Data Analysis for Energy Efficiency Projects

Are You Truly Measuring Energy Savings Scientifically? In any ISO 50001-compliant Energy Management System (EnMS), Establishing an Energy Baseline (EnB) and selecting Energy Performance Indicators (EnPIs) are the absolute foundation. Without them, you cannot reliably prove energy savings or demonstrate continuous improvement. Let us see clear breakdown of these critical steps: 🔹 1. Establishing the Energy Baseline (EnB) The EnB is your quantitative reference point: "How much energy would we have used today if no improvements had been made?" Data Collection: Gather at least 12 months of historical data (energy consumption + relevant variables like production volume, degree days) to capture seasonality. Normalization: Avoid simple static baselines (e.g., last year’s total). Identify and account for key drivers (weather, output levels) that significantly affect consumption. Regression Analysis (Best Practice): Use linear or multivariable regression to build a model (e.g., y = mx + c). This lets you calculate expected vs. actual energy use under current conditions. 🔹 2. Selecting Energy Performance Indicators (EnPIs) EnPIs should be hierarchical — from facility-wide down to specific equipment ,and focus on efficiency, not just total consumption. A. High-Level (Facility-Wide) Energy Use Intensity (EUI): Total energy ÷ floor area (kWh/m²/yr) — ideal for buildings. Energy Intensity (EI): Total energy ÷ production output (e.g., kWh/unit) , standard in manufacturing. B. System & Equipment Level (Significant Energy Users) Chillers: kW/ton or COP Boilers: Combustion efficiency (%) or steam intensity Compressed Air: Specific power (kW/100 cfm) C. Productivity Metrics Link energy to value: kWh/kg of product or energy cost per unit sold. The Process in a Nutshell Identify Significant Energy Users (SEUs) Determine key driving variables Build the EnB using regression on historical data Choose EnPIs that track true efficiency Getting these steps right turns energy management from guesswork into data-driven success. And a final question for energy managers, sustainability leaders, and facility engineers: what has your experience been with baselines and EnPIs? Have you encountered common pitfalls, or found go‑to tools, for regression analysis? If you have a question, insight, or story to share, feel free to comment. #EnergyManagement #ISO50001 #EnergyEfficiency #Sustainability #EnMS #EnergyPerformance #NetZero

Electric utilities sit on oceans of data but lack the pipelines to turn it into insight. Smart meters record consumption every 15 minutes. SCADA systems log voltages every few seconds. Asset databases hold transformer histories stretching back decades. Yet these datasets remain scattered—locked in silos, misaligned in time, and inconsistent in structure. This project covers practical methods for cleaning, resampling, and integrating AMI, SCADA, weather, and asset data so it can power analytics and machine learning. The examples move from raw telemetry to actionable intelligence: aligning disparate feeds, reconciling missing data, joining operational and asset records, and producing unified time series that tell the real story of grid health. https://lnkd.in/gsa-N8jY

Energy costs are up. Ops teams are lean. And the old playbook—setpoints, spreadsheets, and “we’ll tune it when we have time”—doesn’t scale across a portfolio. Most owners don’t have an effort problem. They have a leverage problem. In this case, the symptoms were familiar: -Demand charges climbing -Hot/cold complaints that never fully go away -Utility data living in finance, BMS data trapped in vendor silos -Engineers drowning in alarms instead of fixing root causes So we shifted the mindset from “set-and-forget” to closed-loop optimization. We unified the data layer first. Not for pretty dashboards—so the data became queryable, comparable, auditable across sites. Then we used agents to surface rank-ordered actions tied to real dollars: schedules drifting, economizer logic issues, sequencing problems, condenser delta-T gaps. And where it was safe and deterministic, we automated the wins. Pre-cool, targeted shed, schedule enforcement. The big difference? Every change got verified in live data. If it saved, it stayed. If not, it rolled back. That’s not hype. That’s discipline—codified. #CRE #PropTech #SmartBuildings #EnergyEfficiency #AI #BuildingOperations #DataGovernance #DigitalInfrastructure #ESG

We know energy costs are soaring. So what can building owners and managers do to use energy more efficiently? In our experience monitoring countless buildings globally for nearly a decade, analytics software is the common thread that binds together the most effective energy-cutting strategies. Here are some to consider. 🔎 Keep a constant eye on your portfolio Continuous asset monitoring is foundational to identify energy cost-cutting opportunities across a portfolio, helping to avoid the 10-30% of wasted energy that would otherwise be lost to ‘drift’. It offers a high-level view to detect and resolve inefficiencies, a process that becomes scalable with digitisation. Digitising requires an analytics-led automated fault detection and diagnosis (AFDD) platform like PEAK. ⚙️ Improve efficiency through optimised control strategies Optimisation seeks to maximise the operational efficiency of existing plant and equipment, facilitating energy savings of more than 15% while extending equipment life cycle by an average of 2 years. There are a number of tried-and-tested BMS control strategy reviews that will identify and resolve operational inefficiencies. Think: outside air temperature lockouts, economy mode operation, cooling tower temperature control, chiller cooling & boiler heating calls, reviewing of zone temperature setpoints, and night purge. 🛠️ Adopt a data-driven approach to maintenance Data-Driven Maintenance (DDM) is favoured by early-adopting owners. Rather than a contractor regularly checking functional equipment or sensors, they can leverage analytics to organise their maintenance schedules in a far more targeted manner. This has implications for the negotiation of maintenance contract costs which can be reduced by more than 20%. 🔄 Upgrade and electrify While using your existing equipment more intelligently will deliver the best results, there will still be instances where equipment will need to be upgraded. Monitoring and optimisation should generate significant savings which owners can then invest in upgrades to dated equipment or system replacements. Common examples include LED lighting, VSDs, BMS upgrades, window revamps, chiller and boiler upgrades. And, of course, electrification should be considered in any portfolio upgrade. ♻️ Embrace renewable energy sources To become truly sustainable, we must ultimately transition to electrified portfolios powered by zero-carbon electricity. Circumstances permitting, this can be derived onsite via solar, biofuels, photovoltaic systems, solar thermal systems, energy storage systems etc. Where on-site generation isn’t possible, renewables can be procured offsite through PPA’s. But of course, any capex investment should be complemented by a foundational strategy of monitoring and optimisation. What have I missed? Let me know in the comments. #energyefficiency #sustainability #electricityprices #gasprices #operationalefficiency

What insights can we extract from large scale AMI data to inform building operation, HVAC system type, occupant behavior, and strategies to improve energy efficiency? In this recent study collaborating with Portland General Electric, we presents a comprehensive data-mining framework for analyzing AMI data at multiple temporal and spatial scales, extracting key statistics such as start hour, duration, and peak hour of load periods across daily, weekly, and annual evaluation windows. The framework employs a list of techniques including load-level detection, home vacancy detection, and weather-sensitivity analysis and statistical methods to provide detailed insights into building energy dynamics. Key findings highlight the substantial impact of the COVID-19 pandemic on residential energy use, uncover patterns like intraday load variations, weekly consumption trends, and annual weather sensitivity. The insights gained can potentially inform better energy management strategies, support grid operations and planning, guide policy-making for energy efficiency improvements, as well as improve input and assumptions in urban scale building energy modeling. Details are presented at the open access article in the Energy and AI journal. https://lnkd.in/grak4rVG

We can’t directly measure the absence of energy. Instead, we verify savings by estimating how much energy we’ve avoided consuming. Counterfactual models help us do this, by predicting what the consumption in a building would have been without efficiency projects. I released a series of Python tutorials that guide you through all of the steps: 1. Loading and preprocessing the data 2. Building a robust counterfactual model with LightGBM 3. Estimating uncertainty in the savings 4. Extrapolating short-term results to annual estimates All code linked in the comments below 👇 I would love to hear from other practitioners using ML for M&V. Have you tried these tutorials? Which tools or methodologies have you found most useful in your projects?

Electricity management is increasingly an analytics problem where AI needs to step in. Decarbonization, variable demand, regenerative energy, and complex infrastructure make it impossible to rely on static rules or occasional reporting. Value comes from analyzing operational data continuously and turning it into decisions. The usual analytics setup does not scale. Work is often done in silos, with data pulled into notebooks, results shared as static reports, and little reuse across projects. Domain experts are separated from the analysis, cycles are slow, and each new use case starts largely from scratch. A collaborative model is a catalyst enabling AI to change the economics. At Mitsubishi Electric, data scientists work directly with domain experts on shared workflows. Analytics is used to identify concrete issues and opportunities. In railways, analysis showed where braking generates surplus energy and how it could be reused. In thermal energy management, a full year of building data was analyzed in 20 business days to optimize heating and cooling. Platform efficiency matters. By running the full AI lifecycle in Dataiku, Mitsubishi Electric reduced their time to produce new projects by about 60 percent. That translates into delivering value roughly 2.5 times faster, which means more use cases delivered and quicker operational impact. This is what AI Success looks like in energy and industrial systems. Read the full story on our website: https://lnkd.in/evhhuQNF