A smart city is a system that uses technology means to create, implement, and promote environmentally friendly solutions to the problems caused by growing urbanisation. The smart city is a key answer that will allow us to continue with our regular lives during and after the epidemic. To better serve its citizens, a smart city takes advantage of modern technology and innovative solutions in areas including healthcare, educational, energy provision, transport, and communications. Applications of the Internet of Things have led to the development of "Smart Cities" all around the globe. In order to further the development of smart cities toward effective sharing and interconnection, this study will examine the smart city data technology based on the Internet of Things (IoT) and cloud computing (CC). Initially, we gather IoT data based on the smart cities. The gathered data is normalised. Machine learning sets the way for the IoT, which allows machines to communicate with one another without any human intervention. So we utilize machine learning algorithm called Advanced Random Forest (ARF). For multi-criteria optimization, we suggest Adaptive cloud computing virtual machine resource allocation technique (ACC-VMRA). We analyse and simulate the use of IoT and CC technologies in a smart city to verify its efficacy. The experimental finding demonstrates the recommended optimization algorithm's superior efficiency to other currently used techniques.