Workflow scheduling is critical for efficient cloud resource management. This paper proposes Tunicate Swarm-Highest Response Ratio Next, a novel scheduler that synergistically combines the Tunicate Swarm Algorithm with the Highest Response Ratio Next policy. The Tunicate Swarm Algorithm generates a cost-minimizing task-to-VM mapping scheme, while the Highest Response Ratio Next dynamically dispatches tasks in the ready queue with the highest-priority. Experimental results demonstrate that the Tunicate Swarm-Highest Response Ratio Next reduces costs by up to 94.8% compared to meta-heuristic baselines. It also achieves competitive cost efficiency vs. a learning-based method while offering superior operational simplicity and efficiency, establishing it as a highly practical solution for dynamic cloud environments.

In the wireless energy transmission service composition optimization problem, a key challenge is accurately capturing users’ preferences for service criteria under complex influencing factors, and optimally selecting a composition solution under their budget constraints. Existing studies typically evaluate satisfaction solely based on energy transmission capacity, while overlooking critical factors such as price and trustworthiness of the provider, leading to a mismatch between optimization outcomes and user needs. To address this gap, we construct a user satisfaction evaluation model for multi-user and multi-provider scenarios, systematically incorporating service price, transmission capacity, and trustworthiness into the satisfaction assessment framework. Furthermore, we propose a Budget-Aware Preference Adjustment Model that predicts users’ baseline preference weights from historical data and dynamically adjusts them according to budget levels, thereby reflecting user preferences more realistically under varying budget constraints. In addition, to tackle the composition optimization problem, we develop a Reflective-Evolutionary Large Language Model—Guided Ant Colony Optimization algorithm, which leverages the reflective evolution capability of large language models to iteratively generate and refine heuristic information that guides the search process. Experimental results demonstrate that the proposed framework effectively integrates personalized preferences with budget sensitivity, accurately predicts users’ preferences, and significantly enhances their satisfaction under complex constraints.