Short-Term Wind Power Prediction Using Hybrid Auto Regressive Integrated Moving Average Model and Dynamic Particle Swarm Optimization

Introduction

The growth and utilization of renewable energy (RE) can make considerable contribution to the energy, environmental and economic policy especially in three interrelated areas. These areas are: (i) energy security (ii) decrease of CO₂ emission and other ecological impact of energy use, and (iii) economic growth (Chang, 2014). Many countries have increased the emphasis on the development of clean & green energy in order to counter the climatic changes and entrust energy security. The developing trend of the world energy is the provision of clean energy with low carbon footprints, and high energy efficiency. As the basis and premise of the low-carbon electricity, smart grid technology has rapidly developed in many countries in the recent years. Due to its high efficiency and no pollution, the wind power has emerged as one of the highly attractive technologies of renewable energy in smart grids (X. Zhao, Wang, & Li, 2011).

Wind power generation plays an important role in the smart grid environment due to its availability in abundance and low carbon footprint. Wind power generation is dependent on the wind speed which is influenced by the geographical and environmental conditions of any particular region. It also varies with height, so the random character of wind is significant. As compared to the conventional generation, one of the major problems of wind power is its reliance on the unpredictability of the wind. The unpredicted variations of wind generation may enhance operating costs, which increases reserves necessities, and poses potential risks to reliability of the power system (Lei, Shiyan, Chuanwen, Hongling, & Yan, 2009; Z. Li et al., 2016) The intermittency of wind power is the major challenge in implementing the wind-energy as a reliable independent source of electric power supply.

Large-scale wind-penetration requires answers to a lot of problems such as competitive market designs, real-time grid operations, standards of interconnection, ancillary service requirements and costs, quality of power, capacity of transmission system and its future upgrades, stability and reliability of power system, optimal reductions in greenhouse gas emissions of entire power system (typically determined by optimal amount of wind penetration into system). The generation load balance is a well-known method for power balance objective in the integrated power systems, the mismatch in demand and generation may affect the stability of the power system, so, in order to overcome the problems of large wind integration and to match the power demand in order to maximize the profits the generating companies rely on the accurate wind power forecasting. When it comes to competitive electricity markets, accurate wind power forecast is always alluring for a variety of reasons. Firstly, appropriate incentives of attractive market price are offered on energy imbalance charges based on market price. Secondly, a correct forecast can help to develop well-functioning hour ahead or day-ahead markets (Madhiarasan & Deepa, 2016; Soman, Zareipour, Malik, & Mandal, 2010).

The wind forecasting can be widely classified on the basis of numerous aspects as shown in Figure 1. Based on time horizon (timescale), the wind forecasting is classified (Mao & Shaoshuai, 2016) with their applications as given in Table 1 (Chang, 2014; Soman et al., 2010).

Figure 1.

Classification of wind forecasting based on different aspects