A fog based load forecasting strategy for smart grids using big electrical data

Internet of things (IoT) enables the smart electrical grids (SEGs) to support a lot of tasks throughout the generation, transmission, distribution and consumption of energy. Large amounts of data are generated through these smart devices, which can be sent to the cloud for further processing. Hence, appropriate actions can be taken based on the cloud processing. However, sending the complete captured data directly to the cloud would lead to resource wastage. To overcome the cloud challenges, fog computing tier acts as a bridge in the middle between the IoT devices embedded in SEG and the cloud. Thus, a 3-tiers architecture is proposed to replace 2-tiers one. The added fog tier offers a place for collecting, computing, storing smart meter data before transmitting them to the cloud. In this paper, a new electrical load forecasting (ELF) strategy has been proposed based on the pre-mentioned three tiers architecture. The proposed strategy consists of two phases; which are; (i) data pre-processing phase (DP2) and (ii) load prediction phase (LP2). Both phases take place at a cloud data center (CDC) on the collected data, which is received from all fogs connected to the entire cloud. The aim of the data preprocessing phase is to; (i) reject outliers from the collected data, and (ii) feature selection. The main contribution of this paper lied on the feature selection, which elects only the effective features for the next load prediction phase. Features selection is an essential pre-processing operation to reduce the dataset dimensions from all irrelevant features leading to enable the ELF from taking fast and correct decision for other electrical subsystems. A new feature selection methodology called fuzzy based feature selection (FBFS) is presented, which involves two stages; feature ranking stage (FRS) and feature selection stage (FS2). FBFS is a hybrid method based on both features selection methods filter and wrapper providing fast and more accurate significant features. Then, during LP2, the filtered data is used to give a fast and accurate load prediction. Experimental results have shown that the proposed FBFS promotes the load forecasting efficiency in terms of precision, recall, accuracy and F-measure compared with recent features selection methodologies. FBFS provides the highest precision, recall, and accuracy results. On the other hand, it provides the lowest error value.

[1]  Marjolijn Verspoor,et al.  Complex Dynamic Systems Theory and L2 pedagogy: Lessons to be learned , 2017 .

[2]  Weisong Shi,et al.  The Promise of Edge Computing , 2016, Computer.

[3]  Qinbao Song,et al.  A Fast Clustering-Based Feature Subset Selection Algorithm for High-Dimensional Data , 2013, IEEE Transactions on Knowledge and Data Engineering.

[4]  Feifei Li,et al.  Efficient Summarization Techniques for Massive Data , 2013 .

[5]  Mianxiong Dong,et al.  When Weather Matters: IoT-Based Electrical Load Forecasting for Smart Grid , 2017, IEEE Communications Magazine.

[6]  Tin Kam Ho,et al.  A Sparse Coding Approach to Household Electricity Demand Forecasting in Smart Grids , 2017, IEEE Transactions on Smart Grid.

[7]  Yongsheng Ma,et al.  A hybrid cost estimation framework based on feature-oriented data mining approach , 2015, Adv. Eng. Informatics.

[8]  Revathi,et al.  Hadoop Based Parallel Framework for Feature Subset Selection in Big Data , 2015 .

[9]  Karsten Menzel,et al.  Mining building performance data for energy-efficient operation , 2011, Adv. Eng. Informatics.

[10]  António Pacheco,et al.  Theoretical evaluation of feature selection methods based on mutual information , 2016, Neurocomputing.

[11]  Rajkumar Buyya,et al.  Fog Computing: Helping the Internet of Things Realize Its Potential , 2016, Computer.

[12]  Waad Bouaguel,et al.  Proceedings in Adaptation, Learning and Optimization , 2015, IES.

[13]  H. P. Vinutha,et al.  An Ensemble Classifier Approach on Different Feature Selection Methods for Intrusion Detection , 2018 .

[14]  George Atia,et al.  Randomized Robust Subspace Recovery and Outlier Detection for High Dimensional Data Matrices , 2015, IEEE Transactions on Signal Processing.

[15]  K. A. Vidhya,et al.  Rough set theory for document clustering: A review , 2017, J. Intell. Fuzzy Syst..

[16]  Yaochu Jin,et al.  Feature selection for high-dimensional classification using a competitive swarm optimizer , 2016, Soft Computing.

[17]  Ibrahim Dincer,et al.  Smart energy systems for a sustainable future , 2017 .

[18]  Song Guo,et al.  Robust Big Data Analytics for Electricity Price Forecasting in the Smart Grid , 2019, IEEE Transactions on Big Data.

[19]  Gary Riley,et al.  Expert Systems: Principles and Programming , 2004 .

[20]  Nacira Ghoualmi Zine,et al.  Two Stages Feature Selection Based on Filter Ranking Methods and SVMRFE on Medical Applications , 2016 .

[21]  Rajalakshmi Selvaraj,et al.  Optimal and Novel Hybrid Feature Selection Framework for Effective Data Classification , 2018 .

[22]  A.App,et al.  Hadoop Based Parallel Framework for FeatureSubset Selection in Big Data , 2015 .

[23]  Khairan D. Rajab,et al.  New Hybrid Features Selection Method: A Case Study on Websites Phishing , 2017, Secur. Commun. Networks.

[24]  Ali I. El-Desouky,et al.  Promoting the performance of vertical recommendation systems by applying new classification techniques , 2015, Knowl. Based Syst..

[25]  Harshali D. Gangurde.  Feature Selection using Clustering Approach for Big Data , 2014 .

[26]  Oļegs Užga-Rebrovs,et al.  Comparative Analysis of Fuzzy Set Defuzzification Methods in the Context of Ecological Risk Assessment , 2017 .

[27]  Weixin Xie,et al.  Two-stage hybrid feature selection algorithms for diagnosing erythemato-squamous diseases , 2013, Health Inf. Sci. Syst..

[28]  Sheng-yi Jiang,et al.  Efficient feature selection based on correlation measure between continuous and discrete features , 2016, Inf. Process. Lett..

[29]  P. Zeng,et al.  Prediction of Slope Stability using Naive Bayes Classifier , 2018 .

[30]  Yasir Saleem,et al.  Internet of Things-Aided Smart Grid: Technologies, Architectures, Applications, Prototypes, and Future Research Directions , 2017, IEEE Access.

[31]  Sonja Filiposka,et al.  Feature Ranking Based on Information Gain for Large Classification Problems with MapReduce , 2015, 2015 IEEE Trustcom/BigDataSE/ISPA.

[32]  Song Guo,et al.  Big Data Analytics for Price Forecasting in Smart Grids , 2016, 2016 IEEE Global Communications Conference (GLOBECOM).

[33]  Shufen Liu,et al.  An Effective Feature Selection Approach Using the Hybrid Filter Wrapper , 2016 .

[34]  Dhruba Kumar Bhattacharyya,et al.  An effective ensemble classification framework using random forests and a correlation based feature selection technique , 2017, Trans. GIS.

[35]  Jianhua Wang,et al.  Optimal feature selection using distance-based discrete firefly algorithm with mutual information criterion , 2017, Neural Computing and Applications.

[36]  Raj Kumar,et al.  Classification Algorithms for Data Mining: a Survey , 2022 .

[37]  Wei Wang,et al.  Efficient detection of DDoS attacks with important attributes , 2008, 2008 Third International Conference on Risks and Security of Internet and Systems.

[38]  Özgür B. Akan,et al.  Energy Harvesting Cognitive Radio Networking for IoT-enabled Smart Grid , 2018, Mob. Networks Appl..

[39]  Amjad Anvari-Moghaddam,et al.  Demand Side Management Using the Internet of Energy Based on Fog and Cloud Computing , 2017, 2017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData).

[40]  Yan-Hong Li.  Text feature selection algorithm based on Chi-square rank correlation factorization , 2017 .

[41]  Abdullah Alqahtani,et al.  Investigating the effect of correlation based feature selection on breast cancer diagnosis using artificial neural network and support vector machines , 2017, 2017 International Conference on Informatics, Health & Technology (ICIHT).

[42]  Mohammad Saraee,et al.  A new unsupervised feature selection method for text clustering based on genetic algorithms , 2012, Journal of Intelligent Information Systems.

[43]  Aboul Ella Hassanien,et al.  Genetic algorithm with different feature selection techniques for anomaly detectors generation , 2013, 2013 Federated Conference on Computer Science and Information Systems.

[44]  Jurgita Antucheviciene,et al.  Recent Fuzzy Generalisations of Rough Sets Theory: A Systematic Review and Methodological Critique of the Literature , 2017, Complex..

[45]  Weixin Xie,et al.  Novel Hybrid Feature Selection Algorithms for Diagnosing Erythemato-Squamous Diseases , 2012, HIS.

[46]  Yong Wang,et al.  A Feature Selection Method for Large-Scale Network Traffic Classification Based on Spark , 2016, Inf..

[47]  Yuan Tian,et al.  Chi-square Statistics Feature Selection Based on Term Frequency and Distribution for Text Categorization , 2015 .

[48]  Abdel-A. Edris,et al.  Transmission Grid Smart Technologies , 2017 .

[49]  Axel Jantsch,et al.  Fog Computing in the Internet of Things , 2018 .

[50]  Radha Senthilkumar,et al.  An online approach for feature selection for classification in big data , 2017 .

[51]  Mohammed Azmi Al-Betar,et al.  Text feature selection with a robust weight scheme and dynamic dimension reduction to text document clustering , 2017, Expert Syst. Appl..

[52]  Abdelkader Bousselham,et al.  The Internet of Energy: Smart Sensor Networks and Big Data Management for Smart Grid , 2015, FNC/MobiSPC.

[53]  Rajkumar Buyya,et al.  Fog Computing: A Taxonomy, Survey and Future Directions , 2016, Internet of Everything.

[54]  Suat Özdemir,et al.  A fog computing based smart grid model , 2016, 2016 International Symposium on Networks, Computers and Communications (ISNCC).

[55]  L. Zhang,et al.  Complexity Theory and Language Development: In Celebration of Diane Larsen-Freeman , 2018, ELT Journal.