| 要約: | With the advent of a smart city that is embedded with smart technology, namely smart streetlight, in urban development, the quality of living for citizens has been vastly improved. Traffic-Aware Street lighting Scheme Management Network (TALiSMaN) is one of the apt smart streetlight schemes to date; however, it possesses certain limitations that led to network congestion and packet dropped during peak road traffic periods. Traffic prediction is vital in network management, especially for real-time decision-making and latency-sensitive application. With that in mind, this work analyses three low-complexity real-time prediction techniques, namely simple moving average, exponential moving average, and weighted moving average, to be embedded onto TALiSMaN, which aims to ease the network congestion. Additionally, this work proposes traffic categorisation and packet propagation control mechanism that uses historical road traffic data to manage the network from overload. The performance of these prediction techniques with TALiSMaN was simulated and compared with the original TALiSMaN scheme. Overall, the simple moving average showed promising results in reducing the packet dropped by 12.9% – 37.4% while capable of improving up to 2.9% of the streetlight usefulness experienced by the road users, when compared to the original TALiSMaN scheme, especially during rush hour.
|
|---|
