EGBP Bioenergy Grid Physically-Calibrated Synthetic Dataset — 15 nodes, 365 days, hourly resolution

131,400 node-hour observations across 15 bioenergy grid nodes (6 anaerobic digesters, 5 gasifiers, 4 CHP units) over 365 days at hourly resolution. Parameters calibrated to Faaij (2006) and Atashbar et al. (2016). Generated for: Ethical Guardrail Bandit Pruning (EGBP).

This repository supports the manuscript "Ethical Guardrail Bandit Pruning (EGBP): A Framework for Sustainable and Equitable AI-Driven Resource Allocation in Bioenergy Grids" (under review). EGBP treats computational efficiency, energy sustainability, and distributional equity as simultaneously binding optimisation constraints rather than sequentially addressed objectives. The central theoretical contribution demonstrates that embedding ethical guardrails directly in the optimisation objective, rather than evaluating them post-hoc preserves the asymptotic regret properties of Thompson Sampling bandit learning while guaranteeing convergence to an ethically-admissible stationary point. The framework integrates four tightly coupled mechanisms: (i) a hybrid bandit-gradient importance estimator combining offline Transformer pre-training with online Thompson Sampling; (ii) an ethical guardrail buffer enforcing differentiable penalties on energy overconsumption and distributional inequity through a Gini-coefficient regulariser applied to physical energy budget allocations; (iii) a cost-weighted magnitude pruning operator coupling gradient sparsity to real-time biomass conversion telemetry; and (iv) a guardrail-filtered federated averaging scheme with analytically bounded exclusion fraction. Theoretical properties are established through three theorems, three propositions, and two corollaries covering energy guardrail self-correction, Gini penalty convexity, Thompson Sampling regret preservation, EGBP convergence, and federated fairness monotonicity. Simulation on a 15-node bioenergy grid over 50,000 training steps demonstrates 38% reduction in energy consumption and 40% improvement in distributional fairness relative to three competitive baselines. This repository contains derived simulation outputs and pipeline code for reproducibility.

This repository supports the manuscript "Decision-Aware Adaptive Dispatch for Bioenergy-Integrated Power Systems Under Load-Shedding: A Sparse Gradient Framework with Variational Anomaly Detection and Adaptive Sparsity" submitted to the International Journal of Electrical Power & Energy Systems (IJEPES, ISSN 0142-0615, Elsevier; Manuscript ID: IJEPES-D-26-02106). The paper develops a physics-informed adaptive dispatch framework for bioenergy-integrated power systems operating under non-stationary load-shedding conditions. Three mathematically grounded contributions are provided: (i) a decision-aware objective function replacing forecast-error minimisation with direct dispatch cost minimisation under NERSA regulatory penalties; (ii) a sparse gradient update rule derived from Jacobian surgery that adapts only causally relevant model parameters under distributional shift, reducing adaptation cost by 94% relative to full retraining; and (iii) a variational free-energy anomaly signal grounded in non-equilibrium thermodynamics providing 8.3-interval advance warning of dispatch failure with 91.7% detection rate. A bioenergy-storage co-optimisation model incorporating Beta-distribution biogas seasonality, battery degradation, and landfill gas carbon credits delivers 19.1% additional cost reduction. Empirical validation on the Eskom 2015–2025 panel yields 23.4% dispatch cost reduction over model predictive control benchmarks, reaching 31.8% at Stage 5–6 load-shedding. Cross-continental validation covers ENTSO-E European data and regional datasets from Ghana, Nigeria, and Kenya. A SHA-256 audit log satisfies NERSA auditability requirements. This repository contains derived outputs and a pipeline skeleton for methodological transparency.