Achieving the accuracy-complexity tradeoffs for compositional timing analyses using Network Calculus is still a hot research topic. In this specific area, we propose in this paper an improved version of the Total Flow Analysis (TFA) algorithm, called TFA++, when taking into account the impact of the finite transmission capacity of the network links on the input and output traffic models at each network node. First, we review the existing analysis algorithms by identifying their main limitations in terms of accuracy and complexity, through a simple but representative network example. Afterwards, we define the TFA++ algorithm and we detail the main steps of the followed methodology to compute the delay upper bounds. Moreover, we conduct comparative analyses of the derived delay bounds and analysis times with the different algorithms, with respect to the network size and load. In doing this, we highlight noticeable enhancements of both metrics under TFA++, in comparison to the existing algorithms; thus the high accuracy and low complexity of TFA++. Finally, this statement has been asserted through a representative avionics case.