| Presentation | 2017-02-18 Prediction Model for Electric Power Demand in Building on Field Data with Extended Goal Graph and Heterogeneous Mixture Modeling Noriyuki Kushiro, Ami Fukuda, Toshihiro Mega, Takuro Shimizu, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | For realizing energy management and demand response in buildings, standardized interfaces, e.g. BACnet and OpenADR, are introduced into building management systems. Huge amount of data, including conditions for spaces and equipment in buildings, are collected from each building and accumulated in an aggregation center via the interfaces. However, control methods for the energy management and the demand response are far behind penetration of these interfaces. As the reason for the delay, both methods for constructing prediction model on big field data and for controlling equipment based on the above prediction model, have not been established yet. We tried to establish the prediction model on two years’ field data. Extended goal graph extracting viewpoints for dividing data on analysis scenarios and explanatory variables, and heterogeneous mixture modeling establishing the perdition model with liner regression were introduced in the study. Results of the above trial are described in this paper. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Prediction Model for Electric Power Demand in Building / Extended Goal Graph / Heterogeneous Mixture Modeling |
| Paper # | AI2016-31 |
| Date of Issue | 2017-02-11 (AI) |
| Conference Information | |
| Committee | AI |
|---|---|
| Conference Date | 2017/2/18(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Toshiharu Sugawara(Waseda Univ.) |
| Vice Chair | Tsunenori Mine(Kyushu Univ.) / Daisuke Katagami(Tokyo Polytechnic Univ.) |
| Secretary | Tsunenori Mine(Ritsumeikan Univ.) / Daisuke Katagami(Shizuoka Univ.) |
| Assistant | Yuichi Sei(Univ. of Electro-Comm.) |
| Paper Information | |
| Registration To | Technical Committee on Artificial Intelligence and Knowledge-Based Processing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Prediction Model for Electric Power Demand in Building on Field Data with Extended Goal Graph and Heterogeneous Mixture Modeling |
| Sub Title (in English) | |
| Keyword(1) | Prediction Model for Electric Power Demand in Building |
| Keyword(2) | Extended Goal Graph |
| Keyword(3) | Heterogeneous Mixture Modeling |
| 1st Author's Name | Noriyuki Kushiro |
| 1st Author's Affiliation | Kyushu Institute of Technology(KIT) |
| 2nd Author's Name | Ami Fukuda |
| 2nd Author's Affiliation | Kyushu Institute of Technology(KIT) |
| 3rd Author's Name | Toshihiro Mega |
| 3rd Author's Affiliation | Mitsubishi Electric Building Techno-Service Corporation(MELTEC) |
| 4th Author's Name | Takuro Shimizu |
| 4th Author's Affiliation | Kyushu Institute of Technology(KIT) |
| Date | 2017-02-18 |
| Paper # | AI2016-31 |
| Volume (vol) | vol.116 |
| Number (no) | AI-460 |
| Page | pp.pp.39-44(AI), |
| #Pages | 6 |
| Date of Issue | 2017-02-11 (AI) |