Search

This paper examines the dynamical impact of market wide liquidity on the volatility by using the Markov switching-regime approach on the Heterogeneous Autoregressive model of the realized range-based volatility (MS-HAR-RRV-LIQ). First, based on the simple partition of the liquidity measures by their historical means, we find the impact of the market liquidity on the realized range-based volatility (RRV) is non-linear with significantly stronger when the market is fluctuating. Second, by utilizing the method of Markov regimes switching, we find that in sample results, the impact of market liquidity on RRV is dynamics with much stronger when the market is fluctuating. In addition, the impact of liquidity on RRV are persistent for both the fluctuating state and the stable state, which indicate that the impact of liquidity on volatility would remain in its original state unless there are major economic events. Third, in order to eliminate the hidden information of volatility in liquidity measures, we further decompose the liquidity measures to obtain the volatility-adjusted liquidity, and find that the impact of liquidity driven by the component of liquidity uncorrelated with volatility on market volatility is also dynamics with much stronger when the market is fluctuating. Finally, out-of-sample results suggest that the models of HAR-RRV-LIQ and their corresponding volatility-adjusted liquidity models with regimes switching can increase the forecasting ability significantly than those without regime switching. • This paper examines the dynamical impact of market wide liquidity on volatility. • The impact of the market wide liquidity on RRV is non-linear. • The impact of market wide liquidity on RRV is dynamics. • Our proposed models can increase the forecasting ability significantly. [ABSTRACT FROM AUTHOR]

The market for urban distributed photovoltaics (DPV) is expected to take off in the next decade. However, these systems are often subject to complex urban contexts and sub-optimal conditions, requiring scalable and comprehensive solutions to detect their underperformances. In recent years, deep generative models (DGMs) have exhibited outstanding performance in the anomaly detection domain, dealing with generic high-dimensional time series data. Nevertheless, the existing applications of DGMs in the photovoltaic (PV) sector are still unable to account for environmental information, limiting their performance under various environmental conditions. This study proposes the Sequential Conditional Variational Autoencoder (SCVAE), which can cope with the sequential impacts of the environment on PV power generation. Using real-world data collected from 30 rooftop PV sites located across China, a data processing pipeline is developed to construct the training datasets which contain mostly normal samples for unsupervised SCVAE model training. This work also constructs a synthetic dataset with a wide variety of artificial anomalies in reference to the domain insights and engineering practice of DPV systems. After checking and refining by experts, the synthetic dataset can finally be used to validate the anomaly detection models. The results demonstrate that the SCVAE model outperforms existing state-of-the-art unsupervised anomaly detection models and can be effectively generalized to unseen PV sites. Moreover, the latent variables of SCVAE could be used to identify the type of DPV failure, thereby enabling more targeted diagnostics of anomaly mechanisms. • An anomaly detection method is proposed for DPV in various environmental scenarios. • A novel unsupervised model is proposed for time series anomaly detection. • A real-world data processing pipeline and a labeled synthetic dataset are proposed. [ABSTRACT FROM AUTHOR]