Predicting Parking Occupancy by FPGA-Accelerated DNN Models at Fog Layer

Model inference is the final stage in machine/deep learning application deployments in practical applications. Hardware-implemented or accelerated model inferences find significant attractions as they offer faster inference than those implemented as programs. This is especially attractive for real-time applications. In this paper, we address models that serve for parking occupancy prediction based on historical time-series parking records. We use the Keras library to build and train software DNN and LSTM models, then compare their prediction performances in terms of accuracy. While the software-implemented inference models indicate advantages of LSTM, we still opted to select only DNN-based models for additional hardware acceleration as the current advanced tool-chains leveraged for automatic software-to-hardware model converting do not allow the creation of LSTM hardware- implemented models. We create, explore and compare the inference performances of hardware (FPGA)-implemented models on relatively low-cost FPGAs. For this, we create an FPGA-accelerated Fog-layer cluster by adding two additional Xilinx FPGA boards of different performances into our existing cluster of four Raspberry Pi (RPi) computers.