Towards Electric Price and Load Forecasting Using CNN-Based Ensembler in Smart Grid

被引:21
|
作者
Aslam, Shahzad [1 ]
Ayub, Nasir [2 ]
Farooq, Umer [3 ]
Alvi, Muhammad Junaid [4 ]
Albogamy, Fahad R. [5 ]
Rukh, Gul [6 ]
Haider, Syed Irtaza [7 ]
Azar, Ahmad Taher [8 ,9 ]
Bukhsh, Rasool [10 ]
机构
[1] Inst Southern Punjab, Dept Stat & Math, Multan 66000, Pakistan
[2] Natl Univ Sci & Technol, Sch Elect Engn & Comp Sci, Islamabad 44000, Pakistan
[3] Islamia Univ Bahawalpur, Dept Comp Sci, Bahawalpur 63100, Pakistan
[4] NFC Inst Engn & Fertilizer Res, Elect Engn Dept, Faisalabad 38000, Pakistan
[5] Taif Univ, Turabah Univ Coll, Comp Sci Program, POB 11099, At Taif 21944, Saudi Arabia
[6] Univ Engn & Technol, Dept Elect Engn, Mardan 23200, Pakistan
[7] King Saud Univ, Coll Comp & Informat Sci, Riyadh 11543, Saudi Arabia
[8] Prince Sultan Univ, Coll Comp & Informat Sci, Riyadh 11586, Saudi Arabia
[9] Bertha Univ, Fac Comp & Artificial Intelligence, Bertha 13518, Egypt
[10] COMSATS Univ Islamabad CUI, Dept Comp Sci, Islamabad 44000, Pakistan
关键词
smart grid; electricity price forecasting; energy management; electricity load forecasting; convolutional neural network; corona virus herd immunity optimization; FEATURE-SELECTION TECHNIQUE; DEMAND RESPONSE; NEURAL-NETWORK; RANDOM FOREST; REGRESSION; ALGORITHM; POWER; MANAGEMENT; MACHINE; ENGINE;
D O I
10.3390/su132212653
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Medium-term electricity consumption and load forecasting in smart grids is an attractive topic of study, especially using innovative data analysis approaches for future energy consumption trends. Loss of electricity during generation and use is also a problem to be addressed. Both consumers and utilities can benefit from a predictive study of electricity demand and pricing. In this study, we used a new machine learning approach called AdaBoost to identify key features from an ISO-NE dataset that includes daily consumption data over eight years. Moreover, the DT classifier and RF are widely used to extract the best features from the dataset. Moreover, we predicted the electricity load and price using machine learning techniques including support vector machine (SVM) and deep learning techniques such as a convolutional neural network (CNN). Coronavirus herd immunity optimization (CHIO), a novel optimization approach, was used to modify the hyperparameters to increase efficiency, and it used classifiers to improve the performance of our classifier. By adding additional layers to the CNN and fine-tuning its parameters, the probability of overfitting the classifier was reduced. For method validation, we compared our proposed models with several benchmarks. MAE, MAPE, MSE, RMSE, the f1 score, recall, precision, and accuracy were the measures used for performance evaluation. Moreover, seven different forms of statistical analysis were given to show why our proposed approaches are preferable. The proposed CNN-CHIO and SVM techniques had the lowest MAPE error rates of 6% and 8%, respectively, and the highest accuracy rates of 95% and 92%, respectively.
引用
收藏
页数:28
相关论文
共 50 条
  • [41] CNN-Based Smart Sleep Posture Recognition System
    Tang, Keison
    Kumar, Arjun
    Nadeem, Muhammad
    Maaz, Issam
    [J]. IOT, 2021, 2 (01): : 119 - 139
  • [42] An Approximate Forecasting of Electricity Load and Price of a Smart Home Using Nearest Neighbor
    Nawaz, Muhammad
    Javaid, Nadeem
    Mangla, Fakhar Ullah
    Munir, Maria
    Ihsan, Farwa
    Javaid, Atia
    Asif, Muhammad
    [J]. COMPLEX, INTELLIGENT, AND SOFTWARE INTENSIVE SYSTEMS (CISIS 2019), 2020, 993 : 521 - 533
  • [43] Load and Price Forecasting in Smart Grids Using Enhanced Support Vector Machine
    Nayab, Ammara
    Ashfaq, Tehreem
    Aimal, Syeda
    Rasool, Aimen
    Javaid, Nadeem
    Khan, Zahoor Ali
    [J]. ADVANCES IN INTERNET, DATA AND WEB TECHNOLOGIES, 2019, 29 : 247 - 258
  • [44] Real Time Energy Management and Load Forecasting in Smart Grid using CompactRIO
    Thiyagarajan, K.
    SaravanaKumar, R.
    [J]. INTERNATIONAL CONFERENCE ON COMPUTATIONAL MODELLING AND SECURITY (CMS 2016), 2016, 85 : 656 - 661
  • [45] Hourly Electricity Load Forecasting in Smart Grid Using Deep Learning Techniques
    Khan, Abdul Basit Majeed
    Javaid, Nadeem
    Nazeer, Orooj
    Zahid, Maheen
    Akbar, Mariam
    Khan, Majid Hameed
    [J]. INNOVATIVE MOBILE AND INTERNET SERVICES IN UBIQUITOUS COMPUTING, IMIS-2019, 2020, 994 : 185 - 196
  • [46] Electricity load forecasting and feature extraction in smart grid using neural networks
    Jha, Nishant
    Prashar, Deepak
    Rashid, Mamoon
    Gupta, Sachin Kumar
    Saket, R. K.
    [J]. COMPUTERS & ELECTRICAL ENGINEERING, 2021, 96 (96)
  • [47] Two-Stage Machine Learning Framework for Simultaneous Forecasting of Price-Load in the Smart Grid
    Victoire, Aruldoss Albert T.
    Gobu, B.
    Jaikumar, S.
    Arulmozhi, N.
    Kanimozhi, P.
    Victoire, Amalraj T.
    [J]. 2018 17TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2018, : 1081 - 1086
  • [48] Long-term load forecasting for smart grid
    Kumar, Vikash
    Mandal, Rajib Kumar
    [J]. Engineering Research Express, 2024, 6 (04):
  • [49] Optimization and research of smart grid load forecasting model based on deep learning
    Zhang, Dong
    [J]. INTERNATIONAL JOURNAL OF LOW-CARBON TECHNOLOGIES, 2024, 19 : 594 - 602
  • [50] Short Term Load Forecasting based on Deep Learning for Smart Grid Applications
    Hafeez, Ghulam
    Javaid, Nadeem
    Ullah, Safeer
    Iqbal, Zafar
    Khan, Mahnoor
    Rehman, Aziz Ur
    Ziaullah
    [J]. INNOVATIVE MOBILE AND INTERNET SERVICES IN UBIQUITOUS COMPUTING, IMIS-2018, 2019, 773 : 276 - 288