An Artificial Intelligence Strategy for the Prediction of Wind Speed and Direction in Sarawak for Wind Energy Mapping
Accurate and reliable wind speed and direction prediction is one of the necessary concepts in implementing a wind energy system. In this paper, meteorological and geographical variables were modeled via artificial neural networks (ANNs), taking terrain el
- PDF / 765,047 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 10 Downloads / 212 Views
Abstract Accurate and reliable wind speed and direction prediction is one of the necessary concepts in implementing a wind energy system. In this paper, meteorological and geographical variables were modeled via artificial neural networks (ANNs), taking terrain elevation and roughness class into account. The feedforward neural network (FFNN) with back propagation trained with Levenberg–Marquardt algorithm was utilized, with wind speed and direction as the target function in each model. The results obtained using the formulated topographical models showed a regression value R in the range of 0.8256–0.9883. The optimum network based on the lower mean square error and fast computation time was 9-152-1. Thus, the developed topographical feedforward neural network (T-FFNN) is efficient to predict the wind speed and direction properly. Keywords Wind speed · Wind direction · Neural network · Sarawak
1 Introduction Renewable energy resources are the major competitor of the fossil fuels such as coal, gas, and petroleum. Fossil fuel depletes with time, moreover, the resources are available in some regions around the world. Wind power is an indirect solar potential, which is clean, freely available, environmentally friendly, widely distributed, and naturally abundant almost anywhere around the globe. It has been applied decades S.M. Lawan (B) · W.A.W.Z. Abidin Department of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Malaysia Sarawak (UNIMAS), Sarawak, Malaysia e-mail: [email protected] S.M. Lawan Department of Electrical Engineering, Kano University of Science and Technology, Wudil, Nigeria S. Lawan · A.M. Lawan Faculty of Science, Department of Mathematical Science, Bayero University Kano (BUK), P.M.B 3011 Kano, Nigeria © Springer Science+Business Media Singapore 2016 A. Kılıçman et al. (eds.), Recent Advances in Mathematical Sciences, DOI 10.1007/978-981-10-0519-0_7
71
72
S.M. Lawan et al.
ago for sailing ships, machine grinding, windmills, and crop handling. Recently, it has become popular for electrical power generation. The development of wind energy has reached a large scale in terms of annual installed capacity. Large-scale wind farms are linked to the electrical power transmission lines; meanwhile, small wind turbines rated from few watts up to 10 kW are being used for stand-alone application to provide electricity to the isolated, remote, and rural locations [1–3]. Notwithstanding, many professionals have claimed that the wind potential remains unharnessed. In fact, 2014 is another remarkable year for wind turbine installation. Currently, wind turbine producers are yet to meet up with the present demands [4, 5]. Wind resource assessment (WRA), micrositing and sizing of wind turbines are prerequisite requirements that must be performed during the technical feasibility stage. The essential aspect that needs to be considered is the stochastic and unpredictable nature of wind speed. It is well known that a small deviation of wind speed will lead to a large error in the wind pow
Data Loading...
