1 Introduction
-
Evaluate and compare MMSE, LS and DL methods in estimating the impulse response of different channels for next generation 5G cellular mobile communications based on OFDM modulation. The three methods are evaluated using Tapped Delay Line (TDL) and Clustered Delay Line (CDL) channel models. Both channel models are specified at The European Telecommunications Standards Institute (ETSI) technical report [12‐14] as prominent channel models for LTE and 5G systems working above 6 GHz, The International Telecommunication Union (ITU) model for 5G systems has been used for the three systems as a base of comparison [12‐14].
-
Use the long short-term memory (LSTM) network model [15, 16] to create the DNN for symbol classification at OFDM receiver. LSTM designs can store data over time period. This characteristic is extremely useful when we deal with Time-Series or Sequential Data. It is processing not only single data points (e.g., images), but also entire data sequences (such as speech or video inputs). The LSTM-based neural network is trained for a generated OFDM signal, where the Bit error rate (BER) is calculated and compared with the LS and MMSE estimations. During the offline training and the online deployment stages in this preliminary investigation the wireless channel is presumed to be fixed. A random phase shift for each transmitted OFDM packet is implemented to assess the effectiveness of the neural network.
2 Literature Review
3 Background
3.1 Channel Estimation in OFDM Systems
3.2 Conventional Channel Estimation Methods
3.3 Deep Neural Network Based Channel Estimation
4 LSTM Based Channel Estimation
4.1 System Architecture for DL Channel Estimation
4.2 Model Training
5 Simulation
5.1 Description of Simulation
Parameters | Specifications |
---|---|
Number of subcarriers | 64 |
Number of pilot subcarriers | 64 pilots–8 pilots |
Pilot Ratio | 1 or 8 |
Number of OFDM block | 2 OFDM block that contain the pilots and transmitted symbols, respectively |
The number of paths | 20 paths |
The length of the cyclic prefix | 16 or 0 samples |
max delay | 16 samples |
Signal Constellation | QPSK |
Channel Model | Rayleigh Fading, TDL, CDL and 3GPP TR38.901 |
Carrier Frequency | 4 GHz |
LSTM Architecture | Consists of 5 × 1 Layer array with layers, |
(i) Sequence input layer inputs sequence data to a network with (2*OFDM block number*Subcarrier number) dimension | |
(ii) LSTM layer with 16 hidden units | |
(iii) 4 fully connected layer | |
(iv) Softmax layer | |
(v) Classification Output layer |