Efficient warehousing resources distribution is essential for reducing logistics costs and improving supply chain performance. With advancements in information technology and the rise of the sharing economy, many enterprises are adopting the product-service system (PSS) to support cleaner production (CP) and circular economy (CE) strategies. However, logistics stakeholders face many challenges in developing effective sharing strategies under dynamic markets and personalized demands. To address these challenges, an evolutionary game-based approach to warehousing resource sharing (WRS) under the PSS paradigm to maximize stakeholder benefits is proposed in this paper. By using double auction mechanisms, a utility functions for suppliers and demanders are designed, after which the replicator dynamics equations and Jacobian matrices are applied to identify the evolutionarily stable strategies (ESS). Finally, a case study with numerical simulations are carried out to confirm the feasibility of the proposed approach. The results highlighted three key findings: (1) low cloud platform operating costs are vital for enabling unsupervised management; (2) suppliers exhibit sensitivity to initial sharing probabilities and subsidy rates; and (3) demanders can achieve enhanced flexibility and redundancy reduction through high information resource saturation. These insights can inform the formulation of effective WRS strategies to foster sustainable and competitive logistics ecosystems.

Electricity is fundamental to national economic and social development, and its stable supply depends on accurate power load forecasting. Thus, developing precise forecasting models is essential for efficient power system operation. However, increasing global energy demand exacerbates the volatility, randomness, and intermittency of power loads, compromising forecasting accuracy. To address complex dynamic data characteristics, this study proposes a hybrid forecasting method integrating parallel decomposition and deep learning. The method first decomposes the original data into multiple modal components and stable feature items, iteratively generating optimal sub-feature sets. Subsequently, an optimization framework is constructed based on the Sparrow Search Algorithm (SSA). This framework integrates binary feature selection with hyperparameter tuning. The tuned hyperparameters belong to an advanced neural network combining a Bidirectional Temporal Convolutional Network (BiTCN) and a Long Short-Term Memory (LSTM) network. This achieves joint feature and parameter optimization. Compared with traditional methods, this method fully exploits the temporal and structural characteristics of the data by integrating feature selection and hyperparameter optimization. For 6-step forecasting on dataset1, the method achieves a mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute error (MAE) are 2.30 %, 845.8 and 606.2, respectively.