A Bio-Based Render for Insulating Agglomerated Cork Panels

Natural and bio-based thermal insulation materials play an important role in the lifecycle impact of buildings due to their influence on the amount of energy used in indoor temperature control and the environmental impact of building debris. Among bio-based materials, cork is widespread in the Mediterranean region and is one of the bio-based materials that is most frequently used as thermal insulation for buildings. A particular problem is the protection of the cork-agglomerated panels from external stress and adverse weather conditions; in fact, cork granulates are soft and, consequently, cork panels could be damaged by being hit or by excessive sun radiation. In this study, an innovative external coat for cork-agglomerated panels made of a blending composite of beeswax and rosin (colophony) is proposed. The performance of this composite, using different amounts of elements, was analysed to discover which mix led to the best performance. The mix of 50% beeswax and 50% rosin exhibited the best performance out of all the mixes. This blend demonstrated the best elongation and the lowest fracture density, characteristics that determine the durability of the coating. A performance comparison was carried out between cork panel samples coated with lime render and beeswax–rosin coating. The coating of beeswax and resin highlighted a detachment value about 3.5 times higher than the lime plaster applied on the side of the cork.

Online Implementation of a Soft Actor-Critic Agent to Enhance Indoor Temperature Control and Energy Efficiency in Buildings

Recently, a growing interest has been observed in HVAC control systems based on Artificial Intelligence, to improve comfort conditions while avoiding unnecessary energy consumption. In this work, a model-free algorithm belonging to the Deep Reinforcement Learning (DRL) class, Soft Actor-Critic, was implemented to control the supply water temperature to radiant terminal units of a heating system serving an office building. The controller was trained online, and a preliminary sensitivity analysis on hyperparameters was performed to assess their influence on the agent performance. The DRL agent with the best performance was compared to a rule-based controller assumed as a baseline during a three-month heating season. The DRL controller outperformed the baseline after two weeks of deployment, with an overall performance improvement related to control of indoor temperature conditions. Moreover, the adaptability of the DRL agent was tested for various control scenarios, simulating changes of external weather conditions, indoor temperature setpoint, building envelope features and occupancy patterns. The agent dynamically deployed, despite a slight increase in energy consumption, led to an improvement of indoor temperature control, reducing the cumulative sum of temperature violations on average for all scenarios by 75% and 48% compared to the baseline and statically deployed agent respectively.