energy monitoring and dispatch
The problem
Plants that run a mix of grid supply, captive gas or coal generation, solar, batteries and waste-heat recovery, where dispatch still depends on a phone call and a spreadsheet.
A typical situation
Energy is now one of our largest costs after raw materials. We have grid supply, gas engines, a coal-fired boiler, rooftop solar and a new battery, but dispatch is still decided by phone and by habit. We pay peak-band rates when we should not, we know our total bill but not which line, shift or product drives it, and we cannot show the board whether the solar and battery investment is paying back.
Outcomes
Indicative ranges, validated in your pilot. These figures come from comparable industry programmes, not from TashIT projects. Your pilot sets a baseline with you and measures the actual change.
Typically 3-8% saving on total energy spend
Basis: Sub-metering and dispatch optimisation programmes in energy-intensive plants. Depends on tariff structure, the generation mix and how well dispatch is run today.
Typically 5-15% lower peak-band and maximum-demand charges
Basis: Load shifting and battery peak shaving where tariffs price time of use or maximum demand. Only applies where the tariff rewards it and loads can move.
Typically 1-4% less fuel per kWh generated
Basis: Better engine loading, fewer part-load hours and coordination with waste-heat recovery. Depends on engine condition, load profile and fuel contracts.
Typically from days to hours each month
Basis: Automated collection replaces manual meter readings and spreadsheets for monthly energy, cost-allocation and emissions reports. Depends on metering coverage.
From data to decision
We review your single-line diagram and existing meters, then add sub-meters and gateways at main feeders, large drives, compressors, chillers and every generation source. Reliable data already in PLCs, SCADA or generator controllers is reused.
Energy use is related to production volume, product mix, shift pattern and weather to give a baseline per line and per unit of output. Every saving is measured against this reference.
Models forecast plant load and solar output for the coming hours and days, and combine them with tariff bands, fuel prices, battery state of charge and equipment limits.
An optimiser recommends which sources to run, at what load, and when to charge or discharge the battery, within reliability and safety constraints. Operators see each recommendation and the reason for it. Closed-loop control is optional and comes later, if at all.
Dashboards and monthly reports compare actual cost with the baseline and with the recommended plan, so savings are verified rather than assumed.
Data and integration
How the pilot works
Duration
Scope
Agreed in writing before work starts, with targets set against your baseline.
The pilot follows a short diagnostic and ends with a written results review. Scaling up is a separate decision, made on the measured results. How our engagements work
Solution blueprint
A forecast-based dispatch advisor that schedules grid supply, captive generation, solar and battery storage to meet plant load at the lowest cost per unit.
Status: Reference architecture and pilot plan, available for a paid proof of concept. Reference material, not a client project.
Where it applies
Keep exploring
Pilot 8–12 weeks
Camera-based vehicle, load and label verification at gates and weighbridges, reconciled automatically with ERP and regulatory records.
Pilot 10–16 weeks
Edge camera systems that detect surface, fabric, packaging and assembly defects and trace them to batch and line.
Pilot 10–16 weeks
Condition monitoring and telematics analytics that predict failures and lower maintenance and fuel cost for plants and fleets.
Operations leaders buy lower energy cost, less leakage, compliance data they can trust and faster use of new capacity. Why AI projects stall without data and process foundations, and how a paid pilot with agreed measures works.
5 min read
Many industrial sites now run grid power, captive generation, solar and batteries side by side, scheduled largely by hand. What a dispatch optimiser does, the data it needs, how a pilot runs and what savings are realistic.
5 min read
Every topic
Practical articles on AI, automation and operational data: what works, what it needs and how to test it before you scale.
FAQs
Something else to ask?
Email your question with a little about your site and systems, and we will reply in plain language.
info@tashit.comNo. We read from existing systems and add meters only where data is missing. Recommendations go to operators first. If you later want closed-loop control, it is engineered with your controls team and equipment vendors, and existing safety interlocks stay where they are.
Most dashboards show what happened. This adds a baseline that adjusts for production, forecasts of load and solar output, and a dispatch plan that accounts for tariffs and equipment limits. If your meters and dashboard are sound, we build on them rather than duplicate them.
Against a baseline agreed before the pilot starts, normalised for production volume and, where relevant, weather and tariff changes. We follow the logic of the International Performance Measurement and Verification Protocol (IPMVP) so the figures stand up to finance review.
Tell us about your site or process and the data you already have. We will reply with a diagnostic plan, the measures we would propose for a pilot and an honest view of feasibility.