Dashboards & Analytics

Siteplore Platform — Dashboards & Analytics

See the Trend. Understand the Context.

Siteplore turns connected operational time-series into dashboards, comparisons and analytical workflows that help engineers and operational teams understand what changed, when it changed, how assets or sites compare, and what deserves further investigation.

Siteplore uses dashboards as an analytical interface, not simply as a collection of charts. Useful interpretation still depends on measurement quality, operational context and engineering judgment.
Siteplore Analytical View
Utility & Asset Performance
Energy 32.8 MWh Selected period
Assets 48 Monitored
Events 3 Require review
Historical Performance Trend Illustrative View
Compare Asset vs Asset
Investigate Before / During / After
Context Load • State • Environment
The Analytics Gap

Having data does not automatically mean understanding performance.

Operational systems may collect thousands of measurements, yet teams can still spend hours exporting spreadsheets, switching between systems or manually comparing trends before reaching a useful engineering conclusion.

01

Too Many Separate Trends

Related measurements may exist in different dashboards or systems, making context difficult to see.

02

Current Value Without History

A value can look acceptable today while a longer-term trend shows meaningful deterioration.

03

No Operational Context

Changes in load, production, equipment state or environment can alter how a measurement should be interpreted.

04

Difficult Comparison

Similar assets, areas or sites may perform differently without an easy way to compare them.

05

Event Without Before & After

Investigation becomes harder when the operating trend around an event is not readily available.

06

Dashboard Without Decision

Attractive visualization creates little value unless it supports a real operational or engineering question.

Start With the Question

Analytics should help answer an operational question — not just display a metric.

01

What Changed?

Identify when a measurement, condition or performance pattern began to change.

02

Is It Normal?

Compare current behavior with relevant historical patterns or operating ranges.

03

What Happened at the Same Time?

Compare related signals to understand operational context.

04

Which Asset Performs Differently?

Compare similar assets under relevant operating conditions.

05

Is Performance Improving?

Evaluate changes after maintenance, operational adjustment or improvement activity.

06

What Deserves Investigation?

Prioritize meaningful deviations instead of manually reviewing every available signal.

Analytical Views

Turn historical measurements into useful operational comparisons.

Historical

Trend Analysis

Review how a selected measurement changes over time.

Relative Performance

Asset Comparison

Compare similar machines, feeders, stations or other monitored assets.

Time Comparison

Period Comparison

Compare today, previous shifts, weeks or other relevant operating periods.

Context

Multi-Signal Analysis

Place related measurements on the same analytical view to evaluate coincident changes.

Investigation

Event Analysis

Review conditions before, during and after a selected monitoring event.

Performance

KPI Monitoring

Present selected indicators where the KPI definition is meaningful to the use case.

Operating Context

Load & State Analysis

Interpret metrics against equipment load or operating state where available.

Site-Level

Area / Site Comparison

Compare selected metrics across different operating areas or sites.

Data Quality

Availability Analysis

Review missing, delayed or incomplete data that may affect interpretation.

Siteplore Analytics Architecture

Analytics starts before the dashboard.

Useful visualization depends on credible measurement, structured time-series data, contextual metadata and an analytical question worth answering.

01 — MEASURE

Field Data

Sensors, meters and operational systems provide the source data.

02 — STRUCTURE

Time-Series Data

Measurements are organized with useful timestamps and metadata.

03 — VISUALIZE

Dashboard

Present KPIs, trends and related context.

04 — ANALYZE

Compare & Investigate

Explore patterns, relationships and events.

05 — DECIDE

Operational Action

Inspect, prioritize, maintain or improve based on evidence.

Dashboard Design Principles

A useful dashboard reduces the time needed to understand the operation.

01

Start With the User

Operators, maintenance teams, engineers and managers do not necessarily need the same dashboard.

02

Show What Matters First

Critical context should be easier to find than secondary information.

03

Preserve Engineering Units

Units, ranges and measurement meaning should remain clear.

04

Provide Historical Context

A current number should often be accompanied by relevant historical behavior.

05

Reduce Visual Noise

More panels do not automatically provide more operational insight.

06

Enable Drill-Down

Move from site-level context toward specific areas, assets or measurements.

Analytical Workflow

From “something changed” to a structured investigation.

Siteplore dashboards can support a repeatable engineering workflow rather than relying on isolated screenshots or one-time observations.

1. Identify the Change Find the metric, asset or period that deserves review.
2. Expand the Time Window Determine whether the behavior is sudden, gradual, recurring or persistent.
3. Add Related Signals Review operating state, load, process or environmental context.
4. Compare Similar Conditions Compare another asset, previous period or relevant operating baseline.
5. Form an Engineering Hypothesis Use available evidence to define what should be verified next.
6. Verify & Act Inspect, test, maintain or continue monitoring according to the situation.
Advanced Analytics

Move beyond historical charts when the data foundation is ready.

The Grafana Cloud environment used by Siteplore can provide additional analytical capabilities where they are supported by the customer’s stack, data source, plan and configuration.

Investigation

Investigations

Use structured investigation workflows to explore meaningful monitoring changes and related context.

Machine Learning

Metric Forecasts

Forecast suitable time-series metrics to provide additional future context, anomaly-detection support or capacity-planning insight.

Machine Learning

Outlier Detection

Identify unusual behavior relative to suitable analytical references where configured.

Assisted Investigation

Sift Investigations

Where available, automated investigative workflows can help surface relevant signals for further engineering review.

AI-Assisted

AI Assistant

Available assistant capabilities can support exploration, search and analysis of monitored information.

Event Context

Alerts & Investigations

Combine selected monitoring events with historical and analytical context to support faster investigation.

Automation

Automations & Watchers

Available workflow capabilities can support repeated monitoring and follow-up processes where suitable.

Discovery

Search

Search capabilities can help users navigate monitoring resources and related information.

Reliability Context

SLO & Service Context

Where relevant, selected service-level concepts can support availability and performance monitoring objectives.

Advanced analytics availability depends on the selected Grafana Cloud plan, customer stack, compatible data source, historical data and project configuration. Forecasting, anomaly detection and AI-assisted analysis should not be interpreted as guaranteed prediction or automatic engineering diagnosis.

Analytics Depends on Data Quality

Better algorithms cannot compensate for poor measurement context.

01

Reliable Measurement

Sensors and instruments must provide credible information about the physical condition.

02

Correct Timestamp

Time alignment matters when comparing events across multiple signals.

03

Consistent Units

Engineering units and scaling should remain consistent and understandable.

04

Asset Metadata

Site, area, asset and device identity help preserve data meaning.

05

Operating Context

Load, state, production or environmental context can change interpretation.

06

Data Availability

Missing or delayed data should be understood before drawing conclusions.

Example Analytical Applications

Different operational questions require different analytical views.

Energy

Energy Performance Analysis

Compare selected energy consumption across periods, areas or loads.

Energy Data
→ Compare
→ Investigate Change
Machine Condition

Asset Trend Investigation

Review condition trends and operating context around a developing change.

Condition Data
→ Historical Trend
→ Engineering Review
Utilities

Utility Performance

Compare selected utility measurements with operational demand.

Utility Data
→ Context
→ Performance Review
Environment

Environmental Trend Analysis

Review environmental patterns across time or monitoring stations.

Environmental Data
→ Trend
→ Compare
Maintenance

Before / After Maintenance

Compare equipment behavior before and after selected maintenance activity.

Historical Data
→ Maintenance Event
→ Performance Comparison
Multi-Site

Site Benchmarking

Compare selected standardized metrics across multiple sites.

Site A + Site B
→ Standard Metric
→ Comparison
Data Sources Across Siteplore

One analytics layer can provide context across different monitoring domains.

Multi-Sensor Data

RekaSense

Analyze compatible environmental, water, agriculture and process time-series measurements.

Explore RekaSense →
Electrical & Energy

PowerWatch

Analyze selected electrical and energy trends, comparisons and operating context.

Explore PowerWatch →
Equipment Condition

MachineGuard

Review equipment condition history, trends and selected operating context.

Explore MachineGuard →
What an Analytics Scope Can Include

Build dashboards around the decisions users need to make.

Exact deliverables depend on available data, customer requirements, monitoring scope and the selected Siteplore engagement.

Analytics Requirement Definition

Define the operational or engineering questions the dashboard should support.

Dashboard Architecture

Organize site, area, asset and detailed analytical views.

Historical Trend Views

Relevant time-series visualizations for selected metrics.

Comparison Views

Asset, period, area or site comparison where appropriate.

KPI Definition

Selected calculated indicators where their engineering meaning is clearly defined.

Event Context Views

Historical context around selected monitoring events.

Advanced Analytics Configuration

Suitable advanced capabilities where supported by the deployment and data.

Training & Handover

Explain how users should navigate and interpret configured analytical views.

Analytics Maturity

Start with visibility. Increase analytical sophistication as the data earns your confidence.

01

Visualize

Establish reliable dashboards and historical trends.

02

Compare

Compare periods, assets and operating conditions.

03

Investigate

Combine related signals around meaningful changes.

04

Model

Evaluate forecasting or outlier analytics where appropriate.

05

Improve

Use evidence to improve operational and maintenance decisions.

Important Analytics Boundary

Analytics supports engineering judgment. It does not replace it.

Siteplore provides historical visibility, comparison and analytical context. Advanced methods can help identify patterns, but conclusions still depend on data quality, application knowledge and appropriate verification.

Capability Siteplore Dashboards & Analytics Important Boundary
Historical visualization Yes Depends on available historical data
Asset / period comparison Yes Requires comparable data and context
Calculated KPIs Where defined Formula and engineering meaning must be valid
Event investigation Yes Limited by available measurements
Outlier detection Potentially Requires suitable data and configured capability
Metric forecasting Potentially Forecast quality depends on time-series behavior
AI-assisted analysis Where available Not a verified engineering diagnosis by itself
Guaranteed failure prediction No Requires validated domain-specific predictive model
Guaranteed remaining useful life No Not claimed without validated RUL methodology
Automatic root-cause conclusion No Further engineering investigation remains necessary
Automatic process control No Dedicated control engineering required
Start With the Decision

Define what the dashboard should help your team understand.

Requirements

Site Assessment

For organizations that need to define measurements, KPIs and analytical questions before building dashboards.

  • Operational problem review
  • Data-source review
  • Measurement assessment
  • Analytics requirement definition
  • Recommended monitoring architecture
Request Site Assessment
Integrated Analytics

Siteplore Deployment

For organizations that need multiple dashboards, sites or analytical domains in one monitoring architecture.

  • Dashboard hierarchy
  • Multiple monitored domains
  • Historical analytics
  • Customer Grafana environment
  • Training & support scope
Discuss Deployment
Frequently Asked Questions

Dashboards & Analytics FAQ

What is the difference between a dashboard and analytics?

A dashboard presents information. Analytics goes further by comparing, contextualizing and investigating data to answer a specific operational or engineering question.

Does Siteplore use Grafana Cloud for dashboards?

Grafana Cloud can provide the visualization and analytical interface within the Siteplore architecture. Siteplore also includes the field-data, edge, time-series and engineering layers required to make those dashboards useful.

Where is the historical data stored?

Siteplore can use a configured cloud time-series platform such as InfluxDB Cloud for measurement history, with Grafana Cloud acting as the monitoring and analytical interface.

Can dashboards show real-time and historical data together?

Yes, where the data architecture supports it. Current-state information can be shown together with historical context to make interpretation easier.

Can users compare two machines?

Yes, where comparable measurements exist for both machines. Differences should still be interpreted in the context of load, service and operating condition.

Can Siteplore compare multiple sites?

Yes, where multi-site monitoring and standardized metrics are part of the deployment architecture.

Can dashboards calculate KPIs?

Calculated indicators can be configured where the required source data, formula and engineering definition are available.

Can dashboards show maintenance events?

Maintenance or operating-event context can potentially be incorporated where the relevant information is available and integrated.

Can Siteplore forecast future trends?

Grafana Cloud Metric Forecast capabilities can be evaluated for suitable time-series metrics where available within the customer stack. Forecasting provides analytical context and should not be treated as a guaranteed future outcome.

Can Siteplore automatically detect unusual data?

Outlier-detection capabilities can be evaluated for suitable metrics. Performance depends on the quality and behavior of the underlying data.

Can AI determine the root cause of a machine problem?

AI-assisted analysis can support exploration and investigation where available, but its output should not automatically be treated as a verified engineering root cause.

Does MachineGuard predict remaining useful life?

Remaining useful life should not be claimed unless a validated RUL model has been developed for the relevant asset, failure mode and available data.

Can Siteplore replace Excel analysis?

Siteplore can reduce repeated manual extraction and comparison for monitoring use cases, but specialized engineering studies may still require separate analytical tools.

Can customers build their own dashboards?

The ability to modify dashboards depends on the access role and customer monitoring architecture configured for the deployment.

Does every customer receive advanced AI and machine-learning features?

No. Advanced capabilities depend on the Grafana Cloud plan, customer stack, compatible data source, available history and project configuration.

What data is needed before advanced analytics is useful?

The most important foundation is reliable and relevant measurement data, correct timestamps, consistent units, useful asset metadata and enough operating history for the intended analytical method.

How should we start designing a dashboard?

Start with the question the user needs to answer. Then identify the measurements, context and comparisons needed to answer it. The visualization comes after that.

A dashboard should not just show what the data says. It should help your team understand what the operation is doing.

Rekacipta can help structure the data, define meaningful analytical questions, build Siteplore dashboards and create historical comparison and investigation workflows that support better engineering decisions.