Name
Abstract | ||
|---|---|---|
This paper proposed a novel combination of prediction model based on Adaptive Cauchy and Chaos Quantum-behaved Particle Swarm Optimization (ACCQPSO) and Least Squares Support Vector Machine (LSSVM) to forecast the short-term output power more accurately. To improve the performance of QPSO, chaotic sequences are used to initialize the origin particles, and particle premature convergence criterion, Cauchy and Chaos algorithm are employed, which can effectively increase the diversity of population and avoid the premature convergence. The kernel parameters of LSSVM are optimized by ACCQPSO to obtain hybrid forecasting model. To verify the proposed method, the seven days actual data recorded in a wind farm located in Anhui of China are utilized for application validation. The results show that the proposed combinational model achieves higher prediction accuracy. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1007/978-981-10-6364-0_62 | ADVANCED COMPUTATIONAL METHODS IN ENERGY, POWER, ELECTRIC VEHICLES, AND THEIR INTEGRATION, LSMS 2017, PT 3 |
Keywords | DocType | Volume |
LSSVM,QPSO,Cauchy mutation,Chaotic,Wind power | Conference | 763 |
ISSN | Citations | PageRank |
1865-0929 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nan Xiong | 1 | 0 | 0.68 |
| Minrui Fei | 2 | 1003 | 117.54 |
| Sizhou Sun | 3 | 3 | 1.39 |
| Tai-Cheng Yang | 4 | 288 | 19.73 |