Abstract-The 'super-WiFi' network concept has been proposed for nationwide Internet access in the USA. However, the traditional mains power supply is not necessarily ubiquitous in this large-scale wireless network. Furthermore, the non-uniform geographic distribution of both the based stations and of the teletraffic requires carefully considered user-association. Relying on the rapidly developing energy harvesting techniques, we focus our attention on the sophisticated access point selection strategies conceived for the energy harvesting aided super-WiFi network. Explicitly, we propose a solar radiation model relying on the historical solar activity observation data provided by the University of Queensland, followed a beneficial radiation parameter estimation method. Furthermore, we formulate both a Markov decision process (MDP) as well as a partially observable Markov decision process (POMDP) for supporting the users' decisions on beneficially selecting access points. Moveover, we conceived iterative algorithms for implementing our MDP and POMDP based AP-selection, respectively. Finally, our performance results are benchmarked against a range of traditional decision-making algorithms. Index Terms-Super WiFi network, access point selection algorithm, energy harvesting model, MDP, POMDP.