As the core infrastructure service of cloud computing, Elastic Compute Service (ECS) offers a diverse range of products for users to select from. However, it is challenging for users to combine numerous configurations for the appropriate products, making it critical to be recommended individually. In contrast to traditional recommendation scenarios, ECS combines Business-to-Business (B2B) and Business-to-Consumer (B2C). Compared with enterprise users with rich behaviors, individual users account for a large proportion with limited behaviors, facing a serious cold start problem. Furthermore, enterprise users have high demands and strong preferences, leading to a high concentration on popular products, resulting in long tail distribution. To address the problems, we propose a novel model named the Representation Enhancement based Cold Start Model (ReCSM). Based on dynamic relations among users, the Cold start user Contextual Attention Module (CCAM) is designed to enhance the representation of cold start users with behavior-rich users, thus improving the expressiveness of the inductive model. What’s more, the Generalized Attribute Clustering Embedding module (GACE) is proposed to maintain the clustering center representation for each user to improve the generalization ability. Additionally, we implement the Contrastive Learning based Long tail products Enhancement Module (CL-LEM) to relieve the effect of long tail distribution, ensuring the diversity and fairness of recommendation results. Extensive experiments have proved the validity of ReCSM on two real ECS datasets and one public dataset.

An electromagnetic vibrational energy harvester (EVEH) capable of harvesting low-frequency and high-amplitude vibration energy is designed, fabricated and characterized in this paper. The high impact/shock-resistance of the proposed EVEH is enabled by a pair of specially designed dampers. The dampers, combined with a pair of nonlinear magnetic springs, also expands the effective bandwidth of the EVEH device. The fabricated EVEH, with a size of Φ2 cm X 10 cm, is capable of generating an open-circuit peak-to-peak voltage of 4.35 V and an average output power of 55.3 mW under a sinusoidal excitation of ±10g at 48 Hz. The designed shock/impact-resistance of the EVEH is verified by a sinusoidal excitation of ±20g at 18 Hz, and the fabricated EVEH is capable of generating an output voltage of 4.21V steadily.