time-delay neural network for smart mimo channel estimation in downlink 4g-lte-advance system

1、I.J. Information Technology and Computer Science, 2014, 06, 1-8Published Online May 2014 in MECS (/) DOI: 10.5815/ijitcs.2014.06.01Time-Delay Neural Network for Smart MIMO Channel Estimation in Downlink 4G-LTE- Advance SystemNirmalkumar S. ReshamwalaElectronics and Communicat

2、ion Engineering Department, Sarvajanik College of Engineering and Technology (SCET), Surat, Gujarat, IndiaEmail: Pooja S. SuratiaDepartment of Electrical Engineering, The Maharaja Sayajirao University of Baroda, Vadodara, Gujarat, India Email: Satish

3、K. ShahDepartment of Electrical Engineering, The Maharaja Sayajirao University of Baroda, Vadodara, Gujarat, India Email: satishkshah_20053AbstractLong-Term Evolution (LTE) is the next generation of current mobile telecommunication networks. LTE has a new at radio-network architecture and s

4、ignicant increase in spectrum efficiency. In this paper, main focus on throughput performance analysis of robust MIMO channel estimators for Downlink Long Term Evolution-Advance (DL LTE-A)-4G system using three Artificial Neural Networks: Feed-forward neural network (FFNN), Cascade-forward neural ne

5、twork (CFNN) and Time-Delay neural network (TDNN) are adopted to train the constructed neural networks models separately using Back-Propagation Algorithm. The methods use the information received by the received reference symbols to estimate the total frequency response of the channel in two importa

6、nt phases. In the first phase, the proposed ANN based method learns to adapt to the channel variations, and in the second phase, it estimates the MIMO channel matrix and try to improve throughput of LTE. The performance of the estimation methods is evaluated by simulations in Vienna LTE-A DL Link Le

7、vel Simulator. Performance of the proposed channel estimator, Time-Delay neural network (TDNN) is compared with traditional Least Square (LS) algorithm and ANN based other estimators for Closed Loop Spatial Multiplexing (CLSM)- Single User Multi-input Multi-output (MIMO-22 and 44) in terms of throug

8、hput. Simulation result shows TDNN gives better performance than other ANN based estimations methods and LS.The advances in mobile device technologies, together with the accessibility provided by those devices to the Internet and the numerous applications and services that come with it, are central

9、to need for this research 1. The 3rd Generation Partnership Group standardized Evolved (E-UTRA) as Long Term Evolution to be used as a Next Generation Wireless Network. It is a step towards the fourth generation-4G (LTE-A) that is being developed by 3rd Generation Partnership Project (3GPP), a new s

10、tandard as the evolution of the current network architecture of mobile communications, GSM/HSPA to increase maximum user capacity, the spectral efficiency, low latency and to obtain higher throughput 2-3. LTE towards LTEAdvanced-4G is set to provide higher bit rates in a cost efficient way and, at t

11、he same time, completely fulfill the requirements set by International Telecommunication Union (ITU) for International Mobile Telecommunications-Advanced (IMT Advanced) also referred to as 4G. The features supported by LTE-A are given in 4. Release 10 support enhanced MIMO Techniques with 8X8 in dow

12、nlink and upto 4X4 in uplink with wider bandwidths, enabled by carrier aggregation. It achieves maximum Peak data rate 1 Gbps for downlink and 500 Mbps for uplink. LTE-Advanced downlink uses an Orthogonal Frequency Division Multiplex Access (OFDMA) radio interface in downlink and the Single- Carrier

13、 Frequency Division Multiple Access (SC-FDMA) for the uplink 5-6.The receiver in OFDM-MIMO system requires the knowledge of Channel State Information (CSI) with view to recovering the original transmitted signal data properly without noise. In certain channel estimation methods, pilot symbols are in

14、serted and transmitted over the channel, and are estimated at the receiver in order to recover original transmitted symbols 6-7. The most traditional efficient training based methods are the LeastIndex TermsLTE-A, OFDM-MIMO, Back-Propagation, Feed-forward neural network (FFNN), Cascade-forward neura

15、l network (CFNN), Time-Delay neural network (TDNN)I.INTRODUCTIONResearch beyond 3G mobile radio systems is in progress around the world to allow future mobile networks to support different types of services and applications with high performance as a natural evolution of GSM (Global system for mobil

16、e communications) and UMTS (Universal Mobile Telecommunications System).Copyright 2014 MECSI.J. Information Technology and Computer Science, 2014, 06, 1-82Time-Delay Neural Network for Smart MIMO Channel Estimation in Downlink 4G-LTE-Advance SystemSquares (LS), Minimum Mean Square Error (MMSE)comple

17、xityforreceiverdesign.Also,OFDM-method and Adaptive Filtering channelestimationmulticarrier concept enables the operation of LTE inmethod are given in 8-9. In this paper, Channel estimation by artificial neural networks has beenvarious system bandwidths up to 20 MHz by adapting the number of subcarr

18、iers used. In Closed Loop Spatial Multiplexing-CLSM,Theuplinkfeedbackvalues Channel Quality Indicator (CQI), Rank Indicator (RI) and Precoding Matrix Indicator (PMI) are calculated at the receiver, and are feedback to the eNodeB. In CLSM, Each transmit antenna transmits a different data stream. This

19、 technique significantly increases the peak data rate over the radio link with data quality 13-14.LTE Downlink Physical channels convey information from higher layers in the LTE stack. Each physical channel defines algorithms for bit scrambling, modulation, layer mappin D (Cyclic Delay Diversity), p

20、recoding and resource element assignment. There are three downlink physical channels in LTE 11.In LTE Physical Layer, transport channels act as service access point (SAPs) for higher layers. There are four downlink transport channels in LTE system. Finally, Mapping Downlink Physical Channel to Downl

21、ink Transport Channel is given in 11.deployed in LTE-Advance system, with three different neural networks. In this paper contribution, we propose Study of Different Neural Networks on Throughput Performance of MIMO Channel Estimation for Downlink LTE-Advance System is presented. The principle of thi

22、s method is to exploit the information provided by the received reference symbols to estimate the channel response using channel matrix estimated by conventional LS Estimator 6.This work is organized as follows. In section II, the LTE-A Downlink Physical Layer and The Vienna LTE-A Link Level Simulat

23、or is described. Section III presents different channel estimation techniques like Least Square (LS) and ANN based techniques. Simulation results and throughput performance analysis of proposed ANN based channel estimation techniques are provided in Section IV. Finally, conclusion and future work is

24、 discussed in Section V.II.LTE-A DOWNLINK PHYSICAL LAYER AND VIENNA LTE-A LINK LEVEL SIMULATOR2.1 LTE-A Downlink Physical LayerVarious models LTE-advance Physical Layer is highly efficient means of conveying both data and control information between an enhanced base station (called eNodeB in LTE ter

25、minology) and mobile user equipment (UE). Although, LTE physical layer specification describes both FDD (Frequency Division Duplex) and TDD (Time Division Duplex), the study in this paper is focused on Frequency Division Duplex, thus only LTE physical layer with FDD is discussed below. Furthermore,

26、only downlink data transmission is considered for channel estimation. OFDMA-MIMO system is described in 7, 10. The orthogonal frequency subcarriers are used to share spectrum among users using access technique.Fig. 1. LTE-A Downlink Physical Layer 6TheLTE-APhysicallayeremploysadvancedtechnologies of

27、 wireless cellular systems.LTE-A Downlink Physical Layer 11-12 is described2.2 Vienna LTE-A Link Level SimulatorVienna Link Level Simulator 15-16 is used to emulate the transmission of user data and control information from an eNodeB transmitter to a UE receiver modeling the physical layer with high

28、 precision. The Link level parameters for the presented simulations are as shown in Table I. Transmission modes in the first release of LTE according to 17 are configured in this LTE-A downLink (DL) Link Level Simulator. Simulated MIMO scheme followed CLSM (Close-Loop Spatial Multiplexing) transmiss

29、ion modes are specified in 17-19.The MIMO-OFDM physical channel link level simulator emulates the MIMO-OFDM transmission/ reception through a mobile radio channel. The MIMO channel model and reference scenarios employed as reference for the DL link level simulator are described in 20-21.as shown in

30、Fig. 1. Physical channel processing at eNodeB consists of Scrambling which breaks long strings of 1s and 0s into scrambled bits, Modulation converts scrambled bits into complex-valued symbols uses either QPSK, 16-QAM or 64-QAM modulation, Layer mapper and precoder performs symbol transformations to

31、proceed MIMO transmission techniques, Resource element (RE) mapper maps the symbols to proper locations in the time- frequency Resource grid in physical resource block, OFDM signal mapper generates time domain baseband signals for each antenna port depending upon port 0, 1, 2 or 4 for transmission 1

32、1. Similarly, at receiver side descrambling, demodulation and demapper operationsand MIMO Receiver processing to recoverthetransmitted data streams. LTE-A Downlink modulation is based on OFDMA which provides multi user access, robustness to time dispersion of radio channel, and lowCopyright 2014 MEC

33、SI.J. Information Technology and Computer Science, 2014, 06, 1-8Time-Delay Neural Network for Smart MIMO Channel Estimation in Downlink 4G-LTE-Advance System3A simple network has a feed-forward structure; signals flow from inputs, forwards through any hidden units, eventually reaching the output uni

34、ts. Such a structure has stable behaviour. However, if the network is recurrent (contains connections back from later to earlier neurons with unit delay) it can be unstable, and has very complex dynamics 22.When the network is used in actual application, the input variable values are placed in the i

35、nput units, then output numerical values of each hidden layers and output layer units are progressively calculated with its activation functions. By taking the weighted sum of the outputs of the units in previous layer, and subtracting the threshold. The activation value is passed through the activa

36、tion function to produce the output of the neuron. When the entire network has been executed, the outputs of the output layer act as the output of the whole network 6, 22.A Feed-forward neural Network (FFNN) is one whose topology has no closed paths and number of hidden layer as per requirement and

37、input nodes are connected to the output nodes without any feedback paths. The Back- Propagation Algorithm (BPA) uses the steepest-descent method to reach a global minimum with energy function of MSE. The flowchart of the BPA is given in 6.In Cascade-forward neural network (CFNN), these is similar to

38、 feed forward networks such as Back- Propagation Neural networks (BPNN) with the exception that they have a weight connection from the input and every previous layer to the following layers 6 .Time delay neural network (TDNN) is similar to feed- forward networks, except that the input weight has a t

39、ap delay line associated with it. This allows the network to have a finite dynamic response to time series input data 23.III. CHANNEL ESTIMATION TECHNIQUES BASED ON LS ESTIMATOR AND ANN3.1 Least Square Channel EstimationLeast square channel estimator is obtained by minimizing the square distance bet

40、ween the received signal and the transmitted signal as follows 6-7, 10J(H)= | | = ( )(1)where,is the conjugate transpose operator Bydifferentiating expression (1) with respect and finding the minima, we obtain 7J(H )= + =0to(2)Finally, the LS channel estimation is given by 6-7,10= =(3)In general, LS

41、 channel estimation technique for OFDM systems has low complexity but it suffers from a high mean square error (MSE) 10.3.2 Artificial Neural NetworkNeural networks are algorithms for optimization and learning based loosely on concepts inspired by research into the nature of the brain. An artificial

42、 neural network is defined as follows: It receives a number of inputs either from original data, or from the output of other neurons with delay or without delay from that ANN or others. Each input goes via a connection that has some strength (weight); these weights correspond to synaptic efficacy in

43、 a biological neuron. Each neuron also has a single threshold value. The weighted sum of the inputs is formed, and the threshold subtracted, to compose the activation of the neuron 6, 22.The activation signal is passed through an activation function (also known as a transfer function) to produce the

44、 output of the neuron. There can be neurons of hidden layers those play an important role in the neural network. The input, hidden and output neurons need to be connected together 6, 22.Fig. 2 shows the basic and simple model of feed- forward Neural Network with one hidden layer with five hidden neu

45、rons with one input and one output.3.3 Channel Estimation using Different ANNThe simulation program of each one of conducted Back-Propagationtrainingalgorithm (Feed-Forward neuralnetwork(FFNN),Cascade-Forwardneural network (CFNN) and Time delay neural network (TDNN) includes the following steps 6:1)

46、First of all, estimate channel using traditional LS estimator using transmitted signal and received signal after passing through Flat Rayleigh and AWGN channel and adding noise as shown in Fig. 3.Initialization of network weights, learning rate and Threshold error. Set all iterations to zero.Take re

47、ceived reference symbols as received signal2)3)MIMO matrix as matrix as targetinput and estimated MIMO4)5)Total error = zero; iterations - iterations+1 Feed it to input layer units and Initialize the target output of that ANN.Calculate the outputs of hidden layer units and outputs of output layer un

48、its.Calculate the error = desired output actual output. Total-error - Total-error + error6)7)Fig. 2. Simple model of an Artificial Neuron 6Copyright 2014 MECSI.J. Information Technology and Computer Science, 2014, 06, 1-84Time-Delay Neural Network for Smart MIMO Channel Estimation in Downlink 4G-LTE

49、-Advance System8) Calculate delta sigma of output neurons. Then adjust weights between output and hidden layer units.9) Calculate delta sigma of hidden layer units. Then adjust weights between hidden and input layer units.10) While there is more matrix in the file, go to step 4.11) if Threshold erro

50、r - Total_error then stop, otherwise go to step 3rd steps in this algorithm.4.2 ANN based simulation parametersThe simulation parameters for different Neural Networks are as in Table II.Table 2. Simulation Parameters for FFNN, CFNN and TDNN based EstimatorsIn Feed-forward neural network (FFNN), Casc

51、ade- forward neural network (CFNN) and Time delay neural network (TDNN), the ANN is trained with reference symbols, which is complex type matrix. The target sample set is presented to the ANN in the form of result or estimated complex channel matrix obtained by Least Square (LS). The learning of the

52、 ANN is done in the training phase during which the ANN adjusts its weights according to training algorithm. The ANN is trained for 1000 epochs.In this research paper, Throughput Performance of MIMO Channel Estimation for AWGN and Flat Rayleigh is simulated for downlink LTE-Advanced System using Dif

53、ferent Neural Network. Fig. 4, 5, 6, 7, 8, 9, 10 and 11 show the Throughput versus SNR results for comparison of different neural networks based channel estimation method with LS channel estimator and Ideal Channel for Closed Loop Spatial Multiplexing-Single User Multi- input Multi-output (22 and 44

54、) (CLSM -SUMIMO).In FFNN, CFNN and TDNN, the ANN is trained with reference symbols, which is complex type matrix. The target sample set is presented to the ANN in the form of result or estimated channel obtained by Least Square (LS) complex type matrix. The learning of the ANN is done in the trainin

55、g phase during which the ANN adjusts its weights according to training algorithm. The ANN is trained for 1000 epochs.Fig. 4, 5, 6, and 7 show the Throughput versus SNR results for different ANN based channel estimation method with LS channel estimator and Ideal Channel for Closed Loop Spatial Multip

56、lexing (CLSM)-Single User Multi-input Multi-output (MIMO-22 and 4 4) for AWGN Channel in LTE-A simulator. Fig. 5 and 7 are column chart representation of Fig. 4 and 6, respectively.From Fig. 4, 5, 6, and 7, Cascade-forward neural network (CFNN) is the worst ANN for this application. Feed-forward neu

57、ral network (FFNN) is giving better performance than CFNN. But, Time delay neural network (TDNN) is the most effective to improve performance and shows better results for SNR range 0 dB to 30 dB when compared to ANN based Channel estimators using FFNN and CFNN and traditional method LS estimator.Fig

58、. 3. Channel Estimation using ANN 6The estimator uses the information provided by received reference symbols of sub channels to estimate the total channel frequency response. The input of theneural network is the received reference symbols target of ANN is channel estimated by LS 6, 10.Y,IV. SIMULATION PARAMETERS AND RESULTS4.1 Simulation Parameters for LS Channel Estim