No abstract

No abstract

Using solar energy to generate thermal power is often called concentrating solar power (CSP), is a grid friendly clean energy utilization mode with unique development advantages. Large capacity heat storage system with relatively mature technology and low cost can be configured to ensure stable and controllable power generation. The method can be. Solar thermal power generation has become a strategic emerging industry supported by many countries around the world. Spain, the United States, India, South Africa and other countries have carried out commercial operation of power technology with solar thermal, and installed capacity is growing steadily. China has also given key support to CSP generation technology, which has been vigorously developed. As the most promising new energy technology, CSP generation from molten salt heat storage tower is one of the main technical approaches of CSP generation. The key is to store the absorbed solar heat through thermal storage materials and release it stably for a long time, so as to achieve continuous and stable power generation independent of solar radiation changes. Through analysis, this paper puts forward the key technology research and scheme of molten salt regenerative CSP generation system, promotes the research on the bidirectional relationship between CSP station and power grid, and realizes the innovation of renewable energy technology. Relevant research results and technical schemes can be popularized and applied in demonstration power stations, and can also be used for operation control of newly-built molten salt heat exchange and storage tower power stations in the future.

The optimization of multi-zone residential heating, ventilation, and air conditioning (HVAC) control is not an easy task due to its complex dynamic thermal model and the uncertainty of occupant-driven cooling loads. Deep reinforcement learning (DRL) methods have recently been proposed to address the HVAC control problem. However, the application of single-agent DRL for multi-zone residential HVAC control may lead to non-convergence or slow convergence. In this paper, we propose MAQMC (Multi-Agent deep Q-network for multi-zone residential HVAC Control) to address this challenge with the goal of minimizing energy consumption while maintaining occupants' thermal comfort. MAQMC is divided into MAQMC2 (MAQMC with two agents:one agent controls the temperature of each zone, and the other agent controls the humidity of each zone) and MAQMC3 (MAQMC with three agents:three agents control the temperature and humidity of three zones, respectively). The experimental results show that MAQMC3 can reduce energy consumption by 6.27% and MAQMC2 by 3.73% compared with the xed point; compared with the rule-based, MAQMC3 and MAQMC2 respectively can reduce 61.89% and 59.07% comfort violation. In addition, experiments with di erent regional weather data demonstrate that the well-trained MAQMC RL agents have the robustness and adaptability to unknown environments.

No abstract