In order to address the impact of the uncertainty and intermittency of a photovoltaic power generation system on the smooth operation of the power system, a microgrid scheduling model incorporating photovoltaic power generation forecast is proposed in this paper. Firstly, the factors affecting the accuracy of photovoltaic power generation prediction are analyzed by classifying the photovoltaic power generation data using cluster analysis, analyzing its important features using Pearson correlation coefficients, and downscaling the high-dimensional data using PCA. And based on the theories of the sparrow search algorithm, convolutional neural network, and bidirectional long- and short-term memory network, a combined SSA-CNN-BiLSTM prediction model is established, and the attention mechanism is used to improve the prediction accuracy. Secondly, a multi-temporal dispatch optimization model of the microgrid power system, which aims at the economic optimization of the system operation cost and the minimization of the environmental cost, is constructed based on the prediction results. Further, differential evolution is introduced into the QPSO algorithm and the model is solved using this improved quantum particle swarm optimization algorithm. Finally, the feasibility of the photovoltaic power generation forecasting model and the microgrid power system dispatch optimization model, as well as the validity of the solution algorithms, are verified through real case simulation experiments. The results show that the model in this paper has high prediction accuracy. In terms of scheduling strategy, the generation method with the lowest cost is selected to obtain an effective way to interact with the main grid and realize the stable and economically optimized scheduling of the microgrid system.

Considering the impact of environmental pollution and market competition on the business model of enterprises, a method of constructing sustainable supply chain network model under the price competition environment is proposed to achieve the balance of economic benefit, ecological benefit, environmental benefit and social benefit. Firstly, based on the concepts of sustainability and price competition, the model with maximum total network profit, minimum carbon emission and maximum social benefit is designed. Secondly, based on fuzzy programming theory, an expected value fuzzy chance constrained programming model with confidence measure is constructed to address the challenge of designing a sustainable closed-loop supply chain network in the face of uncertain conditions. Thirdly, the problems of premature convergence and slow convergence during the traditional particle swarm optimization algorithm and genetic algorithm are solved with the particle chaotic ant colony algorithm (PSCACO). Finally, taking a manufacturing enterprise as an example. By analyzing the different confidence level measures under single objective optimization and multi-objective optimization, sustainable closed-loop supply chain network planning method established is verified on feasibility and effectiveness.

This paper uses symmetry to develop a dual-channel supply chain network model, both with and without blockchain technology, ensuring that the solutions for pricing and channel selection are symmetric in both modes. And, in the model that does not employ blockchain technology, mechanisms are used to make the benefits of centralized and decentralized decision-making symmetrical. Consumers often have varied psychological expectations when choosing products. This paper considers the reference quality effect, where consumers establish a reference quality before making a purchase decision. However, the lack of transparency in product sales across supply chain channels can lead to a disparity between actual and expected product quality, impacting market demand and brand reputation. Therefore, manufacturers must balance increasing profits with meeting consumer demand for product traceability. This paper focuses on a dual-channel supply chain model involving manufacturers, retailers, and consumers. Firstly, the pricing issues and channel selections under centralized decision-making and a Stackelberg game with decentralized decision-making are comparatively analyzed in the mode of without adopting blockchain technology and adopt two-part pricing contract to coordinate. Secondly, the impact of blockchain technology on pricing is examined when it is adopted. Thirdly, pricing issues and channel selection strategies based on actual product quality in the dual-channel supply chain are compared under both models. Finally, numerical simulations validate the findings. The study found that: (1) the reference quality effect has a cross-positive influence on the equilibrium price and profit of a dual-channel supply chain; (2) the two-part pricing contract can mitigate the double-marginal effect and enhance profits; and (3) the adoption of the blockchain technology leads to increased equilibrium prices and total profits in the dual-channel supply chain compared to not using it. This paper offers a theoretical foundation for manufacturers and retailers to develop effective pricing and channel selection strategies in dual-channel operations to achieve higher returns.