Time-series forecasting in domains like traffic management and industrial monitoring often requires real-time, energy-efficient processing on edge devices with limited resources. Spiking neural networks (SNNs) offer event-driven computation and ultra-low power and have been proposed for use in this space. Unfortunately, existing SNN-based time-series forecasters often use complex transformer blocks. To address this issue, we propose SpikySpace, a spiking state-space model (SSM) that reduces the quadratic cost in the attention block to linear time via spiking selective scanning. Further, we introduce PTsoftplus and PTSiLU, two efficient approximations of SiLU and Softplus that replace costly exponential and division operations with simple bit-shifts. Evaluated on four multivariate time-series benchmarks, SpikySpace outperforms the leading SNN in terms of accuracy by up to 3.0% while reducing energy consumption by over 96.1%. As the first fully spiking state-space model, SpikySpace bridges neuromorphic efficiency with modern sequence modeling, opening a practical path toward efficient time series forecasting systems. Our code is available at https://anonymous.4open.science/r/SpikySpace.

翻译：在交通管理和工业监控等领域，时间序列预测通常需要在资源受限的边缘设备上进行实时、高效能处理。脉冲神经网络（SNNs）具备事件驱动计算和超低功耗的特性，已被提议应用于这一领域。然而，现有的基于SNN的时间序列预测器常采用复杂的Transformer模块。为解决这一问题，我们提出了SpikySpace，一种脉冲状态空间模型（SSM），它通过脉冲选择性扫描将注意力模块中的二次计算成本降低至线性时间。此外，我们引入了PTsoftplus和PTSiLU，这两种高效的SiLU和Softplus近似方法，用简单的位运算替代了昂贵的指数和除法操作。在四个多元时间序列基准测试上的评估表明，SpikySpace在准确率上优于领先的SNN模型，最高提升达3.0%，同时能耗降低超过96.1%。作为首个全脉冲状态空间模型，SpikySpace将神经形态计算的高效能与现代序列建模相结合，为高效时间序列预测系统开辟了一条实用路径。我们的代码可在https://anonymous.4open.science/r/SpikySpace获取。