Inner Mongolia Electric Power (China)

This paper proposes a safety-constrained Transformer–PPO framework for low-carbon economic dispatch with settable incentive-based demand response (DR) in wind–PV integrated electro–thermal–hydrogen industrial-park energy systems. Hydrogen is modeled as exogenous hydrogen-domain demand and is satisfied through electrolyzer production and hydrogen inventory dynamics. A causal Transformer captures long-horizon multi-energy coupling and intertemporal constraints and is trained with PPO under uncertainty. A dual-layer safety mechanism combines dual-variable (Lagrange multiplier) updates for statistical constraints with an execution-layer quadratic-programming action projection to enforce hard physical constraints, including operating limits, ramping, battery SOC, hydrogen inventory bounds, and energy balance. Baseline–verification–settlement rules and budget-ledger states are embedded to ensure verifiable response quantities and settlement outcomes that are traceable and independently recompilable. Case studies on a real industrial-park scenario in Inner Mongolia show reduced peak-hour maximum grid purchase demand and constraint violations, together with lower total cost, carbon cost, and curtailment penalties versus MILP, PPO-MLP, and Transformer–PPO without safety mechanisms.

This study evaluated the effects of Lactic acid bacteria and cellulase, individually and in combination, on fermentation quality and microbial community dynamics of alfalfa silage. Six treatments were tested, including control, cellulase alone and two lactic acid bacteria species (Pediococcus pentosaceus, Levilactobacillus brevis) applied individually or in combination with cellulase. The results showed that Levilactobacillus brevis in combination with cellulase, producing higher lactic acid concentrations, lower pH (< 4.2) to the other treatments. The microbiome analysis revealed that Lactiplantibacillus was dominant, while undesirable bacterium Achromobacter was suppressed. Functional prediction of microbial communities analysis indicated a higher predicted abundance of sequences associated with pyruvate metabolism, glycolysis/gluconeogenesis and starch and sucrose metabolism pathways. These findings provide insights into optimizing alfalfa silage quality through synergistic use of cellulase and lactic acid bacteria silage inoculants with high metabolic stability.

The energy system is transforming in clean, low-carbon, safe, and efficient directions. As a key carrier of energy consumption, the operation optimization of the integrated energy system (IES) in industrial parks has become an important lever for facilitating energy transformation. This paper focuses on the modeling of the operation optimization of the IES, pays attention to the impact of electricity–carbon–green certificate coordination, and studies the operation optimization of the IES considering hydrogen energy utilization. Firstly, the topological structure of IES is analyzed, and a model of the integrated energy system in industrial parks covering multiple energy links, such as electricity, heat, and gas, is constructed. Hydrogen energy conversion units such as electrolyzers, fuel cells, and methane reactors are introduced. Secondly, the impact of electricity, carbon, and green certificate markets on the operation of IES is analyzed, and a green certificate-carbon trading integration mechanism is designed, along with the establishment of a corresponding market trading model. Then, with the system’s energy purchase and sale costs, electricity curtailment costs, carbon market transaction costs, green certificate transaction revenues, and equipment operation and maintenance costs as the core, an IES daily optimization scheduling model is constructed to minimize the overall cost. Finally, the feasibility of the model constructed in this paper is verified through a case study in the industrial park in the north of Dezhou, Shandong Province, and the result shows that the cost of IES is 15,013.7 yuan under the optimal operation schedule. The utilization rate of new power energy reaches 89.6%, and the 2.135 green certificates are converted into the carbon market. Meanwhile, comparative analysis across multiple scenarios and sensitivity analysis of single factors are conducted to discuss the necessity and effectiveness of the factors considered in this paper, providing a decision-making basis and inspiration for managers to carry out IES operation scheduling.

Efficient management of electric power materials—spanning inspection, storage, and distribution—is crucial for maintaining the reliability and resilience of power systems. Traditional decision-making approaches often rely on heuristic or rule-based systems, which can lack the adaptability and precision needed in dynamic environments. This paper proposes a novel decision optimization method using deep reinforcement learning (DRL) to enhance decision-making across these domains. The proposed model leverages a DRL framework, allowing it to autonomously learn optimal policies through interaction with the environment. Experimental results demonstrate that the DRL-based approach significantly improves operational efficiency, resource allocation, and response times compared to conventional methods. This research offers a data-driven, adaptive solution that aligns with the complex and evolving demands of electric power material management.