Smart energy scheduling for manufacturing
KickstartAI x GOMA
GOMA, a Dutch metalworking company, and KickstartAI are partnering to address grid congestion and energy volatility in the manufacturing sector. By combining production data with energy data and predictive modeling, the project explores how metalworking operations can become more responsive to conditions on the electricity grid. The aim is to support smarter scheduling, reduce energy costs, and develop an approach that could be relevant for other manufacturing SMEs.
The Problem
GOMA operates a high-precision metalworking job shop where production planning has to balance customer orders, machine availability, deadlines, and energy-intensive machinery. Without taking real-time energy constraints into account, heavy machinery is consistently operated during peak-tariff windows. GOMA currently has no automated mechanism to accurately calculate the exact energy consumption of individual customer orders, leaving them exposed to rising costs and unable to prove sustainability efforts.
Goal
The goal of the project is to reduce energy consumption during peak periods by making energy use part of GOMA’s production planning. The scheduling tool will optimize which orders are produced when: energy-intensive orders can be moved to lower-demand, lower-price periods where possible, while less energy-intensive orders can be scheduled during peak periods.
Approach
The approach consists of three phases:
Phase 1: Telemetry Integration. We install physical energy meters across key factory machines to capture granular consumption data.
Phase 2: Data Modeling. We clean and map historical production data, aligning specific customer orders directly to actual machine energy usage.
Phase 3: Simulation and Piloting. We simulate the potential to steer energy consumption per machine and execute a pilot testing the MVP on high-potential machinery.
Expected Results
Deploying this grid-adaptive scheduling tool is expected to deliver structural advantages for GOMA and the broader market:
Reduced Peak Consumption: Achieving a tangible 5 to 10% energy savings during peak grid windows.
Order Transparency: Accurately mapping real-world energy usage to specific customer orders.
Sector Blueprint: Uncovering scalable strategies for MKB and translating these insights to sector stakeholders.