ABSTRACT
High-quality power data is the basis for reliable operation of power systems, efficient data processing, and effective mining of the potential value of power data. How to use big data, artificial intelligence and other technologies to evaluate the quality of power data is a hot research topic in the field of electric power. At present, most of the power data quality evaluation methods are simple and lack the research of general data quality evaluation model. Therefore, this paper proposes a multi-dimensional data quality evaluation model based on a multi-head attention mechanism. The model measures multiple indicators such as completeness, accuracy, smoothness, and correlation. The corresponding methods are used to quantify these indicators to form a data quality evaluation index system oriented to multi-dimensional indicators; then, an application feedback mechanism based on a multi-head attention network is used to correct the calculation weights and score outputs, so as to achieve the evaluation of power data quality. Finally, the validation analysis is carried out based on the electricity data of a region in China. The experimental results show that the proposed method can effectively evaluate the quality of electric power data.
- Zhang Huaying, Wang Qing, You Yihong, Wu Xian, Sun Yihao, Zhang Wenhai. Analysis of the Influence of Power Quality Data Quality on Comprehensive Evaluation Results[J]. Science Technology and Engineering. 2021, 21(24): 10341-09.Google Scholar
- Arazy O, Kopak R. On the measurability of information quality[J]. Journal of the American Society for Information Science & Technology, 2014, 62(1):89-99.Google ScholarDigital Library
- Wang R Y, Strong D M. Beyond accuracy: What data quality means to data consumers[J]. Journal of Management Information Systems, 1996, 12(4):5-33.Google ScholarDigital Library
- Hermans F, Pinzger M, Van Deursen A. Detecting and refactoring code smells in spreadsheet formulas [J]. Empirical Software Engineering, 2015, 20(2):549-575.Google ScholarDigital Library
- Han Jingyu, Chen Kejia. Ranking Data Quality of Web Article Content by Extracting Facts[J]. Computer Science, 2014, 41(11): 247-251+255.Google Scholar
- Hu Yuan, Wei Xiaoying, Wang Can. Research on the Construction of Micro-blog Information Quality Evaluation Indicator System[J]. Journal of Information Resources Management, 2017, 3(6): 44-50.Google Scholar
- Song Lirong, Li Sijing. Study on the Agricultural Science and Technology Information Quality Dimension Based on Network Sharing[J]. Library and Information Service, 2009, 53(22): 85-88.Google Scholar
- Pang Liang. Test data quality evaluation based on rough set and Back-Propagation neural network[J]. Electronic Design Engineering. 2021, 29(13): 56-60.Google Scholar
- YANG Dongshu, YANG Desheng. Data quality assessment based on entropy weight and AHP [J]. Modern Electronics Technique,20 1 3,36(22): 39-42.Google Scholar
- XUN Ting, WANG Xianghao. Power gird comprehensive data quality evaluation sysem and its software realization[J]. Electrical Measurement & Instrumentation, 20 1 9, 56 (4): 62-69.Google Scholar
- PAN Xu, WANG Jinli. Multi-dimensional data quality evaluation method for intelligent distribution network [J]. Proceeding of the CSEE,2018,38(5): 1375-1384.Google Scholar
- L. Cai, Y. Liang, Y. Zu, Historical evolution and development trend of data quality[J]. Comp. Sci. 2018, 45 (2): 1–16.Google Scholar
- A. Aggarwal, Data quality evaluation framework to assess the dimensions of 3VS of big data[J]. Int. J. Emerg. Tech. Adv. Eng. 2017, 7(20): 503–506.Google Scholar
- Kulkarni A. A Study on Metadata Management and Quality Evaluation in Big Data Management[J]. Engineering, Technology and Applied Science Research, 2016, 4(7):455-459.Google Scholar
- X. Zhao, S. Li, W. Yu, , Research on web data source quality assessment method in big data, Comp. Eng. 43 (2017), 48–56.Google Scholar
- T. Nagle, T. Redman, D. Sammon, Assessing data quality: a managerial call to action, Bus. Hor. 63 (2020), 325–337.Google ScholarCross Ref
- B. Liu, L. Pang, Review of domestic and international research on big data quality, J. China Soc. Sci. Tech. Inform. 38 (2019), 217–226.Google Scholar
- K. Desai, Big Data Quality Modeling and Validation, Ph. D. dissertation, San José State University, San Jose, CA, USA, 2018.Google ScholarCross Ref
- D. Ardagna, C. Cappiello, W. Samá, , Contextaware data quality assessment for big data, Future Gener. Comp. Syst. 89(2018), 548–562.Google ScholarDigital Library
- C. Batini, A. Rula, M. Scannapieco, , From data quality to big data quality, J. Database Manage. 26 (2015), 60–82.Google ScholarDigital Library
- Z. Mo, Construction of big data quality measurement model, Inform. Stud. Theory Appl. 41 (2018), 11–15.Google Scholar
- Wenquan Li, Suping Xu, Xindong Peng: Research on Comprehensive Evaluation of Data Source Quality in Big Data Environment. Int. J. Comput. Intell. Syst. 2021, 14(1): 1831-1841.Google ScholarCross Ref
- Jiang Jiajun, Jiang Min, Yang Xiaoyu, Guo Jia. Research on Evaluation of Personalized Image Aesthetic Quality Based on Attention Mechanism[J]. Computing Technology and Development. 2021, 31(10): 56-62.Google Scholar
- Kalyan Das, Satyabrata Das: Energy-Efficient Cloud-Integrated Sensor Network Model Based on Data Forecasting Through ARIMA[J]. International Journal of e-Collaboration (IJeC). 2022, 18(1): 1-17.Google Scholar
- Nguyen Quang Dat, Thi Ngoc Anh Nguyen, Nguyen Nhat Anh, Vijender Kumar Solanki: Hybrid online model based multi seasonal decompose for short-term electricity load forecasting using ARIMA and online RNN[J]. Journal of Intelligent and Fuzzy Systems. 2021, 41(5): 5639-5652.Google ScholarDigital Library
Recommendations
BR4DQ: A methodology for grouping business rules for data quality evaluation
AbstractData quality evaluation is built upon data quality measurement results. “Data quality evaluation” uses the “data quality rules” representing the risk appetite of the organization to decide on the usability of the data; “data quality ...
Highlights- Data quality measurement requires business rules describing the validity of data.
Towards a Data Quality Assessment in Big Data
SITA'20: Proceedings of the 13th International Conference on Intelligent Systems: Theories and ApplicationsIn recent years, as more and more data sources have become available and the volumes of data potentially accessible have increased, the assessment of data quality has taken a central role whether at the academic, professional or any other sector. Given ...
A Model for Data Quality Assessment
OTM '08: Proceedings of the OTM Confederated International Workshops and Posters on On the Move to Meaningful Internet Systems: 2008 Workshops: ADI, AWeSoMe, COMBEK, EI2N, IWSSA, MONET, OnToContent + QSI, ORM, PerSys, RDDS, SEMELS, and SWWSOne of the major causes for the failure of information systems to deliver can be attributed to data quality. Gartner's figures and other similar studies show the failure rate hovering at a plateau of 50% for data warehouses since 2004. While the true ...
Comments