عنوان انگلیسی مقاله:
Integrating reinforcement learning and skyline computing for adaptive service composition
ترجمه فارسی عنوان مقاله:
یکپارچه سازی یادگیری تقویت و محاسبات خط افقی برای ترکیب خدمات سازگار
Sciencedirect - Elsevier - Information Sciences, 519 (2020) 141-160. doi:10.1016/j.ins.2020.01.039
Hongbing Wang a , ∗, Xingguo Hu a , Qi Yu b , Mingzhu Gu a , Wei Zhao a , Jia Yan a , Tianjing Hong a
In service computing, combining multiple services through service composition to address complex user requirements has become a popular research topic. QoS-aware service com- position aims to find the optimal composition scheme with the QoS attributes that best match user requirements. However, certain QoS attributes may continuously change in a dynamic service environment, so service composition methods need to be adaptive. Fur- thermore, the large number of candidate services poses a key challenge for service com- position, where existing service composition approaches based on reinforcement learning (RL) suffer from low efficiency. To deal with the problems above, in this paper, a new ser- vice composition approach is proposed which combines RL with skyline computing where the latter is used for reducing the search space and computational complexity. A WSC- MDP model is proposed to solve the large-scale service composition within a dynamically changing environment. To verify the proposed method, a series of comparative experi- ments are conducted, and the experimental results demonstrate the effectiveness, scala- bility and adaptability of the proposed approach.
Keywords: Service composition | QoS | Reinforcement learning | Skyline computing | Adaptability