Article’s

Вот абстракт готовый к вставке в форму (195 слов, в рамках лимита 200): Energy depletion heterogeneity — not total consumption — determines when wireless sensor networks fail: nodes at traffic hotspots exhaust while peripheral nodes retain 60–80% residual charge, collapsing coverage prematurely. Existing clustering protocols such as LEACH and HEED address efficiency through hierarchical organization, yet their periodic reformation cycles leave them structurally blind to topology changes between updates, and no existing distributed protocol simultaneously optimizes residual energy, transmission distance, and node load using only local information while adapting those weights online through reinforcement learning. This paper presents DEAR (Distributed Energy-Aware Routing), a protocol that makes per-transmission forwarding decisions via a three-term cost function C(n) = α·E_r(n) + β·d(n) + γ·L(n), requiring no global state. DEAR-RL extends this by embedding Q-learning at cluster heads to update weights each round based on observed network conditions. Both protocols were evaluated in MATLAB across six competitors, four network scales (N ∈ {50, 100, 200, 300}), and five environmental scenarios with 50 independent runs per configuration. DEAR raises Half-Node-Death (HND) from 938 to 1,127 rounds versus HEED at N=100 — a 20.1% gain (p<0.001, d=1.31) — while reducing energy balance variance by 44%. Under node mobility, the advantage grows to 35.2%. DEAR-RL adds 8.2% over DEAR in baseline and 13.2% under mixed conditions at only 1.1% computational overhead. Keywords: wireless sensor networks; energy-efficient routing; reinforcement learning; network lifetime; distributed algorithm; clustering protocol; Q-learning