Electricity cost comparison of dynamic pricing model based on load forecasting in home energy management system

To address the primary energy shortage problem, Japan has implemented a series of policies and measures for residential energy conservation and emission reduction. Among them, the home energy management system (HEMS) as a hub connecting users and power companies to realize energy visualization has been widely studied. The research object of this study is a two-story detached residence integrated with HEMS in the “Jono Zero Carbon Smart Community” in Japan. To predict the energy consumed on the next day based on historical data, a short-term household load forecasting model based on the particle swarm optimization regression vector machine algorithm was developed. Then a dynamic pricing model was developed to guide the users’ electricity consumption behavior and adjust the grid load. According to the prediction results obtained by the load forecasting model, the annual electricity charges of users under the three pricing schemes of multistep electricity pricing (MEP), time-of-use pricing (TOU), and real-time pricing (RTP) were calculated and compared. The result indicated that the annual electricity cost generated by RTP was less than those generated by MTP and TOU. In addition, after adjusting the users’ peak load and combining it with the fluctuating future electricity prices, RTP presented evident economic advantage over MTP and TOU in terms of the annual electricity cost of the users. The study results can provide policy suggestions for the future Japanese government’s promotion of RTP strategy, while acting as a reference for further developing the characteristics of HEMS and optimizing the relation between the supply and demand sides. •A short-term forecasting model suitable for household load is established based on PSO-RVM algorithm.•A real-time price (RTP) model is proposed to guide the use behaviors and balance the grid load.•RTP has economic advantages over TOU and MTP under different price schemes.•RTP has a great potential to combine with demand side response and future price fluctuation.•Results can promote RTP and application of HEMS to optimize the relationship between supply and demand.