Digital predistortion (DPD) is a popular technique to enhance signal quality in wideband radio frequency (RF) power amplifiers (PAs). With increasing bandwidth and data rates, DPD faces significant energy consumption challenges during deployment, contrasting with its efficiency goals. State-of-the-art DPD models rely on recurrent neural networks (RNNs), whose computational complexity hinders system efficiency. This letter introduces DeltaDPD, exploring the dynamic temporal sparsity of input signals and neuronal hidden states in RNNs for energy-efficient DPD, reducing arithmetic operations and memory accesses while preserving satisfactory linearization performance. Applying a TM3.1a 200 MHz-BW 256-QAM OFDM signal to a 3.5-GHz GaN Doherty RF PA, DeltaDPD achieves −50.03 dBc in adjacent channel power ratio (ACPR), −37.22dB in normalized mean square error (NMSE) and −38.52 dB in error vector magnitude (EVM) with 52% temporal sparsity, leading to a 1.8\times reduction in estimated inference power.

Broadband amplification of signals is desirable in many applications such as high-speed data communications, high-resolution imaging systems, optoelectronics, and instrumentation systems. Wide bandwidth is one of the prominent factors to be considered in designing such systems because it determines the system's ability to transfer high-data-rate information, transmit/receive short pulses, and process wide-band signals. Designing broadband amplifiers has always been challenging. The ever-increasing demand for higher data rates and low energy consumption in next-generation communication systems further complicates broadband amplifier design.