CONTROL OF COMPUTING TASKS IN MULTI-ACCESS PERIPHERAL COMPUTERS

Description

technical field

[0001] The present invention relates to a field combining computer science and communication networks. More specifically, it relates to the field of multi-access edge computing, or MEC (Multi-access Edge Computing). It particularly concerns the control of offloading computing tasks in multi-access edge computing. Prior state of the art

[0002] Offloading computing tasks from a user terminal to the cloud is considered an effective solution for limiting the user terminal's computing power consumption and meeting latency constraints for the process, including communication and the actual computation. However, offloading computing tasks generates additional communication traffic on both the uplink and downlink: offloading traffic.

[0003] The corresponding communication costs depend on several parameters, including propagation conditions, the required data rate, antenna gains in transmission and reception, and the distance between the user terminal and a radio base station receiving the data. Furthermore, communication times can be significant. Backhaul network congestion can occur, for example, if a large number of users operate in the same geographic area.

[0004] To solve these problems, multi-access edge computing proposes to use the computing and data processing capabilities of network edge equipment called mobile edge hosts (or MEHs).

[0005] Multi-access edge computing (MEC) provides application developers and content providers with cloud computing capabilities and an IT service environment at the network edge. This environment is characterized by very low latency, high throughput, and real-time access to radio network information that can be leveraged by applications. MEC technology enables operators to flexibly and rapidly deploy innovative applications and services to user endpoints.

[0006] The article by Wang Yichuan et al., "An energy saving based on task migration for mobile edge computing," published in Eurasip Journal on Wireless Communications and Networking, vol. 2019, no. 1, May 27, 2019, explains that migrating complex tasks to remote edge servers via wireless networks solves the problems of insufficient computing power and limited battery capacity in mobile devices. The article by P. Mach and Z. Becvar, "Mobile edge computing: A survey on architecture and computation offloading," published in IEEE Communications Surveys & Tutorials 19 (3), pp. 1628–1656, provides a review of the techniques implemented in multi-access edge computing, formerly known as mobile edge computing. Furthermore, the European Telecommunications Standards Institute (ETSI) has standardized MEC technology.

[0007] The decision to offload computing tasks from a user terminal to a server at the network edge is made based on criteria, the main ones being minimizing energy consumption at the user terminal and respecting an acceptable execution time for the offloaded tasks.

[0008] However, communications related to the offloading of computing tasks also generate an increase in electromagnetic fields emitted at the user terminal. Description of the invention

[0009] The invention aims to solve the problems of the prior art by providing a method of offloading computing tasks between a user terminal and an edge host equipment in a communication network according to a multi-access edge computing technique, as claimed in the set of claims.

[0010] Thanks to the invention, communication and computing resources are managed jointly with user exposure to electromagnetic fields, enabling holistic management of resources and user exposure status to electromagnetic fields.

[0011] According to a preferred characteristic, the process of offloading computing tasks includes the following steps: Classification of a set of computing tasks into a subset of tasks that can be moved and a subset of tasks that cannot be moved, based on the technical characteristics of the computing tasks; Identification of the tasks for which moving is necessary, based on the technical characteristics of the user terminal; Estimation, for each task in the subset of tasks that can be moved, whether moving the task presents an advantage based on a latency constraint and a reduction in power associated with moving rather than with computing on the user terminal; Determination whether moving can be done while respecting the criterion of minimizing exposure to electromagnetic fields for the user.

[0012] According to a preferred characteristic, the distance between the user's body and the user terminal's transmitting / receiving device is evaluated based on data provided by at least one of a proximity sensor, an inertial measurement unit, a touchscreen on the user terminal, or by impedance matching tracking of different antennas on the user terminal.

[0013] Based on a preferred characteristic, an instantaneous value of user exposure to electromagnetic fields is determined.

[0014] According to an alternative preferred feature, a cumulative value over a time window of user exposure to electromagnetic fields is determined. The invention also relates to a controller for offloading computing tasks between a user terminal and an edge host device in a communication network using a multi-access edge computing technique, as claimed in the set of claims.

[0015] The invention also relates to a user terminal comprising a controller for offloading computing tasks as previously described.

[0016] The remote controller and the user terminal offer advantages similar to those previously presented.

[0017] In a particular embodiment, the steps of the process according to the invention are implemented by computer program instructions.

[0018] Consequently, the invention also relates to a computer program on an information medium, this program being capable of being implemented in a computer, this program comprising instructions adapted to the implementation of the steps of a process as described above.

[0019] This program can use any programming language, and be in the form of source code, object code, or code somewhere between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0020] The invention also relates to a computer-readable information carrier, comprising computer program instructions adapted to the implementation of the steps of a process as described above.

[0021] The information medium can be any entity or device capable of storing the program. For example, the medium can include 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 floppy disk or a hard disk drive.

[0022] On the other hand, the information medium can be a transmissible medium such as an electrical or optical signal, which can be transmitted via an electrical or optical cable, by Exposure to electromagnetic fields based on specific exposure maps, a sum of exposure to electromagnetic fields of the user or an identified group of people, this exposure being due to the user terminal or other sources of electromagnetic fields near the user terminal

[0023] The invention also relates to a user terminal comprising a controller for offloading computing tasks as previously described.

[0024] The remote controller and the user terminal offer advantages similar to those previously presented.

[0025] In a particular embodiment, the steps of the process according to the invention are implemented by computer program instructions.

[0026] Consequently, the invention also relates to a computer program on an information medium, this program being capable of being implemented in a computer, this program comprising instructions adapted to the implementation of the steps of a process as described above.

[0027] This program can use any programming language, and be in the form of source code, object code, or code somewhere between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0028] The invention also relates to a computer-readable information carrier, comprising computer program instructions adapted to the implementation of the steps of a process as described above.

[0029] The information medium can be any entity or device capable of storing the program. For example, the medium can include 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 floppy disk or a hard disk drive.

[0030] On the other hand, the information medium can be a transmissible medium such as an electrical or optical signal, which can be transmitted via an electrical or optical cable, by radio, or by other means. The program according to the invention can, in particular, be uploaded to a network such as the Internet.

[0031] Alternatively, the information carrier 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 process according to the invention. Brief description of the drawings

[0032] Other features and advantages will become apparent upon reading the following description of a preferred embodiment, given by way of non-limiting example, described with reference to the figures in which: [ Fig. 1 ] illustrates a communication network in which a deportation of computing tasks is implemented, according to an embodiment of the invention, [ Fig. 2] illustrates a method for offloading computational tasks, according to one embodiment of the invention,

[0033] The different parts represented in the figures are not necessarily shown on a uniform scale, in order to make the figures more legible.

[0034] The different possibilities (variants and modes of implementation) should be understood as not being mutually exclusive and can be combined with each other. Detailed description of specific implementation methods

[0035] According to a preferred embodiment, represented in the figure 1 , A communication network comprises a set of devices adapted to communicate and more specifically to communicate according to the principle of multi-access edge computing, known as MEC (from the English: Multi-access Edge Computing).

[0036] Thus, the communication network schematically comprises user terminals UE1, UE2, ...UEm, where m is an integer, which include mobile phones and so-called "IoT" devices (from the English "Internet of Things") that communicate and connect using techniques grouped under the name "Internet of Things." IoT devices are industrial or domestic devices, such as sensors, actuators, and other input / output components, capable of collecting data or performing actions from a real-world environment.

[0037] User terminals are likely to be connected to access points AP1, AP2, ... APn, where n is an integer, of an access network. The access network allows connections of user terminals to a core network. However, here we consider connections and data transmissions between user terminals and one or more edge host devices (EH), or edge computing servers, which are closer to the user terminals than the core network. A single edge host device (EH) has been represented in the diagram. figure 1 but of course their number could be greater.

[0038] Edge host equipment, for example, is located within the access network. It can therefore be in the same location as the access points. Alternatively, it can be located elsewhere, in which case an additional link is required, for example, in a backhaul network.

[0039] Of course, the techniques and devices used vary depending on the type of network: 4G, 5G, 6G, for example.

[0040] For the implementation of multi-access edge computing, a task deferral controller is installed on each user terminal UE1, UE2, ...UEm. A single task deferral controller, CD1, was shown in the figure 1 Alternatively, the remote controller is located in the access network, for example, in edge host equipment. If the remote controller is in the access network, access control signaling information is exchanged between it and user terminals.

[0041] The function of the remote controller is to plan if, when, and how computing tasks are offloaded between a user terminal and an edge host device. As detailed below, the remote controller according to the invention determines, in particular, the transmission power and specific directivity of the user terminal's antennas.

[0042] The remote access controller communicates with an orchestrator located on the network and as defined by the previously mentioned ETSI standard. The orchestrator checks, in particular, whether remote access to computing tasks with the required performance is possible on the network side. Remote access to computing tasks from a user terminal to an edge host device involves the following phases: Signaling to identify the target of the offload request and requests the MEC orchestrator to access such a service. In this phase, the Quality of Service (QoS) parameters are negotiated and granted; communication, during which the bits necessary to perform the computation are transmitted, or offloaded, from the user terminal to an access point and then to the edge host equipment; computation, during which the bits are processed by the edge host equipment; this phase may include the establishment of ad hoc local clusters to federate computing units or cache resources; communication, in which the results of the execution of the offloaded computation task are retransmitted from the edge host equipment to the user terminal, or possibly to one or more other user terminals.

[0043] The computing task offload controller is adapted to perform offload control in the following way.

[0044] The computing task offloading controller first considers a set of computing tasks and classifies them into a subset of offloadable tasks and a subset of non-offloadable tasks, based on technical characteristics of the computing tasks.

[0045] The technical characteristics of a computational task that are taken into account include, for example, the hardware dependency of the computational task or a data dependency between instructions.

[0046] The computing task offloading controller then identifies the tasks that need to be offloaded, based on the technical characteristics of the user terminal.

[0047] Offloading a task is considered necessary when local computation of the task is expensive or impossible. This decision is based on a series of tests that take into account the computing power of the user's terminal, memory requirements, and mobile battery consumption. A task is classified as "should be offloaded" if one of the following conditions is met: The user terminal's battery level is critical, The memory required for the task is greater than the allowed percentage of available memory on the user terminal, The task requires computing power greater than a predefined percentage of the total available capacity on the user terminal, The task requires software that is not present on the user terminal, The task requires data that is not present on the user terminal.

[0048] It should be noted that the offset thresholds defined above are parameters that can be set by the user via their mobile device operating system.

[0049] The computing task offloading controller then estimates, for each task in the offloadable task subset, whether offloading the task offers an advantage based on a latency constraint and a reduction in power associated with offloading rather than computing on the user terminal.

[0050] The result of this estimate includes a set of information: the estimation of offload traffic characteristics such as traffic intensity, periodicity, time constraints, the size of the offload packet generation to be sent to the edge host equipment (uplink packet size) and, in some cases, the size of MEC packets received downlink from the edge host equipment, the estimation of the radio frequency transmission power from the user terminal to the access point for offloading the computing task, the antenna diagram for communication from the user terminal to the access point.

[0051] Along with estimating the benefit of offloading a computing task, the computing task offloading controller assesses whether offloading the computing task can be done while respecting a criterion related to the user's exposure to electromagnetic fields. The goal is to minimize the user's exposure to electromagnetic fields at the user terminal.

[0052] A user's exposure value to electromagnetic fields is calculated based on one or more of the following criteria: a momentary radiofrequency electromagnetic dosimetry measurement or a cumulative dose over a time window, exposure to electromagnetic fields based on specific exposure maps, a sum of exposure to electromagnetic fields of the user or an identified group of people, this exposure being due to the user terminal or other sources of electromagnetic fields close to the user terminal.

[0053] Radiofrequency electromagnetic dosimetry measurements are based on both the distance between the user and the user terminal's transmitting / receiving device, and the power transmitted by the user terminal for offloading computing tasks. The distance between the user's body and the user terminal's transmitting / receiving device is related to electromagnetic energy coupling between the user's body and the user terminal's transmitting / receiving device. This coupling depends on the antenna pattern of the user terminal's antenna.

[0054] The distance between the user and the user terminal's transmitter / receiver is thus determined. This can be done using a proximity sensor, an inertial measurement unit (IMU), the user terminal's human-machine interface (HMI), or the user terminal's touchscreen. When in use, the touchscreen allows the system to determine the user's finger position relative to the terminal and also directs the transmission towards antennas that minimize the user's electromagnetic exposure. Analyzing all the data from these sensors allows for a more precise positioning of the user's body relative to the terminal, recognizing that certain body parts are more critical (e.g., the head).

[0055] Another way to determine the physical distance between the user and the transmitter / receiver of the user terminal is to monitor the impedance matching of the different antennas on the user terminal to assess the immediate surroundings (handling, proximity of the head). Indeed, the dielectric material of the user's body increasingly disrupts the nominal behavior of these antennas as the distance between the user and the antennas decreases.

[0056] Once analyzed, all this information produces a close context environment and therefore a user terminal usage status (web browsing, voice call to the ear, handling or device not being worn) which are associated with a value of exposure to the user's electromagnetic fields.

[0057] The user's exposure to electromagnetic fields is estimated based on four pieces of information: the transmission frequency band(s), the position of the user's body relative to the terminal, the radio frequency power transmitted from the transmitting antenna, the radiation pattern, especially if the latter is reconfigurable (as in the case of antenna arrays).

[0058] From this real-time information, the spatial distribution of electromagnetic energy absorbed in different parts of the human body is estimated, also using models (from measurements or simulations) in the form of a reference table to simplify the calculation.

[0059] As already stated, the user's exposure value to electromagnetic fields is either an instantaneous value or a cumulative value over a time window.

[0060] In both cases, the user's exposure level to electromagnetic fields is compared to a threshold value for electromagnetic field exposure, which sets an exposure limit. This threshold value can vary from user to user.

[0061] The result of the assessment of whether the relocation of the computing task can be carried out while respecting a criterion related to the user's exposure to electromagnetic fields is one of the following decisions: Perform the offloading of the computing task from the user terminal to the edge host equipment, perform the offloading of the computing task from the user terminal to the edge host equipment, conditionally, do not perform the offloading of the computing task during a given time window.

[0062] In the second case, the offset is constrained by one or more of the following conditions: a) limit the transmission power of the user terminal and thus reduce the uplink capacity, b) perform a partial offset and limit the uplink traffic data transmitted to the access point, c) perform a partial offset and limit the downlink traffic data transmitted by the access point, d) cumulative conditions b + c, e) adapt the radiation pattern of the user terminal antenna to reduce exposure to electromagnetic fields for the user taking into account a maximum exposure target (momentary or cumulative).

[0063] By "partial offloading" we mean an offloading of intermittent computing tasks: part of the calculations are performed by the peripheral host equipment after offloading, and another part of the calculations are performed by the user terminal.

[0064] There figure 2represents the operation of the remote controller as a process comprising steps E1 to E4. This process is part of a method for offloading computing tasks between a user terminal and an edge host device in a communication network using a multi-access edge computing technique, comprising the following steps: Data transfer required to perform the calculation from the user terminal to the peripheral host equipment; Data transmission resulting from the calculation performed by the peripheral host equipment, from the peripheral host equipment to the user terminal.

[0065] These steps are known in themselves and will not be detailed here.

[0066] The process of offloading computing tasks is characterized by the fact that data offloading is controlled based on combined criteria of energy efficiency and minimizing exposure to electromagnetic fields for a user of the terminal. It is this data offloading control that is detailed below.

[0067] Step E1 is a classification of a set of computational tasks into a subset of deportable tasks and a subset of non-deportable tasks, based on technical characteristics of the computational tasks.

[0068] The technical characteristics of a computational task that are taken into account include, for example, the hardware dependency of the computational task or a data dependency between instructions.

[0069] The next step E2 is an identification of the tasks whose relocation is necessary, based on the technical characteristics of the user terminal.

[0070] Offloading a task is considered necessary when local computation of the task is expensive or impossible. This decision is based on a series of tests that take into account the computing power of the user's terminal, memory requirements, and mobile battery consumption. A task is classified as "should be offloaded" if one of the following conditions is met: The user terminal's battery level is critical, The memory required for the task is greater than the allowed percentage of available memory on the user terminal, The task requires computing power greater than a predefined percentage of the total available capacity on the user terminal, The task requires software that is not present on the user terminal, The task requires data that is not present on the user terminal.

[0071] It should be noted that the offloading thresholds defined above are parameters that can be set by the user via their mobile device's operating system. The next step, E3, is an estimation to determine, for each task in the subset of offloadable tasks, whether offloading the task offers an advantage based on a latency constraint and a reduction in processing power associated with offloading rather than with the computation on the user's terminal.

[0072] The result of this estimate includes a set of information: the estimation of offload traffic characteristics such as traffic intensity, periodicity, time constraints, the size of the offload packet generation to be sent to the edge host equipment (uplink packet size) and, in some cases, the size of MEC packets received downlink from the edge host equipment, the estimation of the radio frequency transmission power from the user terminal to the access point for offloading the computing task, the antenna diagram for communication from the user terminal to the access point.

[0073] The next step, E4, is an estimation to determine whether the computing task can be offloaded while respecting a criterion related to the user's exposure to electromagnetic fields. Recall that the goal is to minimize the user's exposure to electromagnetic fields at the terminal.

[0074] This estimation is performed jointly with the estimation of the benefit of offloading a computing task.

[0075] A user's exposure value to electromagnetic fields is calculated based on one or more of the following criteria: a momentary radiofrequency electromagnetic dosimetry measurement or a cumulative dose over a time window, exposure to electromagnetic fields based on specific exposure maps, a sum of exposure to electromagnetic fields of the user or an identified group of people, this exposure being due to the user terminal or other sources of electromagnetic fields close to the user terminal.

[0076] Radiofrequency electromagnetic dosimetry measurements are based on both the distance between the user and the user terminal's transmitting / receiving device, and the power transmitted by the user terminal for offloading computing tasks. The distance between the user's body and the user terminal's transmitting / receiving device is related to electromagnetic energy coupling between the user's body and the user terminal's transmitting / receiving device. This coupling depends on the antenna pattern of the user terminal's antenna.

[0077] The physical distance between the user and the user terminal's transmitter / receiver is thus determined. This can be done using a proximity sensor, an inertial measurement unit (IMU), the user terminal's human-machine interface (HMI), or the user terminal's touchscreen. When in use, the touchscreen allows the system to determine the user's finger position relative to the terminal and also directs the transmission towards antennas that minimize the user's electromagnetic exposure. Analyzing all the data from these sensors allows for a more precise positioning of the user's body relative to the terminal, recognizing that certain body parts are more critical (e.g., the head).

[0078] Another way to determine the physical distance between the user and the transmitter / receiver of the user terminal is to monitor the impedance matching of the different antennas on the user terminal to assess the immediate surroundings (handling, proximity of the head). Indeed, the dielectric material of the user's body increasingly disrupts the nominal behavior of these antennas as the distance between the user and the antennas decreases.

[0079] Once analyzed, all this information produces a close context environment and therefore a user terminal usage status (web browsing, voice call to the ear, handling or device not being worn) which are associated with a value of exposure to the user's electromagnetic fields.

[0080] The user's exposure to electromagnetic fields is estimated based on four pieces of information: the transmission frequency band(s), the position of the user's body relative to the terminal, the radio frequency power transmitted from the transmitting antenna, the radiation pattern, especially if the latter is reconfigurable (as in the case of antenna arrays).

[0081] From this real-time information, the spatial distribution of electromagnetic energy absorbed in different parts of the human body is estimated, also using models (from measurements or simulations) in the form of a reference table to simplify the calculation.

[0082] As already stated, the user's exposure value to electromagnetic fields is either an instantaneous value or a cumulative value over a time window.

[0083] In both cases, the user's exposure level to electromagnetic fields is compared to a threshold value for electromagnetic field exposure, which sets an exposure limit. This threshold value can vary from user to user.

[0084] The result of the assessment of whether the relocation of the computing task can be carried out while respecting a criterion related to the user's exposure to electromagnetic fields is one of the following decisions: Perform the offloading of the computing task from the user terminal to the edge host equipment, perform the offloading of the computing task from the user terminal to the edge host equipment, conditionally, do not perform the offloading of the computing task during a given time window.

[0085] In the second case, the offset is constrained by one or more of the following conditions: a) limit the transmission power of the user terminal and thus reduce the uplink capacity, b) perform a partial offset and limit the uplink traffic data transmitted to the access point, c) perform a partial offset and limit the downlink traffic data transmitted by the access point, d) cumulative conditions b + c, e) adapt the radiation pattern of the user terminal antenna to reduce exposure to electromagnetic fields for the user taking into account a maximum exposure target (momentary or cumulative).

[0086] By "partial offloading" we mean an offloading of intermittent computing tasks: part of the calculations are performed by the peripheral host equipment after offloading, and another part of the calculations are performed by the user terminal.

Claims

1. Method for offloading calculation tasks between a user terminal (UE1, UE2, UEm) and a piece of edge host equipment (EH) in a communication network according to a multi-access edge computing technique, including steps of: - Offloading data necessary for the execution of the calculation from the user terminal to the piece of edge host equipment, - Transmitting data resulting from the calculation carried out by the piece of edge host equipment, from the piece of edge host equipment to the user terminal, the offloading of calculation tasks being controlled on the basis of a criterion of energy efficiency, the method being characterized in that the offloading of calculation tasks is further controlled by a criterion of minimization of exposure of a user of the user terminal to electromagnetic fields, a value of exposure of the user to electromagnetic fields being calculated according to one or more of the following criteria: - a measurement of momentary radiofrequency electromagnetic dosimetry or a cumulative dose over a time window, the measurement of momentary radiofrequency electromagnetic dosimetry being based both on the distance between the user and an emitter / receiver device of the user terminal and on the power transmitted by the user terminal for offloading calculation tasks, - the exposure of the user to electromagnetic fields on the basis of specific exposure maps, - a sum of exposure of the user or of an identified group of people to electromagnetic fields, this exposure being caused by the user terminal or by other sources of electromagnetic fields close to the user terminal.

2. Method for offloading calculation tasks according to claim 1, including steps of - Classifying (E1) a set of calculation tasks into a subset of offloadable tasks and a subset of non-offloadable tasks, according to the technical characteristics of the calculation tasks, - Identifying (E2) the tasks for which offloading is necessary, according to technical characteristics of the user terminal, - Estimating (E3), for each task of the subset of offloadable tasks, whether the offloading of the task presents an advantage according to a constraint of latency and a reduction of the power associated with the offloading rather than with the calculation on the user terminal, - Determining (E4) whether the offloading can be carried out while respecting the criterion of minimization of exposure of the user to electromagnetic fields.

3. Method for offloading calculation tasks according to claim 1, wherein the distance between the body of the user and the emission / reception device of the user terminal is evaluated on the basis of data provided by at least one out of a proximity sensor, an inertial measurement unit, a touch screen provided in the user terminal or by a monitoring of adaptation of impedance of various antennas provided in the user terminal.

4. Method for offloading calculation tasks according to any one of claims 1 to 3, wherein an instantaneous value of exposure of the user to electromagnetic fields is determined.

5. Method for offloading calculation tasks according to any one of claims 1 to 3, wherein a cumulative value over a time window of exposure of the user to electromagnetic fields is determined.

6. Controller (CD1) of offloading of calculation tasks between a user terminal (UE1, UE2, UEm) and a piece of edge host equipment (EH) in a communication network according to a multi-access edge computing technique, the user terminal and the piece of edge host equipment being adapted to: - Offload data necessary for the execution of the calculation from the user terminal to the piece of edge host equipment, - Transmit data resulting from the calculation carried out by the piece of edge host equipment, from the piece of edge host equipment to the user terminal, the controller being adapted to control the offloading of calculation tasks on the basis of a criterion of energy efficiency, the controller being characterized in that it is further adapted to control the offloading of calculation tasks on the basis of a criterion of minimization of exposure of a user of the user terminal to electromagnetic fields, a value of exposure of the user to electromagnetic fields being calculated according to one or more of the following criteria: - - a measurement of momentary radiofrequency electromagnetic dosimetry or a cumulative dose over a time window, the measurement of radiofrequency electromagnetic dosimetry being based both on the distance between the user and an emitter / receiver device of the user terminal and on the power transmitted by the user terminal for offloading calculation tasks, - - the exposure of the user to electromagnetic fields on the basis of specific exposure maps, - - a sum of exposure of the user or of an identified group of people to electromagnetic fields, this exposure being caused by the user terminal or by other sources of electromagnetic fields close to the user terminal.

7. User terminal including a controller of offloading of calculation tasks according to claim 6.

8. Computer program including instructions for the execution of the steps of the method according to any one of claims 1 to 5 when said program is executed by a computer.

9. Recording medium readable by a computer on which a computer program according to claim 8 is recorded.