Research on the optimal strategy of pumped storage power station to provide multiple time-scale reserves

In the background of peak carbon emissions and carbon neutrality, renewable energy generation (REG) will become the main generation form in the future power system. Simultaneously, the randomness and volatility increase the reserve requirement in the different time scale. Increasing importance has been attached to energy storage in the aspect of reserve, as energy storage has the advantages of power flexibility and relatively low reserve cost. Trading off the benefits of energy storage in the energy market and the reserve market to maximize its benefits is of great significance to the economic operation and investment of energy storage. In this regard, taking the pumped storage power station (PSPS) as an example, this paper establishes an optimal decision-making model for PSPS to participate in the energy market and to provide reserve services. In addition, an optimal decision model for PSPS to provide multiple reserve services is established. The analysis finds that the power reserve capacity provided by PSPS at different time scales have little impact on each other, but their storage capacity requirements are mutually restricted. Case studies show that the total revenue of the PSPS is significantly increased through providing reserve service. The PSPS may even bid all its capacity to provide reserve service when the compensation price reserve reaches a certain level. In addition, the total revenue of PSPS when providing multiple time-scale reserves is higher than that when providing reserve service at single time scale.

Predicting the trend of stock index based on feature engineering and CatBoost model

As an important tool to measure the current situation of the whole stock market, the stock index has always been the focus of researchers, especially for its prediction. This paper uses trend types, which are received by clustering price series under multiple time scale, combined with the day-of-the-week effect to construct a categorical feature combination. Based on the historical data of six kinds of Chinese stock indexes, the CatBoost model is used for training and predicting. Experimental results show that the out-of-sample prediction accuracy is 0.55, and the long–short trading strategy can obtain average annualized return of 34.43%, which is a great improvement compared with other classical classification algorithms. Under the rolling back-testing, the model can always obtain stable returns in each period of time from 2012 to 2020. Among them, the SSESC’s long–short strategy has the best performance with an annualized return of 40.85% and a sharp ratio of 1.53. Therefore, the trend information on multiple time-scale features based on feature engineering can be learned by the CatBoost model well, which has a guiding effect on predicting stock index trends.

Evaluation of Distraction Effect of Music Stimuli during Cycling Exercise with Low intensity in terms of Multiple Time Scale

These data are obtained from experiments done by individuals.

Evaluation of Distraction Effect of Music Stimuli during Cycling Exercise with Low intensity in terms of Multiple Time Scale

These data are obtained from experiments done by individuals.