Yifeng Li
Yifeng Li has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Chong Sun
NARI-TECH Nanjing Control Systems Ltd., China
1 shared publication - Hang Zhou
State Grid Jiangsu Electric Power Co., Ltd., China
1 shared publication - Lanqing Li
State Grid Jiangsu Electric Power Co., Ltd., China
1 shared publication - Yulin Zhao
State Grid Jiangsu Electric Power Co., Ltd., China
1 shared publication
Latest Publications
- Open Access
- 24 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Energy Saving Evaluation Method for Energy Storage Technologies Based on the Intimate Data Method of Machine Learning
Power storage technology is an important technical measure to transfer peak power, develop low valley power, optimize resource allocation and protect ecological environment. The promotion and application of energy storage technology has just started, and although the scale of promotion and application is not large, the benefits are obvious and the potential is huge. The existing research methods are prone to model errors when dealing with small samples and cannot change the subjectivity of the weights obtained by hierarchical analysis. Therefore, this paper uses an intimate data approach based on machine learning to evaluate the ranking of electricity use for energy storage. The research method introduces the scope of the experimental area and the benchmark data, calculates the Euclidean distance of each sample from the best point and the Euclidean distance of the worst point by comparing them with other constructed measurement points, and integrates their affiliation with the best point and the worst point by using the minimum distance of the best point and the maximum distance of the worst point as references. The experimental results show that it is feasible to use the intimate data method for energy efficiency assessment of energy storage and electricity use technologies, that the method is easy to calculate, and that its results are reliable and valid, reducing environmental pollution and improving the utilization of available resources.
- 24 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessEnergy Saving Evaluation Method for Energy Storage Technologies Based on the Intimate Data Method of Machine Learning
Power storage technology is an important technical measure to transfer peak power, develop low valley power, optimize resource allocation and protect ecological environment. The promotion and application of energy storage technology has just started, and although the scale of promotion and application is not large, the benefits are obvious and the potential is huge. The existing research methods are prone to model errors when dealing with small samples and cannot change the subjectivity of the weights obtained by hierarchical analysis. Therefore, this paper uses an intimate data approach based on machine learning to evaluate the ranking of electricity use for energy storage. The research method introduces the scope of the experimental area and the benchmark data, calculates the Euclidean distance of each sample from the best point and the Euclidean distance of the worst point by comparing them with other constructed measurement points, and integrates their affiliation with the best point and the worst point by using the minimum distance of the best point and the maximum distance of the worst point as references. The experimental results show that it is feasible to use the intimate data method for energy efficiency assessment of energy storage and electricity use technologies, that the method is easy to calculate, and that its results are reliable and valid, reducing environmental pollution and improving the utilization of available resources.