Deregulation in the energy industry poses many challenges because energy plays a significant role in the economies of every nation. The identification of power spikes and the likelihood of power crisis is important to prevent the collapse of the energy sector that can severely affect economies. This paper employs the recently proposed “delay vector variance” method, which examines local predictability of a signal in the phase space to detect the presence of deterministic and non-linearity in time series. The DVV approach utilizes optimal embedding parameters that are obtained via a differential entropy based method using wavelet-based surrogates. The concept of (cross)-recurrence quantification analysis is used to study energy markets in order to locate hidden patterns, non-stationarity, potential spikes and examine the nature of these plots in the event of crisis in the energy and financial sector. Specifically, the recurrence plots are employed to detect and characterize seasonal cycles. The feasibility of these methods are provided with a focus on some emerging European power markets that are useful in the diagnosis and detection of potential power spikes, which is significantly impacted by economic downturns and other main drivers of imbalances in power markets.