(1. NARI Group Corporation(State Grid Electric Power Research Institute), Nanjing 211106, China; 2. State Key Laboratory of Smart Grid Protection and Control, Nanjing 211106, China; 3. School of Electrical Engineering, Southeast University, Nanjing 210096, China; 4. State Key Laboratory of Operation and Control of Renewable Energy & Storage Systems(China Electric Power Research Institute), Nanjing 210003, China; 5. China Shenhua Energy Company Limited, Beijing 100011, China; 6. School of Electrical Engineering, Zhejiang University, Hangzhou 310027, China; 7. Department of Electrical & Electronic Engineering, Universiti Teknologi Brunei, Bandar Seri Begawan BE1410, Brunei)

The state-of-the-art development of spatial correlation based wind speed prediction is reviewed. And the concepts of conditional correlation and its corresponding confidence correlation are introduced to improve traditional spatial correlation. Based on big-data thinking, a framework of integrating data-driven with causality-driven wind speed prediction is proposed. In the framework, correlation is mined from historical data for wind speed prediction. Spatial correlation is employed to import data sources for wind speed prediction to overcome the shortage of historical data in part. Furthermore, spatial correlation with long time lag can be used to predict drastic and sudden change in downstream wind speed. Finally, suggestions for future research under the proposed framework can be made with confidence. This work is supported by the State Key Program of National Natural Science Foundation of China(No. 61533010), NSFC-NRCT(Sino Thai)Cooperation Research Project(No. 51561145011)and State Grid Corporation of China.