A Thermal Time-Constant Framework for Temperature Forecasting and Control in Commercial Broiler Houses

Accurate indoor-temperature forecasting underpins feed-forward control in broiler production, yet the horizons at which data-driven models add value are unclear. Two questions are addressed: at which horizons learned models measurably beat persistence, and what preview a feed-forward controller needs. Thirty-five days of data at 15 min resolution from a commercial stacked-cage broiler house (78,000 birds; outdoor temperature −19 to 16 °C) are used to benchmark 18 single-step and 10 multi-horizon models, probabilistic forecasts, and control simulation. A single time constant, τ=25.7 h, organises the results: at 15 min, all learned models collapse to the persistence baseline (RMSE ≈ 0.105 K), because only 1% of the response relaxes per step; significant gains appear only at ≈1τ (LSTM −25% at 24 h, −30% at 48 h; FDR q ≤ 0.031). In control simulation, 4–8 h of MPC preview held σ = 0.17 K with zero violations (0.74 K for 1 h control), while longer horizons added no benefit and were less robust. Quantile intervals calibrated in-sample (PICP ≈ 0.90) under-covered under distribution shift (0.61–0.72); τ-anchored bands stayed calibrated (0.92–0.97). Design rules: evaluate forecasting models at horizons of at least ≈1τ and set control preview to ≈0.7–1.5τf, re-estimated per house and season.