Abstract
Electricity price risk assessment (EPRA) is essential for spot market analysis and operation. The statistical moments (i.e., the mean and standard deviation) of the price need to be assessed to support market risk control. This paper proposes a data-driven approach for EPRA based on the Gaussian process (GP) framework. Compared with the deep learning algorithms, GP has two merits: (1) the scale of training sample required is small and (2) the time-consuming hyperparameter tuning process is avoided. However, the direct application of GP for EPRA is not tractable due to the complicated discrete relationship between the system operating status and the electricity price. To deal with that, a data-driven EPRA framework is developed that contains a GP surrogate model for the direct current optimal power flow (DC-OPF) problem and a hybrid model-data-based hybrid electricity price calculation method. To guarantee the accuracy of EPRA, an adaptability criterion and a second verification process based on the Karush–Kuhn–Tucker (KKT) condition are developed to distinguish the samples with GP learning errors. Numerical results carried out on IEEE benchmark systems demonstrate that the proposed method can achieve exactly the same EPRA results as Monte Carlo (MC) simulation, which significantly improved the computational efficiency.
Highlights
To reduce pollution and greenhouse gas emissions, a high share of renewable energy integration has become one of the basic characteristics of the smart grid [1,2,3]
E following methods are compared: (i) M0: Monte Carlo simulation (ii) M1: a neural network method based on SAE [37] (iii) M2: a neural network method based on SDAE [38] (iv) M3: a stacked extreme learning machine [24] (v) M4: the Gaussian process [36] (vi) M5: the proposed method e hyperparameter settings of each data-driven method are shown in Table 1, which are obtained according to the artificial experience and reference [39]. e learning error of
(3) Comparing M4 with M1–M3, the results show that the Gaussian process (GP) can achieve a similar accuracy with a small sample size
Summary
To reduce pollution and greenhouse gas emissions, a high share of renewable energy integration has become one of the basic characteristics of the smart grid [1,2,3]. With the development of renewable energy and the adoption of locational marginal pricing (LMP) methodology, the spot market is full of uncertainties, such as load deviation and renewable variation [4]. E abovementioned uncertainties cause the electricity price to fluctuate violently, bringing significant operational and planning risks for electricity market participants. Electricity price risk assessment (EPRA) is crucial for independent system operators (ISOs) and market participants. It is more volatile and challenging to predict the fluctuations in electricity prices than the uncertainties of power production and consumption [8]. Current studies focus on the risk caused by the electricity price fluctuation for the risk assessment in electricity markets. Reference [10] proposes a value-at-risk (VaR) and conditional VaR (CVaR) assessment for electricity price risk based on historical data. Reference [11] analyses the price risk of power portfolios in multimarkets based on the well-established mean-variance model
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
