^^^^ = ^^^^,2^^ + ^^^^,3^^ + ^^^^,4^^ the volume of traffic emitted at the time of the power outage PO, for a k-th RRU among K, during a time interval ^^ , where^^ ^^,^^^^ is the KPI corresponding to the volume of traffic of the network generation nG collected at the time of the outage, where ^^ is for example such that 2 ≤ ^^ ≤ 4.- ^^ ^^the total energy consumed by the site S, as estimated at S0. For this purpose, the method comprises, at the time of the power cut PO, a reception step S200, during which the control device DCC receives, via its communication interface COM: - an estimated value of the energy ^^ ^^ consumed by site S before the power cut PO, from the DME calculation device, - an energy value ^^ ^^ stored in the storage device STO at the time of the PO outage, coming from a communication terminal associated with the site S or from the storage device STP if the latter is equipped with a dedicated communication module, - a value of the duration Te of the power outage PO, coming from the outage management device DIS. Of course, as an alternative, the estimated value of the energy ^^ ^^ , the value of energy ^^ ^^and value of the duration Te of the power outage PO can be received simultaneously or each at different times. Also as in the embodiment of FIG. 7A, the steps complementary to steps 308 and 309, according to the other embodiment further comprise, at the time of the power outage PO, a step S201 of collecting data DR relating to the operation of said RC network, such as the value of the traffic volume ^^^^ = ^^^^,2^^ + ^^^^,3^^ + ^^^^,4^^, in the example shown, indicators of energy consumption associated with the k-th RRU, etc. During a step S202, the calculation module CAL then calculates the time ti+1 of deactivation of the (i+1)-th RRU, RRUi+1, as follows: ^^^^+1 = ^^^^ − ^^ℎ + ^^^^ (10)- where ^^ ^^ is the previous instant of deactivation of the ith RRU, RRUi, - where ^^ ^^ is the autonomy of the STO storage device, calculated at ^^ ^^. During a step S203, the calculation module CAL calculates the remaining energy at the storage device STO as follows: - where is the remaining energy at the STO storage device, which was calculated at ^^ ^^ . A ^^ ^^+1 , the (i+1)-th RRU, RRUi+1 being deactivated, the traffic or data volume associated with it is distributed between the RRUs not yet deactivated, i.e. RRUi+2, …, RRUK. During a step S204, the calculation module CAL calculates the energy consumed by each of the RRUs, RRUi+2 to RRUK, from the aforementioned expression (5): During a step S205, the calculation module CAL calculates the autonomy of the storage device STO at ^^ ^^+1 according to the following relationship: S202 S205 are iterated for remaining RRUs, i.e. RRUi+2 to RRUK. The last time tK of deactivation of RRUK is then calculated as follows in S202: At the initialization of the calculation according to steps S202 to S205, it is considered that the residual energy of the STO storage device is such that E (0)^^ = ^^0 to ^^0 = 0, where ^^0 corresponds to the instant of the power outage PO. In addition, at ^^0, a parameter ^^ for re-parameterizing the threshold ^^ℎ is initialized, such that 0 < ^^ < 1 and such that if ^^0 < ^^ℎ, then ^^ℎ = ^^^^0. We now describe, in relation to Figure 8, a schematic curve illustrating the strategy for deactivating K RRUs in accordance with the calculation S2 implemented according to the embodiment, which has just been described above with reference to Figure 7B. In the example shown, K=4. Figure 6 shows from which autonomy threshold ^^ℎ of the storage device STO, it is necessary to deactivate a first RRU, RRU1, then a second RRU, RRU2, then a third RRU, RRU3, then possibly a fourth RRU, RRU4. Such a deactivation strategy implies that during a PO power failure, the autonomy of the STO storage device must be continuously monitored, as shown in Figure 8.Thus, when the autonomy of the STO storage device reaches the threshold ^^ℎ, RRU1 is deactivated. This increases the autonomy of the STO storage device. Then, the autonomy of the STO storage device is checked again and RRU2 is deactivated when the autonomy of the STO storage device reaches the threshold ^^ℎ, and so on as shown in Figure 8. Note that the fourth RRU, RRU4, may not be deactivated when the autonomy of the STO storage device reaches the threshold ^^ℎ, as symbolized by the dot-and-dash circle in Figure 8. The fourth RRU4 may indeed remain activated until the STO storage device is empty. As shown in Figure 8, at the time of the power outage PO, the RRUs RRU1 to RRU4 are all active. In S205, the autonomy of the STO storage device is calculated as follows from the aforementioned relation (12):. In S202, the instant ^^1 of deactivation of RRU1 is then calculated as follows, from the aforementioned relation (9): At ^^1, the autonomy of the STO storage device reaches the value of ^^ℎ. The remaining energy (in joules) at the level of the STO storage device is then calculated in S203 as follows, from the aforementioned relation (11): As already explained above in relation to Figure 7B, when an RRU is deactivated, the assumption is made that its traffic or data volume is distributed equally over the remaining RRUs, provided that the maximum capacity, in terms of traffic, of each of these remaining RRUs is not exceeded. Such an assumption is well-founded since a positive error on the traffic estimation added on one RRU will be corrected by a negative error on the traffic estimation added on another RRU. In addition, according to Figure 6, the fixed part of the RRU is the one that consumes the most. This means that a slight error on the estimation of the new traffic distribution following a deactivation of an RRU does not have a great impact on the estimation of the energy consumed by the RRU. The indicators (KPIs or raw indicators) related to the traffic on an active RRU increase at the time of the deactivation of another RRU.For the other KPIs, it is assumed that they increase proportionally in the same way as the traffic-related indicators. It is also possible to use a learning model, based for example on linear regression, which expresses each indicator (KPI (apart from traffic) or raw indicator) as a function of the traffic transmitted on the active RRU. Using the new values ​​of the different indicators following a deactivation of an RRU, a recalculation of the energy consumed by the RRUs still active is implemented in accordance with equation (5). At ^^2, the autonomy of the STO storage device reaches the value of ^^ℎ. The remaining energy (in joules) at the STO storage device is then calculated in S203 as follows, from the aforementioned relation (11):. Once RRU2 is deactivated at ^^2, the new values ​​of the energy ^^^^, 3 ≤ ^^ ≤ ^^ are calculated in S204 from the aforementioned equation (3) and the distribution of traffic from RRU2 to the other RRU3 to RRU4 still active. In S205, the autonomy of the STO storage device is calculated again as follows from the aforementioned equation (12): In S202, the instant ^^3 of deactivation of RRU3 is then calculated as follows, from the aforementioned relation (10): At ^^3, the autonomy of the STO storage device reaches the value of ^^ℎ. The remaining energy at the STO storage device is then calculated in S203 as follows, from the aforementioned relation (11): Once RRU3 is deactivated at ^^3, a new value of the energy ^^4 is calculated in S204 from the aforementioned equation (3) and the transfer of traffic from RRU3 to the still active RRU4. In S205, the autonomy of the STO storage device is calculated again as follows from the aforementioned equation (12): In S202, the instant ^^4 of deactivation of RRU4 is then calculated as follows, from the aforementioned relation (13): ^^4 = ^^3 + ^^3Although in relation to FIGS. 7A, 7B and 8, the step of calculating the K instants of deactivation has been described in the context of an RRU by RRU deactivation strategy, it goes without saying that such a step can also be implemented, correspondingly, in the context of a deactivation strategy, and without departing from the scope of the invention: - frequency band by frequency band, - generation of cellular radiocommunication network by generation of cellular radiocommunication network, - set of RRUs by set of RRUs, a set possibly containing one or more RRUs.The steps complementary to steps 308 and 309, described with reference to figures 4, 5, 6, 7A, 7B and 8 make it possible to ensure the continuity of the services provided by the radio site S, when a power outage of a duration greater than the autonomy of the storage device STO is accepted. They also make it possible to optimize the use of energy, thus contributing to a more efficient and sustainable management of the communication infrastructures. The calculation module CAL operates according to an ALGO algorithm, an example of which is shown above. In this example, the algorithm is written in a generic algorithmic language, adaptable to any programming language, such as for example Python, R, C++, Java, Scala, MATLAB, etc. ALGO algorithm: (1) Inputs: ^^0, Cutoff plan, Th, ^^ , ^^. ^^,^^ (1≤k≤K) (2) Inputs: KPIs and ^^ ^^ (1≤k≤K) at the event of power outage and ω (3) Initialization: E (0)^^ = ^^0, ^^0 = 0(4) Calculate ^^0based on Eq. (11 ) (5) If Th > A0, then ^^ℎ = ^^^^0(6) For i from 0 to K – 2 (7) Use Eq. ( 10) to calculate ^^ ^^+1 (8) Use Eq. ( 11) to calculate (9) #Comment: Strategy of mobility (10) Calculate (11) Calculate the vector ^^^^ (12) Find the set S1=find (^^^^ <^^0) (13) Vk=^^ ^^,^^ for all k∈S1 (14) Find the set S2=find (^^^^ ≥^^0) (15) Vk=Vk + ^^0for all k∈S2 (16) u=sum[^^^^ (k)] for all k∈S1 (17) c=cardinal(S2) #Comment: Length S2 (19) While [(a>0) & (c≥1)] (20) Calculate the vector ^^^^ #Comment: of size c (21) Find the set S1=find (^^^^ ≤ ^^) (22) Vk=^^ ^^,^^ for all k∈S1 (23) Find the set S2=find (^^^^ > ^^) (24) Vk=Vk + ^^ for all k∈S2 (25) ^^ =sum[^^^^(k)] for all k∈S1 (26) ^^ =cardinal(S2)(27) ^^ =^^- ^^ - ^^ ^^; ^^ =^^ ^^ (28) End While (29) Update the other KPIs for RRU i+2 to K (30) #Comment: end of the strategy of mobility (31) Calculate the new expressions of ^^ ^^based on Eq. (5) (32) Calculate ^^ ^^+1 based on Eq. (12 ) (33) End For (34) Calculate tK based on Eq. (13)At line (10), ^^0 is the value of the traffic volume of the RRU (^^ + 1) which is deactivated at^^ ^^+1 , this value being averaged over all remaining RRUs. In line (11), ^^^^ is a vector that calculates the remaining capacity (in terms of traffic volume) of RRUs (^^ + 2) to ^^. Then, ^^^^ = ^^^^,^^ − ^^^^ for ^^ + 2 ≤ ^^ ≤ ^^. As shown in line (12), if ^^^^(^^) < ^^0, then RRUk belongs to a set ^^1. This means that the RRU is not able to accept the entire quantity ^^0 because it exceeds its capacity. In this case, as shown in line (13), ^^^^ = ^^^^,^^ . Conversely, in line (14), if the remaining capacity of RRUk is greater than (^^^^(^^) ≥ ^^0),then RRUk belongs to a set ^^2. In this case, as shown in line (15),^^^^ = ^^^^ + ^^0. In lines (16) and (17), an update ^^ of the traffic KPIs of the RRUs belonging to ^^1 and an update ^^ of the traffic KPIs of the RRUs belonging to ^^2 are implemented. The rest of the traffic of the RRUs (^^ + 1) not yet distributed is given in line (18): ^^ =^^^^+1 − ^^ − ^^^^0 , where ^^ and ^^ are given in lines (16) and (17) respectively. In line (18), is r^^ defined, such that ^^ =^^ , as the remaining traffic of the RRU(^^ + 1) averaged over the remaining RRUs that still have the capacity to absorb the traffic (RRUs of the set ^^2). At line (19), as long as ^^ > 0, meaning there is still undelivered traffic, and ^^ ≥1, meaning there are still one or more RRUs that still have capacity, the While loop between lines (19) and (28) is activated to distribute the remaining traffic of the RRU(^^ + 1). As shown in line (24), the algorithm finds the new value of ^^ ^^ for an RRU ^^, such that (1≤k≤K). ^^ ^^ is composed of traffic from the 2G, 3G and 4G layers. In the same way as the algorithm just described, the distribution of ^^ ^^on all layers is also performed iteratively without exceeding the maximum traffic of each layer. For simplicity, we do not add this step in this algorithm. In line (29), an update of the KPIs of the remaining RRUs, RRUs (^^ + 2) to K is implemented. In line (31), ^^ ^^ is again recalculated from the above equation (5). In line (32), the autonomy ^^ ^^+1 of the storage device is calculated from expression (12). At line (34), the algorithm ends with the calculation of the instant ^^ ^^ deactivation of the last RRU, RRUK, from equation (13).

Claims

CLAIMS

1. Method for managing a power outage in a site (S) of a cellular radiocommunication network (RC), said site being provided with an energy storage device (STO), the method comprising: - a reception (300) of a request for power outage from the site, the request indicating a required outage duration; - a prediction (302) of an energy consumption of the site, as a function of at least one indicator representative of an operation of the site; - a decision (305-308) on the request, as a function of a result based on a comparison between a calculated autonomy of the storage device and the required outage duration, said calculated autonomy being a function of the prediction of energy consumption of the site.

2. Method according to claim 1, wherein said at least one indicator representative of the operation of the site (S) comprises a history of past values ​​of an energy consumption indicator of the site.

3. Method according to claim 2, wherein said at least one indicator representative of the operation of the site (S) further comprises at least one current value of at least one other indicator of operation of the site than the energy consumption indicator of the site.

4. Method according to one of claims 2 and 3, wherein the prediction (302) of the energy consumption of the site (S) is based on a predictive model defined by parameters associated respectively with past values ​​of the energy consumption indicator of the history and / or at least one current value of at least one other indicator of operation of the site.

5. The method of claim 4, wherein the parameters are defined by machine learning, from a training data set and a test data set.

6. Method according to one of the preceding claims, wherein said at least one site operation indicator (S) is a global indicator of operation of an entire site.

7. Method according to one of claims 1 to 5, wherein the site (S) operates according to at least one frequency band and / or at least one generation of cellular communication network, and wherein said at least one site operation indicator is an indicator associated with the at least one frequency band and / or the at least one generation of cellular communication network.

8. Method according to one of the preceding claims, wherein, if the autonomy of the storage device (STO) is less than the required outage duration, the decision is a refusal (306) of the power outage.

9. Method according to one of claims 1 to 7, in which, if the autonomy of the storage device (STO) is less than the required cut-off duration, the decision is a transmission (307) of a power cut proposal indicating a new cut-off duration less than the autonomy of the storage device.

10. Method according to one of claims 1 to 7, in which the site (S) operates according to at least one frequency band and / or at least one generation of cellular communication network, in which, if the autonomy of the storage device is less than the required outage duration, the decision comprises an acceptance (308) of the power outage for the required outage duration, and further comprising: - an activation (S1) of the storage device, - a calculation (S2) of a time of deactivation of said at least one frequency band or of said at least one generation of network, said calculation being implemented according to a criterion for optimizing the energy stored in the storage device, - a deactivation (S3), at said calculated time of deactivation, of said at least one frequency band or of said at least one generation of network.

11. Method according to claim 10, wherein when said site (S) operates according to at least two frequency bands and / or at least two generations of cellular radiocommunication network, said method comprises, once the storage device (STO) is activated: - a calculation, according to said optimization criterion, of at least two successive instants of deactivation of respectively said at least two frequency bands or of respectively said at least two generations of network, - a deactivation, at said at least two calculated instants of deactivation, of respectively said at least two frequency bands or of respectively said at least two generations of network.

12. Power outage management device (DIS) in a cellular radiocommunication (RC) site (S), the power outage management device being configured to: - receive a power outage request from the site, the request indicating a required outage duration; - predict an energy consumption of the site, based on at least one indicator representative of an operation of the site; - make a decision on the request, based on a result based on a comparison between a calculated autonomy of the storage device and the required outage duration, said calculated autonomy being a function of the predicted energy consumption of the site.

13. Computer program comprising program code instructions for implementing the method for managing a power outage according to any one of claims 1 to 11, when executed on a computer.

14. A computer-readable information medium comprising instructions of a computer program according to claim 13.

Images