Research on the Internal Mechanism,Model,and Effectiveness of Online Deep Learning

With the in-depth development of internet plus education and the COVID-19 pandemic,online learning has become a universal teaching method in the world.However,the issue of superficial and low-quality in online learning is still widespread.From the internal and external conditions of online deep learning,this study reveals the theory mechanism of how the online learning environment and teacher support,as external conditions,affect students’emotions and learning motivation,and then affect students’internal learning state.On this basis,an online deep teaching model is constructed,which consists of three stages:online asynchronous self-study before class,online synchronous live broadcasting teaching in class,and online asynchronous expansion after class.Meanwhile,a one-term long online teaching practice is carried out in the course named the Instructional System Design.The results show that,in the learning process level,the online deep teaching model can effectively improve students’online learning engagement,promote students to use deep learning methods and deep learning motivation to learn,and enhance the depth of online interaction between students.At the level of learning results,students’critical thinking and online academic performance 9 have been significantly improved.

Optimal Frequency Regulation Based on Characterizing the Air Conditioning Cluster by Online Deep Learning

The air conditioning cluster(ACC)is a potential candidate to provide frequency regulation reserves.However,the effective assessment of the ACC willing reserve capacity is often an obstacle for existing demand response(DR)programs,influenced by incentive prices,temperatures,etc.In this paper,the complex relationship between the ACC willing reserve capacity and its key influence factors is defined as a demand response characteristic(DRC).To learn about DRC along with real-time frequency regulation,an online deep learning-based DRC(ODLDRC)modeling methodology is designed to continuously retrain the deep neural network-based model.The ODL-DRC model trained by incoming new data does not require massive historical training data,which makes it more time-efficient.Then,the coordinate operation between ODL-DRC modeling and optimal frequency regulation(OFR)is presented.A robust decentralized sliding mode controller(DSMC)is designed to manage the ACC response power in primary frequency regulation against any ACC response uncertainty.An ODL-DRC model-based OFR scheme is formulated by taking the learning error into consideration.Thereby,the ODL-DRC model can be applied to minimize the total operational cost while maintaining frequency stability,without waiting for a well-trained model.The simulation cases validate the superiority of the OFR based on characterizing the ACC by online learning,which can capture the real DRC and simultaneously optimize the regulation performance with strong robustness against any ACC response uncertainty and learning error.