{"author":{"name":"F. Fernando Jurado-Lasso, J. F. Jurado","slug":"f-fernando-jurado-lasso-j-f-jurado","article_count":1,"latest_published_at":"2026-04-28T14:34:17.732+00:00","profile_url":"https://vff.ai/authors/f-fernando-jurado-lasso-j-f-jurado","api_url":"https://vff.ai/api/authors/f-fernando-jurado-lasso-j-f-jurado"},"articles":[{"slug":"rl-asl-a-dynamic-listening-optimization-for-tsch-networks-using-reinforcement-le","title":"RL-ASL: Reinforcement Learning Cuts IoT Power Use by 46%","url":"https://vff.ai/article/2026/04/28/rl-asl-a-dynamic-listening-optimization-for-tsch-networks-using-reinforcement-le","content_type":"research_summary","summary":"Researchers have developed RL-ASL, a reinforcement learning framework that optimizes power consumption in TSCH (Time Slotted Channel Hopping) networks by dynamically deciding when to skip idle listening slots. The approach, tested on real IoT hardware and simulators, achieves up to 46% lower power consumption while maintaining reliability and reducing latency by up to 96% versus baseline protocols. The model runs inference on resource-constrained devices with negligible overhead since training happens offline, making it practical for industrial IoT deployments.","published_at":"2026-04-28T14:34:17.732+00:00","updated_at":"2026-05-07T02:19:52.375108+00:00","source":{"url":"https://arxiv.org/abs/2604.07533","name":"ArXiv (cs.AI)"},"featured_image":{"url":"https://www.ibm.com/adobe/dynamicmedia/deliver/dm-aid--8f5e56d3-ec4e-4eda-9822-2ce8cde9d680/reinforcement-learning-figure-1.png?preferwebp=true","alt":null},"categories":[{"name":"Research","slug":"research"},{"name":"AI for Business","slug":"ai-for-business"},{"name":"Infrastructure","slug":"infrastructure"}]}]}