In the arena of Cloud Computing, the emergence of social networks and IoT increased the number of available services on the cloud platform, making service composition and optimal selection (SCOS) in Cloud Manufacturing (CMfg), NP-hard. The existing approaches for addressing SCOS often fail to offer assistance with maximized trust and satisfied QoS preferences. Hence, this research paper presents a novel TeachIng leaRning-based Optimization aLgorithm (TIROL) for achieving the optimal solution for truST enforced clOud seRvice coMposition (STORM) to assist CMfg for improving the trust value with satisfied QoS preference(s). The performance of the proposed framework has been validated using the synthetic dataset generated from different test-cases. Experimental results show that the proposed framework is reliable and outperforms the SOTA approaches in terms of trust value maximization.

中文翻译：

---

基于教学-学习优化的信任强制云服务组合 - STORM

在云计算领域，社交网络和物联网的出现增加了云平台上可用服务的数量，使得云制造（CMfg）中的服务组合和最优选择（SCOS），NP-hard。解决 SCOS 的现有方法通常无法提供最大化信任和满足 QoS 偏好的帮助。因此，本研究论文提出了一部小说吨每个一世吴利R基于宁○优化大号算法（TIROL）用于实现 tru 的最优解英石强制分类○乌瑟R副公司米位置 (STORM) 以协助 CMfg 在满足 QoS 偏好的情况下提高信任值。使用从不同测试用例生成的合成数据集验证了所提出框架的性能。实验结果表明，所提出的框架是可靠的，并且在信任值最大化方面优于 SOTA 方法。