The relic gravitational waves (gw) are the cleanest probe of the violent times in the very early history of the Universe. They are expected to leave signatures in the observed cosmic microwave background anisotropies. We significantly improved our previous analysis [1] of the 5-year WMAP $TT$ and $TE$ data at lower multipoles $ell$. This more general analysis returned essentially the same maximum likelihood (ML) result (unfortunately, surrounded by large remaining uncertainties): the relic gw are present and they are responsible for approximately 20% of the temperature quadrupole. We identify and discuss the reasons by which the contribution of gw can be overlooked in a data analysis. One of the reasons is a misleading reliance on data from very high multipoles $ell$, another - a too narrow understanding of the problem as the search for $B$-modes of polarization, rather than the detection of relic gw with the help of all correlation functions. Our analysis of WMAP5 data has led to the identification of a whole family of models characterized by relatively high values of the likelihood function. Using the Fisher matrix formalism we formulated forecasts for {it Planck} mission in the context of this family of models. We explore in details various `optimistic, `pessimistic and `dream case scenarios. We show that in some circumstances the $B$-mode detection may be very inconclusive, at the level of signal-to-noise ratio $S/N =1.75$, whereas a smarter data analysis can reveal the same gw signal at $S/N= 6.48$. The final result is encouraging. Even under unfavourable conditions in terms of instrumental noises and foregrounds, the relic gw, if they are characterized by the ML parameters that we found from WMAP5 data, will be detected by {it Planck} at the level $S/N = 3.65$.
Download