Short-Term Load Forecasting Using Adaptive Annealing Learning Algorithm Based Reinforcement Neural Network
| Autor: | Chia-Nan Ko, Cheng-Ming Lee |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Mathematical optimization
Engineering Control and Optimization Computer science 020209 energy Load forecasting Energy Engineering and Power Technology short-term load forecasting 02 engineering and technology lcsh:Technology radial basis function neural network support vector regression particle swarm optimization adaptive annealing learning algorithm Radial basis function neural 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering Reinforcement Reinforcement learning algorithm Engineering (miscellaneous) Artificial neural network lcsh:T Renewable Energy Sustainability and the Environment business.industry Particle swarm optimization Automation engineering Term (time) Support vector machine electrical_electronic_engineering business Algorithm Energy (miscellaneous) |
| Zdroj: | Energies, Vol 9, Iss 12, p 987 (2016) Energies; Volume 9; Issue 12; Pages: 987 |
| DOI: | 10.20944/preprints201609.0119.v1 |
| Popis: | Short-Term Load Forecasting Using Adaptive Annealing Learning Algorithm Based Reinforcement Neural Network Cheng-Ming Lee a and Chia-Nan Ko * a Department of Digital Living Innovation, Nan Kai University of Technology, Tsaotun, Nantou 542, Taiwan; t104@nkut.edu.tw b Department of Automation Engineering, Nan Kai University of Technology, Tsaotun, Nantou 542, Taiwan * Correspondence: t105@nkut.edu.tw Abstract: A reinforcement learning algorithm is proposed to improve the accuracy of short-term load forecasting (STLF) in this article. The proposed model integrates radial basis function neural network (RBFNN), support vector regression (SVR), and adaptive annealing learning algorithm (AALA). In the proposed methodology, firstly, the initial structure of RBFNN is determined by using SVR. Then, an AALA with time-varying learning rates is used to optimize the initial parameters of SVR-RBFNN (AALA-SVRRBFNN). In order to overcome the stagnation for searching optimal RBFNN, a particle swarm optimization (PSO) is applied to simultaneously find promising learning rates in AALA. Finally, the short-term load demands are predicted by using the optimal RBFNN. The performance of the proposed methodology is verified on the actual load dataset from Taiwan Power Company (TPC). Simulation results reveal that the proposed AALA-SVRRBFNN can achieve a better load forecasting precision as compared to various RBFNNs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|