Page 57 - 电力与能源2023年第四期
P. 57

邵佳佳,等:面向电力市场交易的客户电量预测技术研究                                      363

                [5]  J  YADONG.  Research  and  application  of  convolution  neu⁃  term  load  forecasting  of  multi-layer  LSTM  neural  network
                               .
                    ral network[D] Chengdu:University of Electronic Science   considering  temperature  fuzzification[C]//IEEE  Confer⁃


                    and Technology of China,2018.                    ence on Sustainable Power and Energy,2020.
                [6]  Y LECUN,Y BENGIO,G HINTON. Deep learning[J]  .  [16] N A MASOOD,M Z SADI,S R DEEBA,et al. Analyz⁃





                    Nature 2015.                                     ing the Impact of temperature on electrical load[C]//Inter⁃
                [7]  H SHI,M H XU,R LI. Deep learning for household load   national  Conference  on  Power  Engineering  and  Optimiza⁃


                                                 .
                    forecasting:a novel pooling deep RNN[J] IEEE Transac⁃  tion,2010.

                    tions on Smart Grid,2018.                   [17] H  JINGJIE,L  YINHONG,L  YANGHENG.  Summer

                [8]  S  HOCHREITER,J  CHMIDHUBER.  Long  short-term   daily  peak  load  forecasting  considering  accumulation  effect


                    memory[J] Neural Computation,1997.               and  abrupt  change  of  temperature[C]//Power  and  Energy
                            .
                [9]  X  MINGLEI.  Short-term  residence  load  forecast  based  on   Society General Meeting,2012.

                    LSTM network[J] Guangdong Electric power,2019.  [18] L  QIRONG,W  QIAOQIAO,Z  GUILIN,et  al.  Maxi⁃

                                 .




                [10] L JIXIANG,Z QIPEI,Y ZHIHONG,et al. Short-term load   mum daily load forecasting based on support vector regres⁃


                    forecasting method based on CNN-LSTM hybrid neural net⁃  sion considering accumulated temperature effect[C]//Con⁃
                              .

                    work model[J] Automation of Electric Power Systems,2019.  ference of Chinese Control and Decision,2018.


                [11] Y LECUN,Y BENGIO,G HINTON. Deep Learning[J]  .  [19] T GUAN,Z XU,L LIN,et al. Maximum incremental load

                    Nature 2015.                                     recursive  model  based  on  LS-SVM  considering  accumu⁃
                [12] J  YADONG.  Research  and  application  of  convolution  neu⁃  lated  temperature  effect[C]//IEEE  Int.  Conf.  on  Internet

                    ral network[D] Chengdu:University of Electronic Science   of Things,2018.

                               .



                    and Technology of China,2018.               [20] H LI,Z LEI,W TAO,et al. Short-term load forecasting


                [13] H  SHI,M  XU,R  LI.  Deep  learning  for  household  load   based  on  suport  vector  regression  considering  cooling  load


                                                 .
                    forecasting:a novel pooling deep RNN[J] IEEE Transac⁃  in  summer[C]//China  Conference  on  Control  and  Deci⁃


                    tions on Smart Grid,2018.                        sion,2020.


                [14] Z LINYAO,S PENGJIA,L XINYI,D. PEIREN,et al.   [21] H JIANGLIN,C ZHENGHONG. A relationship between



                    Air-conditioning load forecasting based on seasonal decom⁃  daily  electric  loads  and  meteorological  elements  in  central
                                                                           .

                    position  and  ARIMA  model[C]//International  Confernece   China[J] Meteorological Monthly,2002.
                    on Advance Computing and Innovative Technologies in En⁃                 收稿日期:2023-04-19
                    gineering,2021.                                                           (本文编辑:赵艳粉)

                [15] R  ZHICHAO,C  CHAO,DYINGYING,et  al.  Short-



                                                                                                                                
               (上接第 343 页)
                                                                 障,并且能快速有效地进行故障隔离及负荷转移。
                                                                 参考文献:
                                                                [1]  丘  明 . 超导输电技术在电网中的应用[J] 电工电能新技
                                                                                                  .
                                                                     术,2017,36(10):55-62.
                                                                [2]  李红雷,林    一,黄兴德 . 高温超导电缆在大都市电网的应
                                                                     用前景[J] 电力与能源,2017,38(3):255-257.
                                                                            .
                                                                [3]  冯湘波 . 高温超导材料在未来电力系统中的应用[J] 大众
                                                                                                         .
                                                                     用电,2001(12):22.
                                                                [4]  宗曦华,魏    东 . 高温超导电缆研究与应用新进展[J] 电
                                                                                                          .
                                                                     线电缆,2013(5):1-3.
                                                                [5]  郭立杰 . 冷绝缘高温超导电缆的稳定性研究[D] 北京:北
                                                                                                      .
                                                                     京交通大学,2012.
                            图 3 超导电缆保护动作逻辑                      [6]  科技情报室 . 超导技术在电力系统中的应用综述[J] 上海
                                                                                                         .
                零序电流保护作为电气量后备保护;以非电气量保                               电力,2019(2):1-19.
                护作为超导电缆冷却系统的保护。整套保护方案涵                                                      收稿日期:2023-05-11
                                                                                              (本文编辑:赵艳粉)
                盖了各种可能影响超导电缆正常运行的异常或者故
   52   53   54   55   56   57   58   59   60   61   62