효과적인 결측치 보완을 통한 다층 퍼셉트론 기반의전력수요 예측 기법 = A Multilayer Perceptron-Based Electric Load Forecasting Scheme via Effective Recovering Missing Data

다국어 초록 (Multilingual Abstract)

Accurate electric load forecasting is very important in the efficient operation of the smart grid. Recently, due to the development of IT technology, many works for constructing accurate forecasting models have been developed based on big data processing using artificial intelligence techniques. These forecasting models usually utilize external factors such as temperature, humidity and historical electric load as independent variables. However, due to diverse internal and external factors, historical electrical load contains many missing data, which makes it very difficult to construct an accurate forecasting model. To solve this problem, in this paper, we propose a random forest-based missing data recovery scheme and construct an electric load forecasting model based on multilayer perceptron using the estimated values of missing data and external factors. We demonstrate the performance of our proposed scheme via various experiments.

국문 초록 (Abstract)

정확한 전력수요 예측은 스마트 그리드의 효율적인 운영에 있어 매우 중요하다. 최근 IT 기술이 획기적으로 발전되면서, 인공지능 기법을 이용한 빅 데이터 처리를 기반으로 정확한 전력수요를 예측하는 많은 연구가 진행되고 있다. 이러한 예측 모델은 주로 외부 요인과 과거 전력수요를 독립 변수로 사용한다. 하지만, 다양한 내부적 또는 외부적 원인으로 전력수요 데이터의 결측치가 발생하게 되면 정확한 예측 모델을 구성하기가 어렵다. 이에 본 논문에서는 랜덤 포레스트 기반의 결측치 데이터 보완 기법을 제안하고, 보완된 데이터를 기반으로 한 다층 퍼셉트론 기반의 전력수요 예측 모델을 구성한다. 다양한 실험을 통해 제안된 기법의 예측 성능을 입증한다.

참고문헌 (Reference)

1 김경환, "하절기 평일의 인공신경망을 이용한 24시간 전력수요 예측 알고리즘" 한국조명.전기설비학회 31 (31): 113-119, 2017

2 문지훈, "인공 신경망과 지지 벡터 회귀분석을 이용한 대학 캠퍼스 건물의 전력 사용량 예측 기법" 한국정보처리학회 5 (5): 293-302, 2016

3 박진웅, "인공 신경망 기반의 고시간 해상도를 갖는 전력수요 예측기법" 한국정보처리학회 6 (6): 527-536, 2017

4 J. Niu, "Twin support vector regression with Huber loss" 32 (32): 4247-4258, 2017

5 M. W. Ahmad, "Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption" 147 : 77-89, 2017

6 M. Abadi, "Tensorflow: a system for large-scale machine learning" 16 : 265-283, 2016

7 H. Chitsaz, "Short-term electricity load forecasting of building in microgrids" 99 : 50-60, 2015

8 W. Kong, "Short-Term Residential Load Forecasting based on LSTM Recurrent Neural Network" 1-11, 2017

9 F. Pedregosa, "Scikit-learn: Machine learning in Python" 12 : 2825-2830, 2011

10 F. Tang, "Random forest missing data algorithms" 10 (10): 363-377, 2017

11 T. Hong, "Probabilistic electric load forecasting:A tutorial review" 32 (32): 914-938, 2016

12 A. Gerossier, "Probabilistic Day-Ahead Forecasting of Household Electricity Demand" 2017 (2017): 2500-2504, 2017

13 G. Dudek, "Pattern-based local linear regression models for short-term load forecasting" 130 : 139-147, 2016

14 W. -W. Kim, "Operation Strategy of Multi-Energy Storage System for Ancillary Services" 32 (32): 4409-4417, 2017

15 X. Ke, "Load Profile Analysis and Short-term Building Load Forecast for a University Campus" 1-5, 2016

16 G. Hinton, "Lecture 6aoverview of mini-batch gradient descent"

17 S. Jurado, "Hybrid methodologies for electricity load forecasting: Entropy-based feature selection with machine learning and soft computing techniques" 86 : 276-291, 2015

18 T. M. Oshiro, "How Many Trees in a Random Forest?" Springer 154-168, 2012

19 T. Niet, "Hedging the risk of increased emissions in long term energy planning" 16 : 1-12, 2017

20 R. K. Jain, "Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy" 123 : 168-178, 2014

21 L. Ghelardoni, "Energy Load Forecasting Using Empirical Mode Decomposition and Support Vector Regression" 4 (4): 549-556, 2013

22 K. Grolinger, "Energy Forecasting for Event Venues: Big Data and Prediction Accuracy" 112 : 222-233, 2016

23 M. R. Sarkar, "Electricity Demand Forecasting of Rajshahi City in Bangladesh Using Fuzzy Linear Regression Model" 1-3, 2015

24 A. Bagnasco, "Electrical consumption forecasting in hospital facilities : An application case" 103 : 261-270, 2015

25 W. Lee, "Development of 24-hour Optimal Scheduling Algorithm for Energy Storage System using Load Forecasting and Renewable Energy Forecasting" 1-5, 2017

26 주성관, "Demand-Side Management Program Planning Using Stochastic Load Forecasting with Extreme Value Theory" 대한전기학회 11 (11): 1093-1099, 2016

27 A. Dedinec, "Deep belief network based electricity load forecasting: An analysis of Macedonian case" 115 : 1688-1700, 2016

28 S. Ryu, "Deep Neural Network Based Demand Side Short Term Load Forecasting" 10 (10): 1-20, 2017

29 G. Panchal, "Behaviour Analysis of Multilayer Perceptrons with Multiple Hidden Neurons and Hidden Layers" 3 (3): 332-337, 2011

30 S. S. Reddy, "Bat algorithm-based back propagation approach for short-term load forecasting considering weather factors" 100 (100): 1297-1303, 2018

31 M. Abdel-Nasser, "Accurate photovoltaic power forecasting models using deep LSTM-RNN" 1-14, 2017

32 N. Zeng, "A switching delayed PSO optimized extreme learning machine for short-term load forecasting" 240 : 175-182, 2017

33 C. Fan, "A short-term building cooling load prediction method using deep learning algorithms" 195 : 222-233, 2017

34 M. Q. Raza, "A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings" 50 : 1352-1372, 2015

35 A. S. Ahmad, "A review on applications of ANN and SVM for building electrical energy consumption forecasting" 33 : 102-109, 2014

36 B. Yildiz, "A review and analysis of regression and machine learning models on commercial building electricity load forecasting" 73 : 1104-1122, 2017

37 B. Zhang, "A multiple time series-based recurrent neural network for short-term load forecasting" 22 (22): 4099-4112, 2018

38 L. Hernandez, "A Survey on Electric Power Demand Forecasting: Future Trends in Smart Grids, Microgrids and Smart Buildings" 16 (16): 1460-1495, 2014

39 J. Moon, "A Short-Term Electric Load Forecasting Scheme Using 2-Stage Predictive Analytics" 219-226, 2018

40 A. Almalaq, "A Review of Deep Learning Methods Applied on Load Forecasting" 511-516, 2017

41 P.-H. Kuo, "A High Precision Artificial Neural Networks Model for Short-Term Energy Load Forecasting" 11 (11): 1-13, 2018

42 S. Park, "A Comparison of Various Machine Learning Techniques for Missing Values Recovering in Load Prediction" 1-2, 2018