Optimized management of resources of a cellular radiocommunication network site

Abstract

The invention relates to a method for managing resources of a site of a cellular radiocommunication network, the site comprising radio resources for transporting data of users of the site, said resources comprising K elements of the same nature, K being an integer greater than or equal to 2, the method comprising: - a prediction (302) of a volume of data traffic transported on said site for a future prediction horizon, as a function of indicators representative of an operation of the site; - a determination (303) of a set of elements sufficient to transport the volume of data traffic predicted in the future prediction horizon; - for at least one element of the site not belonging to the sufficient set of resources, a deactivation (304) of the element of the site before a start time of the future prediction horizon. Fig.3

Description

Title of the invention: Optimized management of the resources of a site of a cellular radiocommunication network Field of invention

[0001] The field of the invention is that of cellular radiocommunication networks and more particularly of the management of the resources of such networks. Prior art

[0002] A mobile cellular radio communication 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 in fact imposes a high energy demand on the cellular radio communication network.

[0003] Cellular radio communication networks continue to expand to support increased data traffic as well as new technologies, such as the generation of 5G networks. This results in an increase in the energy requirements of cellular radio communication networks.

[0004] The manager of a cellular radiocommunication network seeks to ensure better management of energy consumption across all the equipment in the mobile network.

[0005] Some solutions provide for reducing the number of resources of a radio site, by putting one or more cells of the radio site into sleep mode. For example, the document "Energy Efficiency of 5G Mobile Networks with Base Station Sleep Modes", P. Lâhdekorpi, M. Hronec, P. Johna, J. Moilanen, Conference of Standards for Communications and Networking (CSCN), 2017, pages 163 to 168, describes such a solution. In particular, the operator can decide such a switch to sleep when the traffic on the deactivated cell is low or medium, which shifts the traffic to the other resources of the radio site.However, such a standby, without prior knowledge of the future evolution of the traffic volume, can cause a loss of quality of service in the network, in particular if the traffic increases following the standby, and all of the traffic cannot be transported by the resources remaining activated on the radio site.

[0006] Other solutions provide for switching off, during the night, the high frequency bands, such as 2600 MHz, called capacity bands, while keeping the low frequency bands, such as 800 MHz for example, activated. For this purpose, a prediction of the volume of data traffic can be compared with a low traffic threshold, and if the traffic is lower than the traffic threshold, all the capacity layers are deactivated. If the data traffic volume prediction then indicates a medium or high load on the radio site, all capacity layers are reactivated. Thus, in the event of medium load, all capacity layers are activated, although not all of them are required to carry the traffic. This results in poor management of network resources based on the data traffic volume.

[0007] Another solution to reduce the number of resources, particularly in the case of low traffic volume, is national roaming, which is described in the document "National roaming as a fallback or default?", L. Weedage, SRC Magalhaes, S. Bayhan, IFIP Networking Conference, 2023. According to such a solution, in the case of low traffic volume in a given geographical area Z, users of an operator A accessing a first radio site can switch to a second radio site of an operator B, which makes it possible to put the resources of the first radio site on standby. Conversely, in another geographical area Z', in the case of low traffic volume, the resources of a radio site of operator B are put on standby, the users of operator B in area Z' switching to the radio site of operator A. Similar solutions propose sharing the network infrastructure between several operators.The paper “Network sharing and its energy benefits: A study of European mobile network operators”, IEEE Global Communications Conference (GLOBECOM), 2013, pages 2561-2567, describes such a solution.

[0008] However, these latter solutions have the disadvantage of great complexity in the management of the resources of the operators' cellular radiocommunication sites.

[0009] This results in a lack of optimization in the management of the resources of a cellular radiocommunication network according to variations in the volume of traffic on each site of the network. Subject matter and summary of the invention

[0010] 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 resources of a cellular radiocommunication site adapted to the evolution of the volume of traffic on the site. It is thus possible to optimize the use of the resources available on the site and consequently to reduce its energy consumption without reducing the quality of service delivered to the users of the site.

[0011] To this end, an object of the present invention relates to a method for managing resources of a site of a cellular radiocommunication network, the site comprising radio resources for transporting data of users of the site, said resources comprising K elements of the same nature, K being an integer greater than or equal to 2, the method comprising: - a prediction of a volume of data traffic transported on said site for a future prediction horizon, based on indicators representative of the operation of the site; - a determination of a set of elements sufficient to transport the volume of data traffic predicted in the future prediction horizon; - for at least one element of the site not belonging to the sufficient set of resources, a deactivation of the element of the site before a start time of the future prediction horizon.

[0012] Thus, the site's resources are adapted according to a prediction of the volume of data traffic in a future prediction horizon, which makes it possible to optimize the use of the site's resources, and in particular to reduce the overall energy consumption of the site.

[0013] According to embodiments, all elements of the site not belonging to the determined sufficient set of elements can be deactivated before the start time of the future prediction horizon.

[0014] Thus, it is made possible to minimize the overall energy consumption of the site by optimizing the allocation of resources based on a prediction of the volume of data traffic transported on the site.

[0015] According to embodiments, determining the sufficient element set may comprise obtaining the maximum traffic volumes of the elements of the site, and the determined sufficient element set may be the smallest set, in number of elements, for which a sum of the maximum traffic volumes of the elements of the set is greater than the predicted data traffic volume for the future prediction horizon.

[0016] Thus, it is made possible to optimize resource management based on a prediction of the volume of data traffic and without reducing the quality of service for users of the site.

[0017] According to embodiments, the indicators representative of the operation of the site may comprise a history of past values ​​of an indicator of data traffic volume of the site.

[0018] Such a history allows the dynamic evolution of the volume of data traffic transported on the site, or for each element of the site, to be taken into account, which improves the precision associated with the prediction of the volume of data traffic for the prediction horizon.

[0019] 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 the volume of data traffic of the site.

[0020] Such additional indicators make it possible to improve the accuracy associated with the prediction of the site's data traffic volume for the prediction horizon, which improves resource management based on such a prediction.

[0021] In addition or as a variant, the prediction of the volume of data traffic of the site can be based on at least one predictive model defined by parameters associated respectively with past values ​​of the historical data traffic volume indicator and / or at least one current value of at least one other operating indicator of the site.

[0022] Thus, it is made possible to weight, by parameters, the contributions of each of the operating indicators in the prediction of the volume of data traffic of the site for the prediction horizon, which improves the accuracy of the prediction, and makes it possible to determine at least one predictive model specific to a given site.

[0023] Additionally, the parameters can be defined by machine learning, from a training data set and a test data set.

[0024] Thus, the accuracy enabled by the at least one predictive model is improved. Furthermore, when the training and test data are collected on the site, the at least one predictive model developed is site-specific.

[0025] According to embodiments, the site can operate according to at least one frequency band and / or at least one generation of cellular radiocommunication network, and the operating indicators of the site can be indicators associated with the at least one frequency band and / or the at least one generation of cellular radiocommunication network.

[0026] For example, the site operating indicators can 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).

[0027] Thus, a predictive model is provided to determine the volume of data traffic carried by each frequency band and / or each network generation and / or each RRU. The data traffic volume of the site is then obtained by summing the predictions of all the frequency bands and / or network generations and / or RRUs of the site.

[0028] In addition, a remote radio unit, RRU, can be a group of radio cells operating according to the same frequency band for at least two generations of cellular radiocommunication network, and the K elements of the site can be K RRUs.

[0029] The deactivation of at least one RRU has a significant impact on the energy consumption of the site, due to the fixed part of the energy consumption of an RRU (called intercept) which is independent of the volume of data traffic transported by this RRU. The resource management according to the invention thus allows a significant reduction in energy consumption on the site.

[0030] In addition, the prediction of the traffic volume for the site can be based on K prediction models defined respectively for the K RRUs of the site.

[0031] Thus, the accuracy associated with predicting the volume of traffic for the site is improved, which allows for better optimization of the site's resources.

[0032] The invention also relates to a device for managing resources of a site of a cellular radiocommunication network, the site comprising radio resources for transporting data of users of the site, said resources comprising K elements of the same nature, K being an integer greater than or equal to 2, the resource management device being configured to: - predict a volume of data traffic transported on said site for a future prediction horizon, based on indicators representative of the operation of the site; - determine a set of elements sufficient to carry the volume of data traffic predicted in the future prediction horizon; - for at least one site element not belonging to the sufficient resource set, deactivate the site element before a start time of the future prediction horizon.

[0033] Such a device is notably configured to implement the aforementioned resource management method, according to one or other of its embodiments.

[0034] The invention also relates to a computer program comprising instructions for implementing the resource management method according to the invention, according to any one of the particular embodiments described above, when said program is executed by a processor.

[0035] Such instructions can be stored permanently in a non-transitory memory medium of the resource management device implementing the resource management method according to the invention.

[0036] This program may 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.

[0037] 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.

[0038] The recording medium may be any entity or device capable of storing the program. For example, the medium may comprise a storage means, such as a ROM, for example a CD ROM or a microelectronic circuit ROM, or a magnetic recording medium, for example a mobile medium, a hard disk or an SSD.

[0039] On the other hand, the recording medium may be a transmissible medium such as an electrical or optical signal, which may 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 may in particular be downloaded over a network, for example an Internet-type network.

[0040] 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 resource management method.

[0041] According to an exemplary embodiment, the present technique is implemented by means of software and / or hardware components. In this regard, 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

[0042] 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:

[0043] [Fig.l] represents an architecture in which the method for managing resources of a site of a cellular radiocommunication network is implemented, according to a particular embodiment of the invention,

[0044] [Fig.2] represents a resource management device of a site of a cellular radiocommunication network, according to an embodiment of the invention; [Fig.3] represents the main steps implemented in the method for managing resources of a site of a cellular radiocommunication network, according to an embodiment of the invention, as implemented in the architecture of [Fig.l];

[0045] [Fig.4] 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.

[0046] Detailed description of an embodiment of the invention

[0047] [Fig.l] represents an architecture in which a method for managing resources of a site S of a cellular radiocommunication network RC is implemented, according to an embodiment of the invention. Such a network RC is for example of the 3G, 4G, 5G, etc. type.

[0048] Such an architecture includes: - a DGR resource management device, configured to manage radio resources of the site S, according to DR data relating to the operation of the RC network, described below. The DGR resource management device of the site S is for example a server, a platform, for example of the CSON type (“Centralized -self-organizing networks” in English), RIC intelligent controller (“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; - the radio resources of site S comprising K elements ELi, EL2, ..., Ek, ..., ELK of the same nature.

[0049] The RC network being a cellular radiocommunication network, the K elements ELi, EL2, ..., ELk can be respectively K different frequency bands, for example 1800 MHz and 2100 MHz or at least two different cellular network generations, for example 3G and 4G, in the case for example where K=2. The elements ELi 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).

[0050] In the following, it is considered, for illustrative purposes, that the K elements are K RRUs.

[0051] We will now describe, with reference to [Fig.2], the simplified structure of the DGR resource management device.

[0052] The DGR resource management device comprises: - a COL module for collecting DR data relating to the operation of said RC network, including in particular indicators representative of the operation of site S; - a PRED module for predicting a volume Vi+h of data traffic transported on site S for a future prediction horizon H, based on DR data representative of the operation of site S; - a DET module for determining a set E of K* elements sufficient to transport the volume of data traffic predicted in the future prediction horizon H, K* being strictly less than K when the volume of data traffic predicted is average or low (and K* being more generally less than or equal to K); - a DES module for deactivating at least one element ELk of the site not belonging to the set E, before a start time of the future prediction horizon H.

[0053] At initialization, computer program code instructions PG are for example loaded into a RAM memory (not shown) before being executed by a processor PROC of the resource management device DGR. The processor PROC of the UTR processing unit implements in particular the following actions, within the framework of the resource management process, which will be described below, according to the instructions of the PG computer program: - collect DR data relating to the operation of the RC network, in particular site S; - predict the volume of data traffic transported on site S for the future prediction horizon H, based on DR data representative of the operation of site S; - determine the set E of K* elements sufficient to carry the predicted data traffic volume in the future prediction horizon H, K* being strictly less than K when the predicted data traffic volume is medium or low; - deactivate at least one element ELk of the site not belonging to the set E, before the start time of the future prediction horizon H.

[0054] We now describe, in relation to [Fig. 3], together with figures 1 and 2, the progress of a method for managing resources of a site S of the cellular radiocommunication network RC, according to a particular embodiment of the invention.

[0055] In a step 301, the resource management device receives, or collects, the operating data DR of the network RC, comprising indicators representative of the operation of the site S, at a current time.

[0056] 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.

[0057] 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, for each RRU: the throughput, the average number of users, the load of the RRU, the energy consumption of the RRU, etc.

[0058] The transported data traffic volume KPI is also collected by the resource management device.

[0059] The KPIs are sent to the DGR device with a granularity w which varies depending on the modeling context, which can for example be a time interval of 15 minutes (mn), 30 min, 1 hour, etc.

[0060] In a step 302, the resource management device DGR predicts the volume of data traffic 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.

[0061] In the following, an example of prediction PR of the data traffic volume of the site S for the prediction horizon H is described, for illustrative purposes.

[0062] In this example, the prediction PR is a prediction of the total data traffic volume of the site S, which is obtained from K predictions PRk each obtained for one of the K RRUs of the site S.

[0063] The prediction PRk is based on P KPIs collected in step 301, which are denoted jyW in which z corresponds to a time index, in which 1S j < p denotes an index of the KPI and in which the exponent ( k ) refers to the k'th RRU of the site S.

[0064] As indicated previously, the site S is made up of K 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).

[0065] For an RRU l <k<K, pk KPIs sont obtenus à l’étape 301, qui sont notés x^ dans lequel1 correspond à l’indice temporel, dans lequel 1 j’ Pk désigne l’indice du KPI et dans lequel l’exposant (k) fait référence au RRU du site S.

[0066] Alternatively, the PR prediction is obtained from a single prediction of the total volume of data traffic of the site S. The PR prediction is then based on Pt KPIs collected in step 301, which are noted x^ in which * corresponds to a time index, in which 1 J pT designates an index of the KPI and in which the exponent (T) refers to the entire site S.

[0067] For example, the KPIs considered can be any combination of the following indicators:

[0068] - For 2G network generation: flow rate for each cell;

[0069] - For 3G network generation: throughput and average number of users for each cell ;

[0070] - For 4G network generation: cell load and average number of users for each cell; - for the entire RRU, a KPI of energy consumption of the RRU.

[0071] In this example, no indicator is considered for the 5G network generation. However, according to the invention, indicators relating to the 5G network generation may be taken into account for the PRk predictions of data traffic volume of each RRU of index k of step 302.

[0072] In addition, a data traffic volume KPI is obtained, such a KPI being generally available per technology (per network generation). Thus, for a given RRU of index k, the data traffic volume at a current time i, noted is given by the following formula (1):

[0073] y® = vl« + ylk) (1) yir i2G ri jG y ï,4G

[0074]

[0075]

[0076]

[0077]

[0078] in which i thus refers to the time index of the measurement, i.e. the current instant included in the period (0 current; in which the index n in t / X) denotes the technology (network generation), 1 ijtG ytX representing the data traffic volume KPI for index generation n, r ijtiG over the period 0J including the current instant of index i. The data traffic volume KPIs y(k) can be stored by the DGR resource management device for the different instants i, so as to constitute a history of the data traffic volume for each RRU of index k and for each instant i. As previously stated, all KPIs can be collected by the DGR resource management device with a granularity of œ (m = 15, 30, 60 min etc.). Thus, y(k) corresponds to the volume of data traffic carried by the RRU ri of index k during the reference period w including time i. To take into account the granularity of implementation of step 301, the index 1 in the different KPIs is incremented every period 01. Thus, if the value of the index i = 10, then the measurements Xjjoni taken at time t = 10 w, expressed in minutes or hours. The prediction at the current time index1 (the current instant of step 301) of the future data traffic volume PRk for the RRU of index k and for a horizon H -hxœ , that is to say for a horizon comprising the time index i + h (for example ending at the time index i+h), is carried out by considering a history of the data traffic volume of each RRU as well as the current values ​​at instant i of the KPIs according to the following prediction model, PRk being noted t / U for the r i+h RRU: = + <2) l+fl J in which is the history of previous volume values ​​of data traffic for the RRU of index k, the history consisting of L previous measurements and in which 6, (a^, ) and ( / ?, are parameters. To take into account the granularity of collection of the measurements of step 301, the prediction horizon H is preferably a multiple of w. If h = 1 and m = 60 min, then the prediction horizon H = 60 min. If h = 4 and w = 30 min. then H = 120 min, etc. The prediction horizon H (and therefore the value h) can be determined from the current instant of index i so as to estimate the volume of data traffic in a future period of duration including the future instant i+h (for example ending at instant i+h).

[0079] In (2), the parameters 9, ((¾ ...,0,^) and (fi, ...,f3p) are unknown, but can be obtained during a preliminary learning phase, not shown in [Fig.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" in English, or any other technique.

[0080] Machine learning can be performed on a training database, storing values ​​and thus the corresponding target values ​​yW (the ground truth).

[0081] Thus, during the learning phase, the future value yW (for the horizon of ' i+h prediction hxw) is considered as the variable of interest. The historical data traffic volumes y(^) and the current values ​​of other KPIs are predictor variables as shown in Table I where A is the number of observations used during the training phase, i.e. the number of datasets in the training database.

[0082] Table 1: Predictor variables Variable of interest AiJ A kp ut y(k) A 2,1 V^) Alp v'â y(L v 2+h A / V,l AXp yW VN yt*) ' N+h

[0083] However, no restriction is attached to the manner in which the parameters 9, ( üq, ..., ) are determined and which can be obtained by a technique other than a technique based on machine learning.

[0084] Following the learning, the resource management device DGR stores the trained parameters 9, ((¾ ..., ) and ( fi, ..., fip), and is thus able to implement, by the prediction module PRED, a prediction of the RRU data traffic volume per RRU. Note that a set of parameters 9, (ao,...,aLri) and (fi,...,fip) can be determined for each RRU of index k, and the parameters can thus be denoted with (k) as a superscript, as in formula (3) below.

[0085] For the k,th RRU, we obtain: 100861 c (3)

[0087] The obtained value is a prediction of the data traffic volume of the k-th vi+h RRU over a period for the prediction horizon H.

[0088] Thus, for the entire site S, the prediction of the volume of data traffic, noted Ur), Vi+h is given by the following formula (4), by summing the different predictions obtained for the K RRUs of site S:

[0089] a (r) _ a U) (4) Vi+h ~ Lk=]Vi+h

[0090] Thus, the prediction module PRED obtains the prediction of data traffic volume a U) of the site S during step 302. Vi+h

[0091] Alternatively, the prediction a {T) for the entire site is not obtained by determining Vi+h RRU predictions by RRU, but is obtained from a single model of the vi+h formula (5):

[0092] in which the superscript T indicates that the variables concern the entire site, and no longer a single RRU.

[0093] The parameters 0, (a^, ..., ) and ( , ..., ftp) can be determined for the entire site, in the same way as the 0- parameters ("o and ....pp} described previously with the exponent (k) for each k-th RRU.

[0094] Thus, in a first embodiment, the resource management device DGR stores the predictive models corresponding to equations (2) in the prediction module PRED described previously, and the prediction of the data traffic volume of the site S over the period 07 for the prediction horizon H can be obtained by summing all the individual predictions ÿV) of the K RRUs of the site S. Vi+h

[0095] In a second embodiment, the DGR resource management device stores the unique predictive model (5) in the PRED prediction module described previously.

[0096] According to another embodiment not described, the resource management device DGR stores a prediction model of the data traffic volume for each network generation (2G, 3G, 4G, 5G for example) on the site S, and the prediction of the data traffic volume of the site S for a duration ​prediction H can be obtained by summing all the individual predictions of the network generations of site S.

[0097] The predictive models described above were tested, after learning the parameters, on a set of real test data from a cellular radiocommunication network, for a prediction horizon H, with a granularity value w of 60 minutes, and a horizon H also of 60 minutes (therefore with h=l).

[0098] The test period includes data between 10:00 and 17:00 of day d. The parameter learning period includes the two days preceding day d.

[0099] A learning model is created by RRU for the predictive model (2).

[0100] The results show that the predicted values ​​of data traffic volume, per site or per RRU, are very close or even identical to the actual values ​​of data traffic volume.

[0101] In Table 2 below, consider the metric of the absolute value of the relative error RE, between the actual data traffic volume values ​​from the test data and the predicted data traffic volume values ​​obtained from the predictive models (2):

[0102] Table 2 thus gives the rate (or the probability or the percentage) that the relative error RE is less than 25% for H=60min and w = 60 min. The rate is calculated initially on a set SI of the test samples from all the radio sites of a cellular radiocommunication network, then on a set S2 containing all the traffic samples from all the radio sites by removing the samples for which the data traffic volume is very low (for example less than 5% of the maximum data traffic volume). For the samples for which the data traffic volume is very low, a larger relative error is acceptable because the predicted data traffic volume remains low.

[0103] Table 2 shows that the error in predicting the data traffic volume for the entire site S is low.

[0104] Table 2: Set S1 Set S2 Percentage that RE<25% 77% 91%

[0105] Thus, the predictive models (2) are particularly suitable for predicting the volume of data traffic of RRUs of a site S, as a function of radio KPIs such as throughput, load and number of active users.

[0106] Referring again to Figure 3, the resource management method further comprises, following steps 301 and 302, a step 303 of determination, by the determination module DET, of a set E of K* elements sufficient to transport the volume of data traffic a (t) predicted in the prediction horizon H. Indeed, ^i+k in many situations, especially when the predicted data traffic volume a(T) 'i+h is low or medium, it can be transmitted by a number K* of RRUs strictly less than K. This is especially the case when the individual predictions of the RRUs a(X) are low or medium. Vi+h

[0107] The set E can be determined from the maximum data traffic volumes that the K RRUs can respectively support. The maximum data traffic volumes are denoted / \ in the following. The values can be known in advance (predetermined) or can be obtained from the collected data (for example, they can correspond to peak values ​​of data traffic volume over a given period, for example several days).

[0108] According to embodiments, K* is the exact and minimal number of RRUs making it possible to satisfy the volume of data traffic predicted for the site S for the prediction horizon H. Thus, K* can be obtained in the following manner: $ / a(T)\ K = arg min KV^h

[0109] which means that K* is the smallest value verifying a (T), 1 A when the indices of the RRUs are reordered (to simplify the understanding of the invention) so that the first K* RRUs are part of the set E. In this case, according to the invention, in a step 304, at least one of the RRUs indexed from K*+1 to K is deactivated (or switched off) by the deactivation module DES, before the instant i+h (for example in the period œ preceding the instant i+h), which makes it possible to reduce the energy consumption of the site S for the period of the prediction horizon H, while maintaining the quality of service for the users. Preferably, the deactivation module DES deactivates all the RRUs indexed from K* + 1 to K, before the instant i+h (for example from the period M preceding the instant i +h or at the start of the period comprising the instant i+h), which makes it possible to minimize the energy consumption of the site S for the period of the prediction horizon H, while maintaining the quality of service for the users.

[0110] It should be noted that the small error on the prediction of total site data traffic volume, presented in Table 2, does not impact the exact number K* of RRUs allowing to transport the predicted volume on the entire site, since the experiments which led to the results of Table 2 show that the calculation of K* is accurate in almost 99% of cases.

[0111] It should also be noted that, as illustrated in [Fig.4], the fixed part of the energy consumption of an RRU, which does not depend on the volume of data traffic, consumes a lot of energy: approximately 50% or even more of the total consumption of an RRU.

[0112] [Fig.4] shows a curve representing the evolution, in a real situation, of the 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 noted that the fixed value of the energy which does not depend on the volume of data traffic, is quite high compared to the consumption linked to the volume of data traffic. It is noted that the intercept (the fixed value of energy consumption of an RRU, independent of the volume of data traffic) exceeds half of the energy consumption.

[0113] Referring again to [Fig. 3], the steps of the resource management method according to the invention can be iterated, so as to continuously adapt the activated and deactivated resources of the site S, to the predicted evolution of the volume of data traffic.

Claims

Claims

1. Method for managing resources of a site (S) of a cellular radiocommunication network (RC), the site comprising radio resources for transporting data of users of the site, said resources comprising K elements (ELrELK) of the same nature, K being an integer greater than or equal to 2, the method comprising: - a prediction (302) of a volume of data traffic transported on said site for a future prediction horizon, as a function of indicators representative of an operation of the site; - a determination (303) of a set of elements sufficient to transport the volume of data traffic predicted in the future prediction horizon; - for at least one element of the site not belonging to the sufficient set of resources, a deactivation (304) of the element of the site before a start time of the future prediction horizon.

2. Method according to claim 1, in which all the elements (ELr ELk) of the site (S) not belonging to the determined sufficient set of elements are deactivated before the start time of the future prediction horizon.

3. The method of claim 1 or 2, wherein determining (303) the sufficient element set comprises obtaining the maximum traffic volumes of the elements (ELi-ELk) of the site (S), and wherein the determined sufficient element set is the smallest set, in number of elements, for which a sum of the maximum traffic volumes of the elements of the set is greater than the predicted data traffic volume for the future prediction horizon.

4. Method according to one of claims 1 to 3, in which the indicators representative of the operation of the site (S) comprise a history of past values ​​of an indicator of the volume of data traffic of the site.

5. Method according to claim 4, in which the indicators representative of the operation of the site (S) further comprise at least one current value of at least one other indicator of operation of the site than the indicator of volume of data traffic of the site.

6. Method according to one of claims 4 and 5, in which the prediction of the volume of data traffic of the site is based on at least one predictive model defined by parameters associated respectively with past values ​​of the historical data traffic volume indicator and / or at least one current value of at least one other operating indicator of the site.

7. The method of claim 6, wherein the parameters are defined by machine learning, from a training data set and a test data set.

8. Method according to one of the preceding claims, in which the site (S) operates according to at least one frequency band and / or at least one generation of cellular radiocommunication network, and in which the operating indicators of the site are indicators associated with the at least one frequency band and / or the at least one generation of cellular radiocommunication network.

9. Method according to claim 8, in which a remote radio unit, RRU, is a group of radio cells operating according to the same frequency band for at least two generations of cellular radio communication network, and in which the K elements (ELr ELk) of the site (S) are K RRUs.

10. A method according to claim 6 and claim 9, wherein the prediction (302) of the traffic volume for the site (S) is based on K prediction models defined respectively for the K RRUs of the site.

11. Resource management device (DGR) of a site (S) of a cellular radiocommunication network (RC), the site comprising radio resources for transporting data of users of the site, said resources comprising K elements (ELi-ELk) of the same nature, K being an integer greater than or equal to 2, the resource management device being configured to: - predict a volume of data traffic transported on said site for a future prediction horizon, as a function of indicators representative of an operation of the site; - determine a set of elements sufficient to transport the volume of data traffic predicted in the future prediction horizon; - for at least one site element not belonging to the sufficient resource set, deactivate the site element before a start time of the future prediction horizon.

12. A computer program comprising program code instructions for implementing the resource management method according to any one of claims 1 to 10, when executed on a computer.

13. A computer-readable information medium comprising instructions of a computer program according to claim 12.

Images