The scheduling problem of distributed permutation flow shop with limited buffer aiming at production efficiency measures has attracted widespread attention due to its closer alignment with real manufacturing environments. However, the energy efficiency metric is often ignored. The Energy-Efficient scheduling of Distributed Permutation Flow Shop Problem with Limited Buffer (EEDPFSP-LB) with the objectives of Makespan ( $C_{max}$) and Total Energy Consumption (TEC) is studied, and a Cooperative Fruit fly Optimization Algorithm (CFOA) is proposed in this paper. First, the critical path of EEDPFSP-LB is identified, and energy-efficient operation is applied to non-critical paths to reduce the system’s energy consumption. Second, five acceptance criteria for multi-objective optimization are introduced to enhance the diversity of the population. Third, to select a superior next-generation population, a new congestion calculation method is introduced to resolve the issue of indeterminate positional relationships among non-dominated solutions with identical crowding distances at the same dominance level. Finally, CFOA is extensively tested and compared with state-of-the-art algorithms across 360 instances, demonstrating CFOA’s strong competitiveness in solving EEDPFSP-LB.

Accurate wind speed prediction has been becoming an indispensable technology in system security, wind energy utilization, and power grid dispatching in recent years. However, it is an arduous task to predict wind speed due to its variable and random characteristics. For the objective to enhance the performance of forecasting short-term wind speed, this work puts forward a hybrid deep learning model mixing time series decomposition algorithm and gated recurrent unit (GRU). The time series decomposition algorithm combines the following two parts: (1) the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and (2) wavelet packet decomposition (WPD). Firstly, the normalized wind speed time series (WSTS) are handled by CEEMDAN to gain pure fixed-frequency components and a residual signal. The WPD algorithm conducts the second-order decomposition to the first component that contains complex and high frequency signal of raw WSTS. Finally, GRU networks are established for all the relevant components of the signals, and the predicted wind speeds are obtained by superimposing the prediction of each component. Results from two case studies, adopting wind data from laboratory and wind farm, respectively, suggest that the related trend of the WSTS can be separated effectively by the proposed time series decomposition algorithm, and the accuracy of short-time wind speed prediction can be heightened significantly mixing the time series decomposition algorithm and GRU networks.