Wind energy has become one of the most promising new energy sources in the context of the global energy interconnection. However, the inherent uncertainty of wind power and the volatility of its output make it difficu...
Wind energy has become one of the most promising new energy sources in the context of the global energy interconnection. However, the inherent uncertainty of wind power and the volatility of its output make it difficult to join the internet for scheduling. The uncertainty of the output must be reduced or even eliminated by certain methods. In this paper, wind power and energy storage are coordinated to eliminate the uncertainty of wind power output, and to reduce the burden on the grid while ensuring the long-term operation of wind farms. This paper first introduces Q-learning in reinforcement learning as a controller. Through a large number of historical wind power data training, the controller has good decision-making ability, so as to reduce the punishment caused by wind power uncertainty; then the Q-learning is improved aiming at the maximum average income of the stage. Finally, the Q-value network is established with conventional Q-learning and improved Q-learning. The DQN algorithm in the deep reinforcement learning algorithm is introduced for deep training and decision-making and the three algorithms are verified. The result proves that the deep reinforcement learning algorithm can achieve better control effect than Q-learning.
The LiFePOVC battery has been widely used in many fields, and its safety problems are gradually attracting widespread concern. In this paper, two kinds of LiFePO4/C batteries with 25 Ah and 200 Ah were taken as resear...
The LiFePOVC battery has been widely used in many fields, and its safety problems are gradually attracting widespread concern. In this paper, two kinds of LiFePO4/C batteries with 25 Ah and 200 Ah were taken as research objects. The thermal runaway phenomena of two batteries were analyzed, and the difference of thermal runaway phenomena between two batteries were compared. The results show that the safety valve of the 200 Ah battery ruptures earlier and the thermal runaway occurs earlier under the same overcharge rate. The work provides a reference for the protection design of LiFePO4/C batteries.
The regional integrated energy system is an effective way to realize energy cascade utilization and improve the flexibility and economy of the load side operation. Combine cooling heating and power (CCHP) system is a ...
The regional integrated energy system is an effective way to realize energy cascade utilization and improve the flexibility and economy of the load side operation. Combine cooling heating and power (CCHP) system is a typical form of integrated energy systems. However, due to heat-load-based operation mode, the peak modulation capacity of CCHP units and the accommodation of renewable energy are limited. This paper explores methods of increasing the flexibility and economy of the system. An optimal scheduling model is proposed for integrated energy systems containing an electric heat pump, considering heating network characteristics. Simulation results show that the electric heat pump can help the system realize heat-and-power decoupling, improve the flexibility of the system and reduce the operating cost of the system.
A new information publishing system based on Internet of things is proposed, which is composed of four level hierarchical structure, including the screen identification layer, the network transport layer, the service ...
A new information publishing system based on Internet of things is proposed, which is composed of four level hierarchical structure, including the screen identification layer, the network transport layer, the service management layer and the publishing application layer. In the architecture, the screen identification layer has realized the internet of screens in which geographically dispersed independent screens are connected to the internet by the customized set-top boxes. The service management layer uses MQTT protocol to implement a lightweight broker-based publish/subscribe messaging mechanism in constrained environments such as internet of things to solve the bandwidth bottleneck. Meanwhile the cloud-based storage technique is used to storage and manage the promptly increasing multimedia publishing information. The paper has designed and realized a prototype SzIoScreen, and give some related test results.
暂无评论