Economics of Semantic Communication System in Wireless Powered Internet of Things

The semantic communication system enables wireless devices to communicate effectively with the semantic meaning of the data. Wireless powered Internet of Things (IoT) that adopts the semantic communication system relies on harvested energy to transmit semantic information. However, the issue of energy constraint in the semantic communication system is not well studied. In this paper, we propose a semantic-based energy valuation and take an economic approach to solve the energy allocation problem as an incentive mechanism design. In our model, IoT devices (bidders) place their bids for the energy and power transmitter (auctioneer) decides the winner and payment by using deep learning based optimal auction. Results show that the revenue of wireless power transmitter is maximized while satisfying Individual Rationality (IR) and Incentive Compatibility (IC).

1. INTRODUCTION

Internet of Things (IoT) enables and provides many smart systems and intelligent services such as smart home, smart cities and smart healthcare. The success of IoT heavily relies on communication systems that can accurately and effectively transmit information from transmitter to receiver. Recent advancements in natural language processing (NLP) [1], [2] and Deep Learning (DL) enabled end-to-end (E2E) communication system [3] have enabled semantic level communication systems for text transmission. While conventional communications focus on reducing the bit-error rate (BER) or symbol-error rate (SER) [4], [5], semantic communication aims to transmit the information relevant to the transmission goal. Recent works showed that the semantic communication system is robust at low signal-to-noise (SNR) region [6], [7], which helps to increase the reliability of IoT services. The ability to communicate effectively with the semantic meaning behind digital bits can inspire more smart applications of IoT. For example, in text transmission, semantic communication system can process text in the semantic domain by extracting the meanings of the text, filtering out the irrelevant information. For practical implementation in the IoT devices, the size and complexity of the semantic communication model can be reduced by model compression as verified in [7].