System impact of decentralised AI controllers operating on domesticdevices in the intelligent home

摘要

The classical approach to curtailing unwanted occurrences on asystem load profile (totalized load current drawn by a group ofelectricity consumers) has been to employ a centralised measurement andcontrol system. Due to the stochastic nature of the individual users,and the group response to such control signals (e.g. ripple control ofgeysers) a decentralised measurement and control approach is proposedhere as a solution to some of the more common problems associated withthis conventional approach (e.g. “cold-load pickup effect”).An adaptive distributed control system is proposed on two levels, bothwithin the home itself (home automation), as well as being expanded upinto the system level itself. Individual measurement and control nodes(i.e. individual homes) will then operate in union to achieve usercustomization, as well as system specific objectives (e.g. no coldshowers, but also enabling maximum demand control)