Communications in Wireless Sensor Networks (WSNs) are affected by dynamic environments, variable signal fluctuations and interference. Thus, prompt actions are necessary to achieve dependable communications and meet Quality of Service (QoS) requirements. To this end, the deterministic algorithms used in literature and standards, both centralized and distributed ones, are too slow and prone to cascading failures, instability and sub-optimality. Meanwhile, in recent years, cognitive protocols are gradually being introduced. This chapter provides an overview of the Transmission Power Control (TPC) protocols present in literature, categorized as deterministic (proactive and reactive) and cognitive (Swarm Intelligence, Fuzzy Logic and Reinforcement Learning). Only few solutions have considered TPC based on cognitive approaches, including both energy efficiency and QoS management. Our review identifies key shortcomings in deterministic TPC, pinpointing the benefit of the emerging methods based on computational intelligence.