Reinforcement learning for whole-building HVAC control and demand response

This paper proposes a novel reinforcement learning(RL)architecture for the efficient scheduling and control of the heating,ventilation and air conditioning(HVAC)system in a commercial building while harnessing its de-mand response(DR)potentials.With advances in automated building management systems,this can be achieved seamlessly by a smart autonomous RL agent which takes the best action,for example,a change in HVAC temper-ature set point,necessary to change the electricity usage pattern of a building in response to demand response signals,and with minimal thermal comfort impact to customers.Previous research in this area has tackled only individual aspects of the problem using RL.Specifically,due to the challenges in implementing demand response with whole-building models,simpler analytical models which poorly capture reality have been used instead.And where whole-building models are applied,RL is used for HVAC control mainly to achieve energy efficiency goals while demand response is neglected.Thus,in this research,we implement a holistic framework by designing an efficient RL controller for a whole-building model which learns to optimise and control the HVAC system for improved energy efficiency and thermal comfort levels in addition to achieving demand response goals.Our simulation results show that by applying reinforcement learning for normal HVAC operation,a maximum weekly energy reduction of up to 22%can be achieved compared to a handcrafted baseline controller.Furthermore,by employing a DR-aware RL controller during demand response periods,average power reductions or increases of up to 50%can be achieved on a weekly basis compared to the default RL controller,while keeping occupant thermal comfort levels within acceptable bounds.

Spatio-temporal patterns and changes in environmental attitudes and place attachment in Gauteng, South Africa

In this study,we employed a number of geospatial techniques to examine the spatiotemporal patterns and changes of environmental attitudes and place attachment values in the Gauteng province of South Africa.The data were obtained from the Gauteng City Region Observatory’s Quality of Life Survey collected at three separate points in time,namely 2013,2015,and 2017.Results indicated that wards(smallest administrative and analysis units)located on the urban periphery of Gauteng,which are generally less affluent,largely held more negative environmental attitudes and place attachment values during the three time periods.In contrast,centrally located wards,which are generally more affluent,expressed more positive environmental attitudes but less place attachment values,especially in 2017.The findings of this research not only highlight the complex spatio-temporal distribution of environmental attitudes and place attachment values throughout Gauteng but also empha-size the need for spatially targeted state interventions for future environmental planning within the province.

个体化癫痫治疗管理的新时代

关国良及同事探讨认为,癫痫治疗的试错法已有一个多世纪没有改变,但机器学习和患者衍生的干细胞有望提供一种个体化且更有效的治疗策略。癫痫影响了全世界5000万人,没有年龄、种族或地域上的界限1。患者反复癫痫发作,可导致损伤、认知能力下降、社会心理功能障碍,甚至死亡。癫痫是由脑损伤,如创伤、卒中、肿瘤、炎症和感染,以及基因组变异导致的系统性变化而引起的。癫痫患者会有更多的合并症,包括脑血管疾病、神经认知疾病和精神疾病2。因此更好的控制癫痫将改善整体脑健康。