Search

Short-term load forecasting (STLF) of heterogeneous multi-agents plays a significant role in smart grid. Faced with special difficulties of multi-agent STLF due to the high heterogeneity, uncertainty and volatility, traditional local methods usually make predictions based on load aggregation or clustering, the complexity of which will rise greatly with the increase of agent types. It has become more and more difficult for traditional methods to meet the STLF demand of smart grid. Meanwhile, global time series forecasting method emerges gradually in many fields, which can make predictions for many agents only by one model with much lower complexity. However, there is few researches on the multi-agent global STLF. This study proposes a global deep-Long Short-Term Memory (LSTM) STLF model based on a pretraining method. The model fully applies the information such as electricity consumption pattern, weather and calendar in a structural and orderly way. The empirical results show that our model can effectively predict the daily load of heterogeneous households, with prediction accuracies of 87.9–90.2% on the test set across various tasks. Compared with the base model, our model achieves an 8.7% higher accuracy with a much faster convergence speed. Furthermore, the fluctuations of accuracy on different tasks are within 2.3%, showing that our model is robust. The superiority of the global method is proved through the comparison with local method in the empirical results. This study is expected to make contribution to global STLF of heterogeneous households and providing experience for the global prediction of heterogeneous time series based on deep-LSTM and pretraining method. [ABSTRACT FROM AUTHOR]

Demand-side response (DSR) measures, which facilitate the management of system reliability and maintain system resource adequacy of power grids, are gaining prominence. Traditional optimization methods for residential electricity usage in peak-demand hours often lack flexibility and effectiveness in solving practical problems due to a large amount of data and a high degree of data uncertainty. Our study aims to obtain a high degree of responsiveness for numerous and highly dispersed residential customers by integrating data-driven and model-driven methods. In this study, we conducted large-scale DSR controlled trials, collected 15-min intervals of electricity consumption data, and matched the survey data. A dynamic time-warping clustering-based difference-in-difference method was proposed for empirical analysis. The results indicate that monetary incentives induced a statistically significant reduction in electricity usage during peak periods in summer by 18.6%, while the response effect was not significant in winter. The heterogeneity analysis suggests that the reduction was mainly contributed by the middle-income group and the elderly group. Our study provides a basis for policymakers to formulate tailored policies to optimize residents' electricity consumption during peak hours. [ABSTRACT FROM AUTHOR]

Driven by the goal of “carbon neutrality” for achieving energy savings and carbon reductions, various industries are striving to continuously introduce green energy-saving products. This study contributes to providing pricing policies and product launch strategies for the green energy-saving product manufacturers, aiming at increasing their profitability when facing strategic consumers. We develop a two-period pricing model, which considers three pricing policies and three product launch strategies in the presence of green information sharing, and we then investigate the performance of two types of government subsidy programs. The basic results show that the manufacturers would share information and adopt price commitment or price matching with dual rollover launch, when both the information sharing cost and consumer strategic level are low. While sharing green information is always beneficial to manufacturers its impact on sales quantity depends on consumer strategic level and technology preference. The further finding suggests that the highest profits can be achieved by adopting both price commitment and price matching, whereas the largest sales quantity can only be obtained under dynamic pricing. To achieve the promotion goal under price commitment, we derive the optimal subsidies of the manufacturer and consumers, and the results indicate that subsidizing consumers can not only help to reach the maximum promotion but also eliminate the risk of market failure. This study is expected to provide insights of subsidy programs for policy makers to enable manufacturers to achieve the promotion goal of energy-saving product, and it also accelerates the development of sustainable supply chain management. [ABSTRACT FROM AUTHOR]