In the internet of things (IoT), high-dimensional time series data are generated continuously and recorded from different data sources; moreover, these time series are characterized by intrinsic changes known as concept drifts. Beside, decision-making in IoT applications may often involve multiple factors and criteria. Therefore, methods capable of handling high-dimensional non-stationary time series and many outputs are of great value in IoT applications. An important gap in the literature is the absence of fuzzy time series (FTS) multiple-input multiple-output (MIMO) methods. To fill this gap, we present a new methodology for forecasting high-dimensional non-stationary time series called MO-ENSFTS (multiple output embedding non-stationary fuzzy time series). MO-ENSFTS is a first-order MIMO multivariate model. We apply a combination of data embedding transformation and a non-stationary FTS model. We tested the proposed methodology on four real-world high-dimensional IoT time-series data sets. The proposed approach is a data-driven method, which is flexible and adaptable for many IoT applications. The computational results show that the proposed method outperforms recurrent neural networks, random forests and support vector regression methods, and is more parsimonious than deep learning methods.