Presentation | 2020-09-11 Proposal and Evaluation on Prediction Method for Electricity Using Probability of Missing Sensor Value Norifumi Hirata, Osamu Maeshima, Kiyohito Yoshihara, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | VPP (Virtual Power Plant) is known as a system for electric power demand-supply adjustment. VPP is realized by controls of distributed electric power sources. VPP system uses a demand-supply adjustment market for demand-supply adjustment, and need to predict electric power demand and supply sources to bid the market. The success or failure of the demand-supply adjustment is evaluated by the difference between the transaction quantities in the market and the sum of the observation value of the electric power sensor. If a sensor of a power source has a missing value, an observation value of the power source is regarded as zero. A problem by missing observation value is increasing prediction error and wrong controls by the prediction error. VPP system need to a prediction method of observation value based on missing probability of electric sensors that is not an interpolation method of input data. Therefore, we propose a method to reduce the prediction error using missing probability. The missing probability is calculated separately for two types of missing. As a result of evaluating error of missing probability, we confirmed the error ratio by our proposed method is 1.56%, which was smaller than error ratio (2.14%) by the baseline method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Time Series prediction / Missing Data / VPP |
Paper # | IN2020-27 |
Date of Issue | 2020-09-03 (IN) |
Conference Information | |
Committee | CS / IN / NS |
---|---|
Conference Date | 2020/9/10(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Session management (SIP/IMS), Interoperability/Standardization, NGN/NwGN/Future networks, Cloud/Data center networks, SDN (OpenFlow, etc.)/NFV, IPv6, Machine learning, etc. |
Chair | Jun Terada(NTT) / Kenji Ishida(Hiroshima City Univ.) / Akihiro Nakao(Univ. of Tokyo) |
Vice Chair | Daisuke Umehara(Kyoto Inst. of Tech.) / Kunio Hato(Internet Multifeed) / Tetsuya Oishi(NTT) |
Secretary | Daisuke Umehara(Mitsubishi Electric) / Kunio Hato(NICT) / Tetsuya Oishi(Hiroshima City Univ.) |
Assistant | Hiroyuki Saito(OKI) / Takahiro Yamaura(Toshiba) / / Shinya Kawano(NTT) |
Paper Information | |
Registration To | Technical Committee on Communication Systems / Technical Committee on Information Networks / Technical Committee on Network Systems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Proposal and Evaluation on Prediction Method for Electricity Using Probability of Missing Sensor Value |
Sub Title (in English) | |
Keyword(1) | Time Series prediction |
Keyword(2) | Missing Data |
Keyword(3) | VPP |
1st Author's Name | Norifumi Hirata |
1st Author's Affiliation | KDDI Research, Inc.(KDDI Research) |
2nd Author's Name | Osamu Maeshima |
2nd Author's Affiliation | KDDI Research, Inc.(KDDI Research) |
3rd Author's Name | Kiyohito Yoshihara |
3rd Author's Affiliation | KDDI Research, Inc.(KDDI Research) |
Date | 2020-09-11 |
Paper # | IN2020-27 |
Volume (vol) | vol.120 |
Number (no) | IN-163 |
Page | pp.pp.31-36(IN), |
#Pages | 6 |
Date of Issue | 2020-09-03 (IN) |