FIELD OF INVENTION

[0001] The embodiments herein relate to wireless networks and more particularly to a method and an apparatus for switching between various transmission rate predictors as a restless Multi-Armed Bandit (MAB) problem. The present application is based on, and claims priority from an Indian Application Number 201641003618 filed on 2 ^nd February 2016 the disclosure of which is hereby incorporated by reference herein.

BACKGROUND OF INVENTION

[0002] Rate adaptation through various Transmission Rates (TR) have played an important role in exploiting the instantaneous channel capacity by transmitting bits at a rate that is optimally suited to the current channel conditions. The advancements in a practical wireless system is characterized by increase an in the transmission rates supported by the wireless system and this trend is likely to be unchanged.

[0003] A rate adaptation metric, which reflects the channel capacity, is computed at the User Equipment (UE), and is quantized and fed back to the evolved Node B (eNB). In an example, in Long Term Evolution (LTE) the quantized rate adaptation is performed based on a feedback from the UE. The UE provides a Channel Quality Indicator (CQI) feedback, which is a number between 0 and 15, to the eNB. The CQI value is then mapped to a 5 bit Modulation and Coding Scheme (MCS), at the eNB. The CQI to MCS index mapping in LTE depends upon the CQI feedback and the quantity of resources allocated. The MCS index is used to control the transmission rate, i.e., the rate at which data is transmitted from the eNB to the UE.

[0004] The UE also provides an Acknowledgement/Negative Acknowledgement (ACK/NACK) response indicating whether packets are successfully decoded by the UE at a particular transmission rate selected by the eNB. Based on the ACK/NACK response and CQI feedback, the eNB adjusts the transmission rate such that QoS parameters are met. In an example, the QoS parameters can be Block Error Rate (BLER), throughput, latency or the like.

[0005] There are transmission rate predictors in the eNB, which are able to predict the transmission rate based on a transmission rate history. The ACK/NACK response and CQI feedback is received by the eNB intermittently from the UE. The ACK/NACK response and CQI feedback, received from the UE, are accumulated over a period of time and are stored as transmission rate history. Instead of transmitting data at a rate based on the ACK/NACK response and CQI feedback, the eNB transmits data at a rate based on the transmission rate predicted by the transmission rate predictor based on user history.

[0006] However, there are multiple QoS parameters such as BLER, throughput, latency, or the like, which need to be optimized by the transmission rate predictor according to an overall QoS requirement of each UE. The transmission rate predictor needs to ensure that all the QoS parameters are optimized such that the overall QoS is achieved. Since meeting the overall QoS requirement requires optimization of all QoS parameters, the design of the transmission rate predictor becomes complex and the training period of the transmission rate predictor, for predicting the optimal transmission rate, is high since multiple QoS parameters are initialized at the same time.

[0007] Thus, there is a need of having a method which can meet the overall QoS requirements of each UE through a transmission rate predictor having simple architectural and time complexity respectively.

[0008] The above information is presented as background only to help the reader for understanding the present invention. Applicants have made no determination and make no assertion as to whether any of the above might be applicable as Prior Art with regard to the present application.

OBJECT OF INVENTION

[0009] The principal object of the embodiments herein is to provide a method and an apparatus for switching between various transmission rate predictors as a restless Multi-Armed Bandit (MAB) problem.

[0010] Another object of the embodiments herein is to associate each of transmission rate predictors, associated with each of a Quality of Service (QoS) parameter, to each of the arms of the restless MAB, in which each of the QoS parameters is having a predefined target value.

[0011] Another object of the embodiments herein is to determine that a QoS parameter, associated with an arm of the restless MAB, fails to meet the first predefined target QoS value associated the arm of the restless MAB, based on the cumulative ACK/NACK response from the UE. [0012] Another object of the embodiments herein is to select a transmission rate prediction technique associated with a QoS parameter, in which the QoS value is less the predefined target QoS value.

[0013] Another object of the invention herein is to select the arm of the restless MAB based on the QoS requirements.

SUMMARY

[0014] Accordingly embodiments herein provide a method and an apparatus for switching between various transmission rate predictors as a restless Multi-Armed Bandit (MAB) problem. The method includes associating each of transmission rate predictor to each of the arms of the restless MAB. Each of the arms of the restless MAB is associated with a Quality of Service (QoS) parameter, in which each of the QoS parameters is having a predefined target value. The transmission rate predictors allow optimizing and/or correcting corresponding QoS parameter. The method includes determining a cumulative Acknowledgement/Negative Acknowledgement (ACK/NACK) response from a User Equipment (UE) for a Transport Block (TB). The method includes determining that a QoS parameter, associated with an arm of the restless MAB, fails to meet the first predefined target value associated with the arm of the restless MAB. The determination is based on the cumulative ACK/NACK response from the UE. The method includes selecting the transmission rate predictor corresponding to the QoS parameter, failing to meet the predefined target value, to optimize the QoS parameter.

[0015] In an embodiment, the method includes varying the predefined value of the QoS parameter through the transmission rate predictor, based on the cumulative ACK/NACK response from the UE. The method includes determining that the updated value of the QoS parameter meets the first predefined target value based on the cumulative ACK/NACK response.

[0016] Accordingly the embodiments herein provide a computer program product comprising computer executable program code recorded on a computer readable non-transitory storage medium where the computer executable program code when executed causing the actions which includes associating each of transmission rate predictors, corresponding to each of QoS parameter, to each of the arms of a restless MAB, wherein each of the QoS parameters is having a predefined target value. Further, the computer executable program code when executed causing the actions which includes determining a cumulative ACK/NACK response from a UE for a TB. Further, the computer executable program code when executed causing the actions which includes determining that a QoS parameter, associated with an arm of the restless MAB, fails to meet the first predefined target value associated with the arm of the restless MAB, based on the cumulative ACK/NACK response from the UE. Further, the computer executable program code when executed causing the actions which includes selecting the first transmission rate predictor corresponding to the first QoS parameter to optimize the first QoS parameter.

[0017] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.

BRIEF DESCRIPTION OF FIGURES

[0018] This method is illustrated in the accompanying drawings, throughout which like reference letters indicate corresponding parts in the various figures. The embodiments herein will be better understood from the following description with reference to the drawings, in which:

[0019] FIG. 1 illustrates an eNB, transmitting data at various transmission rates, and a UE 102, transmitting feedback based on a transmission rate, according to the embodiments as disclosed herein;

[0020] FIG. 2 is a flowchart depicting a proposed method of switching between various transmission rate predictors as a restless Multi-Armed Bandit (MAB) problem, according to the embodiments as disclosed herein; and

[0021] FIG. 3 illustrates a computing environment implementing the proposed method, according to the embodiments as disclosed herein.

DETAILED DESCRIPTION OF INVENTION

[0022] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well- known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments. The term "or" as used herein, refers to a non-exclusive or, unless otherwise indicated. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those skilled in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

[0023] Accordingly embodiments herein provide a method and an apparatus for switching between various transmission rate predictors as a restless Multi-Armed Bandit (MAB) problem. The method includes associating each of transmission rate predictor to each of the arms of the restless MAB. Each of the arms of the restless MAB is associated with a Quality of Service (QoS) parameter, in which each of the QoS parameters is having a predefined target value. The transmission rate predictors allow optimizing and/or achieving the corresponding QoS parameter. The method includes determining a cumulative Acknowledgement/Negative Acknowledgement (ACK/NACK) response from a User Equipment (UE) for a Transport Block (TB). The method includes determining that a QoS parameter, associated with an arm of the restless MAB, fails to meet the first predefined target value associated with the arm of the restless MAB. The determination is based on the CQI feedback and cumulative ACK/NACK response from the UE. The method includes selecting the transmission rate predictor corresponding to the QoS parameter, failing to meet the predefined target value, to optimize the QoS parameter. Post selection of the transmission rate predictor, the proposed method allows optimizing other QoS parameters such that the overall QoS is achieved.

[0024] Unlike conventional methods, the proposed method allows optimization of multiple QoS parameters such as BLER, throughput, latency, or the like, at the same time. The proposed method provides a plurality of transmission rate predictors, in which each transmission rate predictor optimizes a particular QoS parameter such that an overall QoS requirement is achieved. Each of the transmission rate predictors are associated with an arm of the restless MAB, in which the selection of an arm is based on whether a QoS parameter associated with the arm is able to meet the predefined target value. Associating multiple transmission rate predictors with the arms of the restless MAB prevents the need of having a complex transmission rate predictor. The proposed method allows prediction of the optimal transmission rate for optimizing all QoS parameters for achieving the overall QoS by switching between the transmission rate predictors.

[0025] Referring now to the drawings and more particularly to FIGS. 1 through 3, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments.

[0026] FIG. 1 illustrates an eNB 100, transmitting data at various transmission rates, and a UE 102 transmitting feedback based on a transmission rate, according to the embodiments as disclosed herein.

[0027] As depicted in FIG. 1, the eNB 100 includes a plurality of transmission rate predictors, in which each transmission rate predictor is associated to QoS parameter and is meant for optimizing the associated QoS parameter. The selection of a particular transmission rate predictor is based on whether the associated QoS parameter meets the predefined target value. The particular transmission rate predictor is selected using the restless MAB.

[0028] Once the channel conditions are estimated through the CQI feedback from the UE 102, the eNB 100 transmits data (TB) at a particular transmission rate. The method includes determining a cumulative ACK/NACK response from the UE 102 for the transmitted data. The UE 102 provides an ACK/NACK response, indicating whether the UE 102 is able to successfully decode packets transmitted by the eNB 100.

[0029] The UE 102 transmits the CQI feedback and the ACK/NACK response, which is accumulated with time and stored as transmission rate history in the eNB 100. The transmission rate predictor predicts the transmission rate and transmits data at the predicted transmission rate based on the transmission rate history.

[0030] FIG. 2 is a flowchart 200 depicting a proposed method of switching between various transmission rate predictors as the restless MAB, according to the embodiments as disclosed herein. [0031] At step 202, the method includes associating each of transmission rate predictors to each of the arms of a restless MAB. Each of the transmission rate predictors is associated with each QoS parameter, in which each of the QoS parameters is having a predefined target value. The transmission rate predictors ensure that the corresponding QoS parameter is able to achieve the predefined target value, while the other QoS parameters are optimized such that the overall QoS is met.

[0032] The proposed method allows selection of one transmission rate predictor amongst the plurality of transmission rate predictors based on whether each of the QoS parameters meets the predefined target value. The proposed method, using the restless MAB allows selection of a transmission rate decoder, which allows transmission of data at an optimal transmission rate thereby allowing achieving the overall QoS requirement. In an embodiment, the proposed method allows selection of one transmission rate predictor, amongst the plurality of transmission rate predictors {A],A ₂ , . . .,A _n } for maintaining a target BLER while maximizing the throughput. If there are n transmission rate predictors allowing different QoS parameters {6 ₁ ,6 ₂ , . . . ,6 _n J to achieve the pre-defined target values, then the proposed method allows all the QoS parameters to achieve the respective predefined target value by selecting the optimal transmission rate predictor. In an example, the different QoS parameters are Block Error Rate (BLER), packet delay, a traffic dependent QoS metric, latency, or the like.

[0033] At step 204, the method includes determining a cumulative ACK/NACK response from a UE 102 for a TB. Once the channel conditions are estimated through the CQI feedback, the eNB 100 transmits data at a particular transmission rate. The UE 102 provides ACK/NACK response, indicating whether the UE 102 is able to successfully decode packets transmitted by the eNB 100. The UE 102 intermittingly transmits the CQI feedback and the ACK/NACK response to the eNB 100, which is accumulated with time and stored as transmission rate history. The transmission rate predictor predicts the transmission rate and transmits data at the predicted transmission rate based on the transmission rate history rather than the transmission rate based on the CQI feedback and the ACK/NACK response from the UE 102. In an embodiment, the predicted transmission rate is lower than the transmission rate which is based on the CQI feedback and the ACK/NACK response from the UE 102. In another embodiment, the predicted transmission rate is higher than the transmission rate which is based on the CQI feedback and the ACK/NACK response from the UE 102. [0034] While transmitting data to the UE 102, the different QoS parameters are optimized to ensure that the different QoS parameters meet the predefined target value. Each of the transmission rate predictors transmits data at the predicted transmission rate such that the corresponding QoS parameter is able to achieve the predefined target value. In an example, a transmission rate predictor used for optimizing BLER, predicts the transmission rate for transmitting data such the BLER is able to reach the target BLER. In another example, another transmission rate predictor used for optimizing throughput, predicts the transmission rate for transmitting data such the throughput is able to reach the target maximum throughput.

[0035] At step 206, the method includes determining that a first QoS parameter, associated with a first arm of the restless MAB, fails to meet the first predefined target value associated with the first arm of the restless MAB. The determination is based on the cumulative ACK/NACK response from the UE 102. At step 208, the method includes selecting the first transmission rate predictor associated with the first QoS parameter to meet the predefined target of the first QoS parameter. The first transmission rate predictor is selected due to the fact that the first QoS parameter is not able to meet the predefined target QoS value. Similarly, if another QoS parameter fails to meet the predefined target QoS value, the corresponding transmission rate predictor is selected.

[0036] In an example scenario, considering a second transmission rate predictor which attempts to achieve a target BLER, one of the QoS parameters. In order to achieve the target BLER, the throughput, another QoS parameter, may be reduced. If the throughput reduces below the predefined target throughput, then a transmission rate predictor, i.e., the first transmission rate predictor, meant for optimizing throughput, is selected by the proposed method. The procedure of selecting a particular transmission rate predictor is based on the restless MAB. The transmission rate predictors are associated with the arm of the restless MAB. The first transmission rate predictor allows varying the throughput such that the predefined target throughput is achieved. While the first transmission rate predictor causes an increase in throughput, it has to simultaneously optimize the other QoS parameters such that the overall QoS is achieved. A third transmission rate predictor attempts to reduce latency.

[0037] At step 210, the method includes varying the predefined value of the first QoS parameter through the first transmission rate predictor. The variation is based on the CQI feedback and cumulative ACK/NACK response from the UE 102, and predicted transmission rate. The first transmission rate predictor allows the first QoS parameter to meet its predefined target value. At step 212, the method includes determining that the updated value of the first QoS parameter meets the first predefined target value based on the cumulative ACK/NACK feedback from the UE 102. The ACK/NACK feedback indicates whether the UE 102 is able to successfully decode the data packets transmitted at the predicted transmission rate. It is to be noted that while a particular transmission rate predictor is selected, the selected transmission rate predictor ensures that the overall QoS is achieved.

[0038] The various actions, acts, blocks, steps, or the like in the flowchart 200 may be performed in the order presented, in a different order or simultaneously. Further, in some embodiments, some of the actions, acts, blocks, steps, or the like may be omitted, added, modified, skipped, or the like without departing from the scope of the invention. The method and other description provide a basis for a control program, which can be easily implemented by a microcontroller, microprocessor, or a combination thereof.

[0039] FIG. 3 illustrates a computing environment implementing the proposed method, according to embodiments as disclosed herein.

[0040] As depicted in the FIG. 3, the computing environment 302 comprises at least one processing unit 308 that is equipped with a control unit 304 and an Arithmetic Logic Unit (ALU) 306, a memory 310, a storage unit 316, plurality of networking devices 312 and a plurality Input output (I/O) devices 314. The processing unit 308 is responsible for processing the instructions of the technique. The processing unit 308 receives commands from the control unit in order to perform its processing. Further, any logical and arithmetic operations involved in the execution of the instructions are computed with the help of the ALU 306.

[0041] The overall computing environment 302 can be composed of multiple homogeneous and/or heterogeneous cores, multiple CPUs of different kinds, special media and other accelerators. The processing unit 308 is responsible for processing the instructions of the technique. Further, the plurality of processing units 308 may be located on a single chip or over multiple chips.

[0042] The technique comprising of instructions and codes required for the implementation are stored in either the memory unit 310 or the storage 316 or both. At the time of execution, the instructions may be fetched from the corresponding memory 310 or storage 316, and executed by the processing unit 308. [0043] In case of any hardware implementations various networking devices 312 or external I/O devices 314 may be connected to the computing environment to support the implementation through the networking unit and the I/O device unit.

[0044] The embodiments disclosed herein can be implemented through at least one software program running on at least one hardware device and performing network management functions to control the elements. The elements shown in the FIGS. 1 and 3 include blocks which can be at least one of a hardware device, or a combination of hardware device and software module.

The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.