Meet User’s Service Requirements in Smart Cities Using Recurrent Neural Networks and Optimization Algorithm

Despite significant advancements in Internet of Things (IoT)-based smart cities, service discovery and composition continue to pose challenges. Current methodologies face limitations optimizing Quality Service (QoS) diverse network conditions, thus creating a critical research gap. This study presents an original innovative solution this issue by introducing novel three-layered Recurrent Neural Network (RNN) algorithm. Aimed at QoS the context IoT discovery, our method incorporates user requirements into its evaluation matrix. It also integrates Long Short-Term Memory (LSTM) networks unique Black Widow Optimization (BWO) algorithm, collectively facilitating selection optimal services for specific tasks. approach allows RNN algorithm identify top-K based on under varying conditions. Our methodology’s novelty lies implementing LSTM hidden layer employing backpropagation through time (BPTT) parameter updates, which enables capture temporal patterns intricate relationships between devices services. Further, we use BWO simulates behavior black widow spiders, find combination meet system requirements. factors both attractive repulsive forces isolate best candidate solutions. In comparison with existing methods, shows superior performance terms latency, availability, reliability. Thus, it provides efficient effective IoT-based bridging gap current research.