BEEGroup

Building Energy and Environment

Innovation Unit of CIMNE

About

Building Energy and Environment - BEE Group

Data driven intelligence

BEE Group leads innovative research for decarbonizing buildings and enhancing the climate resilience of cities through data-driven solutions

Team, vision & mission

Mission

Our solutions provide agile responses to critical challenges: climate adaptation, urban decarbonization, community energy empowerment, grid stability and energy soberainity at community level

BEE Group delivers AI-powered analytics to build a low carbon and resilient future. We specialise in:

• Decarbonizing building portfolios: Optimizing energy use and building operation to reduce carbon emissions
• Climate-adapting cities: Enhancing urban resilience against climate threats
• Empowering energy communities: Enabling citizen-led energy sharing and management.
• Scaling Renewable energy bio sources: Making biodigester technology more accessible and effective

BEE Group Technologies

Innovative tools for efficient building's operation and urbant climate adaptation

BEEGroup

Technology: architecture and frameworks

BIGGR

• AI toolbox for clustering, classification, and modeling of buildings time series + metadata.

• Native integration with the BIGG Ontology for semantic consistency.

• Enables interoperable pipelines and data re-use across teams and companies.

 AI-powered building data analytics toolbox

• Python library for linear programming optimization
• Optimizes energy sharing and day-ahead battery operation for PV- and battery-based communities.
• Works with diverse DERs (solar, batteries) at any scale—no limits on clients or asset distribution.
• Supports per-client tariff definitions

What does it do?

BEEGroup

Technology: architecture and frameworks

• Python library for stochasting programming optimization
• Optimizes DER operation under uncertain electricity load predictions

What does it do?

BEEGroup

Technology: architecture and frameworks

Applied Research

Smarter distributed energy resources and flexibility

• Enhance energy flexibility with model predictive control and optimized storage in smart buildings and grids
   

Big data analytics for energy efficiency and buildings' operation

• Developing data-driven processing and models to improve the management and decarbonization of large building portfolios

Energy transition and climate adaptation in cities

• Geospatial artificial intelligence (GeoAI) to build a more resilient future for cities with accelerated spatial problem-solving

Research lines

Low-cost biodigester technology

• Development of low-cost digesters as a widespread biogas technology for various climates.

• BlueBird (2024–2027) Flexibility market design and trading for smart buildings. Involves TSO/DSO coordination.

• CELINE (2024–2027) Digital ecosystem for energy communities, with AI assistant for collective actions.

• Climate‑Ready Barcelona (2023–2025) Climate Vulnerability Index (CVI) for 61,000+ buildings and public-facing energy advice services.

• CLIMRES (2024–2027) Tools to assess and improve climate resilience of buildings and cities.

• POWERUP (2024–2027) Enable renewable adoption across sectors using open-source tools and context-aware strategies.

Vanguard Innovation

• EKATE+ (2024–2026) Cross-border renewable energy communities (Spain–France) with digital twins and electromobility.

• AGROPURITECH (2023–2026) Valorization of pig slurry via low-cost anaerobic digestion.

• COSMIC (2024–2027)  Large-scale pilots to demonstrate how big data and AI can optimize energy resources

• DEDALUS (2023–2026) Participatory demand response from households to districts using AI and social sciences.

• LEADnet (2026–2029) Empower local and regional authorities to plan and implement CET policies efficiently.

Ongoing european projects

Current research projects

BEE Group is currently involved in 11 European research projects and coordinates 3. The most significant ones are:

1. Big data analytics for energy efficiency and buildings' operation

1.1. Ontology based big data architecture

• Orchestrates massive energy and urban data in real time.
• AI-powered analytics, and semantic harmonization to drive energy efficiency and actionable decisions for real-time saving

ENMA

open-source big data architecture developed by BEE Group

G. Mor; J. Vilaplana; S. Danov; J. Cipriano; F. Solsona; D. Chemisana. EMPOWERING, a Smart Big Data Framework for Sustainable Electricity Suppliers. (2018) IEEE Access. vol. 6, pp. 71132 - 71142.

Reference paper

1.1. ENMA

Technology: architecture and frameworks

• Standardized schema (OWL/RDF Turtle) and shared vocabulary for describing IoT devices, buildings and urban areas, enabling interoperability.
• Supports planning, operations, and sustainability with harmonized data and KPI framework for measurement and benchmarking.

• J. M. Broto, J. Cipriano, G. Mor, O. Gavaldà, S. M.-Verki, U. Eicker (2025). An interoperable ontology-based information model for better integration of building physics and IoT data analytics models. IEEE/ACM 7th International Workshop on Software Engineering Research & Practices for the IoT (SERP4IoT). 
• E. Martínez-Sarmiento; J. M. Broto; E. Gabaldon; J. Cipriano, R. García; S. Danov  (2024).Linked Data Generation Methodology and the Geospatial Cross-Sectional Buildings Energy Benchmarking Use Case. Energies 2024, 17(12), 3006

Reference papers

1.2. Interoperable web semantic frameworks

USE CASE 1:  Fault detection of PV inverters

What does it do?
Detects anomalies in the energy produced by PV installations in near real-time

Data used:

• PV generation from monitoring systems

• Historical climate data

Objectives:

• To identify energy performance anomalies

• To assess the possible root of the anomaly

1.3 Artificial Intelligence for fault detection

USE CASE 2: Longitudinal benchmarking

What does it do?
Analyzes a building’s energy performance over time to detect trends and assess potential energy faults.

Data used:

• Time series of energy consumption

• Historical climate data

• Calendar data

Objectives:

• Detect changes in energy indicators of individual buildings over time

Estimation of the balance point temperature for heating and cooling periods

Detection of holiday periods

1.3 Artificial Intelligence for fault detection

What does it do?
Compares the energy performance of multiple buildings at a specific moment to identify inefficient or exemplary performance.

Data used:

• Harmonized KPIs per building

• Static data: use, surface area, climate

• Typological classification of buildings

Objectives:

• Identify best practices and critical buildings

• Prioritize actions based on comparative performance

• Generate benchmarks for new projects

USE CASE 1: Cross-sectional benchmarking

Identification and quantification of discrepancies between actual and historical energy consumption

Estimation of the balance temperature for heating and cooling periods

1.4 Artificial Intelligence for energy assessment

What does it do?

Evaluates the effectiveness of EEM and energy retrofitting actions

Assessed over 400 public buildings in the Zlin Region (Czech republic) and 4,000 public buildings of Generalitat de Catalunya

Data used

• Harmonized time series of energy consumption

• Technical information from systems (SCADA, CMMS, IoT sensors)

• Hourly climate data

• Data base of applied EEMs with their application date

1.4 Artificial Intelligence for energy assessment

USE CASE 2: Assessment of Energy Efficiency Measures

BEE Group solutions: BEEMind tools

Solutions in big data analytics:

MindOpera

• Integration of heterogeneous operational data (consumption and temperature, maintenance orders, energy efficiency measures, RES generation, cadastre, BIM, and SCADA data)

• Automatic harmonization of records from multiple sources (Modbus, Bacnet, DEXMA, etc.)

• Generation of operational indicators (self-consumption, PR, Compliance, etc.)

• Adaptable visualizations for each infrastructure

• AI modules focused on predictive maintenance, control, and energy optimization

Functionalitalities

Benefits

• Orchestration and harmonization of large volumes of operational data from buildings

• Improves overall management of equipment and commercial buildings

• Reduces supervision time and generates smart alerts

• High interoperability and communication with management and maintenance systems

• Suitable for managers of public and commercial building portfolios

Buildings 4.0: Global Operation of Buildings 4.0

MindOpera

Some KPI

Infraestructures.cat

Use case Mind Opera: L'Orquestrador

63.258  zones

1.526

Equipments

129.205  assets

 1.302.786

workOrders

12.400 BMS device

8.526 Monitoring device

Monitoring: Tracking KPIs

Control and Maintenance

MindOpera: L'Orquestrador

Integrate and visualize the energy data of all Generalitat facilities (10,000) and support energy savings through data intelligence:

• Comparison of energy indicators

• Evaluation of the energy performance of each facility

• Verification of savings from Energy Efficiency Measures

• Planning of energy efficiency actions

The project

Use case MindOpera: Sistema Monitorització Energètica – SIME-ICAEN

Seguiment i avaluació del Pla d’Estalvi Energètic dels edificis de la Generalitat de Catalunya.

Goals

Equipment supervision

Monitoring and control of supplies

Monitoring and

control of certificates and audits

Global energy supervision

Monitoring of energy efficiency measures

Monitoring of projects and actions

Data provision to external services

Data verification from different sources

Data provision to external services

Massive comparison: Energy benchmarking

Institut Català d'Energia

MindOpera: SIME

Centralized management

Energy Analytics

Energy Efficiency Measures

Institut Català d'Energia

MindOpera: SIME

2. Energy transition and climate adaptation in cities /geosp

Objective: From Territorial Data to Intelligent Decision Support

CIMNE BEE Group develops advanced methodologies that combine geospatial analytics, data-driven modelling, and Generative AI to transform heterogeneous territorial data into actionable knowledge.

By bridging geospatial science with modern AI architectures, we enable scalable analysis pipelines that support urban planning, energy transition, and climate resilience strategies.

 2.1 Research lines in Energy Transition and climate adaptation

• Data acquisition, harmonization, and semantic interoperability pipelines
  • hypercadaster_ES: Automatic gathering, advanced inference, and interoperability of cadastral data
  • social_ES: Automated geospatial data integration on socio-demographics, households characteristics and economic indicators.
  • greenshadow: Solar exposure, PV potential estimator and shadow modelling for urban environments.
• AI-driven modeling:
  • Air temperature and humidity downscaling at 100m grid
  • Thermal energy demand of buildings
  • Electricity and gas energy consumption of buildings
• Use cases:
  • Heat Vulnerability Index at building level

2.1.1 geosp / Data acquisition / hypercadaster_ES

Python library designed for comprehensive analysis of Spanish official cadastral data. It provides tools for downloading addresses, parcels and buildings cadastral information, integrating attributes of external geographic datasets (administrative levels, DEM, OSM...), and performing advanced building geometry inference, shading analysis, and energy simulation data preparation.

Public repository: https://github.com/BeeGroup-cimne/hypercadaster_ES

2.1.1 geosp / Data acquisition / social_ES

Python library to ingest, clean and harmonise most updated Spanish demographics, socioeconomic and other social-related datasets from National Statistics Institute.

Example datasets:

- Annual Household Income Distribution dataset

- Annual Population Census

- Population Education and Employment Status Census

- Estimated Essential Characteristics of Population and Households by building (hypercadaster_ES is being used in this estimation)

Public repository: https://github.com/BeeGroup-cimne/social_ES

2.1.1 geosp / Data acquisition / greenshadow

Python library for environmental shading analysis using LiDAR data and custom algorithms to simulate the solar shading of rural and urban areas in maximum detail. It uses hillshade techniques combined with cast shadow calculations to provide accurate solar radiation analysis.

Public repository: https://github.com/BeeGroup-cimne/greenshadow

2.1.1 geosp / Data acquisition / greenshadow

Public repository: https://github.com/BeeGroup-cimne/greenshadow

2.1.2 geosp / Modelling / Air temperature and humidity downscaling

Public repository: https://github.com/BeeGroup-cimne/CR_BCN_meteo

2.1.2 geosp / Modelling / Thermal energy demand of buildings

1 - Select a subset of real buildings and their context

2 - Define building envelopes archetypes according to building code

3 - Define user behaviour patterns according to demographics and socioeconomic profiles

4 - Define building systems archetypes according to EPC and cadastral data

5 - Define microlocal weather input files

2.1.2 geosp / Modelling / Electricity and gas energy consumption

Predict electricity and gas consumption at building level, based on a Graph Neural Network

Input data is socio-economic, demographics, energy demand, city graph (buildings, districts, postal codes, census tract...), building characteristics, and weather conditions. 

2.1.2 Use cases: Heat Vulnerability Index at building level

The Heat Vulnerability Map of Barcelona is a geospatial analysis tool that identifies buildings most at risk buildings during extreme heat events considering:

• Building characteristics
• Climate Variability and Extreme Events
• Demographic Indicators
• Infrastructure Indicators
• Energy indicators
• Socio-economic Indicators

The framework is based on the dimensions defined in the IPCC’s Third Assessment Report: Exposure, Sensitivity, and Adaptive Capacity.

It provides an assessment of all residential buildings in Barcelona(61,000)

2.1.3 geosp / Use cases / Heat Vulnerability Index at building level

2.2 Research line in Generative Artificial Intelligence (genAI)

An AI agent is a system where an LLM plans actions, calls tools, evaluates results, and iterates toward a goal.

• Core Capabilities
  • Planning and reasoning loops
  • Tool execution (code, APIs, GIS workflows)
  • Memory and state management
  • Multi-step problem solving
• Architectures
  • ReAct / tool-calling agents
  • Multi-agent orchestration
  • Human-in-the-loop agents
• Practical Use Cases
  • Development copilots (Claude Code, Opencode)
  • OpenClaw-style research agents

2.2.1 genai / RAG Use Cases / beechat

RAG-based conversational interface built on OpenWebUI, enabling semantic search and dialogue over internal project documentation.

• Knowledge Sources (Nextcloud, GitHub)
  • Technical documentation
  • Project deliverables, concept notes and research papers
• Functionalities
  • Connects to GitHub, Nextcloud, DBs
  • Context-aware chat over institutional knowledge
  • Semantic retrieval from large document collections
  • Continuous knowledge enrichment
• Benefits
  • Reduces information silos
  • Accelerates onboarding and research workflows
  • Centralizes access to historical project knowledge

2.2.2 genai / Agent use cases / Openclaw

OpenClaw is an autonomous agent framework designed to execute complex research and analytical workflows by combining LLM reasoning, tool execution, and iterative planning. Some potential applications in Geospatial Analysis include:

Public repository: https://github.com/openclaw/openclaw

• Automated exploration of spatial datasets and metadata
• Generation of preprocessing scripts for GIS workflow
• Literature review and synthesis of urban climate research
• Autonomous creation of spatial indicators and analytical reports
• Assistance in ontology-driven geospatial modelling

3. Smarter distributed energy resources and flexibility

3.1. Optimization of Energy Communities - Energy flexibility

• Platform for the energy management of Energy Communitites

Initial Service Levels

• AI for optimized management of centralised/decentralized batteries
• Optimisation of electricity sharing coefficients.

Advanced services

Additional Services

• Nudging services

Cross-sectorial integrated digital services enabling energy  and community Empowerment

Use case:  Valencia - SAPIENS Energía

To assess energy flexibility

• Maximise self-consumption: PV and battery
• Support the electricity network balance

User empowerment:

• To facilitate data-driven decisions

Energy Communities:

3.1. Optimisation of  Energy communities:Nudging tool for notifications

1. Optimizing Renewable Energy Communities

• Illa Eficient (EKATE+): REC in the eixample of Barcelona (2 building blocks) (55 users) + 2 centralized batteries + 2 PV installations

• PEUSA (La Seu d'Urgell): 15 users with remote controlled HVAC + 1 centralized battery + 4 PV installations in public buildings

• SAPIENS (València): 15 REC with centralized batteries + PV installations + remote controlled HVAC

• Industrial REC: 15 industries in Granollers Mercat

• SIE-Comunitats (Inergy+Beedata): 40 RECS already using ECTOR

3.1. Optimisation of  Energy communities

3.2. Model predictive control for energy flexibility

What does it do?

Optimizes the energy costs based on electricity market price and PV self-consumption generation

• Remotely controls the flexible loads (HVAC) while respecting the comfort boundaries

• Improves the interaction between buildings and the electricity network

3.2. Model predictive control for energy flexibility

1. Optimizing Energy Flexibility in Public Buildings (AMB)

• Casa de la Vil·la (Montcada i Reixach): Optimizing the HVAC system with day-ahead market price + collective self consumption escola Reixach

• La Illa esportiva (Castellbisbal): Optimizing the swimming pool water climatisation + EV chargers optimization

• Centre Cívic Virgínia Amposta (St. Vicenç dels Horts): Optimizing the HVAC system of the building