Zhang, Jie
Permanent URI for this collectionhttps://hdl.handle.net/10735.1/6880
Jie Zhang is an Assistant Professor of Mechanical Engineering. Dr. Zhang's research interests include:
- Multidisciplinary design optimization,
- Complex engineered systems,
- Power & energy systems,
- Renewable energy,
- Grid modernization,
- Big data analytics,
- Probabilistic design
Browse
Browsing Zhang, Jie by Subject "Wind forecasting"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Grid Optimization of Shared Energy Storage Among Wind Farms Based on Wind Forecasting(Institute Of Electrical And Electronics Engineers Inc.) Zhu, K.; Chowdhury, S.; Sun, Mucun; Zhang, Jie; Sun, Mucun; Zhang, JieEnergy storage is crucial for source-side renewable energy power plants for enhancing output stability and reducing mismatch between power generation and demand. However, installing large size energy storage systems for renewable energy plants may not be economic, due to high capital cost and ever-increasing human resources and maintenance cost. As a result, in this paper, a shared energy storage system among multiple wind farms is proposed to address this energy management challenge. A state-of-the-art wind power forecasting method with ensemble numerical weather prediction models is used to optimally determine the size of a shared energy storage system (ESS). A number of scenarios are performed to optimize and explore the energy storage size under different economic and storage resource sharing circumstances. The performance of ESS, namely the net revenue of power plants, is explored subject to ESS size and operating constraints of wind farms and power systems. Results of a case study show that sharing of energy storage among multiple wind farms and lower cost of storage progressively enhance the economic benefits of using storage to mitigate over-production/under-forecasting (thus curtailment) and under-production/over-forecasting scenarios.Item Probabilistic Short-term Wind Forecasting Based on Pinball Loss Optimization(Institute of Electrical and Electronics Engineers Inc.) Sun, Mucun; Feng, Cong; Zhang, Jie; Chartan, E. K.; Hodge, B. -M; Sun, Mucun; Feng, Cong; Zhang, JieProbabilistic wind power forecasts that quantify the uncertainty in wind output have the potential to aid in the economic grid integration of wind power at large penetration levels. In this paper, a novel probabilistic wind forecasting approach based on pinball loss optimization is proposed, in conjunction with a multi-model machine learning based ensemble deterministic forecasting framework. By assuming the point-forecasted value as the mean at each point, one unknown parameter (i.e., standard deviation) of a predictive distribution at each forecasting point is determined by minimizing the pinball loss. A surrogate model is developed to represent the unknown distribution parameter as a function of deterministic forecasts. This surrogate model can be used together with deterministic forecasts to predict the unknown distribution parameter and thereby generate probabilistic forecasts. Numerical results of case studies show that the proposed method has improved the pinball loss by up to 35% compared to a baseline quantile regression forecasting model. © 2018 IEEE.