Brief

This paper introduces a metaheuristic approach using Iterated Local Search (ILS) and Simulated Annealing (SA) to optimize appliance scheduling for solar energy management. The goal is to maximize the utilization of solar energy by aligning appliance usage with generation times, while minimizing user inconvenience and adhering to system constraints like battery charge and inverter limits. The proposed method extends scheduling beyond a single day to handle tasks that spill over, ensuring continuity and enabling multi-day sequential operations. AI

Researchers have developed MiniPIC, a new method for efficient caching in large language model inference that requires fewer than 100 lines of code changes to existing systems like vLLM. This approach improves prefill throughput by 49% and significantly reduces latency for cached spans. Separately, a new technique called BudCache has been introduced for diffusion models, which optimizes caching policies based on a fixed compute budget to maintain output quality, outperforming heuristic methods on FLUX.1-dev and Wan2.1. AI