Decentralized energy markets can coordinate distributed generation, flexible demand and storage, but feeder feasibility, household forecasting and smart-contract settlement are usually assessed separately. This study develops a grid-constrained Decentralized Energy Marketplace (DEM) linking household commitments, bilateral matching, feeder-capacity screening, personalized federated forecasting and auditable energy-quantity settlement in a module-coupled, open-loop configuration with no feedback from settlement outcomes to forecasting or bidding. The principal finding concerns the enforcement mechanism applied when a feeder limit binds. Across 45 paired scenarios of measured Ausgrid households under a 1.5 kW branch-transfer stress cap, whole-trade removal retains 74.9% of the price-only submitted-price surplus, whereas marginal re-clearing retains 93.1%, a paired gain of 0 . 0 2 1 9 ± 0 . 0 0 6 0 EUR per interval ( 𝑡 = 7 . 1 2 ); this ordering holds in eight seasonal and weekday/weekend windows spanning the measured year, with the summer case-study week as the largest-gap case. AC power flow on 4320 accepted schedules shows no voltage or thermal violations; the first demand-side limit occurs at 1.7 times peak demand. In a 30-client non-IID benchmark, plain FedAvg underperforms local training for 87% of client–seed pairs, a known federated-learning effect demonstrated on measured energy data; per-client fine-tuning removes most of the penalty, and forecast-generated commitments materially change deviation-adjusted outcomes. On-chain replay exposed an energy-conservation defect missed by the initial tests; after correction, all 116 tradable intervals (1,325 trades) reconciled within integer rounding and a randomized differential suite matched an integer-exact reference on two EVM clients. Efficient constraint handling, client-level personalization and realistic multi-party settlement testing are central to credible blockchain-enabled local energy trading.
The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.
Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al.· Information and Software Tec...· 394 citations· ⚡54
This state-of-practice investigation was performed using a literature review followed by a multiple-case study approach and presents how inconsistency between managerial strategies and execution can lead to failure by means of a behavioral framework.
Carmine Giardino, Xiaofeng Wang, P. Abrahamsson· International Conference on...· 175 citations· ⚡19
This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.
Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al.· Empirical Software Engineeri...· 127 citations· ⚡15
It is found that roles of MVPs in startups were not fully aware by entrepreneurs, and entrepreneurs should consider a systematic approach to fully explore the value of MVP, as a multiple facet product (MFP).
Anh Nguyen-Duc, P. Abrahamsson· International Conference on...· 93 citations· ⚡9
It is found that what perceived as biggest challenges by software startups do vary across different life cycle stages, even though its significance decreases when the learning focuses of the startups move from problem to solution and their products mature.
Xiaofeng Wang, Henry Edison, Sohaib Shahid Bajwa et al.· International Conference on...· 62 citations· ⚡6
A comprehensive overview of how enhanced sampling methods are reshaping the field, with a particular focus on the data-driven construction of collective variables, is provided.
Kai Zhu, Enrico Trizio, Jintu Zhang et al.· Chemical Reviews· 58 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 7, 2026
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 6, 2026